From 760a4e4567ecf954000504081c21e86b66fa238f Mon Sep 17 00:00:00 2001
From: JamesMVa <111825034+JamesMVa@users.noreply.github.com>
Date: Sat, 6 Jan 2024 22:12:34 -0500
Subject: [PATCH 01/14] Assignment 2 group 7
---
.../assignment_2/group_7_ass_2_2024.ipynb | 582 ++++++++++++++----
1 file changed, 479 insertions(+), 103 deletions(-)
diff --git a/assignments/assignment_2/group_7_ass_2_2024.ipynb b/assignments/assignment_2/group_7_ass_2_2024.ipynb
index db65a409..731a3c64 100644
--- a/assignments/assignment_2/group_7_ass_2_2024.ipynb
+++ b/assignments/assignment_2/group_7_ass_2_2024.ipynb
@@ -32,7 +32,7 @@
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": 33,
"metadata": {},
"outputs": [],
"source": [
@@ -41,7 +41,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": 34,
"metadata": {},
"outputs": [],
"source": [
@@ -50,7 +50,7 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 35,
"metadata": {},
"outputs": [],
"source": [
@@ -59,7 +59,7 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": 36,
"metadata": {},
"outputs": [],
"source": [
@@ -68,7 +68,7 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 37,
"metadata": {},
"outputs": [],
"source": [
@@ -77,7 +77,7 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": 38,
"metadata": {
"scrolled": true
},
@@ -90,7 +90,7 @@
},
{
"cell_type": "code",
- "execution_count": 48,
+ "execution_count": 39,
"metadata": {},
"outputs": [
{
@@ -111,7 +111,7 @@
},
{
"cell_type": "code",
- "execution_count": 19,
+ "execution_count": 40,
"metadata": {},
"outputs": [
{
@@ -132,7 +132,7 @@
},
{
"cell_type": "code",
- "execution_count": 13,
+ "execution_count": 41,
"metadata": {},
"outputs": [
{
@@ -151,7 +151,7 @@
},
{
"cell_type": "code",
- "execution_count": 18,
+ "execution_count": 42,
"metadata": {},
"outputs": [
{
@@ -160,7 +160,7 @@
"'My teacher assistant is so boring.'"
]
},
- "execution_count": 18,
+ "execution_count": 42,
"metadata": {},
"output_type": "execute_result"
}
@@ -174,7 +174,7 @@
},
{
"cell_type": "code",
- "execution_count": 24,
+ "execution_count": 43,
"metadata": {},
"outputs": [
{
@@ -183,7 +183,7 @@
"'My TA My teacher assistant is so boring but is very funny'"
]
},
- "execution_count": 24,
+ "execution_count": 43,
"metadata": {},
"output_type": "execute_result"
}
@@ -205,7 +205,7 @@
},
{
"cell_type": "code",
- "execution_count": 31,
+ "execution_count": 44,
"metadata": {},
"outputs": [
{
@@ -226,7 +226,7 @@
},
{
"cell_type": "code",
- "execution_count": 33,
+ "execution_count": 45,
"metadata": {},
"outputs": [
{
@@ -247,7 +247,7 @@
},
{
"cell_type": "code",
- "execution_count": 37,
+ "execution_count": 46,
"metadata": {},
"outputs": [
{
@@ -272,7 +272,7 @@
},
{
"cell_type": "code",
- "execution_count": 46,
+ "execution_count": 47,
"metadata": {},
"outputs": [
{
@@ -321,7 +321,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 48,
"metadata": {},
"outputs": [],
"source": [
@@ -330,13 +330,178 @@
},
{
"cell_type": "code",
- "execution_count": 18,
+ "execution_count": 49,
"metadata": {},
"outputs": [],
"source": [
"emails = [\"cscornejo@pucp.edu.pe\", \"orellana.cn@pucp.edu.pe\", \"karina.morales@pucp.edu.pe\", \"a20083223@pucp.pe\", \"abel.camacho@pucp.pe\", \"mtintaya@pucp.edu.pe\", \"joselin.chavez@pucp.edu.pe\", \"a20105737@pucp.pe\", \"jfgomezc@pucp.pe\", \"afrania.palomino@pucp.pe\", \"luzon.bianca@pucp.pe\", \"adrian.suanaz@pucp.pe\", \"soto.y@pucp.edu.pe\", \"a20132766@pucp.pe\", \"andre.lama@pucp.edu.pe\", \"gustavo.meza@pucp.edu.pe\", \"pmlozada@pucp.edu.pe\", \"m.zambranoj@pucp.edu.pe\", \"nicolas.jacobs@pucp.edu.pe\", \"gvidal@pucp.edu.pe\", \"jane.torres@pucp.edu.pe\", \"m.lopez@pucp.edu.pe\", \"alejandro.boyco@pucp.edu.pe\", \"a20167070@pucp.edu.pe\", \"riega.stephy@pucp.edu.pe\", \"vlevanot@pucp.edu.pe\", \"sesquives@pucp.edu.pe\", \"perez.juanc@pucp.edu.pe\", \"mariana.otero@pucp.edu.pe\", \"aclavo@pucp.edu.pe\", \"a20182474@pucp.edu.pe\", \"josue.caldas@pucp.edu.pe\", \"fabio.salas@pucp.edu.pe\", \"fernanda.pizarro@pucp.edu.pe\", \"aquillatupa@pucp.pe\"]"
]
},
+ {
+ "cell_type": "code",
+ "execution_count": 50,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "I am too old\n"
+ ]
+ }
+ ],
+ "source": [
+ "# 1. Drop the duplicated blank spaces in str1. Do not use the regular expresions. Do not use the code shown in class. Explain your steps.Hint: Use split method and join function.\n",
+ "\n",
+ "# First, we split the string into a list of words\n",
+ "list_words = str1.split()\n",
+ "\n",
+ "# Then, we remove the empty strings from the list\n",
+ "non_empty_words = [word for word in list_words if word]\n",
+ "\n",
+ "# Lastly, we join the non-empty words back into a string\n",
+ "result_str = ' '.join(non_empty_words)\n",
+ "\n",
+ "print(result_str)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 51,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Number of letters: 9\n"
+ ]
+ }
+ ],
+ "source": [
+ "# 2. Get the number of letters in the string .Hint: Use lenfunction.\n",
+ "\n",
+ "# In order to count the number of letters, we need to remove non-alphabetic characters first, we do that \n",
+ "# using the len function (to printe the lenght)\n",
+ "# and verifying that the character is alphabetic (a letter), using the if function.\n",
+ "num_letters = len([char for char in str1 if char.isalpha()])\n",
+ "\n",
+ "# This is a better way to print the answer, including the string value \"Number of letters\"\n",
+ "print(\"Number of letters:\", num_letters)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 52,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Number of blank spaces: 85\n"
+ ]
+ }
+ ],
+ "source": [
+ "# 3. Get the number of blank spaces (all of them) in the string .Hint: Use lenfunction.\n",
+ "\n",
+ "# First, we create a list with the blank spaces, using the \"isspace\" method\n",
+ "blank_space = [char for char in str1 if char.isspace()]\n",
+ "\n",
+ "# Then we apply the function len() to the list to get the total number of blank spaces\n",
+ "num_blank_spaces = len(blank_space)\n",
+ "\n",
+ "# Finally, we print the result\n",
+ "print(\"Number of blank spaces:\", num_blank_spaces)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 53,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Positions of '@': [9, 11, 14, 9, 12, 8, 14, 9, 8, 16, 12, 13, 6, 9, 10, 12, 8, 11, 14, 6, 11, 7, 15, 9, 12, 8, 9, 11, 13, 6, 9, 12, 11, 16, 11]\n"
+ ]
+ }
+ ],
+ "source": [
+ "# 4. Get the position of @ in each string in the emails list. Hint: Use mapfunction and find method.\n",
+ "\n",
+ "# First we use the map() function to apply the specified lambda function to each element in the emails list. \n",
+ "# Then, with the lambda function takes an email address (email) and finds the position of the '@' symbol using the find() method.\n",
+ "# Also, list(...) Converts the result into a list.\n",
+ "positions_at = list(map(lambda email: email.find('@'), emails))\n",
+ "\n",
+ "# Finally, we print the results\n",
+ "print(\"Positions of '@':\", positions_at)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 54,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Contains '.edu.': [True, True, True, False, False, True, True, False, False, False, False, False, True, False, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, False]\n"
+ ]
+ }
+ ],
+ "source": [
+ "# 5. Identifies if exists .edu. in each string in the emails list. Get a list of Booleans. Hint: Use mapfunction and find method. # \n",
+ "\n",
+ "# First, we use the map function to apply a lambda function to each element in the emails list.\n",
+ "# The lambda function checks if '.edu.' is present in each email address.\n",
+ "contains_edu_lambda = lambda email: '.edu.' in email\n",
+ "mapped_result = map(contains_edu_lambda, emails)\n",
+ "\n",
+ "# Then, we convert the mapped result into a list.\n",
+ "contains_edu_list = list(mapped_result)\n",
+ "\n",
+ "# Finally we print the result\n",
+ "print(\"Contains '.edu.':\", contains_edu_list)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 55,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Substrings before the first dot: ['cscornejo@pucp', 'orellana', 'karina', 'a20083223@pucp', 'abel', 'mtintaya@pucp', 'joselin', 'a20105737@pucp', 'jfgomezc@pucp', 'afrania', 'luzon', 'adrian', 'soto', 'a20132766@pucp', 'andre', 'gustavo', 'pmlozada@pucp', 'm', 'nicolas', 'gvidal@pucp', 'jane', 'm', 'alejandro', 'a20167070@pucp', 'riega', 'vlevanot@pucp', 'sesquives@pucp', 'perez', 'mariana', 'aclavo@pucp', 'a20182474@pucp', 'josue', 'fabio', 'fernanda', 'aquillatupa@pucp']\n",
+ "Number of substrings containing '@': 14\n"
+ ]
+ }
+ ],
+ "source": [
+ "# 6. Get all the strings before the first dot '.' in each string in the emails list.\n",
+ "# First, we identify how many of them have '@'.\n",
+ "\n",
+ "# Then we use the map function to apply a lambda function to each element in the emails list.\n",
+ "# The lambda function extracts the substring before the first dot '.' and checks if it contains '@'.\n",
+ "substring_before_dot_lambda = lambda email: email.split('.')[0]\n",
+ "mapped_result = map(substring_before_dot_lambda, emails)\n",
+ "\n",
+ "# After that, we convert the mapped result into a list.\n",
+ "substring_before_dot_list = list(mapped_result)\n",
+ "\n",
+ "# Also, we count how many substrings contain '@' and print the results\n",
+ "count_with_at = sum('@' in substring for substring in substring_before_dot_list)\n",
+ "\n",
+ "print(\"Substrings before the first dot:\", substring_before_dot_list)\n",
+ "print(\"Number of substrings containing '@':\", count_with_at)"
+ ]
+ },
{
"cell_type": "markdown",
"metadata": {},
@@ -361,14 +526,9 @@
"4. Add Rows:\n",
" a) Add a new row with a date of your choice and fill the other columns with appropriate values. \n",
"\n",
-
- "# Lastly, we join the non-empty words back into a string\n",
- "result_str = ' '.join(non_empty_words)\n",
-
"5. Analysis:\n",
" a) Calculate the average of the column 'Close' for each 'Year'. You need to group for this task.\n",
" b) Count the number of 'High', 'Medium', and 'Low' Level days in the data.\n",
-
"\n",
"Suggestions:\n",
" - Use `pd.cut()` for categorizing 'Close' values.\n",
@@ -379,30 +539,21 @@
},
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": 56,
"metadata": {},
"outputs": [],
"source": [
+ "# 1\n",
"import pandas as pd\n",
"\n",
-
- "# In order to count the number of letters, we need to remove non-alphabetic characters first, we do that \n",
- "# using the len function (to printe the lenght)\n",
- "# and verifying that the character is alphabetic (a letter), using the if function.\n",
- "num_letters = len([char for char in str1 if char.isalpha()])\n",
- "\n",
- "# This is a better way to print the answer, including the string value \"Number of letters\"\n",
- "print(\"Number of letters:\", num_letters)"
-
"# This code loads the data from the provided URL.\n",
"url = \"https://raw.githubusercontent.com/datasets/finance-vix/main/data/vix-daily.csv\"\n",
"df = pd.read_csv(url)"
-
]
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": 57,
"metadata": {},
"outputs": [
{
@@ -483,14 +634,6 @@
" | ... | \n",
" \n",
" \n",
- " | 8571 | \n",
- " 12/28/2023 | \n",
- " 12.44 | \n",
- " 12.65 | \n",
- " 12.38 | \n",
- " 12.47 | \n",
- "
\n",
- " \n",
" | 8572 | \n",
" 12/29/2023 | \n",
" 12.55 | \n",
@@ -522,9 +665,17 @@
" 13.64 | \n",
" 14.13 | \n",
"
\n",
+ " \n",
+ " | 8576 | \n",
+ " 01/05/2024 | \n",
+ " 14.24 | \n",
+ " 14.58 | \n",
+ " 13.29 | \n",
+ " 13.35 | \n",
+ "
\n",
" \n",
"\n",
- "8576 rows × 5 columns
\n",
+ "8577 rows × 5 columns
\n",
""
],
"text/plain": [
@@ -535,16 +686,16 @@
"3 01/05/1990 20.11 20.11 20.11 20.11\n",
"4 01/08/1990 20.26 20.26 20.26 20.26\n",
"... ... ... ... ... ...\n",
- "8571 12/28/2023 12.44 12.65 12.38 12.47\n",
"8572 12/29/2023 12.55 13.19 12.36 12.45\n",
"8573 01/02/2024 13.22 14.23 13.10 13.20\n",
"8574 01/03/2024 13.35 14.22 13.33 14.04\n",
"8575 01/04/2024 13.93 14.20 13.64 14.13\n",
+ "8576 01/05/2024 14.24 14.58 13.29 13.35\n",
"\n",
- "[8576 rows x 5 columns]"
+ "[8577 rows x 5 columns]"
]
},
- "execution_count": 2,
+ "execution_count": 57,
"metadata": {},
"output_type": "execute_result"
}
@@ -556,7 +707,7 @@
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": 58,
"metadata": {},
"outputs": [
{
@@ -585,6 +736,7 @@
}
],
"source": [
+ "# 2\n",
"# We display the first five rows of the DataFrame.\n",
"print(\"Primeras cinco filas del DataFrame:\")\n",
"print(df.head())\n",
@@ -596,7 +748,7 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": 59,
"metadata": {},
"outputs": [
{
@@ -762,12 +914,13 @@
"[8577 rows x 7 columns]"
]
},
- "execution_count": 3,
+ "execution_count": 59,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
+ "# 3\n",
"# We add a 'Level' column to categorize the 'CLOSE' values\n",
"df['Level'] = pd.cut(df['CLOSE'], bins=[-float('inf'), 20, 30, float('inf')],\n",
" labels=['Low', 'Medium', 'High'])\n",
@@ -781,7 +934,7 @@
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": 60,
"metadata": {},
"outputs": [
{
@@ -947,12 +1100,13 @@
"[8578 rows x 7 columns]"
]
},
- "execution_count": 4,
+ "execution_count": 60,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
+ "# 4\n",
"# Temporalmente eliminamos las columnas 'Level' y 'Year' para evitar NaN en el df\n",
"df = df.drop(['Level', 'Year'], axis=1)\n",
"\n",
@@ -975,88 +1129,310 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 61,
"metadata": {},
"outputs": [
{
"data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " Year | \n",
+ " Average Close | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 1990 | \n",
+ " 23.06 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 1991 | \n",
+ " 18.37 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 1992 | \n",
+ " 15.45 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 1993 | \n",
+ " 12.69 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 1994 | \n",
+ " 13.93 | \n",
+ "
\n",
+ " \n",
+ " | 5 | \n",
+ " 1995 | \n",
+ " 12.39 | \n",
+ "
\n",
+ " \n",
+ " | 6 | \n",
+ " 1996 | \n",
+ " 16.44 | \n",
+ "
\n",
+ " \n",
+ " | 7 | \n",
+ " 1997 | \n",
+ " 22.36 | \n",
+ "
\n",
+ " \n",
+ " | 8 | \n",
+ " 1998 | \n",
+ " 25.60 | \n",
+ "
\n",
+ " \n",
+ " | 9 | \n",
+ " 1999 | \n",
+ " 24.37 | \n",
+ "
\n",
+ " \n",
+ " | 10 | \n",
+ " 2000 | \n",
+ " 23.32 | \n",
+ "
\n",
+ " \n",
+ " | 11 | \n",
+ " 2001 | \n",
+ " 25.75 | \n",
+ "
\n",
+ " \n",
+ " | 12 | \n",
+ " 2002 | \n",
+ " 27.29 | \n",
+ "
\n",
+ " \n",
+ " | 13 | \n",
+ " 2003 | \n",
+ " 21.98 | \n",
+ "
\n",
+ " \n",
+ " | 14 | \n",
+ " 2004 | \n",
+ " 15.48 | \n",
+ "
\n",
+ " \n",
+ " | 15 | \n",
+ " 2005 | \n",
+ " 12.81 | \n",
+ "
\n",
+ " \n",
+ " | 16 | \n",
+ " 2006 | \n",
+ " 12.81 | \n",
+ "
\n",
+ " \n",
+ " | 17 | \n",
+ " 2007 | \n",
+ " 17.54 | \n",
+ "
\n",
+ " \n",
+ " | 18 | \n",
+ " 2008 | \n",
+ " 32.70 | \n",
+ "
\n",
+ " \n",
+ " | 19 | \n",
+ " 2009 | \n",
+ " 31.48 | \n",
+ "
\n",
+ " \n",
+ " | 20 | \n",
+ " 2010 | \n",
+ " 22.55 | \n",
+ "
\n",
+ " \n",
+ " | 21 | \n",
+ " 2011 | \n",
+ " 24.20 | \n",
+ "
\n",
+ " \n",
+ " | 22 | \n",
+ " 2012 | \n",
+ " 17.80 | \n",
+ "
\n",
+ " \n",
+ " | 23 | \n",
+ " 2013 | \n",
+ " 14.23 | \n",
+ "
\n",
+ " \n",
+ " | 24 | \n",
+ " 2014 | \n",
+ " 14.18 | \n",
+ "
\n",
+ " \n",
+ " | 25 | \n",
+ " 2015 | \n",
+ " 16.67 | \n",
+ "
\n",
+ " \n",
+ " | 26 | \n",
+ " 2016 | \n",
+ " 15.83 | \n",
+ "
\n",
+ " \n",
+ " | 27 | \n",
+ " 2017 | \n",
+ " 11.09 | \n",
+ "
\n",
+ " \n",
+ " | 28 | \n",
+ " 2018 | \n",
+ " 16.64 | \n",
+ "
\n",
+ " \n",
+ " | 29 | \n",
+ " 2019 | \n",
+ " 15.39 | \n",
+ "
\n",
+ " \n",
+ " | 30 | \n",
+ " 2020 | \n",
+ " 29.25 | \n",
+ "
\n",
+ " \n",
+ " | 31 | \n",
+ " 2021 | \n",
+ " 19.66 | \n",
+ "
\n",
+ " \n",
+ " | 32 | \n",
+ " 2022 | \n",
+ " 25.64 | \n",
+ "
\n",
+ " \n",
+ " | 33 | \n",
+ " 2023 | \n",
+ " 16.85 | \n",
+ "
\n",
+ " \n",
+ " | 34 | \n",
+ " 2024 | \n",
+ " 13.62 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
\n",
- "\n",
- "2. Replicate 4 times the values of the list `p2_list`. We expect an ouput like this: `[ 2 , 3, 4, 5, 2 , 3, 4, 5, 2 , 3, 4, 5, 2 , 3, 4, 5]`. **Hint: Use multiplication function in `lists`and see the output.**
\n",
- "3. Print the length of `f_list`. **Hint: Length function**
\n",
- "4. Print `My teacher assistant is so boring.` using `text1` list. **Hint: Use the [`join` function](https://stackoverflow.com/questions/493819/why-is-it-string-joinlist-instead-of-list-joinstring)**
\n",
- "5. Print `My TA is so boring, but is very funny.` using `text1` list.**Hint: Use the `join` function, and `extend` method.**
\n",
- "6. Print
\n",
- "`The max value of values1 is 86 and is located in the 0 index. `
\n",
- "`The min value of values1 is 0 and is located in the 7 index. `
**Hint: Use the `f-string`, `min`, and `max` functions.**\n",
- "
\n",
- "7. Get two lists: `names` and `last_names` using `last_and_name` list. **Hint: Use `map` and `split`.**\n",
- "
\n",
- "8. Give only the last names of students who do not have email. Use the `emails` and `last_names` listt. **Hint: Use `map` and `split`.**\n",
- "
"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 4,
- "metadata": {},
- "outputs": [],
- "source": [
- "import numpy as np"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "metadata": {},
- "outputs": [],
- "source": [
- "f_list = [np.nan , np.nan, \"Austria\", \"Germany\", np.nan, \"Pakistan\", \"np.nan\", np.nan ]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 6,
- "metadata": {},
- "outputs": [],
- "source": [
- "text1 = ['My', 'teacher', 'assistant', 'is', 'so', 'boring.']"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 7,
- "metadata": {},
- "outputs": [],
- "source": [
- "p2_list = [ 2 , 3, 4, 5 ]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 8,
- "metadata": {},
- "outputs": [],
- "source": [
- "values1 = [ 86, 86, 85, 85, 85, 83, 23, 0, 84, 1 ] "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 9,
- "metadata": {
- "scrolled": true
- },
- "outputs": [],
- "source": [
- "# These two lists a\n",
- "last_and_name = [ \"CORNEJO SANCHEZ, CHRISTIAN SANTOS\", \"ORELLANA QUISPE, CRISTIAN NASSER\", \"MORALES CHOQUEHUANCA, ANGELICA KARINA\", \"GUIMARAY RIBEYRO, JOSE ROBERTO\", \"CAMACHO GAVIDIA, ABEL FERNANDO\", \"TINTAYA ORIHUELA, MEIR ALVARO\", \"CHAVEZ MARTINEZ, JOSELIN ALEXANDRA\", \"FIGUEROA MURO, LEONEL ARTURO\", \"GOMEZ CRIBILLERO, JOSE FELIPE\", \"PALOMINO SEGUÍN, AFRANIA\", \"LUZON CUEVA, BIANCA MARIETTE\", \"SUAÑA ZEGARRA, ADRIAN ANDRE\", \"SOTO POMACHAGUA, DORKAS YOMIRA JHERMY\", \"FIORENTINO MARTINEZ, LADY ALY\", \"LAMA MAVILA, HECTOR ANDRE\", \"MEZA HINOJO, GUSTAVO\", \"LOZADA MURILLO, PERSEO MARCELO\", \"ZAMBRANO JIMENEZ, MIGUEL ALONZO\", \"JACOBS LUQUE, NICOLAS\", \"VIDAL VIDAL, ROCIO GABRIELA\", \"TORRES ANICAMA, JANE CAMILA\", \"LOPEZ ESTRADA, MARIA ELISA\", \"BOYCO ORAMS, ALEJANDRO\", \"DIAZ BERROSPI, KARLINE ROSMELI\", \"RIEGA ESCALANTE, STEPHY ROSARIO\", \"LEVANO TORRES, VALERIA CECILIA\", \"ESQUIVES BRAVO, SEBASTIAN RENATO\", \"PEREZ GONZALES, JUAN CARLOS\", \"OTERO MAGUIÑA, MARIANA\", \"CLAVO CAMPOS, ANDREA BRIZETH\", \"AGUILAR GARCIA, ERICK JOSUE\", \"CALDAS VELASQUEZ, JOSUE DANIEL\", \"SALAS NUÑEZ BORJA, FABIO MANUEL\", \"PIZARRO VILLANES, FERNANDA NICOLLE\", \"QUILLATUPA MORALES, ANGELA ADELINA\", \"HUANCAYA IDONE, CESAR DANTE\", \"CALVO PORTOCARRERO, GABRIELA ISABEL\", \"IBAÑEZ ABANTO, ANGEL MAURICIO\", \"MELÉNDEZ APONTE, JUAN DIEGO\", \"CRISTIAN SERRANO, ARONE\", \"HINOJOSA CAHUANA, PERCY ALBERTH\", \"ANGLAS GARCÍA, KEVIN ARTURO\", \"ALDAVE ACOSTA, CESAR ERNESTO\", \"NÚÑEZ HUAMÁN, CÉSAR AGUSTO\", \"OBREGON HUAMAN, DIANA EDITH\", \"SOTO PACHERRES, RODRIGO FRANCO\", \"INGARUCA RIVERA, GRETTEL ALEXANDRA\", \"ROJAS HUAMAN, ROSA ANGELA\", \"NEYRA SALAS, DANTE OMAR\", \"HUERTA ESPINOZA, YAJAIRA ALEXANDRA\", \"HUANCA MARTINEZ, JORGE ALBERTO\", \"FLORES CADILLO, ALEXIS\" ]\n",
- "emails = [\"cscornejo@pucp.edu.pe\", \"orellana.cn@pucp.edu.pe\", \"karina.morales@pucp.edu.pe\", \"a20083223@pucp.pe\", \"abel.camacho@pucp.pe\", \"mtintaya@pucp.edu.pe\", \"joselin.chavez@pucp.edu.pe\", \"a20105737@pucp.pe\", \"jfgomezc@pucp.pe\", \"afrania.palomino@pucp.pe\", \"luzon.bianca@pucp.pe\", \"adrian.suanaz@pucp.pe\", \"soto.y@pucp.edu.pe\", \"a20132766@pucp.pe\", \"andre.lama@pucp.edu.pe\", \"gustavo.meza@pucp.edu.pe\", \"pmlozada@pucp.edu.pe\", \"m.zambranoj@pucp.edu.pe\", \"nicolas.jacobs@pucp.edu.pe\", \"gvidal@pucp.edu.pe\", \"jane.torres@pucp.edu.pe\", \"m.lopez@pucp.edu.pe\", \"alejandro.boyco@pucp.edu.pe\", \"a20167070@pucp.edu.pe\", \"riega.stephy@pucp.edu.pe\", \"vlevanot@pucp.edu.pe\", \"sesquives@pucp.edu.pe\", \"perez.juanc@pucp.edu.pe\", \"mariana.otero@pucp.edu.pe\", \"aclavo@pucp.edu.pe\", \"a20182474@pucp.edu.pe\", \"josue.caldas@pucp.edu.pe\", \"fabio.salas@pucp.edu.pe\", \"fernanda.pizarro@pucp.edu.pe\", \"aquillatupa@pucp.pe\", \"\", \"\", \"\", \"\", \"\", \"f0873079@pucp.edu.pe\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"flores.alexis@pucp.edu.pe\", ]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 48,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "The indices [0, 1, 4, 7] have np.nan values.\n"
- ]
- }
- ],
- "source": [
- " # Answer 1\n",
- "\n",
- "nan_values = [i for i, value in enumerate(f_list) if value is np.nan]\n",
- "\n",
- "print(f\"The indices {nan_values} have np.nan values.\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 19,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "[2, 3, 4, 5, 2, 3, 4, 5, 2, 3, 4, 5, 2, 3, 4, 5]\n"
- ]
- }
- ],
- "source": [
- " # Answer 2\n",
- "\n",
- "p2_list_2 = p2_list * 4\n",
- "\n",
- "print(p2_list_2)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 13,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "8\n"
- ]
- }
- ],
- "source": [
- " # Answer 3\n",
- "\n",
- "print(len(f_list))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 18,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "'My teacher assistant is so boring.'"
- ]
- },
- "execution_count": 18,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- " # Answer 4\n",
- "\n",
- "answer_4 = ' '.join(text1)\n",
- "answer_4"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 24,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "'My TA My teacher assistant is so boring but is very funny'"
- ]
- },
- "execution_count": 24,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- " # Answer 5\n",
- " \n",
- "text1[-1] = text1[-1].rstrip('.')\n",
- " \n",
- "text_answer = ['My', 'TA']\n",
- "\n",
- "text_answer_b = ['but', 'is', 'very', 'funny']\n",
- "\n",
- "text_answer.extend(text1 + text_answer_b)\n",
- "\n",
- "answer_5 = ' '.join(text_answer)\n",
- "answer_5"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 31,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "The max value of values1 is 86 and is located in the 0 index.\n"
- ]
- }
- ],
- "source": [
- " # Answer 6.1\n",
- " \n",
- "max_index = values1.index(max(values1))\n",
- " \n",
- "print(f\"The max value of values1 is {max(values1)} and is located in the {max_index} index.\")\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 33,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "The min value of values1 is 0 and is located in the 7 index.\n"
- ]
- }
- ],
- "source": [
- " # Answer 6.2\n",
- " \n",
- "min_index = values1.index(min(values1))\n",
- " \n",
- "print(f\"The min value of values1 is {min(values1)} and is located in the {min_index} index.\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 37,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Names: ('CHRISTIAN SANTOS', 'CRISTIAN NASSER', 'ANGELICA KARINA', 'JOSE ROBERTO', 'ABEL FERNANDO', 'MEIR ALVARO', 'JOSELIN ALEXANDRA', 'LEONEL ARTURO', 'JOSE FELIPE', 'AFRANIA', 'BIANCA MARIETTE', 'ADRIAN ANDRE', 'DORKAS YOMIRA JHERMY', 'LADY ALY', 'HECTOR ANDRE', 'GUSTAVO', 'PERSEO MARCELO', 'MIGUEL ALONZO', 'NICOLAS', 'ROCIO GABRIELA', 'JANE CAMILA', 'MARIA ELISA', 'ALEJANDRO', 'KARLINE ROSMELI', 'STEPHY ROSARIO', 'VALERIA CECILIA', 'SEBASTIAN RENATO', 'JUAN CARLOS', 'MARIANA', 'ANDREA BRIZETH', 'ERICK JOSUE', 'JOSUE DANIEL', 'FABIO MANUEL', 'FERNANDA NICOLLE', 'ANGELA ADELINA', 'CESAR DANTE', 'GABRIELA ISABEL', 'ANGEL MAURICIO', 'JUAN DIEGO', 'ARONE', 'PERCY ALBERTH', 'KEVIN ARTURO', 'CESAR ERNESTO', 'CÉSAR AGUSTO', 'DIANA EDITH', 'RODRIGO FRANCO', 'GRETTEL ALEXANDRA', 'ROSA ANGELA', 'DANTE OMAR', 'YAJAIRA ALEXANDRA', 'JORGE ALBERTO', 'ALEXIS')\n",
- "Last Names: ('CORNEJO SANCHEZ', 'ORELLANA QUISPE', 'MORALES CHOQUEHUANCA', 'GUIMARAY RIBEYRO', 'CAMACHO GAVIDIA', 'TINTAYA ORIHUELA', 'CHAVEZ MARTINEZ', 'FIGUEROA MURO', 'GOMEZ CRIBILLERO', 'PALOMINO SEGUÍN', 'LUZON CUEVA', 'SUAÑA ZEGARRA', 'SOTO POMACHAGUA', 'FIORENTINO MARTINEZ', 'LAMA MAVILA', 'MEZA HINOJO', 'LOZADA MURILLO', 'ZAMBRANO JIMENEZ', 'JACOBS LUQUE', 'VIDAL VIDAL', 'TORRES ANICAMA', 'LOPEZ ESTRADA', 'BOYCO ORAMS', 'DIAZ BERROSPI', 'RIEGA ESCALANTE', 'LEVANO TORRES', 'ESQUIVES BRAVO', 'PEREZ GONZALES', 'OTERO MAGUIÑA', 'CLAVO CAMPOS', 'AGUILAR GARCIA', 'CALDAS VELASQUEZ', 'SALAS NUÑEZ BORJA', 'PIZARRO VILLANES', 'QUILLATUPA MORALES', 'HUANCAYA IDONE', 'CALVO PORTOCARRERO', 'IBAÑEZ ABANTO', 'MELÉNDEZ APONTE', 'CRISTIAN SERRANO', 'HINOJOSA CAHUANA', 'ANGLAS GARCÍA', 'ALDAVE ACOSTA', 'NÚÑEZ HUAMÁN', 'OBREGON HUAMAN', 'SOTO PACHERRES', 'INGARUCA RIVERA', 'ROJAS HUAMAN', 'NEYRA SALAS', 'HUERTA ESPINOZA', 'HUANCA MARTINEZ', 'FLORES CADILLO')\n"
- ]
- }
- ],
- "source": [
- " # Answer 7\n",
- "\n",
- "last_names, names = zip(*map(lambda x: x.split(', '), last_and_name))\n",
- " # the lambda function using split divides each name from each last name\n",
- " # the function zip takes the values and puts them in tuples\n",
- " # \"last_names, names\" indicates the code to split the tuples in two separate lists\n",
- "print(\"Names:\", names)\n",
- "print(\"Last Names:\", last_names)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 46,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "['HUANCAYA IDONE', 'CALVO PORTOCARRERO', 'IBAÑEZ ABANTO', 'MELÉNDEZ APONTE', 'CRISTIAN SERRANO', 'ANGLAS GARCÍA', 'ALDAVE ACOSTA', 'NÚÑEZ HUAMÁN', 'OBREGON HUAMAN', 'SOTO PACHERRES', 'INGARUCA RIVERA', 'ROJAS HUAMAN', 'NEYRA SALAS', 'HUERTA ESPINOZA', 'HUANCA MARTINEZ']\n"
- ]
- }
- ],
- "source": [
- " # Answer 8\n",
- " \n",
- "answer_8 = [last_name for last_name, email in zip(last_names, emails) if not email]\n",
- " # zip function pairs last names with its corresponding emails into tuples\n",
- " # \"last_name for last_name, email in ... if not email\" indicates the last name for each pair if email is empty\n",
- "print(answer_8)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## 1.3 Strings\n",
- "\n",
- "\n",
- "1. Drop the duplicated blank spaces in `str1`. Do not use the regular expresions. Do not use the code shown in class. Explain your steps.**Hint: Use `split` method and `join` function.**\n",
- "\n",
- "2. Get the number of letters in the string .**Hint: Use `len`function.**\n",
- "\n",
- "3. Get the number of blank spaces (all of them) in the string .**Hint: Use `len`function.**\n",
- "\n",
- "4. Get the position of `@` in each string in the emails list. **Hint: Use `map`function and `find` method.**\n",
- "\n",
- "5. Identifies if exists `.edu.` in each string in the `emails` list. Get a list of Booleans. **Hint: Use `map`function and `find` method.**\n",
- "\n",
- "6. Get all the strings before the first dot `.`in each string in the `emails` list. Identifies how many of them has `@`. **Hint: Use `map`function and `find` method.**"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "#### Dear professor, the reason why I created this new branch is to correct the fact that I mistakenly edited the main branch of my group when I was writing my part. So, I was the one in charge to complete the \"Strings\" part, and here it is. I hope you can understand this."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "str1 = 'I am too old'"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 18,
- "metadata": {},
- "outputs": [],
- "source": [
- "emails = [\"cscornejo@pucp.edu.pe\", \"orellana.cn@pucp.edu.pe\", \"karina.morales@pucp.edu.pe\", \"a20083223@pucp.pe\", \"abel.camacho@pucp.pe\", \"mtintaya@pucp.edu.pe\", \"joselin.chavez@pucp.edu.pe\", \"a20105737@pucp.pe\", \"jfgomezc@pucp.pe\", \"afrania.palomino@pucp.pe\", \"luzon.bianca@pucp.pe\", \"adrian.suanaz@pucp.pe\", \"soto.y@pucp.edu.pe\", \"a20132766@pucp.pe\", \"andre.lama@pucp.edu.pe\", \"gustavo.meza@pucp.edu.pe\", \"pmlozada@pucp.edu.pe\", \"m.zambranoj@pucp.edu.pe\", \"nicolas.jacobs@pucp.edu.pe\", \"gvidal@pucp.edu.pe\", \"jane.torres@pucp.edu.pe\", \"m.lopez@pucp.edu.pe\", \"alejandro.boyco@pucp.edu.pe\", \"a20167070@pucp.edu.pe\", \"riega.stephy@pucp.edu.pe\", \"vlevanot@pucp.edu.pe\", \"sesquives@pucp.edu.pe\", \"perez.juanc@pucp.edu.pe\", \"mariana.otero@pucp.edu.pe\", \"aclavo@pucp.edu.pe\", \"a20182474@pucp.edu.pe\", \"josue.caldas@pucp.edu.pe\", \"fabio.salas@pucp.edu.pe\", \"fernanda.pizarro@pucp.edu.pe\", \"aquillatupa@pucp.pe\"]"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## 1.4 Pandas\n",
- "\n",
- "You can and should always ask ChatGPT, BARD, Bing, etc.\n",
- "In this exercise, you will work with financial data. Follow the steps below:\n",
- "\n",
- "1. Load Data:\n",
- " Load the financial data available at this URL: https://raw.githubusercontent.com/datasets/finance-vix/main/data/vix-daily.csv\n",
- " Use `pd.read_csv()` adn the link to load the data into a DataFrame.\n",
- "\n",
- "2. Explore Data:\n",
- " a) Display the first five rows of the DataFrame.\n",
- " b) Display the summary statistics of the DataFrame.\n",
- "\n",
- "3. Add Columns:\n",
- " a) Add a new column 'Level' that categorizes the 'Close' column values into 'Low' (< 20), 'Medium' (20-30), and 'High' (>30). You need to make a filter to make this categorization. You can see below some suggestions how to do it.\n",
- " b) Add a new column 'Year' extracted from the 'Date' column. You need to work with dates. You can do it directly workiwith the column splitting it or changing it to date format an dfollowing the below suggestion. \n",
- "\n",
- "4. Add Rows:\n",
- " a) Add a new row with a date of your choice and fill the other columns with appropriate values. \n",
- "\n",
-
- "# Lastly, we join the non-empty words back into a string\n",
- "result_str = ' '.join(non_empty_words)\n",
-
- "5. Analysis:\n",
- " a) Calculate the average of the column 'Close' for each 'Year'. You need to group for this task.\n",
- " b) Count the number of 'High', 'Medium', and 'Low' Level days in the data.\n",
-
- "\n",
- "Suggestions:\n",
- " - Use `pd.cut()` for categorizing 'Close' values.\n",
- " - Use `pd.to_datetime()` and `dt.year` to extract the year from a date.\n",
- " - Use `DataFrame.append()` or `pd.concat()` to add rows.\n",
- " - Use `groupby()` for aggregation tasks."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 1,
- "metadata": {},
- "outputs": [],
- "source": [
- "import pandas as pd\n",
- "\n",
-
- "# In order to count the number of letters, we need to remove non-alphabetic characters first, we do that \n",
- "# using the len function (to printe the lenght)\n",
- "# and verifying that the character is alphabetic (a letter), using the if function.\n",
- "num_letters = len([char for char in str1 if char.isalpha()])\n",
- "\n",
- "# This is a better way to print the answer, including the string value \"Number of letters\"\n",
- "print(\"Number of letters:\", num_letters)"
-
- "# This code loads the data from the provided URL.\n",
- "url = \"https://raw.githubusercontent.com/datasets/finance-vix/main/data/vix-daily.csv\"\n",
- "df = pd.read_csv(url)"
-
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " DATE | \n",
- " OPEN | \n",
- " HIGH | \n",
- " LOW | \n",
- " CLOSE | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 01/02/1990 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 01/03/1990 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 01/04/1990 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 01/05/1990 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 01/08/1990 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- "
\n",
- " \n",
- " | ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- "
\n",
- " \n",
- " | 8571 | \n",
- " 12/28/2023 | \n",
- " 12.44 | \n",
- " 12.65 | \n",
- " 12.38 | \n",
- " 12.47 | \n",
- "
\n",
- " \n",
- " | 8572 | \n",
- " 12/29/2023 | \n",
- " 12.55 | \n",
- " 13.19 | \n",
- " 12.36 | \n",
- " 12.45 | \n",
- "
\n",
- " \n",
- " | 8573 | \n",
- " 01/02/2024 | \n",
- " 13.22 | \n",
- " 14.23 | \n",
- " 13.10 | \n",
- " 13.20 | \n",
- "
\n",
- " \n",
- " | 8574 | \n",
- " 01/03/2024 | \n",
- " 13.35 | \n",
- " 14.22 | \n",
- " 13.33 | \n",
- " 14.04 | \n",
- "
\n",
- " \n",
- " | 8575 | \n",
- " 01/04/2024 | \n",
- " 13.93 | \n",
- " 14.20 | \n",
- " 13.64 | \n",
- " 14.13 | \n",
- "
\n",
- " \n",
- "
\n",
- "
8576 rows × 5 columns
\n",
- "
\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " DATE | \n",
- " OPEN | \n",
- " HIGH | \n",
- " LOW | \n",
- " CLOSE | \n",
- " Level | \n",
- " Year | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 01/02/1990 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 01/03/1990 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 01/04/1990 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 01/05/1990 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 01/08/1990 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- "
\n",
- " \n",
- " | 8572 | \n",
- " 12/29/2023 | \n",
- " 12.55 | \n",
- " 13.19 | \n",
- " 12.36 | \n",
- " 12.45 | \n",
- " Low | \n",
- " 2023 | \n",
- "
\n",
- " \n",
- " | 8573 | \n",
- " 01/02/2024 | \n",
- " 13.22 | \n",
- " 14.23 | \n",
- " 13.10 | \n",
- " 13.20 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8574 | \n",
- " 01/03/2024 | \n",
- " 13.35 | \n",
- " 14.22 | \n",
- " 13.33 | \n",
- " 14.04 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8575 | \n",
- " 01/04/2024 | \n",
- " 13.93 | \n",
- " 14.20 | \n",
- " 13.64 | \n",
- " 14.13 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8576 | \n",
- " 01/05/2024 | \n",
- " 14.24 | \n",
- " 14.58 | \n",
- " 13.29 | \n",
- " 13.35 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- "
\n",
- "
8577 rows × 7 columns
\n",
- "
\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " DATE | \n",
- " OPEN | \n",
- " HIGH | \n",
- " LOW | \n",
- " CLOSE | \n",
- " Level | \n",
- " Year | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 01/02/1990 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 01/03/1990 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 01/04/1990 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 01/05/1990 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 01/08/1990 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- "
\n",
- " \n",
- " | 8573 | \n",
- " 01/02/2024 | \n",
- " 13.22 | \n",
- " 14.23 | \n",
- " 13.10 | \n",
- " 13.20 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8574 | \n",
- " 01/03/2024 | \n",
- " 13.35 | \n",
- " 14.22 | \n",
- " 13.33 | \n",
- " 14.04 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8575 | \n",
- " 01/04/2024 | \n",
- " 13.93 | \n",
- " 14.20 | \n",
- " 13.64 | \n",
- " 14.13 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8576 | \n",
- " 01/05/2024 | \n",
- " 14.24 | \n",
- " 14.58 | \n",
- " 13.29 | \n",
- " 13.35 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8577 | \n",
- " 01/06/2024 | \n",
- " 14.27 | \n",
- " 14.61 | \n",
- " 13.32 | \n",
- " 13.38 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- "
\n",
- "
8578 rows × 7 columns
\n",
- "
\n",
- "\n",
- "2. Replicate 4 times the values of the list `p2_list`. We expect an ouput like this: `[ 2 , 3, 4, 5, 2 , 3, 4, 5, 2 , 3, 4, 5, 2 , 3, 4, 5]`. **Hint: Use multiplication function in `lists`and see the output.**
\n",
- "3. Print the length of `f_list`. **Hint: Length function**
\n",
- "4. Print `My teacher assistant is so boring.` using `text1` list. **Hint: Use the [`join` function](https://stackoverflow.com/questions/493819/why-is-it-string-joinlist-instead-of-list-joinstring)**
\n",
- "5. Print `My TA is so boring, but is very funny.` using `text1` list.**Hint: Use the `join` function, and `extend` method.**
\n",
- "6. Print
\n",
- "`The max value of values1 is 86 and is located in the 0 index. `
\n",
- "`The min value of values1 is 0 and is located in the 7 index. `
**Hint: Use the `f-string`, `min`, and `max` functions.**\n",
- "
\n",
- "7. Get two lists: `names` and `last_names` using `last_and_name` list. **Hint: Use `map` and `split`.**\n",
- "
\n",
- "8. Give only the last names of students who do not have email. Use the `emails` and `last_names` listt. **Hint: Use `map` and `split`.**\n",
- "
"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {},
- "outputs": [],
- "source": [
- "import numpy as np"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 3,
- "metadata": {},
- "outputs": [],
- "source": [
- "f_list = [np.nan , np.nan, \"Austria\", \"Germany\", np.nan, \"Pakistan\", \"np.nan\", np.nan ]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "f_list[0]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 4,
- "metadata": {},
- "outputs": [],
- "source": [
- "text1 = ['My', 'teacher', 'assistant', 'is', 'so', 'boring.']"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "p2_list = [ 2 , 3, 4, 5 ]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "metadata": {},
- "outputs": [],
- "source": [
- "values1 = [ 86, 86, 85, 85, 85, 83, 23, 0, 84, 1 ] "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {},
- "outputs": [],
- "source": [
- "# These two lists a\n",
- "last_and_name = [ \"CORNEJO SANCHEZ, CHRISTIAN SANTOS\", \"ORELLANA QUISPE, CRISTIAN NASSER\", \"MORALES CHOQUEHUANCA, ANGELICA KARINA\", \"GUIMARAY RIBEYRO, JOSE ROBERTO\", \"CAMACHO GAVIDIA, ABEL FERNANDO\", \"TINTAYA ORIHUELA, MEIR ALVARO\", \"CHAVEZ MARTINEZ, JOSELIN ALEXANDRA\", \"FIGUEROA MURO, LEONEL ARTURO\", \"GOMEZ CRIBILLERO, JOSE FELIPE\", \"PALOMINO SEGUÍN, AFRANIA\", \"LUZON CUEVA, BIANCA MARIETTE\", \"SUAÑA ZEGARRA, ADRIAN ANDRE\", \"SOTO POMACHAGUA, DORKAS YOMIRA JHERMY\", \"FIORENTINO MARTINEZ, LADY ALY\", \"LAMA MAVILA, HECTOR ANDRE\", \"MEZA HINOJO, GUSTAVO\", \"LOZADA MURILLO, PERSEO MARCELO\", \"ZAMBRANO JIMENEZ, MIGUEL ALONZO\", \"JACOBS LUQUE, NICOLAS\", \"VIDAL VIDAL, ROCIO GABRIELA\", \"TORRES ANICAMA, JANE CAMILA\", \"LOPEZ ESTRADA, MARIA ELISA\", \"BOYCO ORAMS, ALEJANDRO\", \"DIAZ BERROSPI, KARLINE ROSMELI\", \"RIEGA ESCALANTE, STEPHY ROSARIO\", \"LEVANO TORRES, VALERIA CECILIA\", \"ESQUIVES BRAVO, SEBASTIAN RENATO\", \"PEREZ GONZALES, JUAN CARLOS\", \"OTERO MAGUIÑA, MARIANA\", \"CLAVO CAMPOS, ANDREA BRIZETH\", \"AGUILAR GARCIA, ERICK JOSUE\", \"CALDAS VELASQUEZ, JOSUE DANIEL\", \"SALAS NUÑEZ BORJA, FABIO MANUEL\", \"PIZARRO VILLANES, FERNANDA NICOLLE\", \"QUILLATUPA MORALES, ANGELA ADELINA\", \"HUANCAYA IDONE, CESAR DANTE\", \"CALVO PORTOCARRERO, GABRIELA ISABEL\", \"IBAÑEZ ABANTO, ANGEL MAURICIO\", \"MELÉNDEZ APONTE, JUAN DIEGO\", \"CRISTIAN SERRANO, ARONE\", \"HINOJOSA CAHUANA, PERCY ALBERTH\", \"ANGLAS GARCÍA, KEVIN ARTURO\", \"ALDAVE ACOSTA, CESAR ERNESTO\", \"NÚÑEZ HUAMÁN, CÉSAR AGUSTO\", \"OBREGON HUAMAN, DIANA EDITH\", \"SOTO PACHERRES, RODRIGO FRANCO\", \"INGARUCA RIVERA, GRETTEL ALEXANDRA\", \"ROJAS HUAMAN, ROSA ANGELA\", \"NEYRA SALAS, DANTE OMAR\", \"HUERTA ESPINOZA, YAJAIRA ALEXANDRA\", \"HUANCA MARTINEZ, JORGE ALBERTO\", \"FLORES CADILLO, ALEXIS\" ]\n",
- "emails = [\"cscornejo@pucp.edu.pe\", \"orellana.cn@pucp.edu.pe\", \"karina.morales@pucp.edu.pe\", \"a20083223@pucp.pe\", \"abel.camacho@pucp.pe\", \"mtintaya@pucp.edu.pe\", \"joselin.chavez@pucp.edu.pe\", \"a20105737@pucp.pe\", \"jfgomezc@pucp.pe\", \"afrania.palomino@pucp.pe\", \"luzon.bianca@pucp.pe\", \"adrian.suanaz@pucp.pe\", \"soto.y@pucp.edu.pe\", \"a20132766@pucp.pe\", \"andre.lama@pucp.edu.pe\", \"gustavo.meza@pucp.edu.pe\", \"pmlozada@pucp.edu.pe\", \"m.zambranoj@pucp.edu.pe\", \"nicolas.jacobs@pucp.edu.pe\", \"gvidal@pucp.edu.pe\", \"jane.torres@pucp.edu.pe\", \"m.lopez@pucp.edu.pe\", \"alejandro.boyco@pucp.edu.pe\", \"a20167070@pucp.edu.pe\", \"riega.stephy@pucp.edu.pe\", \"vlevanot@pucp.edu.pe\", \"sesquives@pucp.edu.pe\", \"perez.juanc@pucp.edu.pe\", \"mariana.otero@pucp.edu.pe\", \"aclavo@pucp.edu.pe\", \"a20182474@pucp.edu.pe\", \"josue.caldas@pucp.edu.pe\", \"fabio.salas@pucp.edu.pe\", \"fernanda.pizarro@pucp.edu.pe\", \"aquillatupa@pucp.pe\", \"\", \"\", \"\", \"\", \"\", \"f0873079@pucp.edu.pe\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"flores.alexis@pucp.edu.pe\", ]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "nan_indices = [i for i, value in enumerate(f_list) if isinstance(value, (float, np.floating)) and np.isnan(value)]\n",
- "print(f\"Los índices {', '.join(map(str, nan_indices))} tienen valores np.nan.\")"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## 1.3 Strings\n",
- "\n",
- "\n",
- "1. Drop the duplicated blank spaces in `str1`. Do not use the regular expresions. Do not use the code shown in class. Explain your steps.**Hint: Use `split` method and `join` function.**\n",
- "\n",
- "2. Get the number of letters in the string .**Hint: Use `len`function.**\n",
- "\n",
- "3. Get the number of blank spaces (all of them) in the string .**Hint: Use `len`function.**\n",
- "\n",
- "4. Get the position of `@` in each string in the emails list. **Hint: Use `map`function and `find` method.**\n",
- "\n",
- "5. Identifies if exists `.edu.` in each string in the `emails` list. Get a list of Booleans. **Hint: Use `map`function and `find` method.**\n",
- "\n",
- "6. Get all the strings before the first dot `.`in each string in the `emails` list. Identifies how many of them has `@`. **Hint: Use `map`function and `find` method.**"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "str1 = 'I am too old'"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 18,
- "metadata": {},
- "outputs": [],
- "source": [
- "emails = [\"cscornejo@pucp.edu.pe\", \"orellana.cn@pucp.edu.pe\", \"karina.morales@pucp.edu.pe\", \"a20083223@pucp.pe\", \"abel.camacho@pucp.pe\", \"mtintaya@pucp.edu.pe\", \"joselin.chavez@pucp.edu.pe\", \"a20105737@pucp.pe\", \"jfgomezc@pucp.pe\", \"afrania.palomino@pucp.pe\", \"luzon.bianca@pucp.pe\", \"adrian.suanaz@pucp.pe\", \"soto.y@pucp.edu.pe\", \"a20132766@pucp.pe\", \"andre.lama@pucp.edu.pe\", \"gustavo.meza@pucp.edu.pe\", \"pmlozada@pucp.edu.pe\", \"m.zambranoj@pucp.edu.pe\", \"nicolas.jacobs@pucp.edu.pe\", \"gvidal@pucp.edu.pe\", \"jane.torres@pucp.edu.pe\", \"m.lopez@pucp.edu.pe\", \"alejandro.boyco@pucp.edu.pe\", \"a20167070@pucp.edu.pe\", \"riega.stephy@pucp.edu.pe\", \"vlevanot@pucp.edu.pe\", \"sesquives@pucp.edu.pe\", \"perez.juanc@pucp.edu.pe\", \"mariana.otero@pucp.edu.pe\", \"aclavo@pucp.edu.pe\", \"a20182474@pucp.edu.pe\", \"josue.caldas@pucp.edu.pe\", \"fabio.salas@pucp.edu.pe\", \"fernanda.pizarro@pucp.edu.pe\", \"aquillatupa@pucp.pe\"]"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## 1.4 Pandas\n",
- "\n",
- "You can and should always ask ChatGPT, BARD, Bing, etc.\n",
- "In this exercise, you will work with financial data. Follow the steps below:\n",
- "\n",
- "1. Load Data:\n",
- " Load the financial data available at this URL: https://raw.githubusercontent.com/datasets/finance-vix/main/data/vix-daily.csv\n",
- " Use `pd.read_csv()` adn the link to load the data into a DataFrame.\n",
- "\n",
- "2. Explore Data:\n",
- " a) Display the first five rows of the DataFrame.\n",
- " b) Display the summary statistics of the DataFrame.\n",
- "\n",
- "3. Add Columns:\n",
- " a) Add a new column 'Level' that categorizes the 'Close' column values into 'Low' (< 20), 'Medium' (20-30), and 'High' (>30). You need to make a filter to make this categorization. You can see below some suggestions how to do it.\n",
- " b) Add a new column 'Year' extracted from the 'Date' column. You need to work with dates. You can do it directly workiwith the column splitting it or changing it to date format an dfollowing the below suggestion. \n",
- "\n",
- "4. Add Rows:\n",
- " a) Add a new row with a date of your choice and fill the other columns with appropriate values. \n",
- "\n",
- "5. Analysis:\n",
- " a) Calculate the average of the column 'Close' for each 'Year'. You need to group for this task.\n",
- " b) Count the number of 'High', 'Medium', and 'Low' Level days in the data.\n",
- "\n",
- "Suggestions:\n",
- " - Use `pd.cut()` for categorizing 'Close' values.\n",
- " - Use `pd.to_datetime()` and `dt.year` to extract the year from a date.\n",
- " - Use `DataFrame.append()` or `pd.concat()` to add rows.\n",
- " - Use `groupby()` for aggregation tasks."
- ]
- }
- ],
- "metadata": {
- "hide_input": false,
- "kernelspec": {
- "display_name": "Python 3 (ipykernel)",
- "language": "python",
- "name": "python3"
- },
- "language_info": {
- "codemirror_mode": {
- "name": "ipython",
- "version": 3
- },
- "file_extension": ".py",
- "mimetype": "text/x-python",
- "name": "python",
- "nbconvert_exporter": "python",
- "pygments_lexer": "ipython3",
- "version": "3.11.5"
- },
- "toc": {
- "base_numbering": 1,
- "nav_menu": {},
- "number_sections": true,
- "sideBar": true,
- "skip_h1_title": false,
- "title_cell": "Table of Contents",
- "title_sidebar": "Contents",
- "toc_cell": false,
- "toc_position": {},
- "toc_section_display": true,
- "toc_window_display": false
- }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}
From b61837f8e4081799c68325c0d3640022084fa8be Mon Sep 17 00:00:00 2001
From: JamesMVa <111825034+JamesMVa@users.noreply.github.com>
Date: Sat, 6 Jan 2024 22:19:07 -0500
Subject: [PATCH 04/14] Delete assignments/group_7_ass_2_2024_modificado.ipynb
---
.../group_7_ass_2_2024_modificado.ipynb | 1252 -----------------
1 file changed, 1252 deletions(-)
delete mode 100644 assignments/group_7_ass_2_2024_modificado.ipynb
diff --git a/assignments/group_7_ass_2_2024_modificado.ipynb b/assignments/group_7_ass_2_2024_modificado.ipynb
deleted file mode 100644
index d145f6b1..00000000
--- a/assignments/group_7_ass_2_2024_modificado.ipynb
+++ /dev/null
@@ -1,1252 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "# 1 Assignment 2\n",
- "\n",
- "It is totally prohibited to use any kind of loop. You can use stackoverflow. If you copy codes from previous answers, explain each step. No explanation is `0 points`."
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## 1.2 Lists\n",
- "1. Show the indices of the `np.nan` values in the `f_list` list. We want to see this output: `The indices 0, 1, 4, 7 have np.nan values.` **Hint: Use print function and [f-strings](https://realpython.com/python-f-strings/) to insert the indices values.**
\n",
- "\n",
- "2. Replicate 4 times the values of the list `p2_list`. We expect an ouput like this: `[ 2 , 3, 4, 5, 2 , 3, 4, 5, 2 , 3, 4, 5, 2 , 3, 4, 5]`. **Hint: Use multiplication function in `lists`and see the output.**
\n",
- "3. Print the length of `f_list`. **Hint: Length function**
\n",
- "4. Print `My teacher assistant is so boring.` using `text1` list. **Hint: Use the [`join` function](https://stackoverflow.com/questions/493819/why-is-it-string-joinlist-instead-of-list-joinstring)**
\n",
- "5. Print `My TA is so boring, but is very funny.` using `text1` list.**Hint: Use the `join` function, and `extend` method.**
\n",
- "6. Print
\n",
- "`The max value of values1 is 86 and is located in the 0 index. `
\n",
- "`The min value of values1 is 0 and is located in the 7 index. `
**Hint: Use the `f-string`, `min`, and `max` functions.**\n",
- "
\n",
- "7. Get two lists: `names` and `last_names` using `last_and_name` list. **Hint: Use `map` and `split`.**\n",
- "
\n",
- "8. Give only the last names of students who do not have email. Use the `emails` and `last_names` listt. **Hint: Use `map` and `split`.**\n",
- "
"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 25,
- "metadata": {},
- "outputs": [],
- "source": [
- "import numpy as np"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 26,
- "metadata": {},
- "outputs": [],
- "source": [
- "f_list = [np.nan , np.nan, \"Austria\", \"Germany\", np.nan, \"Pakistan\", \"np.nan\", np.nan ]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 27,
- "metadata": {},
- "outputs": [],
- "source": [
- "text1 = ['My', 'teacher', 'assistant', 'is', 'so', 'boring.']"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 28,
- "metadata": {},
- "outputs": [],
- "source": [
- "p2_list = [ 2 , 3, 4, 5 ]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 49,
- "metadata": {},
- "outputs": [],
- "source": [
- "values1 = [ 86, 86, 85, 85, 85, 83, 23, 0, 84, 1 ] "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 55,
- "metadata": {},
- "outputs": [],
- "source": [
- "# These two lists a\n",
- "last_and_name = [ \"CORNEJO SANCHEZ, CHRISTIAN SANTOS\", \"ORELLANA QUISPE, CRISTIAN NASSER\", \"MORALES CHOQUEHUANCA, ANGELICA KARINA\", \"GUIMARAY RIBEYRO, JOSE ROBERTO\", \"CAMACHO GAVIDIA, ABEL FERNANDO\", \"TINTAYA ORIHUELA, MEIR ALVARO\", \"CHAVEZ MARTINEZ, JOSELIN ALEXANDRA\", \"FIGUEROA MURO, LEONEL ARTURO\", \"GOMEZ CRIBILLERO, JOSE FELIPE\", \"PALOMINO SEGUÍN, AFRANIA\", \"LUZON CUEVA, BIANCA MARIETTE\", \"SUAÑA ZEGARRA, ADRIAN ANDRE\", \"SOTO POMACHAGUA, DORKAS YOMIRA JHERMY\", \"FIORENTINO MARTINEZ, LADY ALY\", \"LAMA MAVILA, HECTOR ANDRE\", \"MEZA HINOJO, GUSTAVO\", \"LOZADA MURILLO, PERSEO MARCELO\", \"ZAMBRANO JIMENEZ, MIGUEL ALONZO\", \"JACOBS LUQUE, NICOLAS\", \"VIDAL VIDAL, ROCIO GABRIELA\", \"TORRES ANICAMA, JANE CAMILA\", \"LOPEZ ESTRADA, MARIA ELISA\", \"BOYCO ORAMS, ALEJANDRO\", \"DIAZ BERROSPI, KARLINE ROSMELI\", \"RIEGA ESCALANTE, STEPHY ROSARIO\", \"LEVANO TORRES, VALERIA CECILIA\", \"ESQUIVES BRAVO, SEBASTIAN RENATO\", \"PEREZ GONZALES, JUAN CARLOS\", \"OTERO MAGUIÑA, MARIANA\", \"CLAVO CAMPOS, ANDREA BRIZETH\", \"AGUILAR GARCIA, ERICK JOSUE\", \"CALDAS VELASQUEZ, JOSUE DANIEL\", \"SALAS NUÑEZ BORJA, FABIO MANUEL\", \"PIZARRO VILLANES, FERNANDA NICOLLE\", \"QUILLATUPA MORALES, ANGELA ADELINA\", \"HUANCAYA IDONE, CESAR DANTE\", \"CALVO PORTOCARRERO, GABRIELA ISABEL\", \"IBAÑEZ ABANTO, ANGEL MAURICIO\", \"MELÉNDEZ APONTE, JUAN DIEGO\", \"CRISTIAN SERRANO, ARONE\", \"HINOJOSA CAHUANA, PERCY ALBERTH\", \"ANGLAS GARCÍA, KEVIN ARTURO\", \"ALDAVE ACOSTA, CESAR ERNESTO\", \"NÚÑEZ HUAMÁN, CÉSAR AGUSTO\", \"OBREGON HUAMAN, DIANA EDITH\", \"SOTO PACHERRES, RODRIGO FRANCO\", \"INGARUCA RIVERA, GRETTEL ALEXANDRA\", \"ROJAS HUAMAN, ROSA ANGELA\", \"NEYRA SALAS, DANTE OMAR\", \"HUERTA ESPINOZA, YAJAIRA ALEXANDRA\", \"HUANCA MARTINEZ, JORGE ALBERTO\", \"FLORES CADILLO, ALEXIS\" ]\n",
- "emails = [\"cscornejo@pucp.edu.pe\", \"orellana.cn@pucp.edu.pe\", \"karina.morales@pucp.edu.pe\", \"a20083223@pucp.pe\", \"abel.camacho@pucp.pe\", \"mtintaya@pucp.edu.pe\", \"joselin.chavez@pucp.edu.pe\", \"a20105737@pucp.pe\", \"jfgomezc@pucp.pe\", \"afrania.palomino@pucp.pe\", \"luzon.bianca@pucp.pe\", \"adrian.suanaz@pucp.pe\", \"soto.y@pucp.edu.pe\", \"a20132766@pucp.pe\", \"andre.lama@pucp.edu.pe\", \"gustavo.meza@pucp.edu.pe\", \"pmlozada@pucp.edu.pe\", \"m.zambranoj@pucp.edu.pe\", \"nicolas.jacobs@pucp.edu.pe\", \"gvidal@pucp.edu.pe\", \"jane.torres@pucp.edu.pe\", \"m.lopez@pucp.edu.pe\", \"alejandro.boyco@pucp.edu.pe\", \"a20167070@pucp.edu.pe\", \"riega.stephy@pucp.edu.pe\", \"vlevanot@pucp.edu.pe\", \"sesquives@pucp.edu.pe\", \"perez.juanc@pucp.edu.pe\", \"mariana.otero@pucp.edu.pe\", \"aclavo@pucp.edu.pe\", \"a20182474@pucp.edu.pe\", \"josue.caldas@pucp.edu.pe\", \"fabio.salas@pucp.edu.pe\", \"fernanda.pizarro@pucp.edu.pe\", \"aquillatupa@pucp.pe\", \"\", \"\", \"\", \"\", \"\", \"f0873079@pucp.edu.pe\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"flores.alexis@pucp.edu.pe\", ]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 43,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "The indices [0, 1, 4, 7] have np.nan values.\n"
- ]
- }
- ],
- "source": [
- "# Answer 1\n",
- "nan_values = [i for i, value in enumerate(f_list) if value is np.nan]\n",
- "print(f\"The indices {nan_values} have np.nan values.\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 44,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "[2, 3, 4, 5, 2, 3, 4, 5, 2, 3, 4, 5, 2, 3, 4, 5]\n"
- ]
- }
- ],
- "source": [
- "# Answer 2\n",
- "p2_list_2 = p2_list * 4\n",
- "print(p2_list_2)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 45,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "8\n"
- ]
- }
- ],
- "source": [
- "# Answer 3\n",
- "print(len(f_list))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 46,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "'My teacher assistant is so boring.'"
- ]
- },
- "execution_count": 46,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# Answer 4\n",
- "answer_4 = ' '.join(text1)\n",
- "answer_4"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 47,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "'My TA My teacher assistant is so boring but is very funny'"
- ]
- },
- "execution_count": 47,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# Answer 5\n",
- "text1[-1] = text1[-1].rstrip('.')\n",
- "text_answer = ['My', 'TA']\n",
- "text_answer_b = ['but', 'is', 'very', 'funny']\n",
- "text_answer.extend(text1 + text_answer_b)\n",
- "answer_5 = ' '.join(text_answer)\n",
- "answer_5"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 50,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "The max value of values1 is 86 and is located in the 0 index.\n"
- ]
- }
- ],
- "source": [
- "# Answer 6.1\n",
- "max_index = values1.index(max(values1))\n",
- "print(f\"The max value of values1 is {max(values1)} and is located in the {max_index} index.\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 51,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "The min value of values1 is 0 and is located in the 7 index.\n"
- ]
- }
- ],
- "source": [
- "# Answer 6.2\n",
- "min_index = values1.index(min(values1))\n",
- "print(f\"The min value of values1 is {min(values1)} and is located in the {min_index} index.\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 53,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Names: ('CHRISTIAN SANTOS', 'CRISTIAN NASSER', 'ANGELICA KARINA', 'JOSE ROBERTO', 'ABEL FERNANDO', 'MEIR ALVARO', 'JOSELIN ALEXANDRA', 'LEONEL ARTURO', 'JOSE FELIPE', 'AFRANIA', 'BIANCA MARIETTE', 'ADRIAN ANDRE', 'DORKAS YOMIRA JHERMY', 'LADY ALY', 'HECTOR ANDRE', 'GUSTAVO', 'PERSEO MARCELO', 'MIGUEL ALONZO', 'NICOLAS', 'ROCIO GABRIELA', 'JANE CAMILA', 'MARIA ELISA', 'ALEJANDRO', 'KARLINE ROSMELI', 'STEPHY ROSARIO', 'VALERIA CECILIA', 'SEBASTIAN RENATO', 'JUAN CARLOS', 'MARIANA', 'ANDREA BRIZETH', 'ERICK JOSUE', 'JOSUE DANIEL', 'FABIO MANUEL', 'FERNANDA NICOLLE', 'ANGELA ADELINA', 'CESAR DANTE', 'GABRIELA ISABEL', 'ANGEL MAURICIO', 'JUAN DIEGO', 'ARONE', 'PERCY ALBERTH', 'KEVIN ARTURO', 'CESAR ERNESTO', 'CÉSAR AGUSTO', 'DIANA EDITH', 'RODRIGO FRANCO', 'GRETTEL ALEXANDRA', 'ROSA ANGELA', 'DANTE OMAR', 'YAJAIRA ALEXANDRA', 'JORGE ALBERTO', 'ALEXIS')\n",
- "Last Names: ('CORNEJO SANCHEZ', 'ORELLANA QUISPE', 'MORALES CHOQUEHUANCA', 'GUIMARAY RIBEYRO', 'CAMACHO GAVIDIA', 'TINTAYA ORIHUELA', 'CHAVEZ MARTINEZ', 'FIGUEROA MURO', 'GOMEZ CRIBILLERO', 'PALOMINO SEGUÍN', 'LUZON CUEVA', 'SUAÑA ZEGARRA', 'SOTO POMACHAGUA', 'FIORENTINO MARTINEZ', 'LAMA MAVILA', 'MEZA HINOJO', 'LOZADA MURILLO', 'ZAMBRANO JIMENEZ', 'JACOBS LUQUE', 'VIDAL VIDAL', 'TORRES ANICAMA', 'LOPEZ ESTRADA', 'BOYCO ORAMS', 'DIAZ BERROSPI', 'RIEGA ESCALANTE', 'LEVANO TORRES', 'ESQUIVES BRAVO', 'PEREZ GONZALES', 'OTERO MAGUIÑA', 'CLAVO CAMPOS', 'AGUILAR GARCIA', 'CALDAS VELASQUEZ', 'SALAS NUÑEZ BORJA', 'PIZARRO VILLANES', 'QUILLATUPA MORALES', 'HUANCAYA IDONE', 'CALVO PORTOCARRERO', 'IBAÑEZ ABANTO', 'MELÉNDEZ APONTE', 'CRISTIAN SERRANO', 'HINOJOSA CAHUANA', 'ANGLAS GARCÍA', 'ALDAVE ACOSTA', 'NÚÑEZ HUAMÁN', 'OBREGON HUAMAN', 'SOTO PACHERRES', 'INGARUCA RIVERA', 'ROJAS HUAMAN', 'NEYRA SALAS', 'HUERTA ESPINOZA', 'HUANCA MARTINEZ', 'FLORES CADILLO')\n"
- ]
- }
- ],
- "source": [
- "# Answer 7\n",
- "last_names, names = zip(*map(lambda x: x.split(', '), last_and_name))\n",
- " # the lambda function using split divides each name from each last name\n",
- " # the function zip takes the values and puts them in tuples\n",
- " # \"last_names, names\" indicates the code to split the tuples in two separate lists\n",
- "print(\"Names:\", names)\n",
- "print(\"Last Names:\",last_names)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 56,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "['HUANCAYA IDONE', 'CALVO PORTOCARRERO', 'IBAÑEZ ABANTO', 'MELÉNDEZ APONTE', 'CRISTIAN SERRANO', 'ANGLAS GARCÍA', 'ALDAVE ACOSTA', 'NÚÑEZ HUAMÁN', 'OBREGON HUAMAN', 'SOTO PACHERRES', 'INGARUCA RIVERA', 'ROJAS HUAMAN', 'NEYRA SALAS', 'HUERTA ESPINOZA', 'HUANCA MARTINEZ']\n"
- ]
- }
- ],
- "source": [
- "# Answer 8\n",
- "answer_8 = [last_name for last_name, email in zip(last_names, emails) if not email]\n",
- " # zip function pairs last names with its corresponding emails into tuples\n",
- " # \"last_name for last_name, email in ... if not email\" indicates the last name for each pair if email is empty\n",
- "print(answer_8)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## 1.3 Strings\n",
- "\n",
- "\n",
- "1. Drop the duplicated blank spaces in `str1`. Do not use the regular expresions. Do not use the code shown in class. Explain your steps.**Hint: Use `split` method and `join` function.**\n",
- "\n",
- "2. Get the number of letters in the string .**Hint: Use `len`function.**\n",
- "\n",
- "3. Get the number of blank spaces (all of them) in the string .**Hint: Use `len`function.**\n",
- "\n",
- "4. Get the position of `@` in each string in the emails list. **Hint: Use `map`function and `find` method.**\n",
- "\n",
- "5. Identifies if exists `.edu.` in each string in the `emails` list. Get a list of Booleans. **Hint: Use `map`function and `find` method.**\n",
- "\n",
- "6. Get all the strings before the first dot `.`in each string in the `emails` list. Identifies how many of them has `@`. **Hint: Use `map`function and `find` method.**"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 30,
- "metadata": {},
- "outputs": [],
- "source": [
- "str1 = 'I am too old'"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 31,
- "metadata": {},
- "outputs": [],
- "source": [
- "emails = [\"cscornejo@pucp.edu.pe\", \"orellana.cn@pucp.edu.pe\", \"karina.morales@pucp.edu.pe\", \"a20083223@pucp.pe\", \"abel.camacho@pucp.pe\", \"mtintaya@pucp.edu.pe\", \"joselin.chavez@pucp.edu.pe\", \"a20105737@pucp.pe\", \"jfgomezc@pucp.pe\", \"afrania.palomino@pucp.pe\", \"luzon.bianca@pucp.pe\", \"adrian.suanaz@pucp.pe\", \"soto.y@pucp.edu.pe\", \"a20132766@pucp.pe\", \"andre.lama@pucp.edu.pe\", \"gustavo.meza@pucp.edu.pe\", \"pmlozada@pucp.edu.pe\", \"m.zambranoj@pucp.edu.pe\", \"nicolas.jacobs@pucp.edu.pe\", \"gvidal@pucp.edu.pe\", \"jane.torres@pucp.edu.pe\", \"m.lopez@pucp.edu.pe\", \"alejandro.boyco@pucp.edu.pe\", \"a20167070@pucp.edu.pe\", \"riega.stephy@pucp.edu.pe\", \"vlevanot@pucp.edu.pe\", \"sesquives@pucp.edu.pe\", \"perez.juanc@pucp.edu.pe\", \"mariana.otero@pucp.edu.pe\", \"aclavo@pucp.edu.pe\", \"a20182474@pucp.edu.pe\", \"josue.caldas@pucp.edu.pe\", \"fabio.salas@pucp.edu.pe\", \"fernanda.pizarro@pucp.edu.pe\", \"aquillatupa@pucp.pe\"]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 32,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "I am too old\n"
- ]
- }
- ],
- "source": [
- "# 1. Drop the duplicated blank spaces in str1. Do not use the regular expresions. Do not use the code shown in class. Explain your steps.Hint: Use split method and join function.\n",
- "\n",
- "# First, we split the string into a list of words\n",
- "list_words = str1.split()\n",
- "\n",
- "# Then, we remove the empty strings from the list\n",
- "non_empty_words = [word for word in list_words if word]\n",
- "\n",
- "# Lastly, we join the non-empty words back into a string\n",
- "result_str = ' '.join(non_empty_words)\n",
- "\n",
- "print(result_str)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 34,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Number of letters: 9\n"
- ]
- }
- ],
- "source": [
- "# 2. Get the number of letters in the string .Hint: Use lenfunction.\n",
- "\n",
- "# In order to count the number of letters, we need to remove non-alphabetic characters first, we do that \n",
- "# using the len function (to printe the lenght)\n",
- "# and verifying that the character is alphabetic (a letter), using the if function.\n",
- "num_letters = len([char for char in str1 if char.isalpha()])\n",
- "\n",
- "# This is a better way to print the answer, including the string value \"Number of letters\"\n",
- "print(\"Number of letters:\",num_letters)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 35,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Number of blank spaces: 85\n"
- ]
- }
- ],
- "source": [
- "# 3. Get the number of blank spaces (all of them) in the string .Hint: Use lenfunction.\n",
- "\n",
- "# First, we create a list with the blank spaces, using the \"isspace\" method\n",
- "blank_space = [char for char in str1 if char.isspace()]\n",
- "\n",
- "# Then we apply the function len() to the list to get the total number of blank spaces\n",
- "num_blank_spaces = len(blank_space)\n",
- "\n",
- "# Finally, we print the result\n",
- "print(\"Number of blank spaces:\", num_blank_spaces)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 37,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Positions of '@': [9, 11, 14, 9, 12, 8, 14, 9, 8, 16, 12, 13, 6, 9, 10, 12, 8, 11, 14, 6, 11, 7, 15, 9, 12, 8, 9, 11, 13, 6, 9, 12, 11, 16, 11]\n"
- ]
- }
- ],
- "source": [
- "# 4. Get the position of @ in each string in the emails list. Hint: Use mapfunction and find method.\n",
- "\n",
- "# First we use the map() function to apply the specified lambda function to each element in the emails list. \n",
- "# Then, with the lambda function takes an email address (email) and finds the position of the '@' symbol using the find() method.\n",
- "# Also, list(...) Converts the result into a list.\n",
- "positions_at = list(map(lambda email: email.find('@'), emails))\n",
- "\n",
- "# Finally, we print the results\n",
- "print(\"Positions of '@':\",positions_at)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 38,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Contains '.edu.': [True, True, True, False, False, True, True, False, False, False, False, False, True, False, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, False]\n"
- ]
- }
- ],
- "source": [
- "# 5. Identifies if exists .edu. in each string in the emails list. Get a list of Booleans. Hint: Use mapfunction and find method. # \n",
- "\n",
- "# First, we use the map function to apply a lambda function to each element in the emails list.\n",
- "# The lambda function checks if '.edu.' is present in each email address.\n",
- "contains_edu_lambda = lambda email: '.edu.' in email\n",
- "mapped_result = map(contains_edu_lambda, emails)\n",
- "\n",
- "# Then, we convert the mapped result into a list.\n",
- "contains_edu_list = list(mapped_result)\n",
- "\n",
- "# Finally we print the result\n",
- "print(\"Contains '.edu.':\",contains_edu_list)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 39,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Substrings before the first dot: ['cscornejo@pucp', 'orellana', 'karina', 'a20083223@pucp', 'abel', 'mtintaya@pucp', 'joselin', 'a20105737@pucp', 'jfgomezc@pucp', 'afrania', 'luzon', 'adrian', 'soto', 'a20132766@pucp', 'andre', 'gustavo', 'pmlozada@pucp', 'm', 'nicolas', 'gvidal@pucp', 'jane', 'm', 'alejandro', 'a20167070@pucp', 'riega', 'vlevanot@pucp', 'sesquives@pucp', 'perez', 'mariana', 'aclavo@pucp', 'a20182474@pucp', 'josue', 'fabio', 'fernanda', 'aquillatupa@pucp']\n",
- "Number of substrings containing '@': 14\n"
- ]
- }
- ],
- "source": [
- "# 6. Get all the strings before the first dot '.' in each string in the emails list.\n",
- "# First, we identify how many of them have '@'.\n",
- "\n",
- "# Then we use the map function to apply a lambda function to each element in the emails list.\n",
- "# The lambda function extracts the substring before the first dot '.' and checks if it contains '@'.\n",
- "substring_before_dot_lambda = lambda email: email.split('.')[0]\n",
- "mapped_result = map(substring_before_dot_lambda, emails)\n",
- "\n",
- "# After that, we convert the mapped result into a list.\n",
- "substring_before_dot_list = list(mapped_result)\n",
- "\n",
- "# Also, we count how many substrings contain '@' and print the results\n",
- "count_with_at = sum('@' in substring for substring in substring_before_dot_list)\n",
- "\n",
- "print(\"Substrings before the first dot:\", substring_before_dot_list)\n",
- "print(\"Number of substrings containing '@':\",count_with_at)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## 1.4 Pandas\n",
- "\n",
- "You can and should always ask ChatGPT, BARD, Bing, etc.\n",
- "In this exercise, you will work with financial data. Follow the steps below:\n",
- "\n",
- "1. Load Data:\n",
- " Load the financial data available at this URL: https://raw.githubusercontent.com/datasets/finance-vix/main/data/vix-daily.csv\n",
- " Use `pd.read_csv()` adn the link to load the data into a DataFrame.\n",
- "\n",
- "2. Explore Data:\n",
- " a) Display the first five rows of the DataFrame.\n",
- " b) Display the summary statistics of the DataFrame.\n",
- "\n",
- "3. Add Columns:\n",
- " a) Add a new column 'Level' that categorizes the 'Close' column values into 'Low' (< 20), 'Medium' (20-30), and 'High' (>30). You need to make a filter to make this categorization. You can see below some suggestions how to do it.\n",
- " b) Add a new column 'Year' extracted from the 'Date' column. You need to work with dates. You can do it directly workiwith the column splitting it or changing it to date format an dfollowing the below suggestion. \n",
- "\n",
- "4. Add Rows:\n",
- " a) Add a new row with a date of your choice and fill the other columns with appropriate values. \n",
- "\n",
- "5. Analysis:\n",
- " a) Calculate the average of the column 'Close' for each 'Year'. You need to group for this task.\n",
- " b) Count the number of 'High', 'Medium', and 'Low' Level days in the data.\n",
- "\n",
- "Suggestions:\n",
- " - Use `pd.cut()` for categorizing 'Close' values.\n",
- " - Use `pd.to_datetime()` and `dt.year` to extract the year from a date.\n",
- " - Use `DataFrame.append()` or `pd.concat()` to add rows.\n",
- " - Use `groupby()` for aggregation tasks."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 40,
- "metadata": {},
- "outputs": [],
- "source": [
- "import pandas as pd\n",
- "\n",
- "# Este código carga los datos desde la URL proporcionada\n",
- "url = \"https://raw.githubusercontent.com/datasets/finance-vix/main/data/vix-daily.csv\"\n",
- "df = pd.read_csv(url)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 41,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " DATE | \n",
- " OPEN | \n",
- " HIGH | \n",
- " LOW | \n",
- " CLOSE | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 01/02/1990 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 01/03/1990 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 01/04/1990 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 01/05/1990 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 01/08/1990 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- "
\n",
- " \n",
- " | ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- "
\n",
- " \n",
- " | 8572 | \n",
- " 12/29/2023 | \n",
- " 12.55 | \n",
- " 13.19 | \n",
- " 12.36 | \n",
- " 12.45 | \n",
- "
\n",
- " \n",
- " | 8573 | \n",
- " 01/02/2024 | \n",
- " 13.22 | \n",
- " 14.23 | \n",
- " 13.10 | \n",
- " 13.20 | \n",
- "
\n",
- " \n",
- " | 8574 | \n",
- " 01/03/2024 | \n",
- " 13.35 | \n",
- " 14.22 | \n",
- " 13.33 | \n",
- " 14.04 | \n",
- "
\n",
- " \n",
- " | 8575 | \n",
- " 01/04/2024 | \n",
- " 13.93 | \n",
- " 14.20 | \n",
- " 13.64 | \n",
- " 14.13 | \n",
- "
\n",
- " \n",
- " | 8576 | \n",
- " 01/05/2024 | \n",
- " 14.24 | \n",
- " 14.58 | \n",
- " 13.29 | \n",
- " 13.35 | \n",
- "
\n",
- " \n",
- "
\n",
- "
8577 rows × 5 columns
\n",
- "
\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " DATE | \n",
- " OPEN | \n",
- " HIGH | \n",
- " LOW | \n",
- " CLOSE | \n",
- " Level | \n",
- " Year | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 01/02/1990 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 01/03/1990 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 01/04/1990 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 01/05/1990 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 01/08/1990 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- "
\n",
- " \n",
- " | 8572 | \n",
- " 12/29/2023 | \n",
- " 12.55 | \n",
- " 13.19 | \n",
- " 12.36 | \n",
- " 12.45 | \n",
- " Low | \n",
- " 2023 | \n",
- "
\n",
- " \n",
- " | 8573 | \n",
- " 01/02/2024 | \n",
- " 13.22 | \n",
- " 14.23 | \n",
- " 13.10 | \n",
- " 13.20 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8574 | \n",
- " 01/03/2024 | \n",
- " 13.35 | \n",
- " 14.22 | \n",
- " 13.33 | \n",
- " 14.04 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8575 | \n",
- " 01/04/2024 | \n",
- " 13.93 | \n",
- " 14.20 | \n",
- " 13.64 | \n",
- " 14.13 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8576 | \n",
- " 01/05/2024 | \n",
- " 14.24 | \n",
- " 14.58 | \n",
- " 13.29 | \n",
- " 13.35 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- "
\n",
- "
8577 rows × 7 columns
\n",
- "
\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " DATE | \n",
- " OPEN | \n",
- " HIGH | \n",
- " LOW | \n",
- " CLOSE | \n",
- " Level | \n",
- " Year | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 01/02/1990 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 01/03/1990 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 01/04/1990 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 01/05/1990 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 01/08/1990 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- "
\n",
- " \n",
- " | 8573 | \n",
- " 01/02/2024 | \n",
- " 13.22 | \n",
- " 14.23 | \n",
- " 13.10 | \n",
- " 13.20 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8574 | \n",
- " 01/03/2024 | \n",
- " 13.35 | \n",
- " 14.22 | \n",
- " 13.33 | \n",
- " 14.04 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8575 | \n",
- " 01/04/2024 | \n",
- " 13.93 | \n",
- " 14.20 | \n",
- " 13.64 | \n",
- " 14.13 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8576 | \n",
- " 01/05/2024 | \n",
- " 14.24 | \n",
- " 14.58 | \n",
- " 13.29 | \n",
- " 13.35 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8577 | \n",
- " 01/06/2024 | \n",
- " 14.27 | \n",
- " 14.61 | \n",
- " 13.32 | \n",
- " 13.38 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- "
\n",
- "
8578 rows × 7 columns
\n",
- "
\n",
- "\n",
- "2. Replicate 4 times the values of the list `p2_list`. We expect an ouput like this: `[ 2 , 3, 4, 5, 2 , 3, 4, 5, 2 , 3, 4, 5, 2 , 3, 4, 5]`. **Hint: Use multiplication function in `lists`and see the output.**
\n",
- "3. Print the length of `f_list`. **Hint: Length function**
\n",
- "4. Print `My teacher assistant is so boring.` using `text1` list. **Hint: Use the [`join` function](https://stackoverflow.com/questions/493819/why-is-it-string-joinlist-instead-of-list-joinstring)**
\n",
- "5. Print `My TA is so boring, but is very funny.` using `text1` list.**Hint: Use the `join` function, and `extend` method.**
\n",
- "6. Print
\n",
- "`The max value of values1 is 86 and is located in the 0 index. `
\n",
- "`The min value of values1 is 0 and is located in the 7 index. `
**Hint: Use the `f-string`, `min`, and `max` functions.**\n",
- "
\n",
- "7. Get two lists: `names` and `last_names` using `last_and_name` list. **Hint: Use `map` and `split`.**\n",
- "
\n",
- "8. Give only the last names of students who do not have email. Use the `emails` and `last_names` listt. **Hint: Use `map` and `split`.**\n",
- "
"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {},
- "outputs": [],
- "source": [
- "import numpy as np"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 3,
- "metadata": {},
- "outputs": [],
- "source": [
- "f_list = [np.nan , np.nan, \"Austria\", \"Germany\", np.nan, \"Pakistan\", \"np.nan\", np.nan ]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 4,
- "metadata": {},
- "outputs": [],
- "source": [
- "text1 = ['My', 'teacher', 'assistant', 'is', 'so', 'boring.']"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "p2_list = [ 2 , 3, 4, 5 ]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "metadata": {},
- "outputs": [],
- "source": [
- "values1 = [ 86, 86, 85, 85, 85, 83, 23, 0, 84, 1 ] "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 32,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "52"
- ]
- },
- "execution_count": 32,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# These two lists a\n",
- "last_and_name = [ \"CORNEJO SANCHEZ, CHRISTIAN SANTOS\", \"ORELLANA QUISPE, CRISTIAN NASSER\", \"MORALES CHOQUEHUANCA, ANGELICA KARINA\", \"GUIMARAY RIBEYRO, JOSE ROBERTO\", \"CAMACHO GAVIDIA, ABEL FERNANDO\", \"TINTAYA ORIHUELA, MEIR ALVARO\", \"CHAVEZ MARTINEZ, JOSELIN ALEXANDRA\", \"FIGUEROA MURO, LEONEL ARTURO\", \"GOMEZ CRIBILLERO, JOSE FELIPE\", \"PALOMINO SEGUÍN, AFRANIA\", \"LUZON CUEVA, BIANCA MARIETTE\", \"SUAÑA ZEGARRA, ADRIAN ANDRE\", \"SOTO POMACHAGUA, DORKAS YOMIRA JHERMY\", \"FIORENTINO MARTINEZ, LADY ALY\", \"LAMA MAVILA, HECTOR ANDRE\", \"MEZA HINOJO, GUSTAVO\", \"LOZADA MURILLO, PERSEO MARCELO\", \"ZAMBRANO JIMENEZ, MIGUEL ALONZO\", \"JACOBS LUQUE, NICOLAS\", \"VIDAL VIDAL, ROCIO GABRIELA\", \"TORRES ANICAMA, JANE CAMILA\", \"LOPEZ ESTRADA, MARIA ELISA\", \"BOYCO ORAMS, ALEJANDRO\", \"DIAZ BERROSPI, KARLINE ROSMELI\", \"RIEGA ESCALANTE, STEPHY ROSARIO\", \"LEVANO TORRES, VALERIA CECILIA\", \"ESQUIVES BRAVO, SEBASTIAN RENATO\", \"PEREZ GONZALES, JUAN CARLOS\", \"OTERO MAGUIÑA, MARIANA\", \"CLAVO CAMPOS, ANDREA BRIZETH\", \"AGUILAR GARCIA, ERICK JOSUE\", \"CALDAS VELASQUEZ, JOSUE DANIEL\", \"SALAS NUÑEZ BORJA, FABIO MANUEL\", \"PIZARRO VILLANES, FERNANDA NICOLLE\", \"QUILLATUPA MORALES, ANGELA ADELINA\", \"HUANCAYA IDONE, CESAR DANTE\", \"CALVO PORTOCARRERO, GABRIELA ISABEL\", \"IBAÑEZ ABANTO, ANGEL MAURICIO\", \"MELÉNDEZ APONTE, JUAN DIEGO\", \"CRISTIAN SERRANO, ARONE\", \"HINOJOSA CAHUANA, PERCY ALBERTH\", \"ANGLAS GARCÍA, KEVIN ARTURO\", \"ALDAVE ACOSTA, CESAR ERNESTO\", \"NÚÑEZ HUAMÁN, CÉSAR AGUSTO\", \"OBREGON HUAMAN, DIANA EDITH\", \"SOTO PACHERRES, RODRIGO FRANCO\", \"INGARUCA RIVERA, GRETTEL ALEXANDRA\", \"ROJAS HUAMAN, ROSA ANGELA\", \"NEYRA SALAS, DANTE OMAR\", \"HUERTA ESPINOZA, YAJAIRA ALEXANDRA\", \"HUANCA MARTINEZ, JORGE ALBERTO\", \"FLORES CADILLO, ALEXIS\" ]\n",
- "emails = [\"cscornejo@pucp.edu.pe\", \"orellana.cn@pucp.edu.pe\", \"karina.morales@pucp.edu.pe\", \"a20083223@pucp.pe\", \"abel.camacho@pucp.pe\", \"mtintaya@pucp.edu.pe\", \"joselin.chavez@pucp.edu.pe\", \"a20105737@pucp.pe\", \"jfgomezc@pucp.pe\", \"afrania.palomino@pucp.pe\", \"luzon.bianca@pucp.pe\", \"adrian.suanaz@pucp.pe\", \"soto.y@pucp.edu.pe\", \"a20132766@pucp.pe\", \"andre.lama@pucp.edu.pe\", \"gustavo.meza@pucp.edu.pe\", \"pmlozada@pucp.edu.pe\", \"m.zambranoj@pucp.edu.pe\", \"nicolas.jacobs@pucp.edu.pe\", \"gvidal@pucp.edu.pe\", \"jane.torres@pucp.edu.pe\", \"m.lopez@pucp.edu.pe\", \"alejandro.boyco@pucp.edu.pe\", \"a20167070@pucp.edu.pe\", \"riega.stephy@pucp.edu.pe\", \"vlevanot@pucp.edu.pe\", \"sesquives@pucp.edu.pe\", \"perez.juanc@pucp.edu.pe\", \"mariana.otero@pucp.edu.pe\", \"aclavo@pucp.edu.pe\", \"a20182474@pucp.edu.pe\", \"josue.caldas@pucp.edu.pe\", \"fabio.salas@pucp.edu.pe\", \"fernanda.pizarro@pucp.edu.pe\", \"aquillatupa@pucp.pe\", \"\", \"\", \"\", \"\", \"\", \"f0873079@pucp.edu.pe\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"flores.alexis@pucp.edu.pe\", ]"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## 1.3 Strings\n",
- "\n",
- "\n",
- "1. Drop the duplicated blank spaces in `str1`. Do not use the regular expresions. Do not use the code shown in class. Explain your steps.**Hint: Use `split` method and `join` function.**\n",
- "\n",
- "2. Get the number of letters in the string .**Hint: Use `len`function.**\n",
- "\n",
- "3. Get the number of blank spaces (all of them) in the string .**Hint: Use `len`function.**\n",
- "\n",
- "4. Get the position of `@` in each string in the emails list. **Hint: Use `map`function and `find` method.**\n",
- "\n",
- "5. Identifies if exists `.edu.` in each string in the `emails` list. Get a list of Booleans. **Hint: Use `map`function and `find` method.**\n",
- "\n",
- "6. Get all the strings before the first dot `.`in each string in the `emails` list. Identifies how many of them has `@`. **Hint: Use `map`function and `find` method.**"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "str1 = 'I am too old'"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 18,
- "metadata": {},
- "outputs": [],
- "source": [
- "emails = [\"cscornejo@pucp.edu.pe\", \"orellana.cn@pucp.edu.pe\", \"karina.morales@pucp.edu.pe\", \"a20083223@pucp.pe\", \"abel.camacho@pucp.pe\", \"mtintaya@pucp.edu.pe\", \"joselin.chavez@pucp.edu.pe\", \"a20105737@pucp.pe\", \"jfgomezc@pucp.pe\", \"afrania.palomino@pucp.pe\", \"luzon.bianca@pucp.pe\", \"adrian.suanaz@pucp.pe\", \"soto.y@pucp.edu.pe\", \"a20132766@pucp.pe\", \"andre.lama@pucp.edu.pe\", \"gustavo.meza@pucp.edu.pe\", \"pmlozada@pucp.edu.pe\", \"m.zambranoj@pucp.edu.pe\", \"nicolas.jacobs@pucp.edu.pe\", \"gvidal@pucp.edu.pe\", \"jane.torres@pucp.edu.pe\", \"m.lopez@pucp.edu.pe\", \"alejandro.boyco@pucp.edu.pe\", \"a20167070@pucp.edu.pe\", \"riega.stephy@pucp.edu.pe\", \"vlevanot@pucp.edu.pe\", \"sesquives@pucp.edu.pe\", \"perez.juanc@pucp.edu.pe\", \"mariana.otero@pucp.edu.pe\", \"aclavo@pucp.edu.pe\", \"a20182474@pucp.edu.pe\", \"josue.caldas@pucp.edu.pe\", \"fabio.salas@pucp.edu.pe\", \"fernanda.pizarro@pucp.edu.pe\", \"aquillatupa@pucp.pe\"]"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## 1.4 Pandas\n",
- "\n",
- "You can and should always ask ChatGPT, BARD, Bing, etc.\n",
- "In this exercise, you will work with financial data. Follow the steps below:\n",
- "\n",
- "1. Load Data:\n",
- " Load the financial data available at this URL: https://raw.githubusercontent.com/datasets/finance-vix/main/data/vix-daily.csv\n",
- " Use `pd.read_csv()` adn the link to load the data into a DataFrame.\n",
- "\n",
- "2. Explore Data:\n",
- " a) Display the first five rows of the DataFrame.\n",
- " b) Display the summary statistics of the DataFrame.\n",
- "\n",
- "3. Add Columns:\n",
- " a) Add a new column 'Level' that categorizes the 'Close' column values into 'Low' (< 20), 'Medium' (20-30), and 'High' (>30). You need to make a filter to make this categorization. You can see below some suggestions how to do it.\n",
- " b) Add a new column 'Year' extracted from the 'Date' column. You need to work with dates. You can do it directly workiwith the column splitting it or changing it to date format an dfollowing the below suggestion. \n",
- "\n",
- "4. Add Rows:\n",
- " a) Add a new row with a date of your choice and fill the other columns with appropriate values. \n",
- "\n",
- "5. Analysis:\n",
- " a) Calculate the average of the column 'Close' for each 'Year'. You need to group for this task.\n",
- " b) Count the number of 'High', 'Medium', and 'Low' Level days in the data.\n",
- "\n",
- "Suggestions:\n",
- " - Use `pd.cut()` for categorizing 'Close' values.\n",
- " - Use `pd.to_datetime()` and `dt.year` to extract the year from a date.\n",
- " - Use `DataFrame.append()` or `pd.concat()` to add rows.\n",
- " - Use `groupby()` for aggregation tasks."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 1,
- "metadata": {},
- "outputs": [],
- "source": [
- "import pandas as pd\n",
- "\n",
- "# Este código carga los datos desde la URL proporcionada\n",
- "url = \"https://raw.githubusercontent.com/datasets/finance-vix/main/data/vix-daily.csv\"\n",
- "df = pd.read_csv(url)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " DATE | \n",
- " OPEN | \n",
- " HIGH | \n",
- " LOW | \n",
- " CLOSE | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 01/02/1990 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 01/03/1990 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 01/04/1990 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 01/05/1990 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 01/08/1990 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- "
\n",
- " \n",
- " | ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- "
\n",
- " \n",
- " | 8572 | \n",
- " 12/29/2023 | \n",
- " 12.55 | \n",
- " 13.19 | \n",
- " 12.36 | \n",
- " 12.45 | \n",
- "
\n",
- " \n",
- " | 8573 | \n",
- " 01/02/2024 | \n",
- " 13.22 | \n",
- " 14.23 | \n",
- " 13.10 | \n",
- " 13.20 | \n",
- "
\n",
- " \n",
- " | 8574 | \n",
- " 01/03/2024 | \n",
- " 13.35 | \n",
- " 14.22 | \n",
- " 13.33 | \n",
- " 14.04 | \n",
- "
\n",
- " \n",
- " | 8575 | \n",
- " 01/04/2024 | \n",
- " 13.93 | \n",
- " 14.20 | \n",
- " 13.64 | \n",
- " 14.13 | \n",
- "
\n",
- " \n",
- " | 8576 | \n",
- " 01/05/2024 | \n",
- " 14.24 | \n",
- " 14.58 | \n",
- " 13.29 | \n",
- " 13.35 | \n",
- "
\n",
- " \n",
- "
\n",
- "
8577 rows × 5 columns
\n",
- "
\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " DATE | \n",
- " OPEN | \n",
- " HIGH | \n",
- " LOW | \n",
- " CLOSE | \n",
- " Level | \n",
- " Year | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 01/02/1990 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 01/03/1990 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 01/04/1990 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 01/05/1990 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 01/08/1990 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- "
\n",
- " \n",
- " | 8572 | \n",
- " 12/29/2023 | \n",
- " 12.55 | \n",
- " 13.19 | \n",
- " 12.36 | \n",
- " 12.45 | \n",
- " Low | \n",
- " 2023 | \n",
- "
\n",
- " \n",
- " | 8573 | \n",
- " 01/02/2024 | \n",
- " 13.22 | \n",
- " 14.23 | \n",
- " 13.10 | \n",
- " 13.20 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8574 | \n",
- " 01/03/2024 | \n",
- " 13.35 | \n",
- " 14.22 | \n",
- " 13.33 | \n",
- " 14.04 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8575 | \n",
- " 01/04/2024 | \n",
- " 13.93 | \n",
- " 14.20 | \n",
- " 13.64 | \n",
- " 14.13 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8576 | \n",
- " 01/05/2024 | \n",
- " 14.24 | \n",
- " 14.58 | \n",
- " 13.29 | \n",
- " 13.35 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- "
\n",
- "
8577 rows × 7 columns
\n",
- "
\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " DATE | \n",
- " OPEN | \n",
- " HIGH | \n",
- " LOW | \n",
- " CLOSE | \n",
- " Level | \n",
- " Year | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 01/02/1990 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 01/03/1990 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 01/04/1990 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 01/05/1990 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 01/08/1990 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- "
\n",
- " \n",
- " | 8573 | \n",
- " 01/02/2024 | \n",
- " 13.22 | \n",
- " 14.23 | \n",
- " 13.10 | \n",
- " 13.20 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8574 | \n",
- " 01/03/2024 | \n",
- " 13.35 | \n",
- " 14.22 | \n",
- " 13.33 | \n",
- " 14.04 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8575 | \n",
- " 01/04/2024 | \n",
- " 13.93 | \n",
- " 14.20 | \n",
- " 13.64 | \n",
- " 14.13 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8576 | \n",
- " 01/05/2024 | \n",
- " 14.24 | \n",
- " 14.58 | \n",
- " 13.29 | \n",
- " 13.35 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8577 | \n",
- " 01/06/2024 | \n",
- " 14.27 | \n",
- " 14.61 | \n",
- " 13.32 | \n",
- " 13.38 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- "
\n",
- "
8578 rows × 7 columns
\n",
- "
\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " Year | \n",
- " Average Close | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 1990 | \n",
- " 23.06 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 1991 | \n",
- " 18.37 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 1992 | \n",
- " 15.45 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 1993 | \n",
- " 12.69 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 1994 | \n",
- " 13.93 | \n",
- "
\n",
- " \n",
- " | 5 | \n",
- " 1995 | \n",
- " 12.39 | \n",
- "
\n",
- " \n",
- " | 6 | \n",
- " 1996 | \n",
- " 16.44 | \n",
- "
\n",
- " \n",
- " | 7 | \n",
- " 1997 | \n",
- " 22.36 | \n",
- "
\n",
- " \n",
- " | 8 | \n",
- " 1998 | \n",
- " 25.60 | \n",
- "
\n",
- " \n",
- " | 9 | \n",
- " 1999 | \n",
- " 24.37 | \n",
- "
\n",
- " \n",
- " | 10 | \n",
- " 2000 | \n",
- " 23.32 | \n",
- "
\n",
- " \n",
- " | 11 | \n",
- " 2001 | \n",
- " 25.75 | \n",
- "
\n",
- " \n",
- " | 12 | \n",
- " 2002 | \n",
- " 27.29 | \n",
- "
\n",
- " \n",
- " | 13 | \n",
- " 2003 | \n",
- " 21.98 | \n",
- "
\n",
- " \n",
- " | 14 | \n",
- " 2004 | \n",
- " 15.48 | \n",
- "
\n",
- " \n",
- " | 15 | \n",
- " 2005 | \n",
- " 12.81 | \n",
- "
\n",
- " \n",
- " | 16 | \n",
- " 2006 | \n",
- " 12.81 | \n",
- "
\n",
- " \n",
- " | 17 | \n",
- " 2007 | \n",
- " 17.54 | \n",
- "
\n",
- " \n",
- " | 18 | \n",
- " 2008 | \n",
- " 32.70 | \n",
- "
\n",
- " \n",
- " | 19 | \n",
- " 2009 | \n",
- " 31.48 | \n",
- "
\n",
- " \n",
- " | 20 | \n",
- " 2010 | \n",
- " 22.55 | \n",
- "
\n",
- " \n",
- " | 21 | \n",
- " 2011 | \n",
- " 24.20 | \n",
- "
\n",
- " \n",
- " | 22 | \n",
- " 2012 | \n",
- " 17.80 | \n",
- "
\n",
- " \n",
- " | 23 | \n",
- " 2013 | \n",
- " 14.23 | \n",
- "
\n",
- " \n",
- " | 24 | \n",
- " 2014 | \n",
- " 14.18 | \n",
- "
\n",
- " \n",
- " | 25 | \n",
- " 2015 | \n",
- " 16.67 | \n",
- "
\n",
- " \n",
- " | 26 | \n",
- " 2016 | \n",
- " 15.83 | \n",
- "
\n",
- " \n",
- " | 27 | \n",
- " 2017 | \n",
- " 11.09 | \n",
- "
\n",
- " \n",
- " | 28 | \n",
- " 2018 | \n",
- " 16.64 | \n",
- "
\n",
- " \n",
- " | 29 | \n",
- " 2019 | \n",
- " 15.39 | \n",
- "
\n",
- " \n",
- " | 30 | \n",
- " 2020 | \n",
- " 29.25 | \n",
- "
\n",
- " \n",
- " | 31 | \n",
- " 2021 | \n",
- " 19.66 | \n",
- "
\n",
- " \n",
- " | 32 | \n",
- " 2022 | \n",
- " 25.64 | \n",
- "
\n",
- " \n",
- " | 33 | \n",
- " 2023 | \n",
- " 16.85 | \n",
- "
\n",
- " \n",
- " | 34 | \n",
- " 2024 | \n",
- " 13.62 | \n",
- "
\n",
- " \n",
- "
\n",
- "
\n",
- "\n",
- "2. Replicate 4 times the values of the list `p2_list`. We expect an ouput like this: `[ 2 , 3, 4, 5, 2 , 3, 4, 5, 2 , 3, 4, 5, 2 , 3, 4, 5]`. **Hint: Use multiplication function in `lists`and see the output.**
\n",
- "3. Print the length of `f_list`. **Hint: Length function**
\n",
- "4. Print `My teacher assistant is so boring.` using `text1` list. **Hint: Use the [`join` function](https://stackoverflow.com/questions/493819/why-is-it-string-joinlist-instead-of-list-joinstring)**
\n",
- "5. Print `My TA is so boring, but is very funny.` using `text1` list.**Hint: Use the `join` function, and `extend` method.**
\n",
- "6. Print
\n",
- "`The max value of values1 is 86 and is located in the 0 index. `
\n",
- "`The min value of values1 is 0 and is located in the 7 index. `
**Hint: Use the `f-string`, `min`, and `max` functions.**\n",
- "
\n",
- "7. Get two lists: `names` and `last_names` using `last_and_name` list. **Hint: Use `map` and `split`.**\n",
- "
\n",
- "8. Give only the last names of students who do not have email. Use the `emails` and `last_names` listt. **Hint: Use `map` and `split`.**\n",
- "
"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 33,
- "metadata": {},
- "outputs": [],
- "source": [
- "import numpy as np"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 34,
- "metadata": {},
- "outputs": [],
- "source": [
- "f_list = [np.nan , np.nan, \"Austria\", \"Germany\", np.nan, \"Pakistan\", \"np.nan\", np.nan ]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 35,
- "metadata": {},
- "outputs": [],
- "source": [
- "text1 = ['My', 'teacher', 'assistant', 'is', 'so', 'boring.']"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 36,
- "metadata": {},
- "outputs": [],
- "source": [
- "p2_list = [ 2 , 3, 4, 5 ]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 37,
- "metadata": {},
- "outputs": [],
- "source": [
- "values1 = [ 86, 86, 85, 85, 85, 83, 23, 0, 84, 1 ] "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 38,
- "metadata": {
- "scrolled": true
- },
- "outputs": [],
- "source": [
- "# These two lists a\n",
- "last_and_name = [ \"CORNEJO SANCHEZ, CHRISTIAN SANTOS\", \"ORELLANA QUISPE, CRISTIAN NASSER\", \"MORALES CHOQUEHUANCA, ANGELICA KARINA\", \"GUIMARAY RIBEYRO, JOSE ROBERTO\", \"CAMACHO GAVIDIA, ABEL FERNANDO\", \"TINTAYA ORIHUELA, MEIR ALVARO\", \"CHAVEZ MARTINEZ, JOSELIN ALEXANDRA\", \"FIGUEROA MURO, LEONEL ARTURO\", \"GOMEZ CRIBILLERO, JOSE FELIPE\", \"PALOMINO SEGUÍN, AFRANIA\", \"LUZON CUEVA, BIANCA MARIETTE\", \"SUAÑA ZEGARRA, ADRIAN ANDRE\", \"SOTO POMACHAGUA, DORKAS YOMIRA JHERMY\", \"FIORENTINO MARTINEZ, LADY ALY\", \"LAMA MAVILA, HECTOR ANDRE\", \"MEZA HINOJO, GUSTAVO\", \"LOZADA MURILLO, PERSEO MARCELO\", \"ZAMBRANO JIMENEZ, MIGUEL ALONZO\", \"JACOBS LUQUE, NICOLAS\", \"VIDAL VIDAL, ROCIO GABRIELA\", \"TORRES ANICAMA, JANE CAMILA\", \"LOPEZ ESTRADA, MARIA ELISA\", \"BOYCO ORAMS, ALEJANDRO\", \"DIAZ BERROSPI, KARLINE ROSMELI\", \"RIEGA ESCALANTE, STEPHY ROSARIO\", \"LEVANO TORRES, VALERIA CECILIA\", \"ESQUIVES BRAVO, SEBASTIAN RENATO\", \"PEREZ GONZALES, JUAN CARLOS\", \"OTERO MAGUIÑA, MARIANA\", \"CLAVO CAMPOS, ANDREA BRIZETH\", \"AGUILAR GARCIA, ERICK JOSUE\", \"CALDAS VELASQUEZ, JOSUE DANIEL\", \"SALAS NUÑEZ BORJA, FABIO MANUEL\", \"PIZARRO VILLANES, FERNANDA NICOLLE\", \"QUILLATUPA MORALES, ANGELA ADELINA\", \"HUANCAYA IDONE, CESAR DANTE\", \"CALVO PORTOCARRERO, GABRIELA ISABEL\", \"IBAÑEZ ABANTO, ANGEL MAURICIO\", \"MELÉNDEZ APONTE, JUAN DIEGO\", \"CRISTIAN SERRANO, ARONE\", \"HINOJOSA CAHUANA, PERCY ALBERTH\", \"ANGLAS GARCÍA, KEVIN ARTURO\", \"ALDAVE ACOSTA, CESAR ERNESTO\", \"NÚÑEZ HUAMÁN, CÉSAR AGUSTO\", \"OBREGON HUAMAN, DIANA EDITH\", \"SOTO PACHERRES, RODRIGO FRANCO\", \"INGARUCA RIVERA, GRETTEL ALEXANDRA\", \"ROJAS HUAMAN, ROSA ANGELA\", \"NEYRA SALAS, DANTE OMAR\", \"HUERTA ESPINOZA, YAJAIRA ALEXANDRA\", \"HUANCA MARTINEZ, JORGE ALBERTO\", \"FLORES CADILLO, ALEXIS\" ]\n",
- "emails = [\"cscornejo@pucp.edu.pe\", \"orellana.cn@pucp.edu.pe\", \"karina.morales@pucp.edu.pe\", \"a20083223@pucp.pe\", \"abel.camacho@pucp.pe\", \"mtintaya@pucp.edu.pe\", \"joselin.chavez@pucp.edu.pe\", \"a20105737@pucp.pe\", \"jfgomezc@pucp.pe\", \"afrania.palomino@pucp.pe\", \"luzon.bianca@pucp.pe\", \"adrian.suanaz@pucp.pe\", \"soto.y@pucp.edu.pe\", \"a20132766@pucp.pe\", \"andre.lama@pucp.edu.pe\", \"gustavo.meza@pucp.edu.pe\", \"pmlozada@pucp.edu.pe\", \"m.zambranoj@pucp.edu.pe\", \"nicolas.jacobs@pucp.edu.pe\", \"gvidal@pucp.edu.pe\", \"jane.torres@pucp.edu.pe\", \"m.lopez@pucp.edu.pe\", \"alejandro.boyco@pucp.edu.pe\", \"a20167070@pucp.edu.pe\", \"riega.stephy@pucp.edu.pe\", \"vlevanot@pucp.edu.pe\", \"sesquives@pucp.edu.pe\", \"perez.juanc@pucp.edu.pe\", \"mariana.otero@pucp.edu.pe\", \"aclavo@pucp.edu.pe\", \"a20182474@pucp.edu.pe\", \"josue.caldas@pucp.edu.pe\", \"fabio.salas@pucp.edu.pe\", \"fernanda.pizarro@pucp.edu.pe\", \"aquillatupa@pucp.pe\", \"\", \"\", \"\", \"\", \"\", \"f0873079@pucp.edu.pe\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"flores.alexis@pucp.edu.pe\", ]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 39,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "The indices [0, 1, 4, 7] have np.nan values.\n"
- ]
- }
- ],
- "source": [
- " # Answer 1\n",
- "\n",
- "nan_values = [i for i, value in enumerate(f_list) if value is np.nan]\n",
- "\n",
- "print(f\"The indices {nan_values} have np.nan values.\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 40,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "[2, 3, 4, 5, 2, 3, 4, 5, 2, 3, 4, 5, 2, 3, 4, 5]\n"
- ]
- }
- ],
- "source": [
- " # Answer 2\n",
- "\n",
- "p2_list_2 = p2_list * 4\n",
- "\n",
- "print(p2_list_2)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 41,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "8\n"
- ]
- }
- ],
- "source": [
- " # Answer 3\n",
- "\n",
- "print(len(f_list))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 42,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "'My teacher assistant is so boring.'"
- ]
- },
- "execution_count": 42,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- " # Answer 4\n",
- "\n",
- "answer_4 = ' '.join(text1)\n",
- "answer_4"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 43,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "'My TA My teacher assistant is so boring but is very funny'"
- ]
- },
- "execution_count": 43,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- " # Answer 5\n",
- " \n",
- "text1[-1] = text1[-1].rstrip('.')\n",
- " \n",
- "text_answer = ['My', 'TA']\n",
- "\n",
- "text_answer_b = ['but', 'is', 'very', 'funny']\n",
- "\n",
- "text_answer.extend(text1 + text_answer_b)\n",
- "\n",
- "answer_5 = ' '.join(text_answer)\n",
- "answer_5"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 44,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "The max value of values1 is 86 and is located in the 0 index.\n"
- ]
- }
- ],
- "source": [
- " # Answer 6.1\n",
- " \n",
- "max_index = values1.index(max(values1))\n",
- " \n",
- "print(f\"The max value of values1 is {max(values1)} and is located in the {max_index} index.\")\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 45,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "The min value of values1 is 0 and is located in the 7 index.\n"
- ]
- }
- ],
- "source": [
- " # Answer 6.2\n",
- " \n",
- "min_index = values1.index(min(values1))\n",
- " \n",
- "print(f\"The min value of values1 is {min(values1)} and is located in the {min_index} index.\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 46,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Names: ('CHRISTIAN SANTOS', 'CRISTIAN NASSER', 'ANGELICA KARINA', 'JOSE ROBERTO', 'ABEL FERNANDO', 'MEIR ALVARO', 'JOSELIN ALEXANDRA', 'LEONEL ARTURO', 'JOSE FELIPE', 'AFRANIA', 'BIANCA MARIETTE', 'ADRIAN ANDRE', 'DORKAS YOMIRA JHERMY', 'LADY ALY', 'HECTOR ANDRE', 'GUSTAVO', 'PERSEO MARCELO', 'MIGUEL ALONZO', 'NICOLAS', 'ROCIO GABRIELA', 'JANE CAMILA', 'MARIA ELISA', 'ALEJANDRO', 'KARLINE ROSMELI', 'STEPHY ROSARIO', 'VALERIA CECILIA', 'SEBASTIAN RENATO', 'JUAN CARLOS', 'MARIANA', 'ANDREA BRIZETH', 'ERICK JOSUE', 'JOSUE DANIEL', 'FABIO MANUEL', 'FERNANDA NICOLLE', 'ANGELA ADELINA', 'CESAR DANTE', 'GABRIELA ISABEL', 'ANGEL MAURICIO', 'JUAN DIEGO', 'ARONE', 'PERCY ALBERTH', 'KEVIN ARTURO', 'CESAR ERNESTO', 'CÉSAR AGUSTO', 'DIANA EDITH', 'RODRIGO FRANCO', 'GRETTEL ALEXANDRA', 'ROSA ANGELA', 'DANTE OMAR', 'YAJAIRA ALEXANDRA', 'JORGE ALBERTO', 'ALEXIS')\n",
- "Last Names: ('CORNEJO SANCHEZ', 'ORELLANA QUISPE', 'MORALES CHOQUEHUANCA', 'GUIMARAY RIBEYRO', 'CAMACHO GAVIDIA', 'TINTAYA ORIHUELA', 'CHAVEZ MARTINEZ', 'FIGUEROA MURO', 'GOMEZ CRIBILLERO', 'PALOMINO SEGUÍN', 'LUZON CUEVA', 'SUAÑA ZEGARRA', 'SOTO POMACHAGUA', 'FIORENTINO MARTINEZ', 'LAMA MAVILA', 'MEZA HINOJO', 'LOZADA MURILLO', 'ZAMBRANO JIMENEZ', 'JACOBS LUQUE', 'VIDAL VIDAL', 'TORRES ANICAMA', 'LOPEZ ESTRADA', 'BOYCO ORAMS', 'DIAZ BERROSPI', 'RIEGA ESCALANTE', 'LEVANO TORRES', 'ESQUIVES BRAVO', 'PEREZ GONZALES', 'OTERO MAGUIÑA', 'CLAVO CAMPOS', 'AGUILAR GARCIA', 'CALDAS VELASQUEZ', 'SALAS NUÑEZ BORJA', 'PIZARRO VILLANES', 'QUILLATUPA MORALES', 'HUANCAYA IDONE', 'CALVO PORTOCARRERO', 'IBAÑEZ ABANTO', 'MELÉNDEZ APONTE', 'CRISTIAN SERRANO', 'HINOJOSA CAHUANA', 'ANGLAS GARCÍA', 'ALDAVE ACOSTA', 'NÚÑEZ HUAMÁN', 'OBREGON HUAMAN', 'SOTO PACHERRES', 'INGARUCA RIVERA', 'ROJAS HUAMAN', 'NEYRA SALAS', 'HUERTA ESPINOZA', 'HUANCA MARTINEZ', 'FLORES CADILLO')\n"
- ]
- }
- ],
- "source": [
- " # Answer 7\n",
- "\n",
- "last_names, names = zip(*map(lambda x: x.split(', '), last_and_name))\n",
- " # the lambda function using split divides each name from each last name\n",
- " # the function zip takes the values and puts them in tuples\n",
- " # \"last_names, names\" indicates the code to split the tuples in two separate lists\n",
- "print(\"Names:\", names)\n",
- "print(\"Last Names:\", last_names)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 47,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "['HUANCAYA IDONE', 'CALVO PORTOCARRERO', 'IBAÑEZ ABANTO', 'MELÉNDEZ APONTE', 'CRISTIAN SERRANO', 'ANGLAS GARCÍA', 'ALDAVE ACOSTA', 'NÚÑEZ HUAMÁN', 'OBREGON HUAMAN', 'SOTO PACHERRES', 'INGARUCA RIVERA', 'ROJAS HUAMAN', 'NEYRA SALAS', 'HUERTA ESPINOZA', 'HUANCA MARTINEZ']\n"
- ]
- }
- ],
- "source": [
- " # Answer 8\n",
- " \n",
- "answer_8 = [last_name for last_name, email in zip(last_names, emails) if not email]\n",
- " # zip function pairs last names with its corresponding emails into tuples\n",
- " # \"last_name for last_name, email in ... if not email\" indicates the last name for each pair if email is empty\n",
- "print(answer_8)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## 1.3 Strings\n",
- "\n",
- "\n",
- "1. Drop the duplicated blank spaces in `str1`. Do not use the regular expresions. Do not use the code shown in class. Explain your steps.**Hint: Use `split` method and `join` function.**\n",
- "\n",
- "2. Get the number of letters in the string .**Hint: Use `len`function.**\n",
- "\n",
- "3. Get the number of blank spaces (all of them) in the string .**Hint: Use `len`function.**\n",
- "\n",
- "4. Get the position of `@` in each string in the emails list. **Hint: Use `map`function and `find` method.**\n",
- "\n",
- "5. Identifies if exists `.edu.` in each string in the `emails` list. Get a list of Booleans. **Hint: Use `map`function and `find` method.**\n",
- "\n",
- "6. Get all the strings before the first dot `.`in each string in the `emails` list. Identifies how many of them has `@`. **Hint: Use `map`function and `find` method.**"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "#### Dear professor, the reason why I created this new branch is to correct the fact that I mistakenly edited the main branch of my group when I was writing my part. So, I was the one in charge to complete the \"Strings\" part, and here it is. I hope you can understand this."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 48,
- "metadata": {},
- "outputs": [],
- "source": [
- "str1 = 'I am too old'"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 49,
- "metadata": {},
- "outputs": [],
- "source": [
- "emails = [\"cscornejo@pucp.edu.pe\", \"orellana.cn@pucp.edu.pe\", \"karina.morales@pucp.edu.pe\", \"a20083223@pucp.pe\", \"abel.camacho@pucp.pe\", \"mtintaya@pucp.edu.pe\", \"joselin.chavez@pucp.edu.pe\", \"a20105737@pucp.pe\", \"jfgomezc@pucp.pe\", \"afrania.palomino@pucp.pe\", \"luzon.bianca@pucp.pe\", \"adrian.suanaz@pucp.pe\", \"soto.y@pucp.edu.pe\", \"a20132766@pucp.pe\", \"andre.lama@pucp.edu.pe\", \"gustavo.meza@pucp.edu.pe\", \"pmlozada@pucp.edu.pe\", \"m.zambranoj@pucp.edu.pe\", \"nicolas.jacobs@pucp.edu.pe\", \"gvidal@pucp.edu.pe\", \"jane.torres@pucp.edu.pe\", \"m.lopez@pucp.edu.pe\", \"alejandro.boyco@pucp.edu.pe\", \"a20167070@pucp.edu.pe\", \"riega.stephy@pucp.edu.pe\", \"vlevanot@pucp.edu.pe\", \"sesquives@pucp.edu.pe\", \"perez.juanc@pucp.edu.pe\", \"mariana.otero@pucp.edu.pe\", \"aclavo@pucp.edu.pe\", \"a20182474@pucp.edu.pe\", \"josue.caldas@pucp.edu.pe\", \"fabio.salas@pucp.edu.pe\", \"fernanda.pizarro@pucp.edu.pe\", \"aquillatupa@pucp.pe\"]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 50,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "I am too old\n"
- ]
- }
- ],
- "source": [
- "# 1. Drop the duplicated blank spaces in str1. Do not use the regular expresions. Do not use the code shown in class. Explain your steps.Hint: Use split method and join function.\n",
- "\n",
- "# First, we split the string into a list of words\n",
- "list_words = str1.split()\n",
- "\n",
- "# Then, we remove the empty strings from the list\n",
- "non_empty_words = [word for word in list_words if word]\n",
- "\n",
- "# Lastly, we join the non-empty words back into a string\n",
- "result_str = ' '.join(non_empty_words)\n",
- "\n",
- "print(result_str)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 51,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Number of letters: 9\n"
- ]
- }
- ],
- "source": [
- "# 2. Get the number of letters in the string .Hint: Use lenfunction.\n",
- "\n",
- "# In order to count the number of letters, we need to remove non-alphabetic characters first, we do that \n",
- "# using the len function (to printe the lenght)\n",
- "# and verifying that the character is alphabetic (a letter), using the if function.\n",
- "num_letters = len([char for char in str1 if char.isalpha()])\n",
- "\n",
- "# This is a better way to print the answer, including the string value \"Number of letters\"\n",
- "print(\"Number of letters:\", num_letters)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 52,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Number of blank spaces: 85\n"
- ]
- }
- ],
- "source": [
- "# 3. Get the number of blank spaces (all of them) in the string .Hint: Use lenfunction.\n",
- "\n",
- "# First, we create a list with the blank spaces, using the \"isspace\" method\n",
- "blank_space = [char for char in str1 if char.isspace()]\n",
- "\n",
- "# Then we apply the function len() to the list to get the total number of blank spaces\n",
- "num_blank_spaces = len(blank_space)\n",
- "\n",
- "# Finally, we print the result\n",
- "print(\"Number of blank spaces:\", num_blank_spaces)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 53,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Positions of '@': [9, 11, 14, 9, 12, 8, 14, 9, 8, 16, 12, 13, 6, 9, 10, 12, 8, 11, 14, 6, 11, 7, 15, 9, 12, 8, 9, 11, 13, 6, 9, 12, 11, 16, 11]\n"
- ]
- }
- ],
- "source": [
- "# 4. Get the position of @ in each string in the emails list. Hint: Use mapfunction and find method.\n",
- "\n",
- "# First we use the map() function to apply the specified lambda function to each element in the emails list. \n",
- "# Then, with the lambda function takes an email address (email) and finds the position of the '@' symbol using the find() method.\n",
- "# Also, list(...) Converts the result into a list.\n",
- "positions_at = list(map(lambda email: email.find('@'), emails))\n",
- "\n",
- "# Finally, we print the results\n",
- "print(\"Positions of '@':\", positions_at)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 54,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Contains '.edu.': [True, True, True, False, False, True, True, False, False, False, False, False, True, False, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, False]\n"
- ]
- }
- ],
- "source": [
- "# 5. Identifies if exists .edu. in each string in the emails list. Get a list of Booleans. Hint: Use mapfunction and find method. # \n",
- "\n",
- "# First, we use the map function to apply a lambda function to each element in the emails list.\n",
- "# The lambda function checks if '.edu.' is present in each email address.\n",
- "contains_edu_lambda = lambda email: '.edu.' in email\n",
- "mapped_result = map(contains_edu_lambda, emails)\n",
- "\n",
- "# Then, we convert the mapped result into a list.\n",
- "contains_edu_list = list(mapped_result)\n",
- "\n",
- "# Finally we print the result\n",
- "print(\"Contains '.edu.':\", contains_edu_list)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 55,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Substrings before the first dot: ['cscornejo@pucp', 'orellana', 'karina', 'a20083223@pucp', 'abel', 'mtintaya@pucp', 'joselin', 'a20105737@pucp', 'jfgomezc@pucp', 'afrania', 'luzon', 'adrian', 'soto', 'a20132766@pucp', 'andre', 'gustavo', 'pmlozada@pucp', 'm', 'nicolas', 'gvidal@pucp', 'jane', 'm', 'alejandro', 'a20167070@pucp', 'riega', 'vlevanot@pucp', 'sesquives@pucp', 'perez', 'mariana', 'aclavo@pucp', 'a20182474@pucp', 'josue', 'fabio', 'fernanda', 'aquillatupa@pucp']\n",
- "Number of substrings containing '@': 14\n"
- ]
- }
- ],
- "source": [
- "# 6. Get all the strings before the first dot '.' in each string in the emails list.\n",
- "# First, we identify how many of them have '@'.\n",
- "\n",
- "# Then we use the map function to apply a lambda function to each element in the emails list.\n",
- "# The lambda function extracts the substring before the first dot '.' and checks if it contains '@'.\n",
- "substring_before_dot_lambda = lambda email: email.split('.')[0]\n",
- "mapped_result = map(substring_before_dot_lambda, emails)\n",
- "\n",
- "# After that, we convert the mapped result into a list.\n",
- "substring_before_dot_list = list(mapped_result)\n",
- "\n",
- "# Also, we count how many substrings contain '@' and print the results\n",
- "count_with_at = sum('@' in substring for substring in substring_before_dot_list)\n",
- "\n",
- "print(\"Substrings before the first dot:\", substring_before_dot_list)\n",
- "print(\"Number of substrings containing '@':\", count_with_at)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## 1.4 Pandas\n",
- "\n",
- "You can and should always ask ChatGPT, BARD, Bing, etc.\n",
- "In this exercise, you will work with financial data. Follow the steps below:\n",
- "\n",
- "1. Load Data:\n",
- " Load the financial data available at this URL: https://raw.githubusercontent.com/datasets/finance-vix/main/data/vix-daily.csv\n",
- " Use `pd.read_csv()` adn the link to load the data into a DataFrame.\n",
- "\n",
- "2. Explore Data:\n",
- " a) Display the first five rows of the DataFrame.\n",
- " b) Display the summary statistics of the DataFrame.\n",
- "\n",
- "3. Add Columns:\n",
- " a) Add a new column 'Level' that categorizes the 'Close' column values into 'Low' (< 20), 'Medium' (20-30), and 'High' (>30). You need to make a filter to make this categorization. You can see below some suggestions how to do it.\n",
- " b) Add a new column 'Year' extracted from the 'Date' column. You need to work with dates. You can do it directly workiwith the column splitting it or changing it to date format an dfollowing the below suggestion. \n",
- "\n",
- "4. Add Rows:\n",
- " a) Add a new row with a date of your choice and fill the other columns with appropriate values. \n",
- "\n",
- "5. Analysis:\n",
- " a) Calculate the average of the column 'Close' for each 'Year'. You need to group for this task.\n",
- " b) Count the number of 'High', 'Medium', and 'Low' Level days in the data.\n",
- "\n",
- "Suggestions:\n",
- " - Use `pd.cut()` for categorizing 'Close' values.\n",
- " - Use `pd.to_datetime()` and `dt.year` to extract the year from a date.\n",
- " - Use `DataFrame.append()` or `pd.concat()` to add rows.\n",
- " - Use `groupby()` for aggregation tasks."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 56,
- "metadata": {},
- "outputs": [],
- "source": [
- "# 1\n",
- "import pandas as pd\n",
- "\n",
- "# This code loads the data from the provided URL.\n",
- "url = \"https://raw.githubusercontent.com/datasets/finance-vix/main/data/vix-daily.csv\"\n",
- "df = pd.read_csv(url)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 57,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " DATE | \n",
- " OPEN | \n",
- " HIGH | \n",
- " LOW | \n",
- " CLOSE | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 01/02/1990 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 01/03/1990 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 01/04/1990 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 01/05/1990 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 01/08/1990 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- "
\n",
- " \n",
- " | ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- "
\n",
- " \n",
- " | 8572 | \n",
- " 12/29/2023 | \n",
- " 12.55 | \n",
- " 13.19 | \n",
- " 12.36 | \n",
- " 12.45 | \n",
- "
\n",
- " \n",
- " | 8573 | \n",
- " 01/02/2024 | \n",
- " 13.22 | \n",
- " 14.23 | \n",
- " 13.10 | \n",
- " 13.20 | \n",
- "
\n",
- " \n",
- " | 8574 | \n",
- " 01/03/2024 | \n",
- " 13.35 | \n",
- " 14.22 | \n",
- " 13.33 | \n",
- " 14.04 | \n",
- "
\n",
- " \n",
- " | 8575 | \n",
- " 01/04/2024 | \n",
- " 13.93 | \n",
- " 14.20 | \n",
- " 13.64 | \n",
- " 14.13 | \n",
- "
\n",
- " \n",
- " | 8576 | \n",
- " 01/05/2024 | \n",
- " 14.24 | \n",
- " 14.58 | \n",
- " 13.29 | \n",
- " 13.35 | \n",
- "
\n",
- " \n",
- "
\n",
- "
8577 rows × 5 columns
\n",
- "
\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " DATE | \n",
- " OPEN | \n",
- " HIGH | \n",
- " LOW | \n",
- " CLOSE | \n",
- " Level | \n",
- " Year | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 01/02/1990 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 01/03/1990 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 01/04/1990 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 01/05/1990 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 01/08/1990 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- "
\n",
- " \n",
- " | 8572 | \n",
- " 12/29/2023 | \n",
- " 12.55 | \n",
- " 13.19 | \n",
- " 12.36 | \n",
- " 12.45 | \n",
- " Low | \n",
- " 2023 | \n",
- "
\n",
- " \n",
- " | 8573 | \n",
- " 01/02/2024 | \n",
- " 13.22 | \n",
- " 14.23 | \n",
- " 13.10 | \n",
- " 13.20 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8574 | \n",
- " 01/03/2024 | \n",
- " 13.35 | \n",
- " 14.22 | \n",
- " 13.33 | \n",
- " 14.04 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8575 | \n",
- " 01/04/2024 | \n",
- " 13.93 | \n",
- " 14.20 | \n",
- " 13.64 | \n",
- " 14.13 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8576 | \n",
- " 01/05/2024 | \n",
- " 14.24 | \n",
- " 14.58 | \n",
- " 13.29 | \n",
- " 13.35 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- "
\n",
- "
8577 rows × 7 columns
\n",
- "
\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " DATE | \n",
- " OPEN | \n",
- " HIGH | \n",
- " LOW | \n",
- " CLOSE | \n",
- " Level | \n",
- " Year | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 01/02/1990 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 01/03/1990 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 01/04/1990 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 01/05/1990 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 01/08/1990 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- "
\n",
- " \n",
- " | 8573 | \n",
- " 01/02/2024 | \n",
- " 13.22 | \n",
- " 14.23 | \n",
- " 13.10 | \n",
- " 13.20 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8574 | \n",
- " 01/03/2024 | \n",
- " 13.35 | \n",
- " 14.22 | \n",
- " 13.33 | \n",
- " 14.04 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8575 | \n",
- " 01/04/2024 | \n",
- " 13.93 | \n",
- " 14.20 | \n",
- " 13.64 | \n",
- " 14.13 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8576 | \n",
- " 01/05/2024 | \n",
- " 14.24 | \n",
- " 14.58 | \n",
- " 13.29 | \n",
- " 13.35 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8577 | \n",
- " 01/06/2024 | \n",
- " 14.27 | \n",
- " 14.61 | \n",
- " 13.32 | \n",
- " 13.38 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- "
\n",
- "
8578 rows × 7 columns
\n",
- "
\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " Year | \n",
- " Average Close | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 1990 | \n",
- " 23.06 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 1991 | \n",
- " 18.37 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 1992 | \n",
- " 15.45 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 1993 | \n",
- " 12.69 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 1994 | \n",
- " 13.93 | \n",
- "
\n",
- " \n",
- " | 5 | \n",
- " 1995 | \n",
- " 12.39 | \n",
- "
\n",
- " \n",
- " | 6 | \n",
- " 1996 | \n",
- " 16.44 | \n",
- "
\n",
- " \n",
- " | 7 | \n",
- " 1997 | \n",
- " 22.36 | \n",
- "
\n",
- " \n",
- " | 8 | \n",
- " 1998 | \n",
- " 25.60 | \n",
- "
\n",
- " \n",
- " | 9 | \n",
- " 1999 | \n",
- " 24.37 | \n",
- "
\n",
- " \n",
- " | 10 | \n",
- " 2000 | \n",
- " 23.32 | \n",
- "
\n",
- " \n",
- " | 11 | \n",
- " 2001 | \n",
- " 25.75 | \n",
- "
\n",
- " \n",
- " | 12 | \n",
- " 2002 | \n",
- " 27.29 | \n",
- "
\n",
- " \n",
- " | 13 | \n",
- " 2003 | \n",
- " 21.98 | \n",
- "
\n",
- " \n",
- " | 14 | \n",
- " 2004 | \n",
- " 15.48 | \n",
- "
\n",
- " \n",
- " | 15 | \n",
- " 2005 | \n",
- " 12.81 | \n",
- "
\n",
- " \n",
- " | 16 | \n",
- " 2006 | \n",
- " 12.81 | \n",
- "
\n",
- " \n",
- " | 17 | \n",
- " 2007 | \n",
- " 17.54 | \n",
- "
\n",
- " \n",
- " | 18 | \n",
- " 2008 | \n",
- " 32.70 | \n",
- "
\n",
- " \n",
- " | 19 | \n",
- " 2009 | \n",
- " 31.48 | \n",
- "
\n",
- " \n",
- " | 20 | \n",
- " 2010 | \n",
- " 22.55 | \n",
- "
\n",
- " \n",
- " | 21 | \n",
- " 2011 | \n",
- " 24.20 | \n",
- "
\n",
- " \n",
- " | 22 | \n",
- " 2012 | \n",
- " 17.80 | \n",
- "
\n",
- " \n",
- " | 23 | \n",
- " 2013 | \n",
- " 14.23 | \n",
- "
\n",
- " \n",
- " | 24 | \n",
- " 2014 | \n",
- " 14.18 | \n",
- "
\n",
- " \n",
- " | 25 | \n",
- " 2015 | \n",
- " 16.67 | \n",
- "
\n",
- " \n",
- " | 26 | \n",
- " 2016 | \n",
- " 15.83 | \n",
- "
\n",
- " \n",
- " | 27 | \n",
- " 2017 | \n",
- " 11.09 | \n",
- "
\n",
- " \n",
- " | 28 | \n",
- " 2018 | \n",
- " 16.64 | \n",
- "
\n",
- " \n",
- " | 29 | \n",
- " 2019 | \n",
- " 15.39 | \n",
- "
\n",
- " \n",
- " | 30 | \n",
- " 2020 | \n",
- " 29.25 | \n",
- "
\n",
- " \n",
- " | 31 | \n",
- " 2021 | \n",
- " 19.66 | \n",
- "
\n",
- " \n",
- " | 32 | \n",
- " 2022 | \n",
- " 25.64 | \n",
- "
\n",
- " \n",
- " | 33 | \n",
- " 2023 | \n",
- " 16.85 | \n",
- "
\n",
- " \n",
- " | 34 | \n",
- " 2024 | \n",
- " 13.62 | \n",
- "
\n",
- " \n",
- "
\n",
- "
\n",
+ "\n",
+ "2. Replicate 4 times the values of the list `p2_list`. We expect an ouput like this: `[ 2 , 3, 4, 5, 2 , 3, 4, 5, 2 , 3, 4, 5, 2 , 3, 4, 5]`. **Hint: Use multiplication function in `lists`and see the output.**
\n",
+ "3. Print the length of `f_list`. **Hint: Length function**
\n",
+ "4. Print `My teacher assistant is so boring.` using `text1` list. **Hint: Use the [`join` function](https://stackoverflow.com/questions/493819/why-is-it-string-joinlist-instead-of-list-joinstring)**
\n",
+ "5. Print `My TA is so boring, but is very funny.` using `text1` list.**Hint: Use the `join` function, and `extend` method.**
\n",
+ "6. Print
\n",
+ "`The max value of values1 is 86 and is located in the 0 index. `
\n",
+ "`The min value of values1 is 0 and is located in the 7 index. `
**Hint: Use the `f-string`, `min`, and `max` functions.**\n",
+ "
\n",
+ "7. Get two lists: `names` and `last_names` using `last_and_name` list. **Hint: Use `map` and `split`.**\n",
+ "
\n",
+ "8. Give only the last names of students who do not have email. Use the `emails` and `last_names` listt. **Hint: Use `map` and `split`.**\n",
+ "
"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 33,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import numpy as np"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 34,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "f_list = [np.nan , np.nan, \"Austria\", \"Germany\", np.nan, \"Pakistan\", \"np.nan\", np.nan ]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 35,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "text1 = ['My', 'teacher', 'assistant', 'is', 'so', 'boring.']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 36,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "p2_list = [ 2 , 3, 4, 5 ]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "values1 = [ 86, 86, 85, 85, 85, 83, 23, 0, 84, 1 ] "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 38,
+ "metadata": {
+ "scrolled": true
+ },
+ "outputs": [],
+ "source": [
+ "# These two lists a\n",
+ "last_and_name = [ \"CORNEJO SANCHEZ, CHRISTIAN SANTOS\", \"ORELLANA QUISPE, CRISTIAN NASSER\", \"MORALES CHOQUEHUANCA, ANGELICA KARINA\", \"GUIMARAY RIBEYRO, JOSE ROBERTO\", \"CAMACHO GAVIDIA, ABEL FERNANDO\", \"TINTAYA ORIHUELA, MEIR ALVARO\", \"CHAVEZ MARTINEZ, JOSELIN ALEXANDRA\", \"FIGUEROA MURO, LEONEL ARTURO\", \"GOMEZ CRIBILLERO, JOSE FELIPE\", \"PALOMINO SEGUÍN, AFRANIA\", \"LUZON CUEVA, BIANCA MARIETTE\", \"SUAÑA ZEGARRA, ADRIAN ANDRE\", \"SOTO POMACHAGUA, DORKAS YOMIRA JHERMY\", \"FIORENTINO MARTINEZ, LADY ALY\", \"LAMA MAVILA, HECTOR ANDRE\", \"MEZA HINOJO, GUSTAVO\", \"LOZADA MURILLO, PERSEO MARCELO\", \"ZAMBRANO JIMENEZ, MIGUEL ALONZO\", \"JACOBS LUQUE, NICOLAS\", \"VIDAL VIDAL, ROCIO GABRIELA\", \"TORRES ANICAMA, JANE CAMILA\", \"LOPEZ ESTRADA, MARIA ELISA\", \"BOYCO ORAMS, ALEJANDRO\", \"DIAZ BERROSPI, KARLINE ROSMELI\", \"RIEGA ESCALANTE, STEPHY ROSARIO\", \"LEVANO TORRES, VALERIA CECILIA\", \"ESQUIVES BRAVO, SEBASTIAN RENATO\", \"PEREZ GONZALES, JUAN CARLOS\", \"OTERO MAGUIÑA, MARIANA\", \"CLAVO CAMPOS, ANDREA BRIZETH\", \"AGUILAR GARCIA, ERICK JOSUE\", \"CALDAS VELASQUEZ, JOSUE DANIEL\", \"SALAS NUÑEZ BORJA, FABIO MANUEL\", \"PIZARRO VILLANES, FERNANDA NICOLLE\", \"QUILLATUPA MORALES, ANGELA ADELINA\", \"HUANCAYA IDONE, CESAR DANTE\", \"CALVO PORTOCARRERO, GABRIELA ISABEL\", \"IBAÑEZ ABANTO, ANGEL MAURICIO\", \"MELÉNDEZ APONTE, JUAN DIEGO\", \"CRISTIAN SERRANO, ARONE\", \"HINOJOSA CAHUANA, PERCY ALBERTH\", \"ANGLAS GARCÍA, KEVIN ARTURO\", \"ALDAVE ACOSTA, CESAR ERNESTO\", \"NÚÑEZ HUAMÁN, CÉSAR AGUSTO\", \"OBREGON HUAMAN, DIANA EDITH\", \"SOTO PACHERRES, RODRIGO FRANCO\", \"INGARUCA RIVERA, GRETTEL ALEXANDRA\", \"ROJAS HUAMAN, ROSA ANGELA\", \"NEYRA SALAS, DANTE OMAR\", \"HUERTA ESPINOZA, YAJAIRA ALEXANDRA\", \"HUANCA MARTINEZ, JORGE ALBERTO\", \"FLORES CADILLO, ALEXIS\" ]\n",
+ "emails = [\"cscornejo@pucp.edu.pe\", \"orellana.cn@pucp.edu.pe\", \"karina.morales@pucp.edu.pe\", \"a20083223@pucp.pe\", \"abel.camacho@pucp.pe\", \"mtintaya@pucp.edu.pe\", \"joselin.chavez@pucp.edu.pe\", \"a20105737@pucp.pe\", \"jfgomezc@pucp.pe\", \"afrania.palomino@pucp.pe\", \"luzon.bianca@pucp.pe\", \"adrian.suanaz@pucp.pe\", \"soto.y@pucp.edu.pe\", \"a20132766@pucp.pe\", \"andre.lama@pucp.edu.pe\", \"gustavo.meza@pucp.edu.pe\", \"pmlozada@pucp.edu.pe\", \"m.zambranoj@pucp.edu.pe\", \"nicolas.jacobs@pucp.edu.pe\", \"gvidal@pucp.edu.pe\", \"jane.torres@pucp.edu.pe\", \"m.lopez@pucp.edu.pe\", \"alejandro.boyco@pucp.edu.pe\", \"a20167070@pucp.edu.pe\", \"riega.stephy@pucp.edu.pe\", \"vlevanot@pucp.edu.pe\", \"sesquives@pucp.edu.pe\", \"perez.juanc@pucp.edu.pe\", \"mariana.otero@pucp.edu.pe\", \"aclavo@pucp.edu.pe\", \"a20182474@pucp.edu.pe\", \"josue.caldas@pucp.edu.pe\", \"fabio.salas@pucp.edu.pe\", \"fernanda.pizarro@pucp.edu.pe\", \"aquillatupa@pucp.pe\", \"\", \"\", \"\", \"\", \"\", \"f0873079@pucp.edu.pe\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"flores.alexis@pucp.edu.pe\", ]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 39,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "The indices [0, 1, 4, 7] have np.nan values.\n"
+ ]
+ }
+ ],
+ "source": [
+ " # Answer 1\n",
+ "\n",
+ "nan_values = [i for i, value in enumerate(f_list) if value is np.nan]\n",
+ "\n",
+ "print(f\"The indices {nan_values} have np.nan values.\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 40,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "[2, 3, 4, 5, 2, 3, 4, 5, 2, 3, 4, 5, 2, 3, 4, 5]\n"
+ ]
+ }
+ ],
+ "source": [
+ " # Answer 2\n",
+ "\n",
+ "p2_list_2 = p2_list * 4\n",
+ "\n",
+ "print(p2_list_2)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 41,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "8\n"
+ ]
+ }
+ ],
+ "source": [
+ " # Answer 3\n",
+ "\n",
+ "print(len(f_list))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 42,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'My teacher assistant is so boring.'"
+ ]
+ },
+ "execution_count": 42,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ " # Answer 4\n",
+ "\n",
+ "answer_4 = ' '.join(text1)\n",
+ "answer_4"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 43,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'My TA My teacher assistant is so boring but is very funny'"
+ ]
+ },
+ "execution_count": 43,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ " # Answer 5\n",
+ " \n",
+ "text1[-1] = text1[-1].rstrip('.')\n",
+ " \n",
+ "text_answer = ['My', 'TA']\n",
+ "\n",
+ "text_answer_b = ['but', 'is', 'very', 'funny']\n",
+ "\n",
+ "text_answer.extend(text1 + text_answer_b)\n",
+ "\n",
+ "answer_5 = ' '.join(text_answer)\n",
+ "answer_5"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 44,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "The max value of values1 is 86 and is located in the 0 index.\n"
+ ]
+ }
+ ],
+ "source": [
+ " # Answer 6.1\n",
+ " \n",
+ "max_index = values1.index(max(values1))\n",
+ " \n",
+ "print(f\"The max value of values1 is {max(values1)} and is located in the {max_index} index.\")\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 45,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "The min value of values1 is 0 and is located in the 7 index.\n"
+ ]
+ }
+ ],
+ "source": [
+ " # Answer 6.2\n",
+ " \n",
+ "min_index = values1.index(min(values1))\n",
+ " \n",
+ "print(f\"The min value of values1 is {min(values1)} and is located in the {min_index} index.\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 46,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Names: ('CHRISTIAN SANTOS', 'CRISTIAN NASSER', 'ANGELICA KARINA', 'JOSE ROBERTO', 'ABEL FERNANDO', 'MEIR ALVARO', 'JOSELIN ALEXANDRA', 'LEONEL ARTURO', 'JOSE FELIPE', 'AFRANIA', 'BIANCA MARIETTE', 'ADRIAN ANDRE', 'DORKAS YOMIRA JHERMY', 'LADY ALY', 'HECTOR ANDRE', 'GUSTAVO', 'PERSEO MARCELO', 'MIGUEL ALONZO', 'NICOLAS', 'ROCIO GABRIELA', 'JANE CAMILA', 'MARIA ELISA', 'ALEJANDRO', 'KARLINE ROSMELI', 'STEPHY ROSARIO', 'VALERIA CECILIA', 'SEBASTIAN RENATO', 'JUAN CARLOS', 'MARIANA', 'ANDREA BRIZETH', 'ERICK JOSUE', 'JOSUE DANIEL', 'FABIO MANUEL', 'FERNANDA NICOLLE', 'ANGELA ADELINA', 'CESAR DANTE', 'GABRIELA ISABEL', 'ANGEL MAURICIO', 'JUAN DIEGO', 'ARONE', 'PERCY ALBERTH', 'KEVIN ARTURO', 'CESAR ERNESTO', 'CÉSAR AGUSTO', 'DIANA EDITH', 'RODRIGO FRANCO', 'GRETTEL ALEXANDRA', 'ROSA ANGELA', 'DANTE OMAR', 'YAJAIRA ALEXANDRA', 'JORGE ALBERTO', 'ALEXIS')\n",
+ "Last Names: ('CORNEJO SANCHEZ', 'ORELLANA QUISPE', 'MORALES CHOQUEHUANCA', 'GUIMARAY RIBEYRO', 'CAMACHO GAVIDIA', 'TINTAYA ORIHUELA', 'CHAVEZ MARTINEZ', 'FIGUEROA MURO', 'GOMEZ CRIBILLERO', 'PALOMINO SEGUÍN', 'LUZON CUEVA', 'SUAÑA ZEGARRA', 'SOTO POMACHAGUA', 'FIORENTINO MARTINEZ', 'LAMA MAVILA', 'MEZA HINOJO', 'LOZADA MURILLO', 'ZAMBRANO JIMENEZ', 'JACOBS LUQUE', 'VIDAL VIDAL', 'TORRES ANICAMA', 'LOPEZ ESTRADA', 'BOYCO ORAMS', 'DIAZ BERROSPI', 'RIEGA ESCALANTE', 'LEVANO TORRES', 'ESQUIVES BRAVO', 'PEREZ GONZALES', 'OTERO MAGUIÑA', 'CLAVO CAMPOS', 'AGUILAR GARCIA', 'CALDAS VELASQUEZ', 'SALAS NUÑEZ BORJA', 'PIZARRO VILLANES', 'QUILLATUPA MORALES', 'HUANCAYA IDONE', 'CALVO PORTOCARRERO', 'IBAÑEZ ABANTO', 'MELÉNDEZ APONTE', 'CRISTIAN SERRANO', 'HINOJOSA CAHUANA', 'ANGLAS GARCÍA', 'ALDAVE ACOSTA', 'NÚÑEZ HUAMÁN', 'OBREGON HUAMAN', 'SOTO PACHERRES', 'INGARUCA RIVERA', 'ROJAS HUAMAN', 'NEYRA SALAS', 'HUERTA ESPINOZA', 'HUANCA MARTINEZ', 'FLORES CADILLO')\n"
+ ]
+ }
+ ],
+ "source": [
+ " # Answer 7\n",
+ "\n",
+ "last_names, names = zip(*map(lambda x: x.split(', '), last_and_name))\n",
+ " # the lambda function using split divides each name from each last name\n",
+ " # the function zip takes the values and puts them in tuples\n",
+ " # \"last_names, names\" indicates the code to split the tuples in two separate lists\n",
+ "print(\"Names:\", names)\n",
+ "print(\"Last Names:\", last_names)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 47,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "['HUANCAYA IDONE', 'CALVO PORTOCARRERO', 'IBAÑEZ ABANTO', 'MELÉNDEZ APONTE', 'CRISTIAN SERRANO', 'ANGLAS GARCÍA', 'ALDAVE ACOSTA', 'NÚÑEZ HUAMÁN', 'OBREGON HUAMAN', 'SOTO PACHERRES', 'INGARUCA RIVERA', 'ROJAS HUAMAN', 'NEYRA SALAS', 'HUERTA ESPINOZA', 'HUANCA MARTINEZ']\n"
+ ]
+ }
+ ],
+ "source": [
+ " # Answer 8\n",
+ " \n",
+ "answer_8 = [last_name for last_name, email in zip(last_names, emails) if not email]\n",
+ " # zip function pairs last names with its corresponding emails into tuples\n",
+ " # \"last_name for last_name, email in ... if not email\" indicates the last name for each pair if email is empty\n",
+ "print(answer_8)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 1.3 Strings\n",
+ "\n",
+ "\n",
+ "1. Drop the duplicated blank spaces in `str1`. Do not use the regular expresions. Do not use the code shown in class. Explain your steps.**Hint: Use `split` method and `join` function.**\n",
+ "\n",
+ "2. Get the number of letters in the string .**Hint: Use `len`function.**\n",
+ "\n",
+ "3. Get the number of blank spaces (all of them) in the string .**Hint: Use `len`function.**\n",
+ "\n",
+ "4. Get the position of `@` in each string in the emails list. **Hint: Use `map`function and `find` method.**\n",
+ "\n",
+ "5. Identifies if exists `.edu.` in each string in the `emails` list. Get a list of Booleans. **Hint: Use `map`function and `find` method.**\n",
+ "\n",
+ "6. Get all the strings before the first dot `.`in each string in the `emails` list. Identifies how many of them has `@`. **Hint: Use `map`function and `find` method.**"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Dear professor, the reason why I created this new branch is to correct the fact that I mistakenly edited the main branch of my group when I was writing my part. So, I was the one in charge to complete the \"Strings\" part, and here it is. I hope you can understand this."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 48,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "str1 = 'I am too old'"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 49,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "emails = [\"cscornejo@pucp.edu.pe\", \"orellana.cn@pucp.edu.pe\", \"karina.morales@pucp.edu.pe\", \"a20083223@pucp.pe\", \"abel.camacho@pucp.pe\", \"mtintaya@pucp.edu.pe\", \"joselin.chavez@pucp.edu.pe\", \"a20105737@pucp.pe\", \"jfgomezc@pucp.pe\", \"afrania.palomino@pucp.pe\", \"luzon.bianca@pucp.pe\", \"adrian.suanaz@pucp.pe\", \"soto.y@pucp.edu.pe\", \"a20132766@pucp.pe\", \"andre.lama@pucp.edu.pe\", \"gustavo.meza@pucp.edu.pe\", \"pmlozada@pucp.edu.pe\", \"m.zambranoj@pucp.edu.pe\", \"nicolas.jacobs@pucp.edu.pe\", \"gvidal@pucp.edu.pe\", \"jane.torres@pucp.edu.pe\", \"m.lopez@pucp.edu.pe\", \"alejandro.boyco@pucp.edu.pe\", \"a20167070@pucp.edu.pe\", \"riega.stephy@pucp.edu.pe\", \"vlevanot@pucp.edu.pe\", \"sesquives@pucp.edu.pe\", \"perez.juanc@pucp.edu.pe\", \"mariana.otero@pucp.edu.pe\", \"aclavo@pucp.edu.pe\", \"a20182474@pucp.edu.pe\", \"josue.caldas@pucp.edu.pe\", \"fabio.salas@pucp.edu.pe\", \"fernanda.pizarro@pucp.edu.pe\", \"aquillatupa@pucp.pe\"]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 50,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "I am too old\n"
+ ]
+ }
+ ],
+ "source": [
+ "# 1. Drop the duplicated blank spaces in str1. Do not use the regular expresions. Do not use the code shown in class. Explain your steps.Hint: Use split method and join function.\n",
+ "\n",
+ "# First, we split the string into a list of words\n",
+ "list_words = str1.split()\n",
+ "\n",
+ "# Then, we remove the empty strings from the list\n",
+ "non_empty_words = [word for word in list_words if word]\n",
+ "\n",
+ "# Lastly, we join the non-empty words back into a string\n",
+ "result_str = ' '.join(non_empty_words)\n",
+ "\n",
+ "print(result_str)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 51,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Number of letters: 9\n"
+ ]
+ }
+ ],
+ "source": [
+ "# 2. Get the number of letters in the string .Hint: Use lenfunction.\n",
+ "\n",
+ "# In order to count the number of letters, we need to remove non-alphabetic characters first, we do that \n",
+ "# using the len function (to printe the lenght)\n",
+ "# and verifying that the character is alphabetic (a letter), using the if function.\n",
+ "num_letters = len([char for char in str1 if char.isalpha()])\n",
+ "\n",
+ "# This is a better way to print the answer, including the string value \"Number of letters\"\n",
+ "print(\"Number of letters:\", num_letters)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 52,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Number of blank spaces: 85\n"
+ ]
+ }
+ ],
+ "source": [
+ "# 3. Get the number of blank spaces (all of them) in the string .Hint: Use lenfunction.\n",
+ "\n",
+ "# First, we create a list with the blank spaces, using the \"isspace\" method\n",
+ "blank_space = [char for char in str1 if char.isspace()]\n",
+ "\n",
+ "# Then we apply the function len() to the list to get the total number of blank spaces\n",
+ "num_blank_spaces = len(blank_space)\n",
+ "\n",
+ "# Finally, we print the result\n",
+ "print(\"Number of blank spaces:\", num_blank_spaces)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 53,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Positions of '@': [9, 11, 14, 9, 12, 8, 14, 9, 8, 16, 12, 13, 6, 9, 10, 12, 8, 11, 14, 6, 11, 7, 15, 9, 12, 8, 9, 11, 13, 6, 9, 12, 11, 16, 11]\n"
+ ]
+ }
+ ],
+ "source": [
+ "# 4. Get the position of @ in each string in the emails list. Hint: Use mapfunction and find method.\n",
+ "\n",
+ "# First we use the map() function to apply the specified lambda function to each element in the emails list. \n",
+ "# Then, with the lambda function takes an email address (email) and finds the position of the '@' symbol using the find() method.\n",
+ "# Also, list(...) Converts the result into a list.\n",
+ "positions_at = list(map(lambda email: email.find('@'), emails))\n",
+ "\n",
+ "# Finally, we print the results\n",
+ "print(\"Positions of '@':\", positions_at)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 54,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Contains '.edu.': [True, True, True, False, False, True, True, False, False, False, False, False, True, False, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, False]\n"
+ ]
+ }
+ ],
+ "source": [
+ "# 5. Identifies if exists .edu. in each string in the emails list. Get a list of Booleans. Hint: Use mapfunction and find method. # \n",
+ "\n",
+ "# First, we use the map function to apply a lambda function to each element in the emails list.\n",
+ "# The lambda function checks if '.edu.' is present in each email address.\n",
+ "contains_edu_lambda = lambda email: '.edu.' in email\n",
+ "mapped_result = map(contains_edu_lambda, emails)\n",
+ "\n",
+ "# Then, we convert the mapped result into a list.\n",
+ "contains_edu_list = list(mapped_result)\n",
+ "\n",
+ "# Finally we print the result\n",
+ "print(\"Contains '.edu.':\", contains_edu_list)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 55,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Substrings before the first dot: ['cscornejo@pucp', 'orellana', 'karina', 'a20083223@pucp', 'abel', 'mtintaya@pucp', 'joselin', 'a20105737@pucp', 'jfgomezc@pucp', 'afrania', 'luzon', 'adrian', 'soto', 'a20132766@pucp', 'andre', 'gustavo', 'pmlozada@pucp', 'm', 'nicolas', 'gvidal@pucp', 'jane', 'm', 'alejandro', 'a20167070@pucp', 'riega', 'vlevanot@pucp', 'sesquives@pucp', 'perez', 'mariana', 'aclavo@pucp', 'a20182474@pucp', 'josue', 'fabio', 'fernanda', 'aquillatupa@pucp']\n",
+ "Number of substrings containing '@': 14\n"
+ ]
+ }
+ ],
+ "source": [
+ "# 6. Get all the strings before the first dot '.' in each string in the emails list.\n",
+ "# First, we identify how many of them have '@'.\n",
+ "\n",
+ "# Then we use the map function to apply a lambda function to each element in the emails list.\n",
+ "# The lambda function extracts the substring before the first dot '.' and checks if it contains '@'.\n",
+ "substring_before_dot_lambda = lambda email: email.split('.')[0]\n",
+ "mapped_result = map(substring_before_dot_lambda, emails)\n",
+ "\n",
+ "# After that, we convert the mapped result into a list.\n",
+ "substring_before_dot_list = list(mapped_result)\n",
+ "\n",
+ "# Also, we count how many substrings contain '@' and print the results\n",
+ "count_with_at = sum('@' in substring for substring in substring_before_dot_list)\n",
+ "\n",
+ "print(\"Substrings before the first dot:\", substring_before_dot_list)\n",
+ "print(\"Number of substrings containing '@':\", count_with_at)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 1.4 Pandas\n",
+ "\n",
+ "You can and should always ask ChatGPT, BARD, Bing, etc.\n",
+ "In this exercise, you will work with financial data. Follow the steps below:\n",
+ "\n",
+ "1. Load Data:\n",
+ " Load the financial data available at this URL: https://raw.githubusercontent.com/datasets/finance-vix/main/data/vix-daily.csv\n",
+ " Use `pd.read_csv()` adn the link to load the data into a DataFrame.\n",
+ "\n",
+ "2. Explore Data:\n",
+ " a) Display the first five rows of the DataFrame.\n",
+ " b) Display the summary statistics of the DataFrame.\n",
+ "\n",
+ "3. Add Columns:\n",
+ " a) Add a new column 'Level' that categorizes the 'Close' column values into 'Low' (< 20), 'Medium' (20-30), and 'High' (>30). You need to make a filter to make this categorization. You can see below some suggestions how to do it.\n",
+ " b) Add a new column 'Year' extracted from the 'Date' column. You need to work with dates. You can do it directly workiwith the column splitting it or changing it to date format an dfollowing the below suggestion. \n",
+ "\n",
+ "4. Add Rows:\n",
+ " a) Add a new row with a date of your choice and fill the other columns with appropriate values. \n",
+ "\n",
+ "5. Analysis:\n",
+ " a) Calculate the average of the column 'Close' for each 'Year'. You need to group for this task.\n",
+ " b) Count the number of 'High', 'Medium', and 'Low' Level days in the data.\n",
+ "\n",
+ "Suggestions:\n",
+ " - Use `pd.cut()` for categorizing 'Close' values.\n",
+ " - Use `pd.to_datetime()` and `dt.year` to extract the year from a date.\n",
+ " - Use `DataFrame.append()` or `pd.concat()` to add rows.\n",
+ " - Use `groupby()` for aggregation tasks."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 56,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# 1\n",
+ "import pandas as pd\n",
+ "\n",
+ "# This code loads the data from the provided URL.\n",
+ "url = \"https://raw.githubusercontent.com/datasets/finance-vix/main/data/vix-daily.csv\"\n",
+ "df = pd.read_csv(url)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 57,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " DATE | \n",
+ " OPEN | \n",
+ " HIGH | \n",
+ " LOW | \n",
+ " CLOSE | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 01/02/1990 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 01/03/1990 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 01/04/1990 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 01/05/1990 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 01/08/1990 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 8572 | \n",
+ " 12/29/2023 | \n",
+ " 12.55 | \n",
+ " 13.19 | \n",
+ " 12.36 | \n",
+ " 12.45 | \n",
+ "
\n",
+ " \n",
+ " | 8573 | \n",
+ " 01/02/2024 | \n",
+ " 13.22 | \n",
+ " 14.23 | \n",
+ " 13.10 | \n",
+ " 13.20 | \n",
+ "
\n",
+ " \n",
+ " | 8574 | \n",
+ " 01/03/2024 | \n",
+ " 13.35 | \n",
+ " 14.22 | \n",
+ " 13.33 | \n",
+ " 14.04 | \n",
+ "
\n",
+ " \n",
+ " | 8575 | \n",
+ " 01/04/2024 | \n",
+ " 13.93 | \n",
+ " 14.20 | \n",
+ " 13.64 | \n",
+ " 14.13 | \n",
+ "
\n",
+ " \n",
+ " | 8576 | \n",
+ " 01/05/2024 | \n",
+ " 14.24 | \n",
+ " 14.58 | \n",
+ " 13.29 | \n",
+ " 13.35 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
8577 rows × 5 columns
\n",
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " DATE | \n",
+ " OPEN | \n",
+ " HIGH | \n",
+ " LOW | \n",
+ " CLOSE | \n",
+ " Level | \n",
+ " Year | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 01/02/1990 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " Low | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 01/03/1990 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " Low | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 01/04/1990 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " Low | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 01/05/1990 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " Medium | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 01/08/1990 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " Medium | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 8572 | \n",
+ " 12/29/2023 | \n",
+ " 12.55 | \n",
+ " 13.19 | \n",
+ " 12.36 | \n",
+ " 12.45 | \n",
+ " Low | \n",
+ " 2023 | \n",
+ "
\n",
+ " \n",
+ " | 8573 | \n",
+ " 01/02/2024 | \n",
+ " 13.22 | \n",
+ " 14.23 | \n",
+ " 13.10 | \n",
+ " 13.20 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8574 | \n",
+ " 01/03/2024 | \n",
+ " 13.35 | \n",
+ " 14.22 | \n",
+ " 13.33 | \n",
+ " 14.04 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8575 | \n",
+ " 01/04/2024 | \n",
+ " 13.93 | \n",
+ " 14.20 | \n",
+ " 13.64 | \n",
+ " 14.13 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8576 | \n",
+ " 01/05/2024 | \n",
+ " 14.24 | \n",
+ " 14.58 | \n",
+ " 13.29 | \n",
+ " 13.35 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
8577 rows × 7 columns
\n",
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " DATE | \n",
+ " OPEN | \n",
+ " HIGH | \n",
+ " LOW | \n",
+ " CLOSE | \n",
+ " Level | \n",
+ " Year | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 01/02/1990 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " Low | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 01/03/1990 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " Low | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 01/04/1990 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " Low | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 01/05/1990 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " Medium | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 01/08/1990 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " Medium | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 8573 | \n",
+ " 01/02/2024 | \n",
+ " 13.22 | \n",
+ " 14.23 | \n",
+ " 13.10 | \n",
+ " 13.20 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8574 | \n",
+ " 01/03/2024 | \n",
+ " 13.35 | \n",
+ " 14.22 | \n",
+ " 13.33 | \n",
+ " 14.04 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8575 | \n",
+ " 01/04/2024 | \n",
+ " 13.93 | \n",
+ " 14.20 | \n",
+ " 13.64 | \n",
+ " 14.13 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8576 | \n",
+ " 01/05/2024 | \n",
+ " 14.24 | \n",
+ " 14.58 | \n",
+ " 13.29 | \n",
+ " 13.35 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8577 | \n",
+ " 01/06/2024 | \n",
+ " 14.27 | \n",
+ " 14.61 | \n",
+ " 13.32 | \n",
+ " 13.38 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
8578 rows × 7 columns
\n",
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " Year | \n",
+ " Average Close | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 1990 | \n",
+ " 23.06 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 1991 | \n",
+ " 18.37 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 1992 | \n",
+ " 15.45 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 1993 | \n",
+ " 12.69 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 1994 | \n",
+ " 13.93 | \n",
+ "
\n",
+ " \n",
+ " | 5 | \n",
+ " 1995 | \n",
+ " 12.39 | \n",
+ "
\n",
+ " \n",
+ " | 6 | \n",
+ " 1996 | \n",
+ " 16.44 | \n",
+ "
\n",
+ " \n",
+ " | 7 | \n",
+ " 1997 | \n",
+ " 22.36 | \n",
+ "
\n",
+ " \n",
+ " | 8 | \n",
+ " 1998 | \n",
+ " 25.60 | \n",
+ "
\n",
+ " \n",
+ " | 9 | \n",
+ " 1999 | \n",
+ " 24.37 | \n",
+ "
\n",
+ " \n",
+ " | 10 | \n",
+ " 2000 | \n",
+ " 23.32 | \n",
+ "
\n",
+ " \n",
+ " | 11 | \n",
+ " 2001 | \n",
+ " 25.75 | \n",
+ "
\n",
+ " \n",
+ " | 12 | \n",
+ " 2002 | \n",
+ " 27.29 | \n",
+ "
\n",
+ " \n",
+ " | 13 | \n",
+ " 2003 | \n",
+ " 21.98 | \n",
+ "
\n",
+ " \n",
+ " | 14 | \n",
+ " 2004 | \n",
+ " 15.48 | \n",
+ "
\n",
+ " \n",
+ " | 15 | \n",
+ " 2005 | \n",
+ " 12.81 | \n",
+ "
\n",
+ " \n",
+ " | 16 | \n",
+ " 2006 | \n",
+ " 12.81 | \n",
+ "
\n",
+ " \n",
+ " | 17 | \n",
+ " 2007 | \n",
+ " 17.54 | \n",
+ "
\n",
+ " \n",
+ " | 18 | \n",
+ " 2008 | \n",
+ " 32.70 | \n",
+ "
\n",
+ " \n",
+ " | 19 | \n",
+ " 2009 | \n",
+ " 31.48 | \n",
+ "
\n",
+ " \n",
+ " | 20 | \n",
+ " 2010 | \n",
+ " 22.55 | \n",
+ "
\n",
+ " \n",
+ " | 21 | \n",
+ " 2011 | \n",
+ " 24.20 | \n",
+ "
\n",
+ " \n",
+ " | 22 | \n",
+ " 2012 | \n",
+ " 17.80 | \n",
+ "
\n",
+ " \n",
+ " | 23 | \n",
+ " 2013 | \n",
+ " 14.23 | \n",
+ "
\n",
+ " \n",
+ " | 24 | \n",
+ " 2014 | \n",
+ " 14.18 | \n",
+ "
\n",
+ " \n",
+ " | 25 | \n",
+ " 2015 | \n",
+ " 16.67 | \n",
+ "
\n",
+ " \n",
+ " | 26 | \n",
+ " 2016 | \n",
+ " 15.83 | \n",
+ "
\n",
+ " \n",
+ " | 27 | \n",
+ " 2017 | \n",
+ " 11.09 | \n",
+ "
\n",
+ " \n",
+ " | 28 | \n",
+ " 2018 | \n",
+ " 16.64 | \n",
+ "
\n",
+ " \n",
+ " | 29 | \n",
+ " 2019 | \n",
+ " 15.39 | \n",
+ "
\n",
+ " \n",
+ " | 30 | \n",
+ " 2020 | \n",
+ " 29.25 | \n",
+ "
\n",
+ " \n",
+ " | 31 | \n",
+ " 2021 | \n",
+ " 19.66 | \n",
+ "
\n",
+ " \n",
+ " | 32 | \n",
+ " 2022 | \n",
+ " 25.64 | \n",
+ "
\n",
+ " \n",
+ " | 33 | \n",
+ " 2023 | \n",
+ " 16.85 | \n",
+ "
\n",
+ " \n",
+ " | 34 | \n",
+ " 2024 | \n",
+ " 13.62 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " DATE | \n",
+ " OPEN | \n",
+ " HIGH | \n",
+ " LOW | \n",
+ " CLOSE | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 01/02/1990 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 01/03/1990 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 01/04/1990 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 01/05/1990 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 01/08/1990 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 8572 | \n",
+ " 12/29/2023 | \n",
+ " 12.55 | \n",
+ " 13.19 | \n",
+ " 12.36 | \n",
+ " 12.45 | \n",
+ "
\n",
+ " \n",
+ " | 8573 | \n",
+ " 01/02/2024 | \n",
+ " 13.22 | \n",
+ " 14.23 | \n",
+ " 13.10 | \n",
+ " 13.20 | \n",
+ "
\n",
+ " \n",
+ " | 8574 | \n",
+ " 01/03/2024 | \n",
+ " 13.35 | \n",
+ " 14.22 | \n",
+ " 13.33 | \n",
+ " 14.04 | \n",
+ "
\n",
+ " \n",
+ " | 8575 | \n",
+ " 01/04/2024 | \n",
+ " 13.93 | \n",
+ " 14.20 | \n",
+ " 13.64 | \n",
+ " 14.13 | \n",
+ "
\n",
+ " \n",
+ " | 8576 | \n",
+ " 01/05/2024 | \n",
+ " 14.24 | \n",
+ " 14.58 | \n",
+ " 13.29 | \n",
+ " 13.35 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
8577 rows × 5 columns
\n",
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " DATE | \n",
+ " OPEN | \n",
+ " HIGH | \n",
+ " LOW | \n",
+ " CLOSE | \n",
+ " Level | \n",
+ " Year | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 01/02/1990 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " Low | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 01/03/1990 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " Low | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 01/04/1990 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " Low | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 01/05/1990 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " Medium | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 01/08/1990 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " Medium | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 8572 | \n",
+ " 12/29/2023 | \n",
+ " 12.55 | \n",
+ " 13.19 | \n",
+ " 12.36 | \n",
+ " 12.45 | \n",
+ " Low | \n",
+ " 2023 | \n",
+ "
\n",
+ " \n",
+ " | 8573 | \n",
+ " 01/02/2024 | \n",
+ " 13.22 | \n",
+ " 14.23 | \n",
+ " 13.10 | \n",
+ " 13.20 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8574 | \n",
+ " 01/03/2024 | \n",
+ " 13.35 | \n",
+ " 14.22 | \n",
+ " 13.33 | \n",
+ " 14.04 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8575 | \n",
+ " 01/04/2024 | \n",
+ " 13.93 | \n",
+ " 14.20 | \n",
+ " 13.64 | \n",
+ " 14.13 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8576 | \n",
+ " 01/05/2024 | \n",
+ " 14.24 | \n",
+ " 14.58 | \n",
+ " 13.29 | \n",
+ " 13.35 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
8577 rows × 7 columns
\n",
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " DATE | \n",
+ " OPEN | \n",
+ " HIGH | \n",
+ " LOW | \n",
+ " CLOSE | \n",
+ " Level | \n",
+ " Year | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 01/02/1990 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " Low | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 01/03/1990 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " Low | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 01/04/1990 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " Low | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 01/05/1990 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " Medium | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 01/08/1990 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " Medium | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 8573 | \n",
+ " 01/02/2024 | \n",
+ " 13.22 | \n",
+ " 14.23 | \n",
+ " 13.10 | \n",
+ " 13.20 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8574 | \n",
+ " 01/03/2024 | \n",
+ " 13.35 | \n",
+ " 14.22 | \n",
+ " 13.33 | \n",
+ " 14.04 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8575 | \n",
+ " 01/04/2024 | \n",
+ " 13.93 | \n",
+ " 14.20 | \n",
+ " 13.64 | \n",
+ " 14.13 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8576 | \n",
+ " 01/05/2024 | \n",
+ " 14.24 | \n",
+ " 14.58 | \n",
+ " 13.29 | \n",
+ " 13.35 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8577 | \n",
+ " 01/06/2024 | \n",
+ " 14.27 | \n",
+ " 14.61 | \n",
+ " 13.32 | \n",
+ " 13.38 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
8578 rows × 7 columns
\n",
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " Year | \n",
+ " Average Close | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 1990 | \n",
+ " 23.06 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 1991 | \n",
+ " 18.37 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 1992 | \n",
+ " 15.45 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 1993 | \n",
+ " 12.69 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 1994 | \n",
+ " 13.93 | \n",
+ "
\n",
+ " \n",
+ " | 5 | \n",
+ " 1995 | \n",
+ " 12.39 | \n",
+ "
\n",
+ " \n",
+ " | 6 | \n",
+ " 1996 | \n",
+ " 16.44 | \n",
+ "
\n",
+ " \n",
+ " | 7 | \n",
+ " 1997 | \n",
+ " 22.36 | \n",
+ "
\n",
+ " \n",
+ " | 8 | \n",
+ " 1998 | \n",
+ " 25.60 | \n",
+ "
\n",
+ " \n",
+ " | 9 | \n",
+ " 1999 | \n",
+ " 24.37 | \n",
+ "
\n",
+ " \n",
+ " | 10 | \n",
+ " 2000 | \n",
+ " 23.32 | \n",
+ "
\n",
+ " \n",
+ " | 11 | \n",
+ " 2001 | \n",
+ " 25.75 | \n",
+ "
\n",
+ " \n",
+ " | 12 | \n",
+ " 2002 | \n",
+ " 27.29 | \n",
+ "
\n",
+ " \n",
+ " | 13 | \n",
+ " 2003 | \n",
+ " 21.98 | \n",
+ "
\n",
+ " \n",
+ " | 14 | \n",
+ " 2004 | \n",
+ " 15.48 | \n",
+ "
\n",
+ " \n",
+ " | 15 | \n",
+ " 2005 | \n",
+ " 12.81 | \n",
+ "
\n",
+ " \n",
+ " | 16 | \n",
+ " 2006 | \n",
+ " 12.81 | \n",
+ "
\n",
+ " \n",
+ " | 17 | \n",
+ " 2007 | \n",
+ " 17.54 | \n",
+ "
\n",
+ " \n",
+ " | 18 | \n",
+ " 2008 | \n",
+ " 32.70 | \n",
+ "
\n",
+ " \n",
+ " | 19 | \n",
+ " 2009 | \n",
+ " 31.48 | \n",
+ "
\n",
+ " \n",
+ " | 20 | \n",
+ " 2010 | \n",
+ " 22.55 | \n",
+ "
\n",
+ " \n",
+ " | 21 | \n",
+ " 2011 | \n",
+ " 24.20 | \n",
+ "
\n",
+ " \n",
+ " | 22 | \n",
+ " 2012 | \n",
+ " 17.80 | \n",
+ "
\n",
+ " \n",
+ " | 23 | \n",
+ " 2013 | \n",
+ " 14.23 | \n",
+ "
\n",
+ " \n",
+ " | 24 | \n",
+ " 2014 | \n",
+ " 14.18 | \n",
+ "
\n",
+ " \n",
+ " | 25 | \n",
+ " 2015 | \n",
+ " 16.67 | \n",
+ "
\n",
+ " \n",
+ " | 26 | \n",
+ " 2016 | \n",
+ " 15.83 | \n",
+ "
\n",
+ " \n",
+ " | 27 | \n",
+ " 2017 | \n",
+ " 11.09 | \n",
+ "
\n",
+ " \n",
+ " | 28 | \n",
+ " 2018 | \n",
+ " 16.64 | \n",
+ "
\n",
+ " \n",
+ " | 29 | \n",
+ " 2019 | \n",
+ " 15.39 | \n",
+ "
\n",
+ " \n",
+ " | 30 | \n",
+ " 2020 | \n",
+ " 29.25 | \n",
+ "
\n",
+ " \n",
+ " | 31 | \n",
+ " 2021 | \n",
+ " 19.66 | \n",
+ "
\n",
+ " \n",
+ " | 32 | \n",
+ " 2022 | \n",
+ " 25.64 | \n",
+ "
\n",
+ " \n",
+ " | 33 | \n",
+ " 2023 | \n",
+ " 16.85 | \n",
+ "
\n",
+ " \n",
+ " | 34 | \n",
+ " 2024 | \n",
+ " 13.62 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " DATE | \n",
+ " OPEN | \n",
+ " HIGH | \n",
+ " LOW | \n",
+ " CLOSE | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 01/02/1990 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 01/03/1990 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 01/04/1990 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 01/05/1990 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 01/08/1990 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 8572 | \n",
+ " 12/29/2023 | \n",
+ " 12.55 | \n",
+ " 13.19 | \n",
+ " 12.36 | \n",
+ " 12.45 | \n",
+ "
\n",
+ " \n",
+ " | 8573 | \n",
+ " 01/02/2024 | \n",
+ " 13.22 | \n",
+ " 14.23 | \n",
+ " 13.10 | \n",
+ " 13.20 | \n",
+ "
\n",
+ " \n",
+ " | 8574 | \n",
+ " 01/03/2024 | \n",
+ " 13.35 | \n",
+ " 14.22 | \n",
+ " 13.33 | \n",
+ " 14.04 | \n",
+ "
\n",
+ " \n",
+ " | 8575 | \n",
+ " 01/04/2024 | \n",
+ " 13.93 | \n",
+ " 14.20 | \n",
+ " 13.64 | \n",
+ " 14.13 | \n",
+ "
\n",
+ " \n",
+ " | 8576 | \n",
+ " 01/05/2024 | \n",
+ " 14.24 | \n",
+ " 14.58 | \n",
+ " 13.29 | \n",
+ " 13.35 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
8577 rows × 5 columns
\n",
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " DATE | \n",
+ " OPEN | \n",
+ " HIGH | \n",
+ " LOW | \n",
+ " CLOSE | \n",
+ " Level | \n",
+ " Year | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 01/02/1990 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " Low | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 01/03/1990 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " Low | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 01/04/1990 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " Low | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 01/05/1990 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " Medium | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 01/08/1990 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " Medium | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 8572 | \n",
+ " 12/29/2023 | \n",
+ " 12.55 | \n",
+ " 13.19 | \n",
+ " 12.36 | \n",
+ " 12.45 | \n",
+ " Low | \n",
+ " 2023 | \n",
+ "
\n",
+ " \n",
+ " | 8573 | \n",
+ " 01/02/2024 | \n",
+ " 13.22 | \n",
+ " 14.23 | \n",
+ " 13.10 | \n",
+ " 13.20 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8574 | \n",
+ " 01/03/2024 | \n",
+ " 13.35 | \n",
+ " 14.22 | \n",
+ " 13.33 | \n",
+ " 14.04 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8575 | \n",
+ " 01/04/2024 | \n",
+ " 13.93 | \n",
+ " 14.20 | \n",
+ " 13.64 | \n",
+ " 14.13 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8576 | \n",
+ " 01/05/2024 | \n",
+ " 14.24 | \n",
+ " 14.58 | \n",
+ " 13.29 | \n",
+ " 13.35 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
8577 rows × 7 columns
\n",
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " DATE | \n",
+ " OPEN | \n",
+ " HIGH | \n",
+ " LOW | \n",
+ " CLOSE | \n",
+ " Level | \n",
+ " Year | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 01/02/1990 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " 17.24 | \n",
+ " Low | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 01/03/1990 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " 18.19 | \n",
+ " Low | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 01/04/1990 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " 19.22 | \n",
+ " Low | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 01/05/1990 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " 20.11 | \n",
+ " Medium | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 01/08/1990 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " 20.26 | \n",
+ " Medium | \n",
+ " 1990 | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 8573 | \n",
+ " 01/02/2024 | \n",
+ " 13.22 | \n",
+ " 14.23 | \n",
+ " 13.10 | \n",
+ " 13.20 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8574 | \n",
+ " 01/03/2024 | \n",
+ " 13.35 | \n",
+ " 14.22 | \n",
+ " 13.33 | \n",
+ " 14.04 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8575 | \n",
+ " 01/04/2024 | \n",
+ " 13.93 | \n",
+ " 14.20 | \n",
+ " 13.64 | \n",
+ " 14.13 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8576 | \n",
+ " 01/05/2024 | \n",
+ " 14.24 | \n",
+ " 14.58 | \n",
+ " 13.29 | \n",
+ " 13.35 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ " | 8577 | \n",
+ " 01/06/2024 | \n",
+ " 14.27 | \n",
+ " 14.61 | \n",
+ " 13.32 | \n",
+ " 13.38 | \n",
+ " Low | \n",
+ " 2024 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
8578 rows × 7 columns
\n",
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " Year | \n",
+ " Average Close | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 1990 | \n",
+ " 23.06 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 1991 | \n",
+ " 18.37 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 1992 | \n",
+ " 15.45 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 1993 | \n",
+ " 12.69 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 1994 | \n",
+ " 13.93 | \n",
+ "
\n",
+ " \n",
+ " | 5 | \n",
+ " 1995 | \n",
+ " 12.39 | \n",
+ "
\n",
+ " \n",
+ " | 6 | \n",
+ " 1996 | \n",
+ " 16.44 | \n",
+ "
\n",
+ " \n",
+ " | 7 | \n",
+ " 1997 | \n",
+ " 22.36 | \n",
+ "
\n",
+ " \n",
+ " | 8 | \n",
+ " 1998 | \n",
+ " 25.60 | \n",
+ "
\n",
+ " \n",
+ " | 9 | \n",
+ " 1999 | \n",
+ " 24.37 | \n",
+ "
\n",
+ " \n",
+ " | 10 | \n",
+ " 2000 | \n",
+ " 23.32 | \n",
+ "
\n",
+ " \n",
+ " | 11 | \n",
+ " 2001 | \n",
+ " 25.75 | \n",
+ "
\n",
+ " \n",
+ " | 12 | \n",
+ " 2002 | \n",
+ " 27.29 | \n",
+ "
\n",
+ " \n",
+ " | 13 | \n",
+ " 2003 | \n",
+ " 21.98 | \n",
+ "
\n",
+ " \n",
+ " | 14 | \n",
+ " 2004 | \n",
+ " 15.48 | \n",
+ "
\n",
+ " \n",
+ " | 15 | \n",
+ " 2005 | \n",
+ " 12.81 | \n",
+ "
\n",
+ " \n",
+ " | 16 | \n",
+ " 2006 | \n",
+ " 12.81 | \n",
+ "
\n",
+ " \n",
+ " | 17 | \n",
+ " 2007 | \n",
+ " 17.54 | \n",
+ "
\n",
+ " \n",
+ " | 18 | \n",
+ " 2008 | \n",
+ " 32.70 | \n",
+ "
\n",
+ " \n",
+ " | 19 | \n",
+ " 2009 | \n",
+ " 31.48 | \n",
+ "
\n",
+ " \n",
+ " | 20 | \n",
+ " 2010 | \n",
+ " 22.55 | \n",
+ "
\n",
+ " \n",
+ " | 21 | \n",
+ " 2011 | \n",
+ " 24.20 | \n",
+ "
\n",
+ " \n",
+ " | 22 | \n",
+ " 2012 | \n",
+ " 17.80 | \n",
+ "
\n",
+ " \n",
+ " | 23 | \n",
+ " 2013 | \n",
+ " 14.23 | \n",
+ "
\n",
+ " \n",
+ " | 24 | \n",
+ " 2014 | \n",
+ " 14.18 | \n",
+ "
\n",
+ " \n",
+ " | 25 | \n",
+ " 2015 | \n",
+ " 16.67 | \n",
+ "
\n",
+ " \n",
+ " | 26 | \n",
+ " 2016 | \n",
+ " 15.83 | \n",
+ "
\n",
+ " \n",
+ " | 27 | \n",
+ " 2017 | \n",
+ " 11.09 | \n",
+ "
\n",
+ " \n",
+ " | 28 | \n",
+ " 2018 | \n",
+ " 16.64 | \n",
+ "
\n",
+ " \n",
+ " | 29 | \n",
+ " 2019 | \n",
+ " 15.39 | \n",
+ "
\n",
+ " \n",
+ " | 30 | \n",
+ " 2020 | \n",
+ " 29.25 | \n",
+ "
\n",
+ " \n",
+ " | 31 | \n",
+ " 2021 | \n",
+ " 19.66 | \n",
+ "
\n",
+ " \n",
+ " | 32 | \n",
+ " 2022 | \n",
+ " 25.64 | \n",
+ "
\n",
+ " \n",
+ " | 33 | \n",
+ " 2023 | \n",
+ " 16.85 | \n",
+ "
\n",
+ " \n",
+ " | 34 | \n",
+ " 2024 | \n",
+ " 13.62 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
\n",
- "\n",
- "2. Replicate 4 times the values of the list `p2_list`. We expect an ouput like this: `[ 2 , 3, 4, 5, 2 , 3, 4, 5, 2 , 3, 4, 5, 2 , 3, 4, 5]`. **Hint: Use multiplication function in `lists`and see the output.**
\n",
- "3. Print the length of `f_list`. **Hint: Length function**
\n",
- "4. Print `My teacher assistant is so boring.` using `text1` list. **Hint: Use the [`join` function](https://stackoverflow.com/questions/493819/why-is-it-string-joinlist-instead-of-list-joinstring)**
\n",
- "5. Print `My TA is so boring, but is very funny.` using `text1` list.**Hint: Use the `join` function, and `extend` method.**
\n",
- "6. Print
\n",
- "`The max value of values1 is 86 and is located in the 0 index. `
\n",
- "`The min value of values1 is 0 and is located in the 7 index. `
**Hint: Use the `f-string`, `min`, and `max` functions.**\n",
- "
\n",
- "7. Get two lists: `names` and `last_names` using `last_and_name` list. **Hint: Use `map` and `split`.**\n",
- "
\n",
- "8. Give only the last names of students who do not have email. Use the `emails` and `last_names` listt. **Hint: Use `map` and `split`.**\n",
- "
"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 33,
- "metadata": {},
- "outputs": [],
- "source": [
- "import numpy as np"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 34,
- "metadata": {},
- "outputs": [],
- "source": [
- "f_list = [np.nan , np.nan, \"Austria\", \"Germany\", np.nan, \"Pakistan\", \"np.nan\", np.nan ]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 35,
- "metadata": {},
- "outputs": [],
- "source": [
- "text1 = ['My', 'teacher', 'assistant', 'is', 'so', 'boring.']"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 36,
- "metadata": {},
- "outputs": [],
- "source": [
- "p2_list = [ 2 , 3, 4, 5 ]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 37,
- "metadata": {},
- "outputs": [],
- "source": [
- "values1 = [ 86, 86, 85, 85, 85, 83, 23, 0, 84, 1 ] "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 38,
- "metadata": {
- "scrolled": true
- },
- "outputs": [],
- "source": [
- "# These two lists a\n",
- "last_and_name = [ \"CORNEJO SANCHEZ, CHRISTIAN SANTOS\", \"ORELLANA QUISPE, CRISTIAN NASSER\", \"MORALES CHOQUEHUANCA, ANGELICA KARINA\", \"GUIMARAY RIBEYRO, JOSE ROBERTO\", \"CAMACHO GAVIDIA, ABEL FERNANDO\", \"TINTAYA ORIHUELA, MEIR ALVARO\", \"CHAVEZ MARTINEZ, JOSELIN ALEXANDRA\", \"FIGUEROA MURO, LEONEL ARTURO\", \"GOMEZ CRIBILLERO, JOSE FELIPE\", \"PALOMINO SEGUÍN, AFRANIA\", \"LUZON CUEVA, BIANCA MARIETTE\", \"SUAÑA ZEGARRA, ADRIAN ANDRE\", \"SOTO POMACHAGUA, DORKAS YOMIRA JHERMY\", \"FIORENTINO MARTINEZ, LADY ALY\", \"LAMA MAVILA, HECTOR ANDRE\", \"MEZA HINOJO, GUSTAVO\", \"LOZADA MURILLO, PERSEO MARCELO\", \"ZAMBRANO JIMENEZ, MIGUEL ALONZO\", \"JACOBS LUQUE, NICOLAS\", \"VIDAL VIDAL, ROCIO GABRIELA\", \"TORRES ANICAMA, JANE CAMILA\", \"LOPEZ ESTRADA, MARIA ELISA\", \"BOYCO ORAMS, ALEJANDRO\", \"DIAZ BERROSPI, KARLINE ROSMELI\", \"RIEGA ESCALANTE, STEPHY ROSARIO\", \"LEVANO TORRES, VALERIA CECILIA\", \"ESQUIVES BRAVO, SEBASTIAN RENATO\", \"PEREZ GONZALES, JUAN CARLOS\", \"OTERO MAGUIÑA, MARIANA\", \"CLAVO CAMPOS, ANDREA BRIZETH\", \"AGUILAR GARCIA, ERICK JOSUE\", \"CALDAS VELASQUEZ, JOSUE DANIEL\", \"SALAS NUÑEZ BORJA, FABIO MANUEL\", \"PIZARRO VILLANES, FERNANDA NICOLLE\", \"QUILLATUPA MORALES, ANGELA ADELINA\", \"HUANCAYA IDONE, CESAR DANTE\", \"CALVO PORTOCARRERO, GABRIELA ISABEL\", \"IBAÑEZ ABANTO, ANGEL MAURICIO\", \"MELÉNDEZ APONTE, JUAN DIEGO\", \"CRISTIAN SERRANO, ARONE\", \"HINOJOSA CAHUANA, PERCY ALBERTH\", \"ANGLAS GARCÍA, KEVIN ARTURO\", \"ALDAVE ACOSTA, CESAR ERNESTO\", \"NÚÑEZ HUAMÁN, CÉSAR AGUSTO\", \"OBREGON HUAMAN, DIANA EDITH\", \"SOTO PACHERRES, RODRIGO FRANCO\", \"INGARUCA RIVERA, GRETTEL ALEXANDRA\", \"ROJAS HUAMAN, ROSA ANGELA\", \"NEYRA SALAS, DANTE OMAR\", \"HUERTA ESPINOZA, YAJAIRA ALEXANDRA\", \"HUANCA MARTINEZ, JORGE ALBERTO\", \"FLORES CADILLO, ALEXIS\" ]\n",
- "emails = [\"cscornejo@pucp.edu.pe\", \"orellana.cn@pucp.edu.pe\", \"karina.morales@pucp.edu.pe\", \"a20083223@pucp.pe\", \"abel.camacho@pucp.pe\", \"mtintaya@pucp.edu.pe\", \"joselin.chavez@pucp.edu.pe\", \"a20105737@pucp.pe\", \"jfgomezc@pucp.pe\", \"afrania.palomino@pucp.pe\", \"luzon.bianca@pucp.pe\", \"adrian.suanaz@pucp.pe\", \"soto.y@pucp.edu.pe\", \"a20132766@pucp.pe\", \"andre.lama@pucp.edu.pe\", \"gustavo.meza@pucp.edu.pe\", \"pmlozada@pucp.edu.pe\", \"m.zambranoj@pucp.edu.pe\", \"nicolas.jacobs@pucp.edu.pe\", \"gvidal@pucp.edu.pe\", \"jane.torres@pucp.edu.pe\", \"m.lopez@pucp.edu.pe\", \"alejandro.boyco@pucp.edu.pe\", \"a20167070@pucp.edu.pe\", \"riega.stephy@pucp.edu.pe\", \"vlevanot@pucp.edu.pe\", \"sesquives@pucp.edu.pe\", \"perez.juanc@pucp.edu.pe\", \"mariana.otero@pucp.edu.pe\", \"aclavo@pucp.edu.pe\", \"a20182474@pucp.edu.pe\", \"josue.caldas@pucp.edu.pe\", \"fabio.salas@pucp.edu.pe\", \"fernanda.pizarro@pucp.edu.pe\", \"aquillatupa@pucp.pe\", \"\", \"\", \"\", \"\", \"\", \"f0873079@pucp.edu.pe\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"\", \"flores.alexis@pucp.edu.pe\", ]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 39,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "The indices [0, 1, 4, 7] have np.nan values.\n"
- ]
- }
- ],
- "source": [
- " # Answer 1\n",
- "\n",
- "nan_values = [i for i, value in enumerate(f_list) if value is np.nan]\n",
- "\n",
- "print(f\"The indices {nan_values} have np.nan values.\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 40,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "[2, 3, 4, 5, 2, 3, 4, 5, 2, 3, 4, 5, 2, 3, 4, 5]\n"
- ]
- }
- ],
- "source": [
- " # Answer 2\n",
- "\n",
- "p2_list_2 = p2_list * 4\n",
- "\n",
- "print(p2_list_2)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 41,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "8\n"
- ]
- }
- ],
- "source": [
- " # Answer 3\n",
- "\n",
- "print(len(f_list))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 42,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "'My teacher assistant is so boring.'"
- ]
- },
- "execution_count": 42,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- " # Answer 4\n",
- "\n",
- "answer_4 = ' '.join(text1)\n",
- "answer_4"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 43,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "'My TA My teacher assistant is so boring but is very funny'"
- ]
- },
- "execution_count": 43,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- " # Answer 5\n",
- " \n",
- "text1[-1] = text1[-1].rstrip('.')\n",
- " \n",
- "text_answer = ['My', 'TA']\n",
- "\n",
- "text_answer_b = ['but', 'is', 'very', 'funny']\n",
- "\n",
- "text_answer.extend(text1 + text_answer_b)\n",
- "\n",
- "answer_5 = ' '.join(text_answer)\n",
- "answer_5"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 44,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "The max value of values1 is 86 and is located in the 0 index.\n"
- ]
- }
- ],
- "source": [
- " # Answer 6.1\n",
- " \n",
- "max_index = values1.index(max(values1))\n",
- " \n",
- "print(f\"The max value of values1 is {max(values1)} and is located in the {max_index} index.\")\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 45,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "The min value of values1 is 0 and is located in the 7 index.\n"
- ]
- }
- ],
- "source": [
- " # Answer 6.2\n",
- " \n",
- "min_index = values1.index(min(values1))\n",
- " \n",
- "print(f\"The min value of values1 is {min(values1)} and is located in the {min_index} index.\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 46,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Names: ('CHRISTIAN SANTOS', 'CRISTIAN NASSER', 'ANGELICA KARINA', 'JOSE ROBERTO', 'ABEL FERNANDO', 'MEIR ALVARO', 'JOSELIN ALEXANDRA', 'LEONEL ARTURO', 'JOSE FELIPE', 'AFRANIA', 'BIANCA MARIETTE', 'ADRIAN ANDRE', 'DORKAS YOMIRA JHERMY', 'LADY ALY', 'HECTOR ANDRE', 'GUSTAVO', 'PERSEO MARCELO', 'MIGUEL ALONZO', 'NICOLAS', 'ROCIO GABRIELA', 'JANE CAMILA', 'MARIA ELISA', 'ALEJANDRO', 'KARLINE ROSMELI', 'STEPHY ROSARIO', 'VALERIA CECILIA', 'SEBASTIAN RENATO', 'JUAN CARLOS', 'MARIANA', 'ANDREA BRIZETH', 'ERICK JOSUE', 'JOSUE DANIEL', 'FABIO MANUEL', 'FERNANDA NICOLLE', 'ANGELA ADELINA', 'CESAR DANTE', 'GABRIELA ISABEL', 'ANGEL MAURICIO', 'JUAN DIEGO', 'ARONE', 'PERCY ALBERTH', 'KEVIN ARTURO', 'CESAR ERNESTO', 'CÉSAR AGUSTO', 'DIANA EDITH', 'RODRIGO FRANCO', 'GRETTEL ALEXANDRA', 'ROSA ANGELA', 'DANTE OMAR', 'YAJAIRA ALEXANDRA', 'JORGE ALBERTO', 'ALEXIS')\n",
- "Last Names: ('CORNEJO SANCHEZ', 'ORELLANA QUISPE', 'MORALES CHOQUEHUANCA', 'GUIMARAY RIBEYRO', 'CAMACHO GAVIDIA', 'TINTAYA ORIHUELA', 'CHAVEZ MARTINEZ', 'FIGUEROA MURO', 'GOMEZ CRIBILLERO', 'PALOMINO SEGUÍN', 'LUZON CUEVA', 'SUAÑA ZEGARRA', 'SOTO POMACHAGUA', 'FIORENTINO MARTINEZ', 'LAMA MAVILA', 'MEZA HINOJO', 'LOZADA MURILLO', 'ZAMBRANO JIMENEZ', 'JACOBS LUQUE', 'VIDAL VIDAL', 'TORRES ANICAMA', 'LOPEZ ESTRADA', 'BOYCO ORAMS', 'DIAZ BERROSPI', 'RIEGA ESCALANTE', 'LEVANO TORRES', 'ESQUIVES BRAVO', 'PEREZ GONZALES', 'OTERO MAGUIÑA', 'CLAVO CAMPOS', 'AGUILAR GARCIA', 'CALDAS VELASQUEZ', 'SALAS NUÑEZ BORJA', 'PIZARRO VILLANES', 'QUILLATUPA MORALES', 'HUANCAYA IDONE', 'CALVO PORTOCARRERO', 'IBAÑEZ ABANTO', 'MELÉNDEZ APONTE', 'CRISTIAN SERRANO', 'HINOJOSA CAHUANA', 'ANGLAS GARCÍA', 'ALDAVE ACOSTA', 'NÚÑEZ HUAMÁN', 'OBREGON HUAMAN', 'SOTO PACHERRES', 'INGARUCA RIVERA', 'ROJAS HUAMAN', 'NEYRA SALAS', 'HUERTA ESPINOZA', 'HUANCA MARTINEZ', 'FLORES CADILLO')\n"
- ]
- }
- ],
- "source": [
- " # Answer 7\n",
- "\n",
- "last_names, names = zip(*map(lambda x: x.split(', '), last_and_name))\n",
- " # the lambda function using split divides each name from each last name\n",
- " # the function zip takes the values and puts them in tuples\n",
- " # \"last_names, names\" indicates the code to split the tuples in two separate lists\n",
- "print(\"Names:\", names)\n",
- "print(\"Last Names:\", last_names)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 47,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "['HUANCAYA IDONE', 'CALVO PORTOCARRERO', 'IBAÑEZ ABANTO', 'MELÉNDEZ APONTE', 'CRISTIAN SERRANO', 'ANGLAS GARCÍA', 'ALDAVE ACOSTA', 'NÚÑEZ HUAMÁN', 'OBREGON HUAMAN', 'SOTO PACHERRES', 'INGARUCA RIVERA', 'ROJAS HUAMAN', 'NEYRA SALAS', 'HUERTA ESPINOZA', 'HUANCA MARTINEZ']\n"
- ]
- }
- ],
- "source": [
- " # Answer 8\n",
- " \n",
- "answer_8 = [last_name for last_name, email in zip(last_names, emails) if not email]\n",
- " # zip function pairs last names with its corresponding emails into tuples\n",
- " # \"last_name for last_name, email in ... if not email\" indicates the last name for each pair if email is empty\n",
- "print(answer_8)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## 1.3 Strings\n",
- "\n",
- "\n",
- "1. Drop the duplicated blank spaces in `str1`. Do not use the regular expresions. Do not use the code shown in class. Explain your steps.**Hint: Use `split` method and `join` function.**\n",
- "\n",
- "2. Get the number of letters in the string .**Hint: Use `len`function.**\n",
- "\n",
- "3. Get the number of blank spaces (all of them) in the string .**Hint: Use `len`function.**\n",
- "\n",
- "4. Get the position of `@` in each string in the emails list. **Hint: Use `map`function and `find` method.**\n",
- "\n",
- "5. Identifies if exists `.edu.` in each string in the `emails` list. Get a list of Booleans. **Hint: Use `map`function and `find` method.**\n",
- "\n",
- "6. Get all the strings before the first dot `.`in each string in the `emails` list. Identifies how many of them has `@`. **Hint: Use `map`function and `find` method.**"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "#### Dear professor, the reason why I created this new branch is to correct the fact that I mistakenly edited the main branch of my group when I was writing my part. So, I was the one in charge to complete the \"Strings\" part, and here it is. I hope you can understand this."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 48,
- "metadata": {},
- "outputs": [],
- "source": [
- "str1 = 'I am too old'"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 49,
- "metadata": {},
- "outputs": [],
- "source": [
- "emails = [\"cscornejo@pucp.edu.pe\", \"orellana.cn@pucp.edu.pe\", \"karina.morales@pucp.edu.pe\", \"a20083223@pucp.pe\", \"abel.camacho@pucp.pe\", \"mtintaya@pucp.edu.pe\", \"joselin.chavez@pucp.edu.pe\", \"a20105737@pucp.pe\", \"jfgomezc@pucp.pe\", \"afrania.palomino@pucp.pe\", \"luzon.bianca@pucp.pe\", \"adrian.suanaz@pucp.pe\", \"soto.y@pucp.edu.pe\", \"a20132766@pucp.pe\", \"andre.lama@pucp.edu.pe\", \"gustavo.meza@pucp.edu.pe\", \"pmlozada@pucp.edu.pe\", \"m.zambranoj@pucp.edu.pe\", \"nicolas.jacobs@pucp.edu.pe\", \"gvidal@pucp.edu.pe\", \"jane.torres@pucp.edu.pe\", \"m.lopez@pucp.edu.pe\", \"alejandro.boyco@pucp.edu.pe\", \"a20167070@pucp.edu.pe\", \"riega.stephy@pucp.edu.pe\", \"vlevanot@pucp.edu.pe\", \"sesquives@pucp.edu.pe\", \"perez.juanc@pucp.edu.pe\", \"mariana.otero@pucp.edu.pe\", \"aclavo@pucp.edu.pe\", \"a20182474@pucp.edu.pe\", \"josue.caldas@pucp.edu.pe\", \"fabio.salas@pucp.edu.pe\", \"fernanda.pizarro@pucp.edu.pe\", \"aquillatupa@pucp.pe\"]"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 50,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "I am too old\n"
- ]
- }
- ],
- "source": [
- "# 1. Drop the duplicated blank spaces in str1. Do not use the regular expresions. Do not use the code shown in class. Explain your steps.Hint: Use split method and join function.\n",
- "\n",
- "# First, we split the string into a list of words\n",
- "list_words = str1.split()\n",
- "\n",
- "# Then, we remove the empty strings from the list\n",
- "non_empty_words = [word for word in list_words if word]\n",
- "\n",
- "# Lastly, we join the non-empty words back into a string\n",
- "result_str = ' '.join(non_empty_words)\n",
- "\n",
- "print(result_str)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 51,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Number of letters: 9\n"
- ]
- }
- ],
- "source": [
- "# 2. Get the number of letters in the string .Hint: Use lenfunction.\n",
- "\n",
- "# In order to count the number of letters, we need to remove non-alphabetic characters first, we do that \n",
- "# using the len function (to printe the lenght)\n",
- "# and verifying that the character is alphabetic (a letter), using the if function.\n",
- "num_letters = len([char for char in str1 if char.isalpha()])\n",
- "\n",
- "# This is a better way to print the answer, including the string value \"Number of letters\"\n",
- "print(\"Number of letters:\", num_letters)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 52,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Number of blank spaces: 85\n"
- ]
- }
- ],
- "source": [
- "# 3. Get the number of blank spaces (all of them) in the string .Hint: Use lenfunction.\n",
- "\n",
- "# First, we create a list with the blank spaces, using the \"isspace\" method\n",
- "blank_space = [char for char in str1 if char.isspace()]\n",
- "\n",
- "# Then we apply the function len() to the list to get the total number of blank spaces\n",
- "num_blank_spaces = len(blank_space)\n",
- "\n",
- "# Finally, we print the result\n",
- "print(\"Number of blank spaces:\", num_blank_spaces)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 53,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Positions of '@': [9, 11, 14, 9, 12, 8, 14, 9, 8, 16, 12, 13, 6, 9, 10, 12, 8, 11, 14, 6, 11, 7, 15, 9, 12, 8, 9, 11, 13, 6, 9, 12, 11, 16, 11]\n"
- ]
- }
- ],
- "source": [
- "# 4. Get the position of @ in each string in the emails list. Hint: Use mapfunction and find method.\n",
- "\n",
- "# First we use the map() function to apply the specified lambda function to each element in the emails list. \n",
- "# Then, with the lambda function takes an email address (email) and finds the position of the '@' symbol using the find() method.\n",
- "# Also, list(...) Converts the result into a list.\n",
- "positions_at = list(map(lambda email: email.find('@'), emails))\n",
- "\n",
- "# Finally, we print the results\n",
- "print(\"Positions of '@':\", positions_at)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 54,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Contains '.edu.': [True, True, True, False, False, True, True, False, False, False, False, False, True, False, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, True, False]\n"
- ]
- }
- ],
- "source": [
- "# 5. Identifies if exists .edu. in each string in the emails list. Get a list of Booleans. Hint: Use mapfunction and find method. # \n",
- "\n",
- "# First, we use the map function to apply a lambda function to each element in the emails list.\n",
- "# The lambda function checks if '.edu.' is present in each email address.\n",
- "contains_edu_lambda = lambda email: '.edu.' in email\n",
- "mapped_result = map(contains_edu_lambda, emails)\n",
- "\n",
- "# Then, we convert the mapped result into a list.\n",
- "contains_edu_list = list(mapped_result)\n",
- "\n",
- "# Finally we print the result\n",
- "print(\"Contains '.edu.':\", contains_edu_list)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 55,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Substrings before the first dot: ['cscornejo@pucp', 'orellana', 'karina', 'a20083223@pucp', 'abel', 'mtintaya@pucp', 'joselin', 'a20105737@pucp', 'jfgomezc@pucp', 'afrania', 'luzon', 'adrian', 'soto', 'a20132766@pucp', 'andre', 'gustavo', 'pmlozada@pucp', 'm', 'nicolas', 'gvidal@pucp', 'jane', 'm', 'alejandro', 'a20167070@pucp', 'riega', 'vlevanot@pucp', 'sesquives@pucp', 'perez', 'mariana', 'aclavo@pucp', 'a20182474@pucp', 'josue', 'fabio', 'fernanda', 'aquillatupa@pucp']\n",
- "Number of substrings containing '@': 14\n"
- ]
- }
- ],
- "source": [
- "# 6. Get all the strings before the first dot '.' in each string in the emails list.\n",
- "# First, we identify how many of them have '@'.\n",
- "\n",
- "# Then we use the map function to apply a lambda function to each element in the emails list.\n",
- "# The lambda function extracts the substring before the first dot '.' and checks if it contains '@'.\n",
- "substring_before_dot_lambda = lambda email: email.split('.')[0]\n",
- "mapped_result = map(substring_before_dot_lambda, emails)\n",
- "\n",
- "# After that, we convert the mapped result into a list.\n",
- "substring_before_dot_list = list(mapped_result)\n",
- "\n",
- "# Also, we count how many substrings contain '@' and print the results\n",
- "count_with_at = sum('@' in substring for substring in substring_before_dot_list)\n",
- "\n",
- "print(\"Substrings before the first dot:\", substring_before_dot_list)\n",
- "print(\"Number of substrings containing '@':\", count_with_at)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## 1.4 Pandas\n",
- "\n",
- "You can and should always ask ChatGPT, BARD, Bing, etc.\n",
- "In this exercise, you will work with financial data. Follow the steps below:\n",
- "\n",
- "1. Load Data:\n",
- " Load the financial data available at this URL: https://raw.githubusercontent.com/datasets/finance-vix/main/data/vix-daily.csv\n",
- " Use `pd.read_csv()` adn the link to load the data into a DataFrame.\n",
- "\n",
- "2. Explore Data:\n",
- " a) Display the first five rows of the DataFrame.\n",
- " b) Display the summary statistics of the DataFrame.\n",
- "\n",
- "3. Add Columns:\n",
- " a) Add a new column 'Level' that categorizes the 'Close' column values into 'Low' (< 20), 'Medium' (20-30), and 'High' (>30). You need to make a filter to make this categorization. You can see below some suggestions how to do it.\n",
- " b) Add a new column 'Year' extracted from the 'Date' column. You need to work with dates. You can do it directly workiwith the column splitting it or changing it to date format an dfollowing the below suggestion. \n",
- "\n",
- "4. Add Rows:\n",
- " a) Add a new row with a date of your choice and fill the other columns with appropriate values. \n",
- "\n",
- "5. Analysis:\n",
- " a) Calculate the average of the column 'Close' for each 'Year'. You need to group for this task.\n",
- " b) Count the number of 'High', 'Medium', and 'Low' Level days in the data.\n",
- "\n",
- "Suggestions:\n",
- " - Use `pd.cut()` for categorizing 'Close' values.\n",
- " - Use `pd.to_datetime()` and `dt.year` to extract the year from a date.\n",
- " - Use `DataFrame.append()` or `pd.concat()` to add rows.\n",
- " - Use `groupby()` for aggregation tasks."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 56,
- "metadata": {},
- "outputs": [],
- "source": [
- "# 1\n",
- "import pandas as pd\n",
- "\n",
- "# This code loads the data from the provided URL.\n",
- "url = \"https://raw.githubusercontent.com/datasets/finance-vix/main/data/vix-daily.csv\"\n",
- "df = pd.read_csv(url)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 57,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/html": [
- "\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " DATE | \n",
- " OPEN | \n",
- " HIGH | \n",
- " LOW | \n",
- " CLOSE | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 01/02/1990 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 01/03/1990 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 01/04/1990 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 01/05/1990 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 01/08/1990 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- "
\n",
- " \n",
- " | ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- "
\n",
- " \n",
- " | 8572 | \n",
- " 12/29/2023 | \n",
- " 12.55 | \n",
- " 13.19 | \n",
- " 12.36 | \n",
- " 12.45 | \n",
- "
\n",
- " \n",
- " | 8573 | \n",
- " 01/02/2024 | \n",
- " 13.22 | \n",
- " 14.23 | \n",
- " 13.10 | \n",
- " 13.20 | \n",
- "
\n",
- " \n",
- " | 8574 | \n",
- " 01/03/2024 | \n",
- " 13.35 | \n",
- " 14.22 | \n",
- " 13.33 | \n",
- " 14.04 | \n",
- "
\n",
- " \n",
- " | 8575 | \n",
- " 01/04/2024 | \n",
- " 13.93 | \n",
- " 14.20 | \n",
- " 13.64 | \n",
- " 14.13 | \n",
- "
\n",
- " \n",
- " | 8576 | \n",
- " 01/05/2024 | \n",
- " 14.24 | \n",
- " 14.58 | \n",
- " 13.29 | \n",
- " 13.35 | \n",
- "
\n",
- " \n",
- "
\n",
- "
8577 rows × 5 columns
\n",
- "
\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " DATE | \n",
- " OPEN | \n",
- " HIGH | \n",
- " LOW | \n",
- " CLOSE | \n",
- " Level | \n",
- " Year | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 01/02/1990 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 01/03/1990 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 01/04/1990 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 01/05/1990 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 01/08/1990 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- "
\n",
- " \n",
- " | 8572 | \n",
- " 12/29/2023 | \n",
- " 12.55 | \n",
- " 13.19 | \n",
- " 12.36 | \n",
- " 12.45 | \n",
- " Low | \n",
- " 2023 | \n",
- "
\n",
- " \n",
- " | 8573 | \n",
- " 01/02/2024 | \n",
- " 13.22 | \n",
- " 14.23 | \n",
- " 13.10 | \n",
- " 13.20 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8574 | \n",
- " 01/03/2024 | \n",
- " 13.35 | \n",
- " 14.22 | \n",
- " 13.33 | \n",
- " 14.04 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8575 | \n",
- " 01/04/2024 | \n",
- " 13.93 | \n",
- " 14.20 | \n",
- " 13.64 | \n",
- " 14.13 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8576 | \n",
- " 01/05/2024 | \n",
- " 14.24 | \n",
- " 14.58 | \n",
- " 13.29 | \n",
- " 13.35 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- "
\n",
- "
8577 rows × 7 columns
\n",
- "
\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " DATE | \n",
- " OPEN | \n",
- " HIGH | \n",
- " LOW | \n",
- " CLOSE | \n",
- " Level | \n",
- " Year | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 01/02/1990 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " 17.24 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 01/03/1990 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " 18.19 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 01/04/1990 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " 19.22 | \n",
- " Low | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 01/05/1990 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " 20.11 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 01/08/1990 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " 20.26 | \n",
- " Medium | \n",
- " 1990 | \n",
- "
\n",
- " \n",
- " | ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- " ... | \n",
- "
\n",
- " \n",
- " | 8573 | \n",
- " 01/02/2024 | \n",
- " 13.22 | \n",
- " 14.23 | \n",
- " 13.10 | \n",
- " 13.20 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8574 | \n",
- " 01/03/2024 | \n",
- " 13.35 | \n",
- " 14.22 | \n",
- " 13.33 | \n",
- " 14.04 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8575 | \n",
- " 01/04/2024 | \n",
- " 13.93 | \n",
- " 14.20 | \n",
- " 13.64 | \n",
- " 14.13 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8576 | \n",
- " 01/05/2024 | \n",
- " 14.24 | \n",
- " 14.58 | \n",
- " 13.29 | \n",
- " 13.35 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- " | 8577 | \n",
- " 01/06/2024 | \n",
- " 14.27 | \n",
- " 14.61 | \n",
- " 13.32 | \n",
- " 13.38 | \n",
- " Low | \n",
- " 2024 | \n",
- "
\n",
- " \n",
- "
\n",
- "
8578 rows × 7 columns
\n",
- "
\n",
- "\n",
- "
\n",
- " \n",
- " \n",
- " | \n",
- " Year | \n",
- " Average Close | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- " | 0 | \n",
- " 1990 | \n",
- " 23.06 | \n",
- "
\n",
- " \n",
- " | 1 | \n",
- " 1991 | \n",
- " 18.37 | \n",
- "
\n",
- " \n",
- " | 2 | \n",
- " 1992 | \n",
- " 15.45 | \n",
- "
\n",
- " \n",
- " | 3 | \n",
- " 1993 | \n",
- " 12.69 | \n",
- "
\n",
- " \n",
- " | 4 | \n",
- " 1994 | \n",
- " 13.93 | \n",
- "
\n",
- " \n",
- " | 5 | \n",
- " 1995 | \n",
- " 12.39 | \n",
- "
\n",
- " \n",
- " | 6 | \n",
- " 1996 | \n",
- " 16.44 | \n",
- "
\n",
- " \n",
- " | 7 | \n",
- " 1997 | \n",
- " 22.36 | \n",
- "
\n",
- " \n",
- " | 8 | \n",
- " 1998 | \n",
- " 25.60 | \n",
- "
\n",
- " \n",
- " | 9 | \n",
- " 1999 | \n",
- " 24.37 | \n",
- "
\n",
- " \n",
- " | 10 | \n",
- " 2000 | \n",
- " 23.32 | \n",
- "
\n",
- " \n",
- " | 11 | \n",
- " 2001 | \n",
- " 25.75 | \n",
- "
\n",
- " \n",
- " | 12 | \n",
- " 2002 | \n",
- " 27.29 | \n",
- "
\n",
- " \n",
- " | 13 | \n",
- " 2003 | \n",
- " 21.98 | \n",
- "
\n",
- " \n",
- " | 14 | \n",
- " 2004 | \n",
- " 15.48 | \n",
- "
\n",
- " \n",
- " | 15 | \n",
- " 2005 | \n",
- " 12.81 | \n",
- "
\n",
- " \n",
- " | 16 | \n",
- " 2006 | \n",
- " 12.81 | \n",
- "
\n",
- " \n",
- " | 17 | \n",
- " 2007 | \n",
- " 17.54 | \n",
- "
\n",
- " \n",
- " | 18 | \n",
- " 2008 | \n",
- " 32.70 | \n",
- "
\n",
- " \n",
- " | 19 | \n",
- " 2009 | \n",
- " 31.48 | \n",
- "
\n",
- " \n",
- " | 20 | \n",
- " 2010 | \n",
- " 22.55 | \n",
- "
\n",
- " \n",
- " | 21 | \n",
- " 2011 | \n",
- " 24.20 | \n",
- "
\n",
- " \n",
- " | 22 | \n",
- " 2012 | \n",
- " 17.80 | \n",
- "
\n",
- " \n",
- " | 23 | \n",
- " 2013 | \n",
- " 14.23 | \n",
- "
\n",
- " \n",
- " | 24 | \n",
- " 2014 | \n",
- " 14.18 | \n",
- "
\n",
- " \n",
- " | 25 | \n",
- " 2015 | \n",
- " 16.67 | \n",
- "
\n",
- " \n",
- " | 26 | \n",
- " 2016 | \n",
- " 15.83 | \n",
- "
\n",
- " \n",
- " | 27 | \n",
- " 2017 | \n",
- " 11.09 | \n",
- "
\n",
- " \n",
- " | 28 | \n",
- " 2018 | \n",
- " 16.64 | \n",
- "
\n",
- " \n",
- " | 29 | \n",
- " 2019 | \n",
- " 15.39 | \n",
- "
\n",
- " \n",
- " | 30 | \n",
- " 2020 | \n",
- " 29.25 | \n",
- "
\n",
- " \n",
- " | 31 | \n",
- " 2021 | \n",
- " 19.66 | \n",
- "
\n",
- " \n",
- " | 32 | \n",
- " 2022 | \n",
- " 25.64 | \n",
- "
\n",
- " \n",
- " | 33 | \n",
- " 2023 | \n",
- " 16.85 | \n",
- "
\n",
- " \n",
- " | 34 | \n",
- " 2024 | \n",
- " 13.62 | \n",
- "
\n",
- " \n",
- "
\n",
- "