Regression.py

# -*- coding: utf-8 -*-
"""Linear_reg.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1xC6Nxb_zg_RQNhOtl6cNGR_kG6BxFx-8
"""

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn import linear_model
from sklearn.metrics import  mean_squared_error, r2_score
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVR


"""### **Simple Linear Regression**"""

from google.colab import files
uploaded = files.upload()

dataset = pd.read_csv('Salary_Data.csv')
dataset.head()
X = dataset.iloc[:,:-1].values
y = dataset.iloc[:,-1].values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 1/3, random_state = 0)

# Feature Scaling
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)
# sc_y = StandardScaler()
# y_train = sc_y.fit_transform(y_train)

model = linear_model.LinearRegression()

model.fit(X_train, y_train)

y_predicted = model.predict(X_test)

print("Mean squared error is: ", mean_squared_error(y_test, y_predicted))

print("Weights: ", model.coef_)
print("Intercept: ", model.intercept_)

score=r2_score(y_test,y_predicted)
print("Score: ", score)

# Visualising the Training set results
plt.scatter(X_train, y_train, color = 'red')
plt.plot(X_train, model.predict(X_train), color = 'blue')
plt.title('Salary vs Experience (Test set)')
plt.xlabel('Years of Experience')
plt.ylabel('Salary')
plt.show()

# Visualising the Test set results
plt.scatter(X_test, y_test, color = 'red')
plt.plot(X_train, model.predict(X_train), color = 'blue')
plt.title('Salary vs Experience (Test set)')
plt.xlabel('Years of Experience')
plt.ylabel('Salary')
plt.show()

a = np.savetxt('res.txt',y_predicted,delimiter=',')
files.download('res.txt')

"""### **Multiple Linear Regression**"""

uploaded = files.upload()

dataset = pd.read_csv('50_Startups.csv')
# dataset.head()
X = dataset.iloc[:,:-1]
y = dataset.iloc[:,-1]

#Convert the column into categorical columns
states=pd.get_dummies(X['State'],drop_first=False)

# Drop the state coulmn
X = X.drop('State',axis=1)

# concat the dummy variables
X=pd.concat([X,states],axis=1)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)

model = linear_model.LinearRegression()

model.fit(X_train, y_train)

y_predicted = model.predict(X_test)

print("Mean squared error is: ", mean_squared_error(y_test, y_predicted))

print("Weights: ", model.coef_)
print("Intercept: ", model.intercept_)

score=r2_score(y_test,y_predicted)
print("Score: ", score)



"""# *Other Dataset *"""

uploaded = files.upload()

dataset = pd.read_csv('Social_Network_Ads.csv')
dataset.head()
X = dataset.iloc[:,:-1]
y = dataset.iloc[:,-1]

#Convert the column into categorical columns
gender = pd.Categorical(pd.factorize(X.Gender)[0])

# Drop the state coulmn
X = X.drop('Gender',axis=1)

# concat the dummy variables
X=pd.concat([X,pd.DataFrame({'Gender': gender})],axis=1)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)

model = linear_model.LinearRegression(fit_intercept=True, normalize=True)

model.fit(X_train, y_train)

y_predicted = model.predict(X_test)

print("Mean squared error is: ", mean_squared_error(y_test, y_predicted))

print("Weights: ", model.coef_)
print("Intercept: ", model.intercept_)

score=r2_score(y_test,y_predicted)
print("Score: ", score)

res = pd.DataFrame(y_predicted, columns=['Prediction'])
res.to_csv('res.csv')
files.download('res.csv')



"""## **Reading txt**"""

uploaded = files.upload()

dataset= np.loadtxt('res.txt',delimiter=",")
dataset



"""## **Filling NANs**"""

uploaded = files.upload()

dataset = pd.read_csv('Data.csv')
dataset = dataset.interpolate(method ='linear', limit_direction ='forward')

country = pd.Categorical(pd.factorize(dataset.Country)[0])
purchased = pd.Categorical(pd.factorize(dataset.Purchased)[0])

dataset= dataset.drop(['Country','Purchased'],axis=1)

dataset= pd.concat([dataset,pd.DataFrame(country),pd.DataFrame(purchased)],axis=1)

X = dataset.iloc[:,:-1]
y = dataset.iloc[:,-1]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.5, random_state = 0)

model = linear_model.LinearRegression(fit_intercept=True, normalize=True)

model.fit(X_train, y_train)

y_predicted = model.predict(X_test)

print("Mean squared error is: ", mean_squared_error(y_test, y_predicted))

print("Weights: ", model.coef_)
print("Intercept: ", model.intercept_)

score=r2_score(y_test,y_predicted)
print("Score: ", score)



"""## **SVR**"""

# Create and train the Support Vector Machine (Regressor)
svr_rbf = SVR(kernel='rbf', C=1e3, gamma=0.1)
svr_rbf.fit(x_train, y_train)

# Testing Model: Score returns the coefficient of determination R^2 of the prediction. 
# The best possible score is 1.0
svm_confidence = svr_rbf.score(x_test, y_test)
print("svm confidence: ", svm_confidence)