Skip to content

Remove FutureWarnings due to pandas 2.0 #157

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
patrickleonardy merged 4 commits into from
May 12, 2023
Merged

Remove FutureWarnings due to pandas 2.0 #157

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
61ef47c
remove FutureWarnings due to pandas
Apr 4, 2023
9fb464f
CHANGE d.loc[:, "colname"]= TO d["colname"]=
Apr 5, 2023
7344747
Revert "remove FutureWarnings due to pandas"
Apr 5, 2023
10338e4
format test back and fix further FutureWarnings
Apr 5, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions cobra/preprocessing/categorical_data_processor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -309,10 +309,10 @@ def _transform_column(self, data: pd.DataFrame,
"""

column_name_clean = column_name + "_processed"
data.loc[:, column_name_clean] = data[column_name].astype(object)
data[column_name_clean] = data[column_name].astype(object)

# Fill missings first
data.loc[:, column_name_clean] = (CategoricalDataProcessor
data[column_name_clean] = (CategoricalDataProcessor
._replace_missings(
data,
column_name_clean
Expand All @@ -329,14 +329,14 @@ def _transform_column(self, data: pd.DataFrame,
"and will be skipped".format(column_name))
return data

data.loc[:, column_name_clean] = (CategoricalDataProcessor
data[column_name_clean] = (CategoricalDataProcessor
._replace_categories(
data[column_name_clean],
categories,
self.regroup_name))

# change data to categorical
data.loc[:, column_name_clean] = (data[column_name_clean]
data[column_name_clean] = (data[column_name_clean]
.astype("category"))

return data
Expand Down
6 changes: 3 additions & 3 deletions cobra/preprocessing/kbins_discretizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -315,19 +315,19 @@ def _transform_column(self, data: pd.DataFrame,
column_name_bin = column_name + "_bin"

# use pd.cut to compute bins
data.loc[:, column_name_bin] = pd.cut(x=data[column_name],
data[column_name_bin] = pd.cut(x=data[column_name],
bins=interval_idx)

# Rename bins so that the output has a proper format
bin_labels = self._create_bin_labels(bins)

data.loc[:, column_name_bin] = (data[column_name_bin]
data[column_name_bin] = (data[column_name_bin]
.cat.rename_categories(bin_labels))

if data[column_name_bin].isnull().sum() > 0:

# Add an additional bin for missing values
data[column_name_bin].cat.add_categories(["Missing"], inplace=True)
data[column_name_bin]=data[column_name_bin].cat.add_categories(["Missing"])

# Replace NULL with "Missing"
# Otherwise these will be ignored in groupby
Expand Down
2 changes: 1 addition & 1 deletion tests/preprocessing/test_preprocessor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ def test_train_selection_validation_split(
):
X = np.arange(100).reshape(10, 10)
data = pd.DataFrame(X, columns=[f"c{i+1}" for i in range(10)])
data.loc[:, "target"] = np.array([0] * 7 + [1] * 3)
data["target"] = np.array([0] * 7 + [1] * 3)

actual = PreProcessor.train_selection_validation_split(
data, train_prop, selection_prop, validation_prop
Expand Down
6 changes: 2 additions & 4 deletions tests/preprocessing/test_target_encoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -260,8 +260,7 @@ def test_target_encoder_transform_new_category_binary_classification(self):
'neutral'],
'target': [1, 1, 0, 0, 1, 0, 0, 0, 1, 1]})

df_appended = df.append({"variable": "new", "target": 1},
ignore_index=True)
df_appended = pd.concat([df, pd.DataFrame({"variable": "new", "target": 1}, index=[len(df)])], ignore_index=True)

# inputs of TargetEncoder will be of dtype category
df["variable"] = df["variable"].astype("category")
Expand All @@ -285,8 +284,7 @@ def test_target_encoder_transform_new_category_linear_regression(self):
'neutral', 'positive'],
'target': [5, 4, -5, 0, -4, 5, -5, 0, 1, 0, 4]})

df_appended = df.append({"variable": "new", "target": 10},
ignore_index=True)
df_appended = pd.concat([df, pd.DataFrame({"variable": "new", "target": 10}, index=[len(df)])], ignore_index=True)

# inputs of TargetEncoder will be of dtype category
df["variable"] = df["variable"].astype("category")
Expand Down