Skip to content

⚡️ DropColumns uses tide select for Columns selection #38

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
BaptisteDE merged 1 commit into from
Apr 16, 2025
Merged

⚡️ DropColumns uses tide select for Columns selection #38

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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 tests/test_processing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -963,19 +963,19 @@ def test_drop_columns(self):
index=pd.date_range("2009", freq="h", periods=2, tz="UTC"),
)

col_dropper = KeepColumns()
col_dropper = DropColumns()
col_dropper.fit(df)
res = col_dropper.transform(df.copy())
pd.testing.assert_frame_equal(df, res)
check_feature_names_out(col_dropper, res)
assert res.shape == (2, 0)
check_feature_names_out(col_dropper, pd.DataFrame(index=df.index))

col_dropper = DropColumns(columns="a")
col_dropper.fit(df)
res = col_dropper.transform(df.copy())
pd.testing.assert_frame_equal(df[["b", "c"]], res)
check_feature_names_out(col_dropper, res)

col_dropper = DropColumns(columns=["a", "b", "c"])
col_dropper = DropColumns(columns=["a|b", "c"])
col_dropper.fit(df)
res = col_dropper.transform(df.copy())
assert res.shape == (2, 0)
Expand Down
153 changes: 75 additions & 78 deletions tide/processing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2639,8 +2639,8 @@ class DropColumns(BaseProcessing):
----------
columns : str | list[str], optional (default=None)
The column name or a list of column names to be dropped.
If None, no columns are dropped and the DataFrame is returned unchanged.
Example: 'temp__°C' or ['temp__°C', 'humid__%']
If None, ALL columns are dropped, only the index is kept.
Example: 'temp__°C' or ['temp__°C', 'humid__%'] or '°C|%'

Attributes
----------
Expand Down Expand Up @@ -2673,7 +2673,7 @@ class DropColumns(BaseProcessing):
2024-01-01 00:01:00+00:00 50.0 1010.0
2024-01-01 00:02:00+00:00 55.0 1020.0
>>> # Drop multiple columns
>>> dropper_multi = DropColumns(columns=["temp__°C", "humid__%"])
>>> dropper_multi = DropColumns(columns="°C|%")
>>> result_multi = dropper_multi.fit_transform(df)
>>> print(result_multi)
press__Pa
Expand All @@ -2686,8 +2686,8 @@ class DropColumns(BaseProcessing):
- If a specified column doesn't exist in the DataFrame, it will be silently
ignored
- The order of remaining columns is preserved
- If no columns are specified (columns=None), the DataFrame is returned
unchanged
- If no columns are specified (columns=None), a DataFrame with no values is
returned

Returns
-------
Expand All @@ -2702,85 +2702,82 @@ def __init__(self, columns: str | list[str] = None):
BaseProcessing.__init__(self)

def _fit_implementation(self, X: pd.Series | pd.DataFrame, y=None):
self.required_columns = self.columns
if self.columns is not None:
self.feature_names_out_ = list(X.columns.drop(self.columns))
self.required_columns = tide_request(X, self.columns)
self.feature_names_out_ = list(
X.drop(self.required_columns, axis="columns").columns
)

def _transform_implementation(self, X: pd.Series | pd.DataFrame):
return (
X.drop(self.required_columns, axis="columns")
if self.columns is not None
else X
)
return X.drop(self.required_columns, axis="columns")


class KeepColumns(BaseProcessing):
"""
A transformer that keeps specified columns from a pandas DataFrame.

It is particularly useful at the final step of data preprocessing.
When only some columns are passed to a model

Parameters
----------
columns : str | list[str], optional (default=None)
The column name or a list of column names to be dropped.
If None, no columns are dropped and the DataFrame is returned unchanged.
Example: 'temp__°C' or ['temp__°C', 'humid__%'] or '°C|%'

Attributes
----------
feature_names_in_ : list[str]
Names of input columns (set during fit).
feature_names_out_ : list[str]
Names of output columns (input columns minus dropped columns).

Examples
--------
>>> import pandas as pd
>>> # Create DataFrame with DateTimeIndex
>>> dates = pd.date_range(
... start="2024-01-01 00:00:00", end="2024-01-01 00:02:00", freq="1min"
... ).tz_localize("UTC")
>>> df = pd.DataFrame(
... {
... "temp__°C": [20, 21, 22],
... "humid__%": [45, 50, 55],
... "press__Pa": [1000, 1010, 1020],
... },
... index=dates,
... )
>>> # Keep a single column
>>> keeper = KeepColumns(columns="temp__°C")
>>> result = keeper.fit_transform(df)
>>> print(result)
temp__°C
2024-01-01 00:00:00+00:00 20
2024-01-01 00:01:00+00:00 21
2024-01-01 00:02:00+00:00 22
>>> # Keep multiple columns
>>> keeper_multi = KeepColumns(columns="°C|%")
>>> result_multi = keeper_multi.fit_transform(df)
>>> print(result_multi)
temp__°C humid__%
2024-01-01 00:00:00+00:00 20 45
2024-01-01 00:01:00+00:00 21 50
2024-01-01 00:02:00+00:00 22 55

Notes
-----
- If a specified column doesn't exist in the DataFrame, it will be silently
ignored
- The order of selected columns is preserved
- If no columns are specified (columns=None), the DataFrame is returned
unchanged

Returns
-------
pd.DataFrame
The DataFrame with specified columns removed. The output maintains
the same DateTimeIndex as the input, with only the specified columns
removed.
A transformer that keeps specified columns from a pandas DataFrame.

It is particularly useful at the final step of data preprocessing.
When only some columns are passed to a model

Parameters
----------
columns : str | list[str], optional (default=None)
The column name or a list of column names to be kept.
If None, no columns are dropped and the DataFrame is returned unchanged.
Example: 'temp__°C' or ['temp__°C', 'humid__%'] or '°C|%'

Attributes
----------
feature_names_in_ : list[str]
Names of input columns (set during fit).
feature_names_out_ : list[str]
Names of output columns (input columns minus dropped columns).

Examples
--------
>>> import pandas as pd
>>> # Create DataFrame with DateTimeIndex
>>> dates = pd.date_range(
... start="2024-01-01 00:00:00", end="2024-01-01 00:02:00", freq="1min"
... ).tz_localize("UTC")
>>> df = pd.DataFrame(
... {
... "temp__°C": [20, 21, 22],
... "humid__%": [45, 50, 55],
... "press__Pa": [1000, 1010, 1020],
... },
... index=dates,
... )
>>> # Keep a single column
>>> keeper = KeepColumns(columns="temp__°C")
>>> result = keeper.fit_transform(df)
>>> print(result)
temp__°C
2024-01-01 00:00:00+00:00 20
2024-01-01 00:01:00+00:00 21
2024-01-01 00:02:00+00:00 22
>>> # Keep multiple columns
>>> keeper_multi = KeepColumns(columns="°C|%")
>>> result_multi = keeper_multi.fit_transform(df)
>>> print(result_multi)
temp__°C humid__%
2024-01-01 00:00:00+00:00 20 45
2024-01-01 00:01:00+00:00 21 50
2024-01-01 00:02:00+00:00 22 55

Notes
-----
- If a specified column doesn't exist in the DataFrame, it will be silently
ignored
- The order of selected columns is preserved
- If no columns are specified (columns=None), the DataFrame is returned
unchanged

Returns
-------
pd.DataFrame
The DataFrame with specified columns removed. The output maintains
the same DateTimeIndex as the input, with only the specified columns
removed.
"""

def __init__(self, columns: str | list[str] = None):
Expand Down