From b8949420e2c018fb686f971559ef98ed68209db4 Mon Sep 17 00:00:00 2001
From: Antonio Carlos <falcaopetri@gmail.com>
Date: Sun, 17 Oct 2021 14:37:23 -0300
Subject: [PATCH 01/12] Use new transformer.get_feature_names_out function
- Prefer `estimator.get_feature_names_out()` over `estimator.get_features_names()`
- Configure nox to run tests with both scikit-learn 0.23 and 1.0
---
noxfile.py | 4 +++-
sklearn_pandas/dataframe_mapper.py | 12 +++++++-----
tests/test_dataframe_mapper.py | 18 ++++++++++++++++++
3 files changed, 28 insertions(+), 6 deletions(-)
diff --git a/noxfile.py b/noxfile.py
index ee6f1e7..6ab16a7 100644
--- a/noxfile.py
+++ b/noxfile.py
@@ -10,13 +10,15 @@ def lint(session):
@nox.session
@nox.parametrize('numpy', ['1.18.1', '1.19.4', '1.20.1'])
+@nox.parametrize('sklearn', ['0.23.0', '0.24.2', '1.0'])
@nox.parametrize('scipy', ['1.5.4', '1.6.0'])
@nox.parametrize('pandas', ['1.1.4', '1.2.2'])
-def tests(session, numpy, scipy, pandas):
+def tests(session, numpy, sklearn, scipy, pandas):
session.install('pytest>=5.3.5',
'setuptools>=45.2',
'wheel>=0.34.2',
f'numpy=={numpy}',
+ f'scikit-learn=={sklearn}',
f'scipy=={scipy}',
f'pandas=={pandas}'
)
diff --git a/sklearn_pandas/dataframe_mapper.py b/sklearn_pandas/dataframe_mapper.py
index ca4568e..35a4320 100644
--- a/sklearn_pandas/dataframe_mapper.py
+++ b/sklearn_pandas/dataframe_mapper.py
@@ -47,6 +47,8 @@ def _get_feature_names(estimator):
"""
if hasattr(estimator, 'classes_'):
return estimator.classes_
+ elif hasattr(estimator, 'get_feature_names_out'):
+ return estimator.get_feature_names_out()
elif hasattr(estimator, 'get_feature_names'):
return estimator.get_feature_names()
return None
@@ -290,11 +292,11 @@ def get_names(self, columns, transformer, x, alias=None, prefix='',
else:
names = _get_feature_names(transformer)
- if names is not None and len(names) == num_cols:
- output = [f"{name}_{o}" for o in names]
- # otherwise, return name concatenated with '_1', '_2', etc.
- else:
- output = [name + '_' + str(o) for o in range(num_cols)]
+ if names is None or len(names) != num_cols:
+ # return name concatenated with '_0', '_1', etc.
+ names = range(num_cols)
+
+ output = [f"{name}_{o}" for o in names]
else:
output = [name]
diff --git a/tests/test_dataframe_mapper.py b/tests/test_dataframe_mapper.py
index 7e75f1b..29ff619 100644
--- a/tests/test_dataframe_mapper.py
+++ b/tests/test_dataframe_mapper.py
@@ -344,6 +344,24 @@ def test_onehot_df():
assert cols[3] == 'target_x0_3'
+def test_onehot_2cols_df():
+ """
+ Check level ids from one-hot when mapping 2 columns
+ """
+ df = pd.DataFrame({
+ 'col': [0, 0, 1, 1, 2, 3, 0],
+ 'target': [0, 0, 1, 1, 2, 3, 0]
+ })
+ mapper = DataFrameMapper([
+ (['col', 'target'], OneHotEncoder())
+ ], df_out=True)
+ transformed = mapper.fit_transform(df)
+ cols = transformed.columns
+ assert len(cols) == 8
+ assert cols[0] == 'col_target_x0_0'
+ assert cols[4] == 'col_target_x1_0'
+
+
def test_customtransform_df():
"""
Check level ids from a transformer in which
From bc5a5f403d5b067c75dc1f65ccf4ba0024edfcae Mon Sep 17 00:00:00 2001
From: Ritesh Agrawal <ragrawal@gmail.com>
Date: Sun, 7 Aug 2022 19:42:02 -0700
Subject: [PATCH 02/12] Included input_features as one of the parameter
* changed the order to use get_features_names_out as the first option . Otherwise fallback on classes_
* Passing input_features
---
.gitignore | 1 +
.tool-versions | 2 ++
README.rst | 8 ++++-
pyproject.toml | 20 +++++++++++
setup.py | 7 ++--
sklearn_pandas/__init__.py | 4 +--
sklearn_pandas/dataframe_mapper.py | 22 ++++++------
sklearn_pandas/transformers.py | 55 ------------------------------
tests/test_transformers.py | 47 -------------------------
9 files changed, 48 insertions(+), 118 deletions(-)
create mode 100644 .tool-versions
create mode 100644 pyproject.toml
delete mode 100644 sklearn_pandas/transformers.py
delete mode 100644 tests/test_transformers.py
diff --git a/.gitignore b/.gitignore
index 250c89a..1e83d4e 100644
--- a/.gitignore
+++ b/.gitignore
@@ -6,3 +6,4 @@ dist/
.cache/
.idea/
.pytest_cache/
+.DS_Store
diff --git a/.tool-versions b/.tool-versions
new file mode 100644
index 0000000..6581a35
--- /dev/null
+++ b/.tool-versions
@@ -0,0 +1,2 @@
+python 3.9.10
+poetry 1.1.12
diff --git a/README.rst b/README.rst
index 681ae7c..1f5003b 100644
--- a/README.rst
+++ b/README.rst
@@ -194,7 +194,7 @@ In some situations the columns are not known before hand and we would like to dy
>>> t.fit(df).transform(df).shape
(3, 6)
>>> t.transformed_names_
- ['x_0', 'x_1', 'x_2', 'x_3', 'petal_0', 'petal_1']
+ ['x_sepal length (cm)', 'x_sepal width (cm)', 'x_petal length (cm)', 'x_petal width (cm)', 'petal_0', 'petal_1']
@@ -513,6 +513,12 @@ Below example shows how to change logging level.
Changelog
---------
+3.0.0 (2022-08-07)
+******************
+* Leveraging `get_feature_names_out` to get vectorized feature names. Note that this is a breaking change as some of the generated
+features names will be different from those generated in the previous major version.
+* Removed support for `NumericalTransformer`
+
2.2.0 (2021-05-07)
******************
diff --git a/pyproject.toml b/pyproject.toml
new file mode 100644
index 0000000..045e210
--- /dev/null
+++ b/pyproject.toml
@@ -0,0 +1,20 @@
+[tool.poetry]
+name = "sklearn-pandas"
+version = "2.2.0"
+description = "Coordinates transformation between pandas and sklearn"
+authors = ["Your Name <you@example.com>"]
+
+[tool.poetry.dependencies]
+python = "^3.7"
+scikit-learn = "^1.0.0"
+scipy = "^1.5.1"
+pandas = "^1.1.4"
+numpy = "^1.18.1"
+
+[tool.poetry.dev-dependencies]
+pytest = "^7.1.2"
+nox = "^2022.1.7"
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"
diff --git a/setup.py b/setup.py
index fb5af98..be9198e 100644
--- a/setup.py
+++ b/setup.py
@@ -1,9 +1,10 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
+import re
+
from setuptools import setup
from setuptools.command.test import test as TestCommand
-import re
for line in open('sklearn_pandas/__init__.py'):
match = re.match("__version__ *= *'(.*)'", line)
@@ -38,10 +39,10 @@ def run(self):
packages=['sklearn_pandas'],
keywords=['scikit', 'sklearn', 'pandas'],
install_requires=[
- 'scikit-learn>=0.23.0',
+ 'scikit-learn>=1.0.0',
'scipy>=1.5.1',
'pandas>=1.1.4',
- 'numpy>=1.18.1'
+ 'numpy>=1.19.4'
],
tests_require=['pytest', 'mock'],
cmdclass={'test': PyTest},
diff --git a/sklearn_pandas/__init__.py b/sklearn_pandas/__init__.py
index 535ecf6..f0a6d64 100644
--- a/sklearn_pandas/__init__.py
+++ b/sklearn_pandas/__init__.py
@@ -1,8 +1,8 @@
-__version__ = '2.2.0'
+__version__ = '3.0.0'
import logging
+
logger = logging.getLogger(__name__)
from .dataframe_mapper import DataFrameMapper # NOQA
from .features_generator import gen_features # NOQA
-from .transformers import NumericalTransformer # NOQA
diff --git a/sklearn_pandas/dataframe_mapper.py b/sklearn_pandas/dataframe_mapper.py
index 35a4320..1f9da6f 100644
--- a/sklearn_pandas/dataframe_mapper.py
+++ b/sklearn_pandas/dataframe_mapper.py
@@ -1,12 +1,14 @@
import contextlib
from datetime import datetime
-import pandas as pd
+
import numpy as np
+import pandas as pd
from scipy import sparse
from sklearn.base import BaseEstimator, TransformerMixin
-from .cross_validation import DataWrapper
-from .pipeline import make_transformer_pipeline, _call_fit, TransformerPipeline
+
from . import logger
+from .cross_validation import DataWrapper
+from .pipeline import TransformerPipeline, _call_fit, make_transformer_pipeline
string_types = text_type = str
@@ -41,16 +43,16 @@ def _elapsed_secs(t1):
return (datetime.now()-t1).total_seconds()
-def _get_feature_names(estimator):
+def _get_feature_names(estimator, input_features=None):
"""
Attempt to extract feature names based on a given estimator
"""
- if hasattr(estimator, 'classes_'):
- return estimator.classes_
- elif hasattr(estimator, 'get_feature_names_out'):
- return estimator.get_feature_names_out()
+ if hasattr(estimator, 'get_feature_names_out'):
+ return estimator.get_feature_names_out(input_features=input_features)
elif hasattr(estimator, 'get_feature_names'):
return estimator.get_feature_names()
+ elif hasattr(estimator, 'classes_'):
+ return estimator.classes_
return None
@@ -286,11 +288,11 @@ def get_names(self, columns, transformer, x, alias=None, prefix='',
if isinstance(transformer, TransformerPipeline):
inverse_steps = transformer.steps[::-1]
estimators = (estimator for name, estimator in inverse_steps)
- names_steps = (_get_feature_names(e) for e in estimators)
+ names_steps = (_get_feature_names(e, input_features = columns) for e in estimators) # noqa
names = next((n for n in names_steps if n is not None), None)
# Otherwise use the only estimator present
else:
- names = _get_feature_names(transformer)
+ names = _get_feature_names(transformer, input_features=columns)
if names is None or len(names) != num_cols:
# return name concatenated with '_0', '_1', etc.
diff --git a/sklearn_pandas/transformers.py b/sklearn_pandas/transformers.py
deleted file mode 100644
index ae693c2..0000000
--- a/sklearn_pandas/transformers.py
+++ /dev/null
@@ -1,55 +0,0 @@
-import numpy as np
-import pandas as pd
-from sklearn.base import TransformerMixin
-import warnings
-
-
-def _get_mask(X, value):
- """
- Compute the boolean mask X == missing_values.
- """
- if value == "NaN" or \
- value is None or \
- (isinstance(value, float) and np.isnan(value)):
- return pd.isnull(X)
- else:
- return X == value
-
-
-class NumericalTransformer(TransformerMixin):
- """
- Provides commonly used numerical transformers.
- """
- SUPPORTED_FUNCTIONS = ['log', 'log1p']
-
- def __init__(self, func):
- """
- Params
-
- func function to apply to input columns. The function will be
- applied to each value. Supported functions are defined
- in SUPPORTED_FUNCTIONS variable. Throws assertion error if the
- not supported.
- """
-
- warnings.warn("""
- NumericalTransformer will be deprecated in 3.0 version.
- Please use Sklearn.base.TransformerMixin to write
- customer transformers
- """, DeprecationWarning)
-
- assert func in self.SUPPORTED_FUNCTIONS, \
- f"Only following func are supported: {self.SUPPORTED_FUNCTIONS}"
- super(NumericalTransformer, self).__init__()
- self.__func = func
-
- def fit(self, X, y=None):
- return self
-
- def transform(self, X, y=None):
- if self.__func == 'log1p':
- return np.vectorize(np.log1p)(X)
- elif self.__func == 'log':
- return np.vectorize(np.log)(X)
-
- raise ValueError(f"Invalid function name: {self.__func}")
diff --git a/tests/test_transformers.py b/tests/test_transformers.py
deleted file mode 100644
index 0cd8d0b..0000000
--- a/tests/test_transformers.py
+++ /dev/null
@@ -1,47 +0,0 @@
-import tempfile
-import pytest
-import numpy as np
-from pandas import DataFrame
-import joblib
-
-from sklearn_pandas import DataFrameMapper
-from sklearn_pandas import NumericalTransformer
-
-
-@pytest.fixture
-def simple_dataset():
- return DataFrame({
- 'feat1': [1, 2, 1, 3, 1],
- 'feat2': [1, 2, 2, 2, 3],
- 'feat3': [1, 2, 3, 4, 5],
- })
-
-
-def test_common_numerical_transformer(simple_dataset):
- """
- Test log transformation
- """
- transfomer = DataFrameMapper([
- ('feat1', NumericalTransformer('log'))
- ], df_out=True)
- df = simple_dataset
- outDF = transfomer.fit_transform(df)
- assert list(outDF.columns) == ['feat1']
- assert np.array_equal(df['feat1'].apply(np.log).values, outDF.feat1.values)
-
-
-def test_numerical_transformer_serialization(simple_dataset):
- """
- Test if you can serialize transformer
- """
- transfomer = DataFrameMapper([
- ('feat1', NumericalTransformer('log'))
- ])
-
- df = simple_dataset
- transfomer.fit(df)
- f = tempfile.NamedTemporaryFile(delete=True)
- joblib.dump(transfomer, f.name)
- transfomer2 = joblib.load(f.name)
- np.array_equal(transfomer.transform(df), transfomer2.transform(df))
- f.close()
From 10eebaea29a5ea158d84d9d7858062fbf0a142cd Mon Sep 17 00:00:00 2001
From: Ritesh Agrawal <ragrawal@gmail.com>
Date: Sun, 7 Aug 2022 19:45:31 -0700
Subject: [PATCH 03/12] add author name
---
README.rst | 1 +
1 file changed, 1 insertion(+)
diff --git a/README.rst b/README.rst
index 1f5003b..fb92b66 100644
--- a/README.rst
+++ b/README.rst
@@ -675,6 +675,7 @@ The code for ``DataFrameMapper`` is based on code originally written by `Ben Ham
Other contributors:
* Ariel Rossanigo (@arielrossanigo)
+* Antonio Carlos Falcão Petri (@falcaopetri)
* Arnau Gil Amat (@arnau126)
* Assaf Ben-David (@AssafBenDavid)
* Brendan Herger (@bjherger)
From 2a184fb5794fe3174665abe2d0131e101f0b153b Mon Sep 17 00:00:00 2001
From: Ritesh Agrawal <ragrawal@gmail.com>
Date: Sun, 7 Aug 2022 20:25:58 -0700
Subject: [PATCH 04/12] fixing column names
fixing column names
---
README.rst | 21 ---------------------
pyproject.toml | 2 +-
sklearn_pandas/dataframe_mapper.py | 8 ++++----
tests/test_dataframe_mapper.py | 4 ++--
4 files changed, 7 insertions(+), 28 deletions(-)
diff --git a/README.rst b/README.rst
index fb92b66..ec544d7 100644
--- a/README.rst
+++ b/README.rst
@@ -478,27 +478,6 @@ a sparse array whenever any of the extracted features is sparse. Example:
The stacking of the sparse features is done without ever densifying them.
-Using ``NumericalTransformer``
-***********************************
-
-While you can use ``FunctionTransformation`` to generate arbitrary transformers, it can present serialization issues
-when pickling. Use ``NumericalTransformer`` instead, which takes the function name as a string parameter and hence
-can be easily serialized.
-
- >>> from sklearn_pandas import NumericalTransformer
- >>> mapper5 = DataFrameMapper([
- ... ('children', NumericalTransformer('log')),
- ... ])
- >>> mapper5.fit_transform(data)
- array([[1.38629436],
- [1.79175947],
- [1.09861229],
- [1.09861229],
- [0.69314718],
- [1.09861229],
- [1.60943791],
- [1.38629436]])
-
Changing Logging level
***********************************
diff --git a/pyproject.toml b/pyproject.toml
index 045e210..f93b075 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -9,7 +9,7 @@ python = "^3.7"
scikit-learn = "^1.0.0"
scipy = "^1.5.1"
pandas = "^1.1.4"
-numpy = "^1.18.1"
+numpy = "^1.19.4"
[tool.poetry.dev-dependencies]
pytest = "^7.1.2"
diff --git a/sklearn_pandas/dataframe_mapper.py b/sklearn_pandas/dataframe_mapper.py
index 1f9da6f..f651f9d 100644
--- a/sklearn_pandas/dataframe_mapper.py
+++ b/sklearn_pandas/dataframe_mapper.py
@@ -43,7 +43,7 @@ def _elapsed_secs(t1):
return (datetime.now()-t1).total_seconds()
-def _get_feature_names(estimator, input_features=None):
+def _get_feature_names(estimator, input_features=None, alias=None):
"""
Attempt to extract feature names based on a given estimator
"""
@@ -287,17 +287,17 @@ def get_names(self, columns, transformer, x, alias=None, prefix='',
# last one
if isinstance(transformer, TransformerPipeline):
inverse_steps = transformer.steps[::-1]
- estimators = (estimator for name, estimator in inverse_steps)
+ estimators = (estimator for _, estimator in inverse_steps)
names_steps = (_get_feature_names(e, input_features = columns) for e in estimators) # noqa
names = next((n for n in names_steps if n is not None), None)
# Otherwise use the only estimator present
else:
- names = _get_feature_names(transformer, input_features=columns)
+ names = _get_feature_names(transformer, input_features=columns, alias = alias)
if names is None or len(names) != num_cols:
# return name concatenated with '_0', '_1', etc.
names = range(num_cols)
-
+
output = [f"{name}_{o}" for o in names]
else:
output = [name]
diff --git a/tests/test_dataframe_mapper.py b/tests/test_dataframe_mapper.py
index 29ff619..e09bcbe 100644
--- a/tests/test_dataframe_mapper.py
+++ b/tests/test_dataframe_mapper.py
@@ -340,8 +340,8 @@ def test_onehot_df():
transformed = mapper.fit_transform(df)
cols = transformed.columns
assert len(cols) == 4
- assert cols[0] == 'target_x0_0'
- assert cols[3] == 'target_x0_3'
+ assert cols[0] == 'target_target_0'
+ assert cols[3] == 'target_target_3'
def test_onehot_2cols_df():
From 1a43a5ae37d02b748bde02def2dfad04aed49779 Mon Sep 17 00:00:00 2001
From: Ritesh Agrawal <ragrawal@gmail.com>
Date: Sun, 7 Aug 2022 20:36:38 -0700
Subject: [PATCH 05/12] fixed column output names
---
tests/test_dataframe_mapper.py | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tests/test_dataframe_mapper.py b/tests/test_dataframe_mapper.py
index e09bcbe..5c9f35c 100644
--- a/tests/test_dataframe_mapper.py
+++ b/tests/test_dataframe_mapper.py
@@ -358,8 +358,8 @@ def test_onehot_2cols_df():
transformed = mapper.fit_transform(df)
cols = transformed.columns
assert len(cols) == 8
- assert cols[0] == 'col_target_x0_0'
- assert cols[4] == 'col_target_x1_0'
+ assert cols[0] == 'col_target_col_0'
+ assert cols[4] == 'col_target_target_0'
def test_customtransform_df():
From a76b0b6641c3c70aa2f57301e6285a111d0804c4 Mon Sep 17 00:00:00 2001
From: Ritesh Agrawal <ragrawal@gmail.com>
Date: Sun, 7 Aug 2022 20:42:54 -0700
Subject: [PATCH 06/12] removed poetry
---
pyproject.toml | 20 --------------------
1 file changed, 20 deletions(-)
delete mode 100644 pyproject.toml
diff --git a/pyproject.toml b/pyproject.toml
deleted file mode 100644
index f93b075..0000000
--- a/pyproject.toml
+++ /dev/null
@@ -1,20 +0,0 @@
-[tool.poetry]
-name = "sklearn-pandas"
-version = "2.2.0"
-description = "Coordinates transformation between pandas and sklearn"
-authors = ["Your Name <you@example.com>"]
-
-[tool.poetry.dependencies]
-python = "^3.7"
-scikit-learn = "^1.0.0"
-scipy = "^1.5.1"
-pandas = "^1.1.4"
-numpy = "^1.19.4"
-
-[tool.poetry.dev-dependencies]
-pytest = "^7.1.2"
-nox = "^2022.1.7"
-
-[build-system]
-requires = ["poetry-core>=1.0.0"]
-build-backend = "poetry.core.masonry.api"
From c6457e0ce81120e1d2ecc50b0e8ac6cd16f18c2b Mon Sep 17 00:00:00 2001
From: Ritesh Agrawal <ragrawal@gmail.com>
Date: Sun, 7 Aug 2022 20:48:19 -0700
Subject: [PATCH 07/12] removed tool versions
---
.tool-versions | 2 --
1 file changed, 2 deletions(-)
delete mode 100644 .tool-versions
diff --git a/.tool-versions b/.tool-versions
deleted file mode 100644
index 6581a35..0000000
--- a/.tool-versions
+++ /dev/null
@@ -1,2 +0,0 @@
-python 3.9.10
-poetry 1.1.12
From 71e6c627867fc6536c8b0eb34e3a14a7d2cae4f5 Mon Sep 17 00:00:00 2001
From: Ritesh Agrawal <ragrawal@gmail.com>
Date: Sun, 7 Aug 2022 20:52:43 -0700
Subject: [PATCH 08/12] fixed lint
---
sklearn_pandas/dataframe_mapper.py | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/sklearn_pandas/dataframe_mapper.py b/sklearn_pandas/dataframe_mapper.py
index f651f9d..6b9f44d 100644
--- a/sklearn_pandas/dataframe_mapper.py
+++ b/sklearn_pandas/dataframe_mapper.py
@@ -292,12 +292,12 @@ def get_names(self, columns, transformer, x, alias=None, prefix='',
names = next((n for n in names_steps if n is not None), None)
# Otherwise use the only estimator present
else:
- names = _get_feature_names(transformer, input_features=columns, alias = alias)
+ names = _get_feature_names(transformer, input_features=columns)
if names is None or len(names) != num_cols:
# return name concatenated with '_0', '_1', etc.
names = range(num_cols)
-
+
output = [f"{name}_{o}" for o in names]
else:
output = [name]
From 8f0c2615790cfa8a6dd38ce7baaf52449059b076 Mon Sep 17 00:00:00 2001
From: Ritesh Agrawal <ragrawal@gmail.com>
Date: Sun, 7 Aug 2022 21:01:35 -0700
Subject: [PATCH 09/12] fixed lint issues
---
sklearn_pandas/dataframe_mapper.py | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/sklearn_pandas/dataframe_mapper.py b/sklearn_pandas/dataframe_mapper.py
index 6b9f44d..8c768cc 100644
--- a/sklearn_pandas/dataframe_mapper.py
+++ b/sklearn_pandas/dataframe_mapper.py
@@ -43,7 +43,7 @@ def _elapsed_secs(t1):
return (datetime.now()-t1).total_seconds()
-def _get_feature_names(estimator, input_features=None, alias=None):
+def _get_feature_names(estimator, input_features=None):
"""
Attempt to extract feature names based on a given estimator
"""
@@ -292,7 +292,7 @@ def get_names(self, columns, transformer, x, alias=None, prefix='',
names = next((n for n in names_steps if n is not None), None)
# Otherwise use the only estimator present
else:
- names = _get_feature_names(transformer, input_features=columns)
+ names = _get_feature_names(transformer, input_features = columns)
if names is None or len(names) != num_cols:
# return name concatenated with '_0', '_1', etc.
From 5343faaad0b9089d31f429e5224c006416685226 Mon Sep 17 00:00:00 2001
From: Ritesh Agrawal <ragrawal@gmail.com>
Date: Sun, 7 Aug 2022 21:08:19 -0700
Subject: [PATCH 10/12] fixed lint issues
---
sklearn_pandas/dataframe_mapper.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/sklearn_pandas/dataframe_mapper.py b/sklearn_pandas/dataframe_mapper.py
index 8c768cc..5ca7b61 100644
--- a/sklearn_pandas/dataframe_mapper.py
+++ b/sklearn_pandas/dataframe_mapper.py
@@ -292,7 +292,7 @@ def get_names(self, columns, transformer, x, alias=None, prefix='',
names = next((n for n in names_steps if n is not None), None)
# Otherwise use the only estimator present
else:
- names = _get_feature_names(transformer, input_features = columns)
+ names = _get_feature_names(transformer, input_features=columns)
if names is None or len(names) != num_cols:
# return name concatenated with '_0', '_1', etc.
From f38baa3c88bc0217ddb6df32b0e2d46ee1c53289 Mon Sep 17 00:00:00 2001
From: Ritesh Agrawal <ragrawal@gmail.com>
Date: Sun, 7 Aug 2022 21:29:48 -0700
Subject: [PATCH 11/12] reduced number of versions
---
noxfile.py | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/noxfile.py b/noxfile.py
index 6ab16a7..bb1f701 100644
--- a/noxfile.py
+++ b/noxfile.py
@@ -9,10 +9,10 @@ def lint(session):
session.run('flake8', 'sklearn_pandas/', 'tests')
@nox.session
-@nox.parametrize('numpy', ['1.18.1', '1.19.4', '1.20.1'])
-@nox.parametrize('sklearn', ['0.23.0', '0.24.2', '1.0'])
-@nox.parametrize('scipy', ['1.5.4', '1.6.0'])
-@nox.parametrize('pandas', ['1.1.4', '1.2.2'])
+@nox.parametrize('numpy', ['1.18.1', '1.20.1'])
+@nox.parametrize('sklearn', ['1.0', '1.1.2'])
+@nox.parametrize('scipy', ['1.6.0'])
+@nox.parametrize('pandas', ['1.2.2'])
def tests(session, numpy, sklearn, scipy, pandas):
session.install('pytest>=5.3.5',
'setuptools>=45.2',
From 65ae37657d1efa5df08981374cfaba6b056822f4 Mon Sep 17 00:00:00 2001
From: Ritesh Agrawal <ragrawal@gmail.com>
Date: Sun, 7 Aug 2022 21:41:35 -0700
Subject: [PATCH 12/12] set minimum version for scikit learn to 1.1.0
---
noxfile.py | 2 +-
setup.py | 2 +-
tests/test_dataframe_mapper.py | 4 ++--
3 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/noxfile.py b/noxfile.py
index bb1f701..1c1210a 100644
--- a/noxfile.py
+++ b/noxfile.py
@@ -10,7 +10,7 @@ def lint(session):
@nox.session
@nox.parametrize('numpy', ['1.18.1', '1.20.1'])
-@nox.parametrize('sklearn', ['1.0', '1.1.2'])
+@nox.parametrize('sklearn', ['1.1.0', '1.1.2'])
@nox.parametrize('scipy', ['1.6.0'])
@nox.parametrize('pandas', ['1.2.2'])
def tests(session, numpy, sklearn, scipy, pandas):
diff --git a/setup.py b/setup.py
index be9198e..9cbb69c 100644
--- a/setup.py
+++ b/setup.py
@@ -39,7 +39,7 @@ def run(self):
packages=['sklearn_pandas'],
keywords=['scikit', 'sklearn', 'pandas'],
install_requires=[
- 'scikit-learn>=1.0.0',
+ 'scikit-learn>=1.1.0',
'scipy>=1.5.1',
'pandas>=1.1.4',
'numpy>=1.19.4'
diff --git a/tests/test_dataframe_mapper.py b/tests/test_dataframe_mapper.py
index 04391e7..92c7515 100644
--- a/tests/test_dataframe_mapper.py
+++ b/tests/test_dataframe_mapper.py
@@ -468,8 +468,8 @@ def test_pca(complex_dataframe):
transformed = mapper.fit_transform(df)
cols = transformed.columns
assert len(cols) == 2
- assert cols[0] == 'feat1_feat2_0'
- assert cols[1] == 'feat1_feat2_1'
+ assert cols[0] == 'feat1_feat2_pca0'
+ assert cols[1] == 'feat1_feat2_pca1'
def test_fit_transform(simple_dataframe):