Merge pull request #415 from PaulWestenthanner/fix/issue_414_412

Fix/issue 414 412
scikit-learn-contrib · Aug 15, 2023 · d73479e · d73479e
2 parents eeff8e3 + 6f412cc
commit d73479e
Show file tree

Hide file tree

Showing 8 changed files with 38 additions and 12 deletions.
diff --git a/category_encoders/backward_difference.py b/category_encoders/backward_difference.py
@@ -71,7 +71,7 @@ class BackwardDifferenceEncoder(BaseContrastEncoder):
  https://stats.idre.ucla.edu/r/library/r-library-contrast-coding-systems-for-categorical-variables/
 
  .. [2] Gregory Carey (2003). Coding Categorical Variables, from
- http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
+ http://ibgwww.colorado.edu/~carey/p5741ndir/Coding_Categorical_Variables.pdf
 
  """
 

diff --git a/category_encoders/base_contrast_encoder.py b/category_encoders/base_contrast_encoder.py
@@ -41,7 +41,7 @@ class BaseContrastEncoder(util.BaseEncoder, util.UnsupervisedTransformerMixin):
  https://stats.idre.ucla.edu/r/library/r-library-contrast-coding-systems-for-categorical-variables/
 
  .. [2] Gregory Carey (2003). Coding Categorical Variables, from
- http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
+ http://ibgwww.colorado.edu/~carey/p5741ndir/Coding_Categorical_Variables.pdf
 
  """
  prefit_ordinal = True

diff --git a/category_encoders/helmert.py b/category_encoders/helmert.py
@@ -72,8 +72,8 @@ class HelmertEncoder(BaseContrastEncoder):
  https://stats.idre.ucla.edu/r/library/r-library-contrast-coding-systems-for-categorical-variables/
 
  .. [2] Gregory Carey (2003). Coding Categorical Variables, from
- http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
-
+ http://ibgwww.colorado.edu/~carey/p5741ndir/Coding_Categorical_Variables.pdf
+ 
  """
  def get_contrast_matrix(self, values_to_encode: np.array) -> ContrastMatrix:
  return Helmert().code_without_intercept(values_to_encode)
diff --git a/category_encoders/one_hot.py b/category_encoders/one_hot.py
@@ -86,8 +86,8 @@ class OneHotEncoder(util.BaseEncoder, util.UnsupervisedTransformerMixin):
  https://stats.idre.ucla.edu/r/library/r-library-contrast-coding-systems-for-categorical-variables/
 
  .. [2] Gregory Carey (2003). Coding Categorical Variables, from
- http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
-
+ http://ibgwww.colorado.edu/~carey/p5741ndir/Coding_Categorical_Variables.pdf
+ 
  """
  prefit_ordinal = True
  encoding_relation = util.EncodingRelation.ONE_TO_N_UNIQUE

diff --git a/category_encoders/ordinal.py b/category_encoders/ordinal.py
@@ -77,8 +77,7 @@ class OrdinalEncoder(util.BaseEncoder, util.UnsupervisedTransformerMixin):
  https://stats.idre.ucla.edu/r/library/r-library-contrast-coding-systems-for-categorical-variables/
 
  .. [2] Gregory Carey (2003). Coding Categorical Variables, from
- http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
-
+ http://ibgwww.colorado.edu/~carey/p5741ndir/Coding_Categorical_Variables.pdf
  """
  prefit_ordinal = False
  encoding_relation = util.EncodingRelation.ONE_TO_ONE
@@ -225,7 +224,7 @@ def ordinal_encoding(X_in, mapping=None, cols=None, handle_unknown='value', hand
  if pd.isna(categories).any():
  categories = [c for c in categories if not pd.isna(c)] + [nan_identity]
  else:
- categories = categories.tolist()
+ categories = list(categories)
  if util.is_category(X[col].dtype):
  # Avoid using pandas category dtype meta-data if possible, see #235, #238.
  if X[col].dtype.ordered:

diff --git a/category_encoders/polynomial.py b/category_encoders/polynomial.py
@@ -71,8 +71,8 @@ class PolynomialEncoder(BaseContrastEncoder):
  https://stats.idre.ucla.edu/r/library/r-library-contrast-coding-systems-for-categorical-variables/
 
  .. [2] Gregory Carey (2003). Coding Categorical Variables, from
- http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
-
+ http://ibgwww.colorado.edu/~carey/p5741ndir/Coding_Categorical_Variables.pdf
+ 
  """
  def get_contrast_matrix(self, values_to_encode: np.array) -> ContrastMatrix:
  return Poly().code_without_intercept(values_to_encode)
diff --git a/category_encoders/sum_coding.py b/category_encoders/sum_coding.py
@@ -71,7 +71,7 @@ class SumEncoder(BaseContrastEncoder):
  https://stats.idre.ucla.edu/r/library/r-library-contrast-coding-systems-for-categorical-variables/
 
  .. [2] Gregory Carey (2003). Coding Categorical Variables, from
- http://psych.colorado.edu/~carey/Courses/PSYC5741/handouts/Coding%20Categorical%20Variables%202006-03-03.pdf
+ http://ibgwww.colorado.edu/~carey/p5741ndir/Coding_Categorical_Variables.pdf
 
  """
 

diff --git a/tests/test_ordinal.py b/tests/test_ordinal.py
@@ -177,6 +177,33 @@ def test_HaveNaNInTrain_ExpectCodedAsOne(self):
 
  self.assertEqual(expected, result)
 
+ def test_Timestamp(self):
+ df = pd.DataFrame(
+ {
+ "timestamps": {
+ 0: pd.Timestamp("1997-09-03 00:00:00"),
+ 1: pd.Timestamp("1997-09-03 00:00:00"),
+ 2: pd.Timestamp("2000-09-03 00:00:00"),
+ 3: pd.Timestamp("1997-09-03 00:00:00"),
+ 4: pd.Timestamp("1999-09-04 00:00:00"),
+ 5: pd.Timestamp("2001-09-03 00:00:00"),
+ },
+ }
+ )
+ enc = encoders.OrdinalEncoder(cols=["timestamps"])
+ encoded_df = enc.fit_transform(df)
+ expected_index = [pd.Timestamp("1997-09-03 00:00:00"),
+ pd.Timestamp("2000-09-03 00:00:00"),
+ pd.Timestamp("1999-09-04 00:00:00"),
+ pd.Timestamp("2001-09-03 00:00:00"),
+ pd.NaT
+ ]
+ expected_mapping = pd.Series([1, 2, 3, 4, -2], index=expected_index)
+ expected_values = [1, 1, 2, 1, 3, 4]
+
+ pd.testing.assert_series_equal(expected_mapping, enc.mapping[0]["mapping"])
+ self.assertListEqual(expected_values, encoded_df["timestamps"].tolist())
+
  def test_NoGaps(self):
  train = pd.DataFrame({"city": ["New York", np.nan, "Rio", None, "Rosenheim"]})
  expected_mapping_value = pd.Series([1, 2, 3, 4], index=["New York", "Rio", "Rosenheim", np.nan])