Upgrade versions

- drop support for python 3.5 and python 3.6
- drop support for pandas <1.0.5
- introduce f strings

Author: PaulWestenthanner

.github/workflows/test-suite.yml

@@ -15,7 +15,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ['3.5', '3.6', '3.7', '3.8', '3.9', '3.10']
+        python-version: ['3.7', '3.8', '3.9', '3.10']
 
     steps:
     - uses: actions/checkout@v2

category_encoders/backward_difference.py

@@ -167,8 +167,7 @@ def fit(self, X, y=None, **kwargs):
                 [self.feature_names.remove(x) for x in self.drop_cols]
             except KeyError as e:
                 if self.verbose > 0:
-                    print("Could not remove column from feature names."
-                          "Not found in generated cols.\n{}".format(e))
+                    print(f"Could not remove column from feature names. Not found in generated cols.\n{e}")
 
         return self
 
@@ -200,7 +199,7 @@ def transform(self, X, override_return_df=False):
 
         # then make sure that it is the right size
         if X.shape[1] != self._dim:
-            raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim, ))
+            raise ValueError(f'Unexpected input dimension {X.shape[1]}, expected {self._dim}')
 
         if not list(self.cols):
             return X
@@ -236,7 +235,7 @@ def fit_backward_difference_coding(col, values, handle_missing, handle_unknown):
 
         backwards_difference_matrix = Diff().code_without_intercept(values_to_encode)
         df = pd.DataFrame(data=backwards_difference_matrix.matrix, index=values_to_encode,
-                          columns=[str(col) + '_%d' % (i, ) for i in range(len(backwards_difference_matrix.column_suffixes))])
+                          columns=[f"{col}_{i}" for i in range(len(backwards_difference_matrix.column_suffixes))])
 
         if handle_unknown == 'return_nan':
             df.loc[-1] = np.nan

category_encoders/basen.py

@@ -174,8 +174,7 @@ def fit(self, X, y=None, **kwargs):
                 [self.feature_names.remove(x) for x in self.drop_cols]
             except KeyError as e:
                 if self.verbose > 0:
-                    print("Could not remove column from feature names."
-                          "Not found in generated cols.\n{}".format(e))
+                    print(f"Could not remove column from feature names. Not found in generated cols.\n{e}")
 
         return self
 
@@ -194,7 +193,7 @@ def fit_base_n_encoding(self, X):
 
             digits = self.calc_required_digits(values)
             X_unique = pd.DataFrame(index=values,
-                                    columns=[str(col) + '_%d' % x for x in range(digits)],
+                                    columns=[f"{col}_{x}" for x in range(digits)],
                                     data=np.array([self.col_transform(x, digits) for x in range(1, len(values) + 1)]))
 
             if self.handle_unknown == 'return_nan':
@@ -239,7 +238,7 @@ def transform(self, X, override_return_df=False):
 
         # then make sure that it is the right size
         if X.shape[1] != self._dim:
-            raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim,))
+            raise ValueError(f'Unexpected input dimension {X.shape[1]}, expected {self._dim}')
 
         if not list(self.cols):
             return X
@@ -290,10 +289,10 @@ def inverse_transform(self, X_in):
         # make sure that it is the right size
         if X.shape[1] != self._dim:
             if self.drop_invariant:
-                raise ValueError("Unexpected input dimension %d, the attribute drop_invariant should "
-                                 "be False when transforming the data" % (X.shape[1],))
+                raise ValueError(f"Unexpected input dimension {X.shape[1]}, the attribute drop_invariant should "
+                                 "be False when transforming the data")
             else:
-                raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim,))
+                raise ValueError(f'Unexpected input dimension {X.shape[1]}, expected {self._dim}')
 
         if not list(self.cols):
             return X if self.return_df else X.values

category_encoders/cat_boost.py

@@ -161,8 +161,7 @@ def fit(self, X, y, **kwargs):
                 [self.feature_names.remove(x) for x in self.drop_cols]
             except KeyError as e:
                 if self.verbose > 0:
-                    print("Could not remove column from feature names."
-                          "Not found in generated cols.\n{}".format(e))
+                    print(f"Could not remove column from feature names. Not found in generated cols.\n{e}")
 
         return self
 
@@ -198,7 +197,7 @@ def transform(self, X, y=None, override_return_df=False):
 
         # then make sure that it is the right size
         if X.shape[1] != self._dim:
-            raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim,))
+            raise ValueError(f'Unexpected input dimension {X.shape[1]}, expected {self._dim}')
 
         if not list(self.cols):
             return X

category_encoders/count.py

@@ -186,8 +186,7 @@ def fit(self, X, y=None, **kwargs):
                 [self.feature_names.remove(x) for x in self.drop_cols]
             except KeyError as e:
                 if self.verbose > 0:
-                    print("Could not remove column from feature names."
-                    "Not found in generated cols.\n{}".format(e))
+                    print(f"Could not remove column from feature names. Not found in generated cols.\n{e}")
 
         return self
 
@@ -290,11 +289,7 @@ def _transform_count_encode(self, X_in, y):
                 self._handle_unknown[col] == 'error'
                 and X[col].isnull().any()
             ):
-
-                raise ValueError(
-                    'Missing data found in column %s at transform time.'
-                    % (col,)
-                )
+                raise ValueError(f'Missing data found in column {col} at transform time.')
 
         return X, self.mapping
 

category_encoders/glmm.py

@@ -172,8 +172,7 @@ def fit(self, X, y, **kwargs):
                 [self.feature_names.remove(x) for x in self.drop_cols]
             except KeyError as e:
                 if self.verbose > 0:
-                    print("Could not remove column from feature names."
-                    "Not found in generated cols.\n{}".format(e))
+                    print(f"Could not remove column from feature names. Not found in generated cols.\n{e}")
         return self
 
     def transform(self, X, y=None, override_return_df=False):
@@ -209,7 +208,7 @@ def transform(self, X, y=None, override_return_df=False):
 
         # Then make sure that it is the right size
         if X.shape[1] != self._dim:
-            raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim,))
+            raise ValueError(f'Unexpected input dimension {X.shape[1]}, expected {self._dim}')
 
         if not list(self.cols):
             return X

category_encoders/hashing.py

@@ -175,8 +175,7 @@ def fit(self, X, y=None, **kwargs):
                 [self.feature_names.remove(x) for x in self.drop_cols]
             except KeyError as e:
                 if self.verbose > 0:
-                    print("Could not remove column from feature names."
-                          "Not found in generated cols.\n{}".format(e))
+                    print(f"Could not remove column from feature names. Not found in generated cols.\n{e}")
 
         return self
 
@@ -228,7 +227,7 @@ def transform(self, X, override_return_df=False):
 
         # then make sure that it is the right size
         if self.X.shape[1] != self._dim:
-            raise ValueError('Unexpected input dimension %d, expected %d' % (self.X.shape[1], self._dim, ))
+            raise ValueError(f'Unexpected input dimension {self.X.shape[1]}, expected {self._dim}')
 
         if not list(self.cols):
             return self.X
@@ -299,7 +298,7 @@ def _transform(self, X, override_return_df=False):
 
         # then make sure that it is the right size
         if X.shape[1] != self._dim:
-            raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim, ))
+            raise ValueError(f'Unexpected input dimension {X.shape[1]}, expected {self._dim}')
 
         if not list(self.cols):
             return X
@@ -350,18 +349,9 @@ def hashing_trick(X_in, hashing_method='md5', N=2, cols=None, make_copy=False):
         for Large Scale Multitask Learning. Proc. ICML.
 
         """
-
-        try:
-            if hashing_method not in hashlib.algorithms_available:
-                raise ValueError('Hashing Method: %s Not Available. Please use one from: [%s]' % (
-                    hashing_method,
-                    ', '.join([str(x) for x in hashlib.algorithms_available])
-                ))
-        except Exception as e:
-            try:
-                _ = hashlib.new(hashing_method)
-            except Exception as e:
-                raise ValueError('Hashing Method: %s Not Found.')
+        if hashing_method not in hashlib.algorithms_available:
+            raise ValueError(f"Hashing Method: {hashing_method} not Available. "
+                             f"Please use one from: [{', '.join([str(x) for x in hashlib.algorithms_available])}]")
 
         if make_copy:
             X = X_in.copy(deep=True)
@@ -383,7 +373,7 @@ def hash_fn(x):
                     tmp[int(hasher.hexdigest(), 16) % N] += 1
             return pd.Series(tmp, index=new_cols)
 
-        new_cols = ['col_%d' % d for d in range(N)]
+        new_cols = [f'col_{d}' for d in range(N)]
 
         X_cat = X.loc[:, cols]
         X_num = X.loc[:, [x for x in X.columns.values if x not in cols]]

category_encoders/helmert.py

@@ -164,8 +164,7 @@ def fit(self, X, y=None, **kwargs):
                 [self.feature_names.remove(x) for x in self.drop_cols]
             except KeyError as e:
                 if self.verbose > 0:
-                    print("Could not remove column from feature names."
-                          "Not found in generated cols.\n{}".format(e))
+                    print(f"Could not remove column from feature names. Not found in generated cols.\n{e}")
 
         return self
 
@@ -197,7 +196,7 @@ def transform(self, X, override_return_df=False):
 
         # then make sure that it is the right size
         if X.shape[1] != self._dim:
-            raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim, ))
+            raise ValueError(f'Unexpected input dimension {X.shape[1]}, expected {self._dim}')
 
         if not list(self.cols):
             return X
@@ -233,8 +232,7 @@ def fit_helmert_coding(col, values, handle_missing, handle_unknown):
 
         helmert_contrast_matrix = Helmert().code_without_intercept(values_to_encode)
         df = pd.DataFrame(data=helmert_contrast_matrix.matrix, index=values_to_encode,
-                          columns=[str(col) + '_%d' % (i,) for i in
-                                   range(len(helmert_contrast_matrix.column_suffixes))])
+                          columns=[f"{col}_{i}" for i in range(len(helmert_contrast_matrix.column_suffixes))])
 
         if handle_unknown == 'return_nan':
             df.loc[-1] = np.nan

category_encoders/james_stein.py

@@ -235,8 +235,7 @@ def fit(self, X, y, **kwargs):
                 [self.feature_names.remove(x) for x in self.drop_cols]
             except KeyError as e:
                 if self.verbose > 0:
-                    print("Could not remove column from feature names."
-                    "Not found in generated cols.\n{}".format(e))
+                    print(f"Could not remove column from feature names. Not found in generated cols.\n{e}")
         return self
 
     def transform(self, X, y=None, override_return_df=False):
@@ -272,7 +271,7 @@ def transform(self, X, y=None, override_return_df=False):
 
         # Then make sure that it is the right size
         if X.shape[1] != self._dim:
-            raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim,))
+            raise ValueError(f'Unexpected input dimension {X.shape[1]}, expected {self._dim}')
 
         if not list(self.cols):
             return X

category_encoders/leave_one_out.py

@@ -146,8 +146,7 @@ def fit(self, X, y, **kwargs):
                 [self.feature_names.remove(x) for x in self.drop_cols]
             except KeyError as e:
                 if self.verbose > 0:
-                    print("Could not remove column from feature names."
-                          "Not found in generated cols.\n{}".format(e))
+                    print(f"Could not remove column from feature names. Not found in generated cols.\n{e}")
 
         return self
 
@@ -185,7 +184,7 @@ def transform(self, X, y=None, override_return_df=False):
 
         # then make sure that it is the right size
         if X.shape[1] != self._dim:
-            raise ValueError('Unexpected input dimension %d, expected %d' % (X.shape[1], self._dim,))
+            raise ValueError(f'Unexpected input dimension {X.shape[1]}, expected {self._dim}')
 
         if not list(self.cols):
             return X