changes after review

Author: PaulWestenthanner

category_encoders/cat_boost.py

@@ -105,13 +105,8 @@ def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True,
     def _fit(self, X, y, **kwargs):
         X = X.copy(deep=True)
 
-        if self.cols is None:
-            cols = X.columns.values
-        else:
-            cols = self.cols
-
         self._mean = y.mean()
-        self.mapping = {col: self._fit_column_map(X[col], y) for col in cols}
+        self.mapping = {col: self._fit_column_map(X[col], y) for col in self.cols}
 
     def _transform(self, X, y=None):
         random_state_ = check_random_state(self.random_state)

category_encoders/count.py

@@ -139,16 +139,16 @@ def _fit(self, X, y=None, **kwargs):
         return self
 
     def _transform(self, X):
-        """Perform the transform count encoding."""
         for col in self.cols:
-            X[col] = X[col].fillna(value=np.nan)
+            # Treat None as np.nan
+            X[col] = pd.Series([el if el is not None else np.NaN for el in X[col]], index=X[col].index)
+            if self.handle_missing == "value":
+                if not util.is_category(X[col].dtype):
+                    X[col] = X[col].fillna(np.nan)
 
             if self._min_group_size is not None:
                 if col in self._min_group_categories.keys():
-                    X[col] = (
-                        X[col].map(self._min_group_categories[col])
-                            .fillna(X[col])
-                    )
+                    X[col] = X[col].map(self._min_group_categories[col]).fillna(X[col])
 
             X[col] = X[col].astype(object).map(self.mapping[col])
             if isinstance(self._handle_unknown[col], (int, np.integer)):
@@ -164,7 +164,6 @@ def _transform(self, X):
                     self._handle_unknown[col] == 'error'
                     and X[col].isnull().any()
             ):
-
                 raise ValueError(f'Missing data found in column {col} at transform time.')
         return X
 

category_encoders/target_encoder.py

@@ -89,13 +89,11 @@ def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True, h
         self.ordinal_encoder = None
         self.min_samples_leaf = min_samples_leaf
         if min_samples_leaf == 1:
-            self.smoothing = float(
-                smoothing)  # Make smoothing a float so that python 2 does not treat as integer division
             warnings.warn("Default parameter min_samples_leaf will change in version 2.6."
                           "See https://github.com/scikit-learn-contrib/category_encoders/issues/327",
                           category=FutureWarning)
         self.smoothing = smoothing
-        if min_samples_leaf == 1.0:
+        if smoothing == 1.0:
             warnings.warn("Default parameter smoothing will change in version 2.6."
                           "See https://github.com/scikit-learn-contrib/category_encoders/issues/327",
                           category=FutureWarning)

docs/source/catboost.rst

@@ -1,5 +1,5 @@
 CatBoost Encoder
-==============
+================
 
 .. autoclass:: category_encoders.cat_boost.CatBoostEncoder
     :members:

docs/source/jamesstein.rst

@@ -1,5 +1,5 @@
 James-Stein Encoder
-==============
+===================
 
 .. autoclass:: category_encoders.james_stein.JamesSteinEncoder
     :members:

docs/source/quantile.rst

@@ -1,5 +1,5 @@
 Quantile Encoder
-==============
+================
 
 .. autoclass:: category_encoders.quantile_encoder.QuantileEncoder
     :members:

docs/source/summary.rst

@@ -1,5 +1,5 @@
 Summary Encoder
-==============
+===============
 
 .. autoclass:: category_encoders.quantile_encoder.SummaryEncoder
     :members:

requirements.txt

@@ -4,4 +4,4 @@ scipy>=1.0.0
 statsmodels>=0.9.0
 pandas>=1.0.5
 patsy>=0.5.1
-unittest2
+unittest2