Merge pull request #175 from datarian/fix-tests-with-new-col-na_categorical

Fix tests with new col na categorical

Author: janmotl

.travis.yml

@@ -14,12 +14,12 @@ env:
     - MODULE=category_encoders
   matrix:
     # The versions should match the minimal requirements in requirements.txt and setup.py
-    - DISTRIB="conda" PYTHON_VERSION="2.7" CYTHON_VERSION="0.21"
-      NUMPY_VERSION="1.11.1" PANDAS_VERSION="0.21.1" PATSY_VERSION="0.4.1"
-      SCIKIT_VERSION="0.20.2" SCIPY_VERSION="0.17.0" STATSMODELS_VERSION="0.6.1"
-    - DISTRIB="conda" PYTHON_VERSION="3.5" COVERAGE="true" CYTHON_VERSION="0.23.4"
-      NUMPY_VERSION="1.11.1" PANDAS_VERSION="0.21.1" PATSY_VERSION="0.4.1"
-      SCIKIT_VERSION="0.17.1" SCIPY_VERSION="0.17.0" STATSMODELS_VERSION="0.6.1"
+    - DISTRIB="conda" PYTHON_VERSION="2.7" CYTHON_VERSION="0.23.5"
+      NUMPY_VERSION="1.11.3" PANDAS_VERSION="0.21.1" PATSY_VERSION="0.4.1"
+      SCIKIT_VERSION="0.20.0" SCIPY_VERSION="0.19.0" STATSMODELS_VERSION="0.6.1"
+    - DISTRIB="conda" PYTHON_VERSION="3.6" COVERAGE="true" CYTHON_VERSION="0.25.2"
+      NUMPY_VERSION="1.11.3" PANDAS_VERSION="0.21.1" PATSY_VERSION="0.4.1"
+      SCIKIT_VERSION="0.20.0" SCIPY_VERSION="0.19.0" STATSMODELS_VERSION="0.6.1"
 
 install: source ci_scripts/install.sh
 script: bash ci_scripts/test.sh

category_encoders/basen.py

@@ -349,21 +349,20 @@ def basen_to_integer(self, X, cols, base):
         -------
         numerical: DataFrame
         """
-        out_cols = X.columns.values
+        out_cols = X.columns.values.tolist()
 
         for col in cols:
             col_list = [col0 for col0 in out_cols if str(col0).startswith(str(col))]
+            insert_at = out_cols.index(col_list[0])
 
             if base == 1:
                 value_array = np.array([int(col0.split('_')[-1]) for col0 in col_list])
             else:
                 len0 = len(col_list)
                 value_array = np.array([base ** (len0 - 1 - i) for i in range(len0)])
-
-            X[col] = np.dot(X[col_list].values, value_array.T)
-            out_cols = [col0 for col0 in out_cols if col0 not in col_list]
-
-        X = X.reindex(columns=out_cols + cols)
+            X.insert(insert_at,col,np.dot(X[col_list].values, value_array.T))
+            X.drop(col_list, axis=1, inplace=True)
+            out_cols = X.columns.values.tolist()
 
         return X
 

category_encoders/tests/helpers.py

@@ -50,9 +50,9 @@ def create_dataset(n_rows=1000, extras=False, has_none=True):
         random.choice(['A', 'B', 'C', np.nan])                                                  # Categorical with missing values
     ] for row in range(n_rows)]
 
-    df = pd.DataFrame(ds, columns=['float', 'float_edge', 'unique_int', 'unique_str', 'invariant', 'underscore', 'none', 'extra', 321, 'categorical', 'categorical_na'])
+    df = pd.DataFrame(ds, columns=['float', 'float_edge', 'unique_int', 'unique_str', 'invariant', 'underscore', 'none', 'extra', 321, 'categorical', 'na_categorical'])
     df['categorical'] = pd.Categorical(df['categorical'], categories=['A', 'B', 'C'])
-    df['categorical_na'] = pd.Categorical(df['categorical_na'], categories=['A', 'B', 'C'])
+    df['na_categorical'] = pd.Categorical(df['na_categorical'], categories=['A', 'B', 'C'])
     return df
 
 

requirements.txt

@@ -1,6 +1,6 @@
-numpy>=1.11.1
-scikit-learn>=0.20.2
-scipy>=0.17.0
+numpy>=1.11.3
+scikit-learn>=0.20.0
+scipy>=0.19.0
 statsmodels>=0.6.1
 pandas>=0.21.1
 patsy>=0.4.1

setup.py

@@ -29,9 +29,9 @@
     include_package_data=True,
     author='Will McGinnis',
     install_requires=[
-      'numpy>=1.11.1',
-      'scikit-learn>=0.20.2',
-      'scipy>=0.17.0',
+      'numpy>=1.11.3',
+      'scikit-learn>=0.20.0',
+      'scipy>=0.19.0',
       'statsmodels>=0.6.1',
       'pandas>=0.21.1',
       'patsy>=0.4.1',