better handling of None as a cols param

CHANGELOG.md

@@ -2,6 +2,8 @@ v1.1.0
 ======
 
  * Optionally pass drop_invariant to any encoder to consistently drop columns with 0 variance from the output (based on training set data in fit())
+ * If None is passed as the cols param, every string column will be encoded (pandas type = object).
+
 v1.0.5
 ======
 

category_encoders/backward_difference.py

@@ -11,6 +11,7 @@
 from sklearn.base import BaseEstimator, TransformerMixin
 from patsy.highlevel import dmatrix
 from category_encoders.ordinal import OrdinalEncoder
+from category_encoders.utils import get_obj_cols
 
 __author__ = 'willmcginnis'
 
@@ -71,8 +72,18 @@ def fit(self, X, y=None, **kwargs):
         :return:
         """
 
+        # if the input dataset isn't already a dataframe, convert it to one (using default column names)
+        if not isinstance(X, pd.DataFrame):
+            X = pd.DataFrame(X)
+
+        # if columns aren't passed, just use every string column
+        if self.cols is None:
+            self.cols = get_obj_cols(X)
+
+        # train an ordinal pre-encoder
         self.ordinal_encoder = self.ordinal_encoder.fit(X)
 
+        # drop all output columns with 0 variance.
         if self.drop_invariant:
             self.drop_cols = []
             X_temp = self.transform(X)

category_encoders/binary.py

@@ -11,6 +11,7 @@
 from sklearn.base import BaseEstimator, TransformerMixin
 import numpy as np
 from category_encoders.ordinal import OrdinalEncoder
+from category_encoders.utils import get_obj_cols
 
 __author__ = 'willmcginnis'
 
@@ -77,8 +78,18 @@ def fit(self, X, y=None, **kwargs):
         :return:
         """
 
+        # if the input dataset isn't already a dataframe, convert it to one (using default column names)
+        if not isinstance(X, pd.DataFrame):
+            X = pd.DataFrame(X)
+
+        # if columns aren't passed, just use every string column
+        if self.cols is None:
+            self.cols = get_obj_cols(X)
+
+        # train an ordinal pre-encoder
         self.ordinal_encoder = self.ordinal_encoder.fit(X)
 
+        # drop all output columns with 0 variance.
         if self.drop_invariant:
             self.drop_cols = []
             X_temp = self.transform(X)

category_encoders/hashing.py

@@ -9,6 +9,7 @@
 import copy
 from sklearn.base import BaseEstimator, TransformerMixin
 import pandas as pd
+from category_encoders.utils import get_obj_cols
 
 __author__ = 'willmcginnis'
 
@@ -100,6 +101,15 @@ def fit(self, X, y=None, **kwargs):
         :return:
         """
 
+        # if the input dataset isn't already a dataframe, convert it to one (using default column names)
+        if not isinstance(X, pd.DataFrame):
+            X = pd.DataFrame(X)
+
+        # if columns aren't passed, just use every string column
+        if self.cols is None:
+            self.cols = get_obj_cols(X)
+
+        # drop all output columns with 0 variance.
         if self.drop_invariant:
             self.drop_cols = []
             X_temp = self.transform(X)

category_encoders/helmert.py

@@ -11,6 +11,7 @@
 from sklearn.base import BaseEstimator, TransformerMixin
 from patsy.highlevel import dmatrix
 from category_encoders.ordinal import OrdinalEncoder
+from category_encoders.utils import get_obj_cols
 
 __author__ = 'willmcginnis'
 

category_encoders/ordinal.py

@@ -10,6 +10,7 @@
 import copy
 from sklearn.base import BaseEstimator, TransformerMixin
 import random
+from category_encoders.utils import get_obj_cols
 
 __author__ = 'willmcginnis'
 
@@ -34,6 +35,7 @@ def ordinal_encoding(X_in, mapping=None, cols=None):
         for switch in mapping:
             for category in switch.get('mapping'):
                 X.loc[X[switch.get('col')] == category[0], switch.get('col')] = str(category[1])
+
             X[switch.get('col')] = X[switch.get('col')].astype(int).reshape(-1, )
     else:
         for col in cols:
@@ -78,12 +80,18 @@ def fit(self, X, y=None, **kwargs):
         :return:
         """
 
+        # if the input dataset isn't already a dataframe, convert it to one (using default column names)
         if not isinstance(X, pd.DataFrame):
             X = pd.DataFrame(X)
 
+        # if columns aren't passed, just use every string column
+        if self.cols is None:
+            self.cols = get_obj_cols(X)
+
         _, categories = ordinal_encoding(X, mapping=self.mapping, cols=self.cols)
         self.mapping = categories
 
+        # drop all output columns with 0 variance.
         if self.drop_invariant:
             self.drop_cols = []
             X_temp = self.transform(X)

category_encoders/polynomial.py

@@ -10,7 +10,7 @@
 import pandas as pd
 from sklearn.base import BaseEstimator, TransformerMixin
 from patsy.highlevel import dmatrix
-from category_encoders.ordinal import OrdinalEncoder
+from category_encoders.utils import get_obj_cols
 
 __author__ = 'willmcginnis'
 
@@ -68,6 +68,15 @@ def fit(self, X, y=None, **kwargs):
         :return:
         """
 
+        # if the input dataset isn't already a dataframe, convert it to one (using default column names)
+        if not isinstance(X, pd.DataFrame):
+            X = pd.DataFrame(X)
+
+        # if columns aren't passed, just use every string column
+        if self.cols is None:
+            self.cols = get_obj_cols(X)
+
+        # drop all output columns with 0 variance.
         if self.drop_invariant:
             self.drop_cols = []
             X_temp = self.transform(X)

category_encoders/sum_coding.py

@@ -11,6 +11,7 @@
 from sklearn.base import BaseEstimator, TransformerMixin
 from patsy.highlevel import dmatrix
 from category_encoders.ordinal import OrdinalEncoder
+from category_encoders.utils import get_obj_cols
 
 __author__ = 'willmcginnis'
 
@@ -69,8 +70,20 @@ def fit(self, X, y=None, **kwargs):
         :return:
         """
 
+        # if the input dataset isn't already a dataframe, convert it to one (using default column names)
+        if not isinstance(X, pd.DataFrame):
+            X = pd.DataFrame(X)
+
+        # if columns aren't passed, just use every string column
+        if self.cols is None:
+            self.cols = get_obj_cols(X)
+
+        self.ordinal_encoder = self.ordinal_encoder.fit(X)
+
+        # train an ordinal pre-encoder
         self.ordinal_encoder = self.ordinal_encoder.fit(X)
 
+        # drop all output columns with 0 variance.
         if self.drop_invariant:
             self.drop_cols = []
             X_temp = self.transform(X)

category_encoders/utils.py

@@ -0,0 +1,18 @@
+"""
+
+.. module:: utils
+  :synopsis: generic helper functions shared by many encoders
+  :platform:
+
+"""
+
+__author__ = 'willmcginnis'
+
+
+def get_obj_cols(df):
+    obj_cols = []
+    for idx, dt in enumerate(df.dtypes):
+        if dt == 'object':
+            obj_cols.append(df.columns.values[idx])
+
+    return obj_cols

setup.py

@@ -2,7 +2,7 @@
 from codecs import open
 from os import path
 
-__version__ = '1.0.5'
+__version__ = '1.1.0'
 
 
 here = path.abspath(path.dirname(__file__))