CategoricalImputer: Error out when no mode is found

Author: dukebody

sklearn_pandas/categorical_imputer.py

@@ -1,7 +1,6 @@
 import pandas as pd
 import numpy as np
 
-from collections import Counter
 
 from sklearn.base import BaseEstimator, TransformerMixin
 from sklearn.utils.validation import check_is_fitted
@@ -65,7 +64,12 @@ def fit(self, X, y=None):
         mask = _get_mask(X, self.missing_values)
         X = X[~mask]
 
-        self.fill_ = Counter(X).most_common(1)[0][0]
+        modes = pd.Series(X).mode()
+        if modes.shape[0] == 0:
+            raise ValueError('No value is repeated more than '
+                             'once in the column')
+        else:
+            self.fill_ = modes[0]
 
         return self
 

tests/test_categorical_imputer.py

@@ -34,6 +34,20 @@ def test_unit(input_type, none_value):
     assert (Xt == ['a', 'b', 'b', 'b']).all()
 
 
+@pytest.mark.parametrize('input_type', ['np', 'pd'])
+def test_no_mode(input_type):
+
+    data = ['a', 'b', 'c', np.nan]
+
+    if input_type == 'pd':
+        X = pd.Series(data)
+    else:
+        X = np.asarray(data, dtype=object)
+
+    with pytest.raises(ValueError):
+        CategoricalImputer().fit_transform(X)
+
+
 @pytest.mark.parametrize('input_type', ['np', 'pd'])
 def test_missing_values_param(input_type):