Keep non-feature columns when encoding feature matrix (#111)

* add test for giving extra columns to encode features

* test passes

* fix loop logic

* test for features missing from feature matrix

featuretools/synthesis/encode_features.py

@@ -65,6 +65,15 @@ def encode_features(feature_matrix, features, top_n=10, include_unknown=True,
         X = feature_matrix.copy()
 
     encoded = []
+    feature_names = []
+    for feature in features:
+        fname = feature.get_name()
+        assert fname in X.columns, (
+            "Feature %s not found in feature matrix" % (fname)
+        )
+        feature_names.append(fname)
+
+    extra_columns = [col for col in X.columns if col not in feature_names]
 
     if verbose:
         iterator = make_tqdm_iterator(iterable=features,
@@ -107,15 +116,16 @@ def encode_features(feature_matrix, features, top_n=10, include_unknown=True,
 
         X.drop(f.get_name(), axis=1, inplace=True)
 
-    new_X = X[[e.get_name() for e in encoded]]
+    new_X = X[[e.get_name() for e in encoded] + extra_columns]
     iterator = new_X.columns
     if verbose:
         iterator = make_tqdm_iterator(iterable=new_X.columns,
                                       total=len(new_X.columns),
                                       desc="Encoding pass 2",
                                       unit="feature")
-
     for c in iterator:
+        if c in extra_columns:
+            continue
         try:
             new_X[c] = pd.to_numeric(new_X[c], errors='raise')
         except (TypeError, ValueError):

featuretools/tests/computational_backend/test_encode_features.py

@@ -1,3 +1,4 @@
+import pandas as pd
 import pytest
 
 from ..testing_utils import make_ecommerce_entityset
@@ -65,3 +66,49 @@ def test_to_encode_features(entityset):
     to_encode = ['value']
     feature_matrix_encoded, features_encoded = encode_features(feature_matrix, features, to_encode=to_encode)
     assert feature_matrix_encoded_shape != feature_matrix_encoded.shape
+
+
+def test_encode_features_handles_pass_columns(entityset):
+    f1 = IdentityFeature(entityset["log"]["product_id"])
+    f2 = IdentityFeature(entityset["log"]["value"])
+
+    features = [f1, f2]
+    cutoff_time = pd.DataFrame({'instance_id': range(6),
+                                'time': entityset['log'].df['datetime'][0:6],
+                                'label': [i % 2 for i in range(6)]},
+                               columns=["instance_id", "time", "label"])
+    feature_matrix = calculate_feature_matrix(features, cutoff_time)
+
+    assert 'label' in feature_matrix.columns
+
+    feature_matrix_encoded, features_encoded = encode_features(feature_matrix, features)
+    feature_matrix_encoded_shape = feature_matrix_encoded.shape
+
+    # to_encode should keep product_id as a string, and not create 3 additional columns
+    to_encode = []
+    feature_matrix_encoded, features_encoded = encode_features(feature_matrix, features, to_encode=to_encode)
+    assert feature_matrix_encoded_shape != feature_matrix_encoded.shape
+
+    to_encode = ['value']
+    feature_matrix_encoded, features_encoded = encode_features(feature_matrix, features, to_encode=to_encode)
+    assert feature_matrix_encoded_shape != feature_matrix_encoded.shape
+
+    assert 'label' in feature_matrix_encoded.columns
+
+
+def test_encode_features_catches_features_mismatch(entityset):
+    f1 = IdentityFeature(entityset["log"]["product_id"])
+    f2 = IdentityFeature(entityset["log"]["value"])
+    f3 = IdentityFeature(entityset["log"]["session_id"])
+
+    features = [f1, f2]
+    cutoff_time = pd.DataFrame({'instance_id': range(6),
+                                'time': entityset['log'].df['datetime'][0:6],
+                                'label': [i % 2 for i in range(6)]},
+                               columns=["instance_id", "time", "label"])
+    feature_matrix = calculate_feature_matrix(features, cutoff_time)
+
+    assert 'label' in feature_matrix.columns
+
+    with pytest.raises(AssertionError):
+        encode_features(feature_matrix, [f1, f3])