Merge branch 'staging' into laserprec/code-cov-fix

recommenders/models/sar/sar_singlenode.py

@@ -270,15 +270,15 @@ def fit(self, df):
         self.item_frequencies = item_cooccurrence.diagonal()
 
         logger.info("Calculating item similarity")
-        if self.similarity_type is COOCCUR:
+        if self.similarity_type == COOCCUR:
             logger.info("Using co-occurrence based similarity")
             self.item_similarity = item_cooccurrence
-        elif self.similarity_type is JACCARD:
+        elif self.similarity_type == JACCARD:
             logger.info("Using jaccard based similarity")
             self.item_similarity = jaccard(item_cooccurrence).astype(
                 df[self.col_rating].dtype
             )
-        elif self.similarity_type is LIFT:
+        elif self.similarity_type == LIFT:
             logger.info("Using lift based similarity")
             self.item_similarity = lift(item_cooccurrence).astype(
                 df[self.col_rating].dtype

tests/unit/recommenders/models/test_sar_singlenode.py

@@ -4,6 +4,7 @@
 import codecs
 import csv
 import itertools
+import json
 import pytest
 import numpy as np
 import pandas as pd
@@ -389,3 +390,26 @@ def test_get_normalized_scores(header):
     assert actual.shape == (2, 7)
     assert isinstance(actual, np.ndarray)
     assert np.isclose(expected, np.asarray(actual)).all()
+
+
+def test_match_similarity_type_from_json_file(header):
+    # store parameters in json
+    params_str = json.dumps({'similarity_type': 'lift'})
+    # load parameters in json
+    params = json.loads(params_str)
+
+    params.update(header)
+
+    model = SARSingleNode(**params)
+
+    train = pd.DataFrame(
+        {
+            header["col_user"]: [1, 1, 1, 1, 2, 2, 2, 2],
+            header["col_item"]: [1, 2, 3, 4, 1, 5, 6, 7],
+            header["col_rating"]: [3.0, 4.0, 5.0, 4.0, 3.0, 2.0, 1.0, 5.0],
+            header["col_timestamp"]: [1, 20, 30, 400, 50, 60, 70, 800],
+        }
+    )
+
+    # make sure fit still works when similarity type is loaded from a json file
+    model.fit(train)