Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Danb27/sar literal fix #1663

Merged
merged 3 commits into from
Mar 9, 2022
Merged

Danb27/sar literal fix #1663

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e3238ca
danb27/sar_literal_fix: change is to == for comparing strings
Mar 8, 2022
262bd0e
danb27/sar_literal_fix: change is to == for comparing strings. improv…
Mar 8, 2022
dca7fe7
danb27/sar_literal_fix: change is to == for comparing strings. improv…
Mar 9, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions recommenders/models/sar/sar_singlenode.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
23 changes: 23 additions & 0 deletions tests/unit/recommenders/models/test_sar_singlenode.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@
import codecs
import csv
import itertools
import json
import pytest
import numpy as np
import pandas as pd
Expand Down Expand Up @@ -389,3 +390,25 @@ 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(header):
# store parameters in json
params_str = json.dumps({'similarity_type': 'jaccard'})
# 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],
}
)

model.fit(train)