def test_e2e(spark, pandas_dummy_dataset, header):
sar = SARPlus(spark, **header)
df = spark.createDataFrame(pandas_dummy_dataset)
sar.fit(df)
test_df = spark.createDataFrame(
pd.DataFrame({header["col_user"]: [3], header["col_item"]: [2]})
)
r1 = (
sar.recommend_k_items_slow(test_df, top_k=3, remove_seen=False)
.toPandas()
.sort_values([header["col_user"], header["col_item"]])
.reset_index(drop=True)
)
r2 = (
sar.recommend_k_items(
test_df,
"tests/test_e2e_cache",
top_k=3,
n_user_prediction_partitions=2,
remove_seen=False,
)
.toPandas()
.sort_values([header["col_user"], header["col_item"]])
.reset_index(drop=True)
)
assert (r1.iloc[:, :2] == r2.iloc[:, :2]).all().all()
assert np.allclose(r1.score.values, r2.score.values, 1e-3)
def test_e2e(spark, pandas_dummy_dataset, header):
sar = SARPlus(spark, **header)
df = spark.createDataFrame(pandas_dummy_dataset)
sar.fit(df)
# assert 4*4 + 32 == sar.item_similarity.count()
# print(sar.item_similarity
# .toPandas()
# .pivot_table(index='i1', columns='i2', values='value'))
test_df = spark.createDataFrame(
pd.DataFrame({
header['col_user']: [3],
header['col_item']: [2]
}))
r1 = sar.recommend_k_items_slow(test_df, top_k=3, remove_seen=False)\
.toPandas()\
.sort_values([header['col_user'], header['col_item']])\
.reset_index(drop=True)
r2 = sar.recommend_k_items(test_df, "tests/test_e2e_cache", top_k=3, n_user_prediction_partitions=2, remove_seen=False)\
.toPandas()\
.sort_values([header['col_user'], header['col_item']])\
.reset_index(drop=True)
assert (r1.iloc[:, :2] == r2.iloc[:, :2]).all().all()
assert np.allclose(r1.score.values, r2.score.values, 1e-3)
