def test_recommend_k_items(
threshold, similarity_type, file, header, sar_settings, demo_usage_data
):
time_now = demo_usage_data[header["col_timestamp"]].max()
model = SARSingleNode(
similarity_type=similarity_type,
timedecay_formula=True,
time_decay_coefficient=30,
time_now=time_now,
threshold=threshold,
**header
)
model.fit(demo_usage_data)
true_items, true_scores = load_userpred(
sar_settings["FILE_DIR"]
+ "userpred_"
+ file
+ str(threshold)
+ "_userid_only.csv"
)
test_results = model.recommend_k_items(
demo_usage_data[
demo_usage_data[header["col_user"]] == sar_settings["TEST_USER_ID"]
],
top_k=10,
sort_top_k=True,
remove_seen=True,
)
test_items = list(test_results[header["col_item"]])
test_scores = np.array(test_results["prediction"])
assert true_items == test_items
assert np.allclose(true_scores, test_scores, atol=sar_settings["ATOL"])
"col_timestamp": "Timestamp",
}
model = SARSingleNode(remove_seen=True,
similarity_type="jaccard",
time_decay_coefficient=30,
time_now=None,
timedecay_formula=True,
**header)
start_time = time.time()
model.fit(train)
train_time = time.time() - start_time
start_time = time.time()
topk = model.recommend_k_items(test)
test_time = time.time() - start_time
# TODO: remove this call when the model returns same type as input
topk['UserId'] = pd.to_numeric(topk['UserId'])
topk['MovieId'] = pd.to_numeric(topk['MovieId'])
mlask(begin="\n", end="\n")
mlcat(
"Fit the SAR Model", """\
We will now fit the model (<1s) and apply it to the test dataset
For a random sample of users from the test dataset we list the model's
prediction of their rating of a particular movie. The predicted ratings
time_decay_coefficient=30,
time_now=None,
timedecay_formula=True,
**header)
# train the SAR model
start_time = time.time()
model.fit(train)
train_time = time.time() - start_time
run.log(name="Training time", value=train_time)
start_time = time.time()
top_k = model.recommend_k_items(test)
test_time = time.time() - start_time
run.log(name="Prediction time", value=test_time)
# TODO: remove this call when the model returns same type as input
top_k['UserId'] = pd.to_numeric(top_k['UserId'])
top_k['MovieId'] = pd.to_numeric(top_k['MovieId'])
# evaluate
eval_map = map_at_k(test,
top_k,
col_user="******",
col_item="MovieId",
col_rating="Rating",
col_prediction="prediction",
col_item=header["col_item"],
seed=42)
# set log level to INFO
logging.basicConfig(level=logging.DEBUG,
format='%(asctime)s %(levelname)-8s %(message)s')
model = SARSingleNode(similarity_type="jaccard",
time_decay_coefficient=30,
time_now=None,
timedecay_formula=True,
**header)
model.fit(train)
top_k = model.recommend_k_items(test, remove_seen=True)
top_k_with_titles = (top_k.join(
data[['MovieId', 'Title']].drop_duplicates().set_index('MovieId'),
on='MovieId',
how='inner').sort_values(by=['UserId', 'Prediction'], ascending=False))
args = [test, top_k]
kwargs = dict(col_user='******',
col_item='MovieId',
col_rating='Rating',
col_prediction='Prediction',
relevancy_method='top_k',
k=TOP_K)
eval_map = map_at_k(*args, **kwargs)