def test_random_splitter(test_specs, python_dataset):
"""NOTE: some split results may not match exactly with the ratios, which may be owing to the limited number of
rows in the testing data. A approximate match with certain level of tolerance is therefore used instead for tests.
"""
splits = python_random_split(python_dataset,
ratio=test_specs["ratio"],
seed=test_specs["seed"])
assert len(splits[0]) / test_specs["number_of_rows"] == pytest.approx(
test_specs["ratio"], test_specs["tolerance"])
assert len(splits[1]) / test_specs["number_of_rows"] == pytest.approx(
1 - test_specs["ratio"], test_specs["tolerance"])
splits = python_random_split(python_dataset,
ratio=test_specs["ratios"],
seed=test_specs["seed"])
assert len(splits) == 3
assert len(splits[0]) / test_specs["number_of_rows"] == pytest.approx(
test_specs["ratios"][0], test_specs["tolerance"])
assert len(splits[1]) / test_specs["number_of_rows"] == pytest.approx(
test_specs["ratios"][1], test_specs["tolerance"])
assert len(splits[2]) / test_specs["number_of_rows"] == pytest.approx(
test_specs["ratios"][2], test_specs["tolerance"])
splits = python_random_split(python_dataset,
ratio=test_specs["split_numbers"],
seed=test_specs["seed"])
assert len(splits) == 3
assert len(splits[0]) / test_specs["number_of_rows"] == pytest.approx(
test_specs["ratios"][0], test_specs["tolerance"])
assert len(splits[1]) / test_specs["number_of_rows"] == pytest.approx(
test_specs["ratios"][1], test_specs["tolerance"])
assert len(splits[2]) / test_specs["number_of_rows"] == pytest.approx(
test_specs["ratios"][2], test_specs["tolerance"])
def test_random_splitter(test_specs, python_dataset):
"""NOTE: some split results may not match exactly with the ratios, which may be owing to the limited number of
rows in the testing data. A approximate match with certain level of tolerance is therefore used instead for tests.
"""
splits = python_random_split(
python_dataset, ratio=test_specs["ratio"], seed=test_specs["seed"]
)
assert len(splits[0]) / test_specs["number_of_rows"] == pytest.approx(
test_specs["ratio"], test_specs["tolerance"]
)
assert len(splits[1]) / test_specs["number_of_rows"] == pytest.approx(
1 - test_specs["ratio"], test_specs["tolerance"]
)
for split in splits:
assert set(split.columns) == set(python_dataset.columns)
splits = python_random_split(
python_dataset, ratio=test_specs["ratios"], seed=test_specs["seed"]
)
assert len(splits) == 3
assert len(splits[0]) / test_specs["number_of_rows"] == pytest.approx(
test_specs["ratios"][0], test_specs["tolerance"]
)
assert len(splits[1]) / test_specs["number_of_rows"] == pytest.approx(
test_specs["ratios"][1], test_specs["tolerance"]
)
assert len(splits[2]) / test_specs["number_of_rows"] == pytest.approx(
test_specs["ratios"][2], test_specs["tolerance"]
)
for split in splits:
assert set(split.columns) == set(python_dataset.columns)
splits = python_random_split(
python_dataset, ratio=test_specs["split_numbers"], seed=test_specs["seed"]
)
assert len(splits) == 3
assert len(splits[0]) / test_specs["number_of_rows"] == pytest.approx(
test_specs["ratios"][0], test_specs["tolerance"]
)
assert len(splits[1]) / test_specs["number_of_rows"] == pytest.approx(
test_specs["ratios"][1], test_specs["tolerance"]
)
assert len(splits[2]) / test_specs["number_of_rows"] == pytest.approx(
test_specs["ratios"][2], test_specs["tolerance"]
)
for split in splits:
assert set(split.columns) == set(python_dataset.columns)
data.head()
# data = pd.read_csv("/content/snackratings.csv")
# data.head()
print(
"Total number of ratings are\t{}".format(data.shape[0]),
"Total number of users are\t{}".format(data[USER].nunique()),
"Total number of items are\t{}".format(data[ITEM].nunique()),
sep="\n"
)
#st.subheader("data loaded")
data_train, data_test = python_random_split(data, ratio=0.7)
split =data_train.shape[0], data_test.shape[0]
st.write("Splitting_Ratio:",split)
data = CollabDataBunch.from_df(data_train, seed=42, valid_pct=0.1)
y_range = [0.5,5.5]
st.write(y_range)
factor=N_FACTORS
st.write("No. of factors:",factor)
learn = collab_learner(data, n_factors=factor, y_range=y_range, wd=1e-1)
learn.model
default=10,
help='top k items to recommend')
parser.add_argument('--data-size',
type=str,
dest='data_size',
default=10,
help='Movielens data size: 100k, 1m, 10m, or 20m')
args = parser.parse_args()
run.log("top-k", args.top_k)
run.log("data-size", args.data_size)
data_pickle_path = os.path.join(args.data_folder, args.data_file)
data = pd.read_pickle(path=data_pickle_path)
train, test = python_random_split(data, 0.75)
# instantiate the SAR algorithm and set the index
header = {
"col_user": "******",
"col_item": "MovieId",
"col_rating": "Rating",
"col_timestamp": "Timestamp",
}
logging.basicConfig(level=logging.DEBUG,
format='%(asctime)s %(levelname)-8s %(message)s')
model = SARSingleNode(remove_seen=True,
similarity_type="jaccard",
time_decay_coefficient=30,
