def test_load_features_data():
dates = [datetime.datetime(2016, 1, 1, 0, 0), datetime.datetime(2016, 2, 1, 0, 0)]
# make dataframe for entity ids and dates
ids_dates = create_entity_date_df(
labels=labels,
states=states,
as_of_dates=dates,
label_name="booking",
label_type="binary",
label_timespan="1 month",
)
features = [["f1", "f2"], ["f3", "f4"]]
# make dataframes of features to test against
features_dfs = []
for i, table in enumerate(features_tables):
cols = ["entity_id", "as_of_date"] + features[i]
temp_df = pd.DataFrame(table, columns=cols)
temp_df["as_of_date"] = convert_string_column_to_date(temp_df["as_of_date"])
features_dfs.append(
ids_dates.merge(
right=temp_df, how="left", on=["entity_id", "as_of_date"]
).set_index(["entity_id", "as_of_date"])
)
# create an engine and generate a table with fake feature data
with testing.postgresql.Postgresql() as postgresql:
engine = create_engine(postgresql.url())
create_schemas(
engine=engine, features_tables=features_tables, labels=labels, states=states
)
with get_matrix_storage_engine() as matrix_storage_engine:
builder = MatrixBuilder(
db_config=db_config,
matrix_storage_engine=matrix_storage_engine,
experiment_hash=experiment_hash,
engine=engine,
)
# make the entity-date table
entity_date_table_name = builder.make_entity_date_table(
as_of_times=dates,
label_type="binary",
label_name="booking",
state="active",
matrix_type="train",
matrix_uuid="my_uuid",
label_timespan="1 month",
)
feature_dictionary = dict(
("features{}".format(i), feature_list)
for i, feature_list in enumerate(features)
)
returned_features_dfs = builder.load_features_data(
as_of_times=dates,
feature_dictionary=feature_dictionary,
entity_date_table_name=entity_date_table_name,
matrix_uuid="my_uuid",
)
# get the queries and test them
for result, df in zip(returned_features_dfs, features_dfs):
test = result == df
assert test.all().all()
def test_load_features_data():
dates = [
datetime.datetime(2016, 1, 1, 0, 0),
datetime.datetime(2016, 2, 1, 0, 0)
]
# make dataframe for entity ids and dates
ids_dates = create_entity_date_df(labels=labels,
states=states,
as_of_dates=dates,
state_one=True,
state_two=True,
label_name='booking',
label_type='binary',
label_timespan='1 month')
features = [['f1', 'f2'], ['f3', 'f4']]
# make dataframes of features to test against
features_dfs = []
for i, table in enumerate(features_tables):
cols = ['entity_id', 'as_of_date'] + features[i]
temp_df = pd.DataFrame(table, columns=cols)
temp_df['as_of_date'] = convert_string_column_to_date(
temp_df['as_of_date'])
features_dfs.append(
ids_dates.merge(right=temp_df,
how='left',
on=['entity_id', 'as_of_date'
]).set_index(['entity_id', 'as_of_date']))
# create an engine and generate a table with fake feature data
with testing.postgresql.Postgresql() as postgresql:
engine = create_engine(postgresql.url())
create_schemas(engine=engine,
features_tables=features_tables,
labels=labels,
states=states)
with get_matrix_storage_engine() as matrix_storage_engine:
builder = MatrixBuilder(
db_config=db_config,
matrix_storage_engine=matrix_storage_engine,
engine=engine,
)
# make the entity-date table
entity_date_table_name = builder.make_entity_date_table(
as_of_times=dates,
label_type='binary',
label_name='booking',
state='state_one AND state_two',
matrix_type='train',
matrix_uuid='my_uuid',
label_timespan='1 month')
feature_dictionary = dict(
('features{}'.format(i), feature_list)
for i, feature_list in enumerate(features))
returned_features_dfs = builder.load_features_data(
as_of_times=dates,
feature_dictionary=feature_dictionary,
entity_date_table_name=entity_date_table_name,
matrix_uuid='my_uuid')
# get the queries and test them
for result, df in zip(returned_features_dfs, features_dfs):
test = (result == df)
assert (test.all().all())
