def test_write_labels_data(): """ Test the write_labels_data function by checking whether the query produces the correct labels """ # set up labeling config variables dates = [ datetime.datetime(2016, 1, 1, 0, 0), datetime.datetime(2016, 2, 1, 0, 0) ] # make a dataframe of labels to test against labels_df = pd.DataFrame(labels, columns=[ 'entity_id', 'as_of_date', 'label_timespan', 'label_name', 'label_type', 'label' ]) labels_df['as_of_date'] = convert_string_column_to_date( labels_df['as_of_date']) labels_df.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, features_tables, labels, states) with TemporaryDirectory() as temp_dir: builder = builders.HighMemoryCSVBuilder( db_config=db_config, matrix_directory=temp_dir, 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') csv_filename = builder.write_labels_data( label_name=label_name, label_type=label_type, label_timespan='1 month', matrix_uuid='my_uuid', entity_date_table_name=entity_date_table_name, ) df = pd.DataFrame.from_dict({ 'entity_id': [2, 3, 4, 4], 'as_of_date': ['2016-02-01', '2016-02-01', '2016-01-01', '2016-02-01'], 'booking': [0, 0, 1, 0], }).set_index(['entity_id', 'as_of_date']) result = pd.read_csv(builder.open_fh_for_reading(csv_filename))\ .set_index(['entity_id', 'as_of_date']) test = (result == df) assert (test.all().all())
def test_write_to_csv(): """ Test the write_to_csv function by checking whether the csv contains the correct number of lines. """ with testing.postgresql.Postgresql() as postgresql: # create an engine and generate a table with fake feature data engine = create_engine(postgresql.url()) create_schemas(engine=engine, features_tables=features_tables, labels=labels, states=states) with TemporaryDirectory() as temp_dir: builder = builders.HighMemoryCSVBuilder( db_config=db_config, matrix_directory=temp_dir, engine=engine, ) # for each table, check that corresponding csv has the correct # of rows for table in features_tables: builder.write_to_csv( ''' select * from features.features{} '''.format(features_tables.index(table)), 'test_csv.csv') reader = csv.reader( builder.open_fh_for_reading('test_csv.csv')) assert (len([row for row in reader]) == len(table) + 1)
def test_nullcheck(self): f0_dict = {(r[0], r[1]): r for r in features0_pre} f1_dict = {(r[0], r[1]): r for r in features1_pre} features0 = sorted(f0_dict.values(), key=lambda x: (x[1], x[0])) features1 = sorted(f1_dict.values(), key=lambda x: (x[1], x[0])) features_tables = [features0, features1] with testing.postgresql.Postgresql() as postgresql: # create an engine and generate a table with fake feature data engine = create_engine(postgresql.url()) create_schemas(engine=engine, features_tables=features_tables, labels=labels, states=states) dates = [ datetime.datetime(2016, 1, 1, 0, 0), datetime.datetime(2016, 2, 1, 0, 0), datetime.datetime(2016, 3, 1, 0, 0) ] with TemporaryDirectory() as temp_dir: builder = builders.HighMemoryCSVBuilder( db_config=db_config, matrix_directory=temp_dir, engine=engine) feature_dictionary = { 'features0': ['f1', 'f2'], 'features1': ['f3', 'f4'], } matrix_metadata = { 'matrix_id': 'hi', 'state': 'state_one AND state_two', 'label_name': 'booking', 'end_time': datetime.datetime(2016, 3, 1, 0, 0), 'feature_start_time': datetime.datetime(2016, 1, 1, 0, 0), 'label_timespan': '1 month', 'test_duration': '1 month' } uuid = metta.generate_uuid(matrix_metadata) with self.assertRaises(ValueError): builder.build_matrix(as_of_times=dates, label_name='booking', label_type='binary', feature_dictionary=feature_dictionary, matrix_directory=temp_dir, matrix_metadata=matrix_metadata, matrix_uuid=uuid, matrix_type='test')
def test_train_matrix(self): with testing.postgresql.Postgresql() as postgresql: # create an engine and generate a table with fake feature data engine = create_engine(postgresql.url()) ensure_db(engine) create_schemas(engine=engine, features_tables=features_tables, labels=labels, states=states) dates = [ datetime.datetime(2016, 1, 1, 0, 0), datetime.datetime(2016, 2, 1, 0, 0), datetime.datetime(2016, 3, 1, 0, 0) ] with TemporaryDirectory() as temp_dir: builder = builders.HighMemoryCSVBuilder( db_config=db_config, matrix_directory=temp_dir, engine=engine) feature_dictionary = FeatureGroup(name='mygroup', features_by_table={ 'features0': ['f1', 'f2'], 'features1': ['f3', 'f4'], }) matrix_metadata = { 'matrix_id': 'hi', 'state': 'state_one AND state_two', 'label_name': 'booking', 'end_time': datetime.datetime(2016, 3, 1, 0, 0), 'feature_start_time': datetime.datetime(2016, 1, 1, 0, 0), 'label_timespan': '1 month', 'max_training_history': '1 month' } uuid = metta.generate_uuid(matrix_metadata) builder.build_matrix(as_of_times=dates, label_name='booking', label_type='binary', feature_dictionary=feature_dictionary, matrix_directory=temp_dir, matrix_metadata=matrix_metadata, matrix_uuid=uuid, matrix_type='train') matrix_filename = os.path.join(temp_dir, '{}.csv'.format(uuid)) with open(matrix_filename, 'r') as f: reader = csv.reader(f) assert (len([row for row in reader]) == 6)
def test_make_entity_date_table(): """ Test that the make_entity_date_table function contains the correct values. """ dates = [ datetime.datetime(2016, 1, 1, 0, 0), datetime.datetime(2016, 2, 1, 0, 0), datetime.datetime(2016, 3, 1, 0, 0) ] # make a dataframe of entity ids and dates to test against 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') with testing.postgresql.Postgresql() as postgresql: # create an engine and generate a table with fake feature data engine = create_engine(postgresql.url()) create_schemas(engine=engine, features_tables=features_tables, labels=labels, states=states) with TemporaryDirectory() as temp_dir: builder = builders.HighMemoryCSVBuilder(db_config=db_config, matrix_directory=temp_dir, engine=engine) engine.execute( 'CREATE TABLE features.tmp_entity_date (a int, b date);') # call the function to test the creation of the 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_uuid='my_uuid', matrix_type='train', label_timespan='1 month') # read in the table result = pd.read_sql( "select * from features.{} order by entity_id, as_of_date". format(entity_date_table_name), engine) # compare the table to the test dataframe test = (result == ids_dates) assert (test.all().all())
def test_badinput(self): """We assert column names, so replacing 'date' with 'as_of_date' should result in an error""" with TemporaryDirectory() as temp_dir: builder = builders.HighMemoryCSVBuilder( db_config=db_config, matrix_directory=temp_dir, engine=None, ) rowlists = [ [ ('entity_id', 'date', 'f1'), (1, 3, 3), (4, 5, 6), (7, 8, 9), ], [ ('entity_id', 'date', 'f2'), (1, 2, 3), (4, 5, 9), (7, 8, 15), ], [ ('entity_id', 'date', 'f3'), (1, 2, 2), (4, 5, 20), (7, 8, 56), ], ] filekeys = [] for rows in rowlists: filekey = uuid.uuid4() builder.open_fh_for_writing(filekey) filekeys.append(filekey) writer = csv.writer(builder.filehandles[filekey]) for row in rows: writer.writerow(row) with self.assertRaises(KeyError): builder.merge_feature_csvs(filekeys, matrix_directory=temp_dir, matrix_uuid='1234')
def test_write_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'])) # 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 TemporaryDirectory() as temp_dir: builder = builders.HighMemoryCSVBuilder( db_config=db_config, matrix_directory=temp_dir, 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)) features_csv_names = builder.write_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 feature_csv_name, df in zip(sorted(features_csv_names), features_dfs): df = df.reset_index() result = pd.read_csv(builder.open_fh_for_reading(feature_csv_name))\ .reset_index() result['as_of_date'] = convert_string_column_to_date( result['as_of_date']) test = (result == df) assert (test.all().all())
def test_make_entity_date_table_include_missing_labels(): """ Test that the make_entity_date_table function contains the correct values. """ dates = [ datetime.datetime(2016, 1, 1, 0, 0), datetime.datetime(2016, 2, 1, 0, 0), datetime.datetime(2016, 3, 1, 0, 0), datetime.datetime(2016, 6, 1, 0, 0) ] # same as the other make_entity_date_label test except there is an extra date, 2016-06-01 # entity 0 is included in this date via the states table, but has no label # make a dataframe of entity ids and dates to test against 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') # this line adds the new entity-date combo as an expected one ids_dates = ids_dates.append( { 'entity_id': 0, 'as_of_date': datetime.date(2016, 6, 1) }, ignore_index=True) with testing.postgresql.Postgresql() as postgresql: # create an engine and generate a table with fake feature data engine = create_engine(postgresql.url()) create_schemas(engine=engine, features_tables=features_tables, labels=labels, states=states) with TemporaryDirectory() as temp_dir: builder = builders.HighMemoryCSVBuilder( db_config=db_config, matrix_directory=temp_dir, include_missing_labels_in_train_as=False, engine=engine) engine.execute( 'CREATE TABLE features.tmp_entity_date (a int, b date);') # call the function to test the creation of the 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_uuid='my_uuid', matrix_type='train', label_timespan='1 month') # read in the table result = pd.read_sql( "select * from features.{} order by entity_id, as_of_date". format(entity_date_table_name), engine) # compare the table to the test dataframe assert sorted(result.values.tolist()) == sorted( ids_dates.values.tolist())