def test_collate_data_function():
def f(x):
return pd.read_csv(x).iloc[:10, :3]
df = collate_data("tests/data/NASDAQ/data", function=f)
assert len(df) == 80
assert df.shape == (80, 3)
def test_collate_data():
df = collate_data("tests/data/NASDAQ/data", parse_dates=["Date"])
df = df.rename(lambda x: x.lower(), axis="columns")
df = df.sort_values(by=["date", "symbol"])
engine = create_engine("sqlite://")
dl = DataLoader(directory="tests/data/NASDAQ/data",
mode="SQL",
engine=engine,
tablename="eod")
dl.load_data()
df2 = pd.read_sql_table("eod", engine).sort_values(by=["date", "symbol"])
assert len(df) == len(df2)
for i in range(100):
assert compare(df, df2)
def test_collate_data():
df = collate_data('tests/data/NASDAQ/data', parse_dates=['Date'])
df = df.rename(lambda x: x.lower(), axis='columns')
df = df.sort_values(by=['date', 'symbol'])
engine = create_engine('sqlite://')
dl = DataLoader(directory='tests/data/NASDAQ/data',
mode='SQL',
engine=engine,
tablename='eod')
dl.load_data()
df2 = pd.read_sql_table('eod', engine).sort_values(by=['date', 'symbol'])
assert len(df) == len(df2)
for i in range(100):
assert compare(df, df2)
def test_collate_data_concat_false_two():
df = collate_data("tests/data/NASDAQ/data",
function=lambda x: x.split("/")[-1],
concat=False)
assert len(df) == 8
assert "NASDAQ_20180731.zip" in df
def test_collate_data_concat_false_one():
def f(x):
return pd.read_csv(x).iloc[:10, :3]
df = collate_data("tests/data/NASDAQ/data", function=f, concat=False)
assert len(df) == 8
def test_collate_data_concat_false_two():
df = collate_data('tests/data/NASDAQ/data',
function=lambda x: x.split('/')[-1],
concat=False)
assert len(df) == 8
assert 'NASDAQ_20180731.zip' in df