def test_ReadPandas_pkl():
# create pickle version of table from CSV table
df = pd.read_csv('tests/data/pandas_table.csv')
df.to_pickle('tests/data/pandas_table.pkl')
for ext in ['.pkl', '.csv', '.tsv', '.xlsx']:
filepath = 'tests/data/pandas_table' + ext
samples = ReadPandas(filepath, dropnan=True) >> Collect()
nt.assert_equal(samples, [[1, 4], [3, 6]])
samples = ReadPandas(filepath, dropnan=False) >> Collect()
nt.assert_equal(samples, [[1, 4], [2, np.NaN], [3, 6]])
samples = ReadPandas(filepath, replacenan=None) >> Collect()
nt.assert_equal(samples, [[1, 4], [2, None], [3, 6]])
samples = ReadPandas(filepath, columns=['col1', 'col2']) >> Collect()
nt.assert_equal(samples, [[1, 4], [3, 6]])
samples = ReadPandas(filepath, columns=['col1']) >> Collect()
nt.assert_equal(samples, [[1], [2], [3]])
samples = ReadPandas(filepath, columns=['col2']) >> Collect()
nt.assert_equal(samples, [[4], [6]])
samples = ReadPandas(filepath, columns=['col2'],
replacenan='NA') >> Collect()
nt.assert_equal(samples, [[4], ['NA'], [6]])
samples = ReadPandas(filepath, rows='col1 > 1',
replacenan=0) >> Collect()
nt.assert_equal(samples, [[2, 0], [3, 6]])
samples = ReadPandas(filepath, rows='col1 < 3',
columns=['col1']) >> Collect()
nt.assert_equal(samples, [[1], [2]])
def test_ReadPandas_dply():
filepath = 'tests/data/pandas_table.csv'
samples = (
ReadPandas(filepath).dply() >> dp.select(dp.X.col1) >> DplyToList())
nt.assert_equal(samples, [[1], [2], [3]])