def test_with_index():
df = pd.DataFrame(np.random.randint(0, 100, size=(100, 4)),
columns=list('ABCD'))
df = df.set_index(['A'])
n = FrametoArraySerializer()
a = n.serialize(df)
assert_frame_equal(df, n.deserialize(a))
def test_multiple_data_input_with_no_index_and_invalid_column(column):
df = pd.DataFrame(np.random.randint(0, 100, size=(100, 4)),
columns=list('ABCD'))
n = FrametoArraySerializer()
a = n.serialize(df[['B']])
b = n.serialize(df[['D']])
assert_frame_equal(df[column], n.deserialize([a, b], columns=column))
def test_with_nans():
df = pd.DataFrame(np.random.randint(0, 100, size=(100, 4)),
columns=list('ABCD'))
df['A'] = np.NaN
n = FrametoArraySerializer()
a = n.serialize(df)
assert_frame_equal_(df, n.deserialize(a))
def test_invalid_column_subset_with_index():
df = pd.DataFrame(np.random.randint(0, 100, size=(100, 4)),
columns=list('ABCD'))
df = df.set_index(['A'])
n = FrametoArraySerializer()
a = n.serialize(df)
expected = pd.DataFrame({'N': np.nan}, index=df.index)
assert_frame_equal(expected, n.deserialize(a, columns=['N']))
def test_multi_column_fail():
df = pd.DataFrame(data={'A': [1, 2, 3], 'B': [2, 3, 4], 'C': [3, 4, 5]})
df = df.set_index(['A'])
n = FrametoArraySerializer()
a = n.serialize(df)
with pytest.raises(Exception) as e:
n.deserialize(a, columns=['A', 'B'])
assert ('Duplicate' in str(e.value))
def test_multiple_data_input_different_columns(columns, index):
df = pd.DataFrame(np.random.randint(0, 100, size=(100, 4)),
columns=list('ABCD'))
if index:
df = df.set_index(['A'])
n = FrametoArraySerializer()
a = n.serialize(df[['B']])
b = n.serialize(df[['D']])
expected = df[['B']].append(df[['D']], ignore_index=not index)
assert_frame_equal(expected, n.deserialize([a, b], columns=columns))
def test_empty_columns():
df = pd.DataFrame(data={'A': [], 'B': [], 'C': []})
n = FrametoArraySerializer()
a = n.serialize(df)
assert_frame_equal(df, n.deserialize(a))
def test_empty_dataframe():
df = pd.DataFrame()
n = FrametoArraySerializer()
a = n.serialize(df)
assert_frame_equal(df, n.deserialize(a))