def test_handles_datetime_format():
# check if we load according to the format string
# pass in an ambigious date
datetime_format = "%d-%m-%Y"
actual = pd.Timestamp('Jan 2, 2011')
time_strs = [actual.strftime(datetime_format)] * 3
df = pd.DataFrame({
'id': [0, 1, 2],
'time_format': time_strs,
'time_no_format': time_strs
})
vtypes = {
'id': variable_types.Categorical,
'time_format': (variable_types.Datetime, {
"format": datetime_format
}),
'time_no_format': variable_types.Datetime
}
entityset = EntitySet(id='test')
entityset._import_from_dataframe(entity_id='test_entity',
index='id',
variable_types=vtypes,
dataframe=df)
col_format = entityset['test_entity'].df['time_format']
col_no_format = entityset['test_entity'].df['time_no_format']
# without formatting pandas gets it wrong
assert (col_no_format != actual).all()
# with formatting we correctly get jan2
assert (col_format == actual).all()
def test_converts_datetime():
# string converts to datetime correctly
# This test fails without defining vtypes. Entityset
# infers time column should be numeric type
times = pd.date_range('1/1/2011', periods=3, freq='H')
time_strs = times.strftime('%Y-%m-%d')
df = pd.DataFrame({'id': [0, 1, 2], 'time': time_strs})
vtypes = {'id': variable_types.Categorical,
'time': variable_types.Datetime}
entityset = EntitySet(id='test')
entityset._import_from_dataframe(entity_id='test_entity', index='id',
time_index="time", variable_types=vtypes,
dataframe=df)
pd_col = entityset['test_entity'].df['time']
# assert type(entityset['test_entity']['time']) == variable_types.Datetime
assert type(pd_col[0]) == pd.Timestamp
def test_converts_datetime(self):
# string converts to datetime correctly
# This test fails without defining vtypes. Entityset
# infers time column should be numeric type
times = pd.date_range('1/1/2011', periods=3, freq='H')
time_strs = times.strftime('%Y-%m-%d')
df = pd.DataFrame({'id': [0, 1, 2], 'time': time_strs})
vtypes = {'id': variable_types.Categorical,
'time': variable_types.Datetime}
entityset = EntitySet(id='test')
entityset._import_from_dataframe(entity_id='test_entity', index='id',
time_index="time", variable_types=vtypes,
dataframe=df)
pd_col = entityset.get_column_data('test_entity', 'time')
# assert type(es['test_entity']['time']) == variable_types.Datetime
assert type(pd_col[0]) == pd.Timestamp
def test_handles_datetime_format():
# check if we load according to the format string
# pass in an ambigious date
datetime_format = "%d-%m-%Y"
actual = pd.Timestamp('Jan 2, 2011')
time_strs = [actual.strftime(datetime_format)] * 3
df = pd.DataFrame(
{'id': [0, 1, 2], 'time_format': time_strs, 'time_no_format': time_strs})
vtypes = {'id': variable_types.Categorical,
'time_format': (variable_types.Datetime, {"format": datetime_format}),
'time_no_format': variable_types.Datetime}
entityset = EntitySet(id='test')
entityset._import_from_dataframe(entity_id='test_entity', index='id',
variable_types=vtypes, dataframe=df)
col_format = entityset['test_entity'].df['time_format']
col_no_format = entityset['test_entity'].df['time_no_format']
# without formatting pandas gets it wrong
assert (col_no_format != actual).all()
# with formatting we correctly get jan2
assert (col_format == actual).all()