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.entity_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_variable_type_after_init():
df = pd.DataFrame({'id': [0, 1, 2],
'category': ['a', 'b', 'a'],
'ints': ['1', '2', '1']})
df["category"] = df["category"].astype("category")
entityset = EntitySet(id='test')
entityset.entity_from_dataframe(entity_id='test_entity', index='id',
dataframe=df)
e = entityset['test_entity']
df = entityset['test_entity'].df
e.convert_variable_type('ints', variable_types.Numeric)
assert isinstance(e['ints'], variable_types.Numeric)
assert df['ints'].dtype.name in variable_types.PandasTypes._pandas_numerics
e.convert_variable_type('ints', variable_types.Categorical)
assert isinstance(e['ints'], variable_types.Categorical)
e.convert_variable_type('ints', variable_types.Ordinal)
assert isinstance(e['ints'], variable_types.Ordinal)
e.convert_variable_type('ints', variable_types.Boolean,
true_val=1, false_val=2)
assert isinstance(e['ints'], variable_types.Boolean)
assert df['ints'].dtype.name == 'bool'
def test_check_variables_and_dataframe():
# matches
df = pd.DataFrame({'id': [0, 1, 2], 'category': ['a', 'b', 'a']})
vtypes = {'id': variable_types.Categorical,
'category': variable_types.Categorical}
entityset = EntitySet(id='test')
entityset.entity_from_dataframe('test_entity', df, index='id',
variable_types=vtypes)
assert entityset.entity_dict['test_entity'].variable_types['category'] == variable_types.Categorical
def test_none_index():
df = pd.DataFrame({'category': [1, 2, 3], 'category2': ['1', '2', '3']})
vtypes = {'category': variable_types.Categorical, 'category2': variable_types.Categorical}
entityset = EntitySet(id='test')
entityset.entity_from_dataframe(entity_id='test_entity',
dataframe=df,
variable_types=vtypes)
assert entityset['test_entity'].index == 'category'
assert isinstance(entityset['test_entity']['category'], variable_types.Index)
def test_bad_time_index_variable():
df = pd.DataFrame({'category': ['a', 'b', 'a']})
error_text = "Time index not found in dataframe"
with pytest.raises(LookupError, match=error_text):
entityset = EntitySet(id='test')
entityset.entity_from_dataframe(entity_id='test_entity',
index="id",
dataframe=df,
time_index='time')
def test_handles_datetime_mismatch():
# can't convert arbitrary strings
df = pd.DataFrame({'id': [0, 1, 2], 'time': ['a', 'b', 'tomorrow']})
vtypes = {'id': variable_types.Categorical,
'time': variable_types.Datetime}
with pytest.raises(ValueError):
entityset = EntitySet(id='test')
entityset.entity_from_dataframe('test_entity', df, 'id',
time_index='time', variable_types=vtypes)
def test_unknown_index():
# more variables
df = pd.DataFrame({'category': ['a', 'b', 'a']})
vtypes = {'category': variable_types.Categorical}
entityset = EntitySet(id='test')
entityset.entity_from_dataframe(entity_id='test_entity',
index='id',
variable_types=vtypes, dataframe=df)
assert entityset['test_entity'].index == 'id'
assert entityset['test_entity'].df['id'].tolist() == list(range(3))
def test_doesnt_remake_index():
# more variables
df = pd.DataFrame({'id': [0, 1, 2], 'category': ['a', 'b', 'a']})
error_text = "Cannot make index: index variable already present"
with pytest.raises(RuntimeError, match=error_text):
entityset = EntitySet(id='test')
entityset.entity_from_dataframe(entity_id='test_entity',
index='id',
make_index=True,
dataframe=df)
def test_datetime64_conversion():
df = pd.DataFrame({'id': [0, 1, 2],
'ints': ['1', '2', '1']})
df["time"] = pd.Timestamp.now()
df["time"] = df["time"].astype("datetime64[ns, UTC]")
entityset = EntitySet(id='test')
entityset.entity_from_dataframe(entity_id='test_entity', index='id',
dataframe=df)
vtype_time_index = variable_types.variable.DatetimeTimeIndex
entityset['test_entity'].convert_variable_type('time', vtype_time_index)
def test_extra_variable_type():
# more variables
df = pd.DataFrame({'id': [0, 1, 2], 'category': ['a', 'b', 'a']})
vtypes = {'id': variable_types.Categorical,
'category': variable_types.Categorical,
'category2': variable_types.Categorical}
with pytest.raises(LookupError):
entityset = EntitySet(id='test')
entityset.entity_from_dataframe(entity_id='test_entity',
index='id',
variable_types=vtypes, dataframe=df)
def test_make_index_variable_ordering():
df = pd.DataFrame({'id': [0, 1, 2], 'category': ['a', 'b', 'a']})
vtypes = {'id': variable_types.Categorical,
'category': variable_types.Categorical}
entityset = EntitySet(id='test')
entityset.entity_from_dataframe(entity_id='test_entity',
index='id1',
make_index=True,
variable_types=vtypes,
dataframe=df)
assert entityset.entity_dict['test_entity'].df.columns[0] == 'id1'
def test_make_time_index_keeps_original_sorting():
trips = {
'trip_id': [999 - i for i in range(1000)],
'flight_time': [datetime(1997, 4, 1) for i in range(1000)],
'flight_id': [1 for i in range(350)] + [2 for i in range(650)]
}
order = [i for i in range(1000)]
df = pd.DataFrame.from_dict(trips)
es = EntitySet('flights')
es.entity_from_dataframe("trips",
dataframe=df,
index="trip_id",
time_index='flight_time')
assert (es['trips'].df['trip_id'] == order).all()
es.normalize_entity(base_entity_id="trips",
new_entity_id="flights",
index="flight_id",
make_time_index=True)
assert (es['trips'].df['trip_id'] == order).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.entity_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():
# 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
}
es = EntitySet(id='test')
es.entity_from_dataframe(entity_id='test_entity',
index='id',
time_index="time",
variable_types=vtypes,
dataframe=df)
pd_col = es['test_entity'].df['time']
# assert type(es['test_entity']['time']) == variable_types.Datetime
assert type(pd_col[0]) == pd.Timestamp
def test_already_sorted_parameter():
transactions_df = pd.DataFrame({"id": [1, 2, 3, 4, 5, 6],
"transaction_time": [datetime(2014, 4, 6),
datetime(
2012, 4, 8),
datetime(
2012, 4, 8),
datetime(
2013, 4, 8),
datetime(
2015, 4, 8),
datetime(2016, 4, 9)]})
es = EntitySet(id='test')
es.entity_from_dataframe('t',
transactions_df,
index='id',
time_index="transaction_time",
already_sorted=True)
times = es["t"].df.transaction_time.tolist()
assert times == transactions_df.transaction_time.tolist()
def test_create_entity_from_dask_df(pd_es):
dask_es = EntitySet(id="dask_es")
log_dask = dd.from_pandas(pd_es["log"].df, npartitions=2)
dask_es = dask_es.entity_from_dataframe(
entity_id="log_dask",
dataframe=log_dask,
index="id",
time_index="datetime",
variable_types=pd_es["log"].variable_types)
pd.testing.assert_frame_equal(pd_es["log"].df,
dask_es["log_dask"].df.compute(),
check_like=True)
def test_already_sorted_parameter():
transactions_df = pd.DataFrame({
"id": [1, 2, 3, 4, 5, 6],
"transaction_time": [
datetime(2014, 4, 6),
datetime(2012, 4, 8),
datetime(2012, 4, 8),
datetime(2013, 4, 8),
datetime(2015, 4, 8),
datetime(2016, 4, 9)
]
})
es = EntitySet(id='test')
es.entity_from_dataframe('t',
transactions_df,
index='id',
time_index="transaction_time",
already_sorted=True)
times = es["t"].df.transaction_time.tolist()
assert times == transactions_df.transaction_time.tolist()
def test_calculates_statistics_on_init(self):
df = pd.DataFrame({'id': [0, 1, 2],
'time': [datetime(2011, 4, 9, 10, 31, 3 * i)
for i in range(3)],
'category': ['a', 'b', 'a'],
'number': [4, 5, 6],
'boolean': [True, False, True],
'boolean_with_nan': [True, False, np.nan]})
vtypes = {'id': variable_types.Categorical,
'time': variable_types.Datetime,
'category': variable_types.Categorical,
'number': variable_types.Numeric,
'boolean': variable_types.Boolean,
'boolean_with_nan': variable_types.Boolean}
entityset = EntitySet(id='test')
entityset.entity_from_dataframe('stats_test_entity', df, 'id',
variable_types=vtypes)
e = entityset["stats_test_entity"]
# numerics don't have nunique or percent_unique defined
for v in ['time', 'category', 'number']:
assert e[v].count == 3
for v in ['time', 'number']:
with pytest.raises(AttributeError):
e[v].nunique
with pytest.raises(AttributeError):
e[v].percent_unique
# 'id' column automatically parsed as id
assert e['id'].count == 3
# categoricals have nunique and percent_unique defined
assert e['category'].nunique == 2
assert e['category'].percent_unique == 2. / 3
# booleans have count and number of true/false labels defined
assert e['boolean'].count == 3
# assert e['boolean'].num_true == 3
assert e['boolean'].num_true == 2
assert e['boolean'].num_false == 1
def test_single_table_ks_entityset_dates_not_sorted():
ks_es = EntitySet(id="ks_es")
df = pd.DataFrame({"id": [0, 1, 2, 3],
"values": [1, 12, -34, 27],
"dates": [pd.to_datetime('2019-01-10'),
pd.to_datetime('2019-02-03'),
pd.to_datetime('2019-01-01'),
pd.to_datetime('2017-08-25')]})
primitives_list = ['absolute', 'is_weekend', 'year', 'day']
values_dd = ks.from_pandas(df)
vtypes = {
"id": ft.variable_types.Id,
"values": ft.variable_types.Numeric,
"dates": ft.variable_types.Datetime,
}
ks_es.entity_from_dataframe(entity_id="data",
dataframe=values_dd,
index="id",
time_index="dates",
variable_types=vtypes)
ks_fm, _ = ft.dfs(entityset=ks_es,
target_entity="data",
trans_primitives=primitives_list,
max_depth=1)
pd_es = ft.EntitySet(id="pd_es")
pd_es.entity_from_dataframe(entity_id="data",
dataframe=df,
index="id",
time_index="dates")
fm, _ = ft.dfs(entityset=pd_es,
target_entity="data",
trans_primitives=primitives_list,
max_depth=1)
pd.testing.assert_frame_equal(fm, ks_fm.to_pandas().set_index('id').loc[fm.index])
def test_create_entity_from_ks_df(pd_es):
cleaned_df = pd_to_ks_clean(pd_es["log"].df)
log_ks = ks.from_pandas(cleaned_df)
ks_es = EntitySet(id="ks_es")
ks_es = ks_es.entity_from_dataframe(
entity_id="log_ks",
dataframe=log_ks,
index="id",
time_index="datetime",
variable_types=pd_es["log"].variable_types
)
pd.testing.assert_frame_equal(cleaned_df, ks_es["log_ks"].df.to_pandas(), check_like=True)
def test_converts_variable_types_on_init():
df = pd.DataFrame({'id': [0, 1, 2],
'category': ['a', 'b', 'a'],
'category_int': [1, 2, 3],
'ints': ['1', '2', '3'],
'floats': ['1', '2', '3.0']})
df["category_int"] = df["category_int"].astype("category")
vtypes = {'id': variable_types.Categorical,
'ints': variable_types.Numeric,
'floats': variable_types.Numeric}
es = EntitySet(id='test')
es.entity_from_dataframe(entity_id='test_entity', index='id',
variable_types=vtypes, dataframe=df)
entity_df = es['test_entity'].df
assert entity_df['ints'].dtype.name in variable_types.PandasTypes._pandas_numerics
assert entity_df['floats'].dtype.name in variable_types.PandasTypes._pandas_numerics
# this is infer from pandas dtype
e = es["test_entity"]
assert isinstance(e['category_int'], variable_types.Categorical)
def test_converts_variable_types_on_init():
df = pd.DataFrame({'id': [0, 1, 2],
'category': ['a', 'b', 'a'],
'category_int': [1, 2, 3],
'ints': ['1', '2', '3'],
'floats': ['1', '2', '3.0']})
df["category_int"] = df["category_int"].astype("category")
vtypes = {'id': variable_types.Categorical,
'ints': variable_types.Numeric,
'floats': variable_types.Numeric}
entityset = EntitySet(id='test')
entityset.entity_from_dataframe(entity_id='test_entity', index='id',
variable_types=vtypes, dataframe=df)
entity_df = entityset['test_entity'].df
assert entity_df['ints'].dtype.name in variable_types.PandasTypes._pandas_numerics
assert entity_df['floats'].dtype.name in variable_types.PandasTypes._pandas_numerics
# this is infer from pandas dtype
e = entityset["test_entity"]
assert isinstance(e['category_int'], variable_types.Categorical)
def datetime_es():
cards_df = pd.DataFrame({"id": [1, 2, 3, 4, 5]})
transactions_df = pd.DataFrame({"id": [1, 2, 3, 4, 5],
"card_id": [1, 1, 5, 1, 5],
"transaction_time": pd.to_datetime([
'2011-2-28 04:00', '2012-2-28 05:00',
'2012-2-29 06:00', '2012-3-1 08:00',
'2014-4-1 10:00']),
"fraud": [True, False, False, False, True]})
datetime_es = EntitySet(id="fraud_data")
datetime_es = datetime_es.entity_from_dataframe(entity_id="transactions",
dataframe=transactions_df,
index="id",
time_index="transaction_time")
datetime_es = datetime_es.entity_from_dataframe(entity_id="cards",
dataframe=cards_df,
index="id")
relationship = Relationship(datetime_es["cards"]["id"], datetime_es["transactions"]["card_id"])
datetime_es = datetime_es.add_relationship(relationship)
datetime_es.add_last_time_indexes()
return datetime_es
def test_custom_variable_descriptions():
class ItemList(Categorical):
type_string = "item_list"
_default_pandas_dtype = list
es = EntitySet()
variables = {
'item_list': ItemList,
'time_index': TimeIndex,
'index': Index
}
dataframe = pd.DataFrame(columns=list(variables))
es.entity_from_dataframe('custom_variable',
dataframe,
index='index',
time_index='time_index',
variable_types=variables)
entity = es['custom_variable']
for variable in entity.variables:
description = variable.to_data_description()
_variable = deserialize.description_to_variable(description,
entity=entity)
assert variable.__eq__(_variable)
def test_sets_time_when_adding_entity():
transactions_df = pd.DataFrame({
"id": [1, 2, 3, 4, 5, 6],
"card_id": [1, 2, 1, 3, 4, 5],
"transaction_time": [10, 12, 13, 20, 21, 20],
"fraud": [True, False, False, False, True, True]
})
accounts_df = pd.DataFrame({
"id": [3, 4, 5],
"signup_date":
[datetime(2002, 5, 1),
datetime(2006, 3, 20),
datetime(2011, 11, 11)]
})
accounts_df_string = pd.DataFrame({
"id": [3, 4, 5],
"signup_date": ["element", "exporting", "editable"]
})
# create empty entityset
es = EntitySet("fraud")
# assert it's not set
assert getattr(es, "time_type", None) is None
# add entity
es.entity_from_dataframe("transactions",
transactions_df,
index="id",
time_index="transaction_time")
# assert time_type is set
assert es.time_type == variable_types.NumericTimeIndex
# add another entity
es.normalize_entity("transactions",
"cards",
"card_id",
make_time_index=True)
# assert time_type unchanged
assert es.time_type == variable_types.NumericTimeIndex
# add wrong time type entity
error_text = "accounts time index is <class 'featuretools.variable_types.variable.DatetimeTimeIndex'> type which differs from other entityset time indexes"
with pytest.raises(TypeError, match=error_text):
es.entity_from_dataframe("accounts",
accounts_df,
index="id",
time_index="signup_date")
# add non time type as time index
error_text = "Attempted to convert all string column signup_date to numeric"
with pytest.raises(TypeError, match=error_text):
es.entity_from_dataframe("accounts",
accounts_df_string,
index="id",
time_index="signup_date")
def test_sets_time_when_adding_entity(self):
transactions_df = pd.DataFrame({
"id": [1, 2, 3, 4, 5, 6],
"card_id": [1, 2, 1, 3, 4, 5],
"transaction_time": [10, 12, 13, 20, 21, 20],
"fraud": [True, False, False, False, True, True]
})
accounts_df = pd.DataFrame({
"id": [3, 4, 5],
"signup_date": [
datetime(2002, 5, 1),
datetime(2006, 3, 20),
datetime(2011, 11, 11)
]
})
accounts_df_string = pd.DataFrame({
"id": [3, 4, 5],
"signup_date": ["element", "exporting", "editable"]
})
# create empty entityset
entityset = EntitySet("fraud")
# assert it's not set
assert getattr(entityset, "time_type", None) is None
# add entity
entityset.entity_from_dataframe("transactions",
transactions_df,
index="id",
time_index="transaction_time")
# assert time_type is set
assert entityset.time_type == variable_types.NumericTimeIndex
# add another entity
entityset.normalize_entity("transactions",
"cards",
"card_id",
make_time_index=True)
# assert time_type unchanged
assert entityset.time_type == variable_types.NumericTimeIndex
# add wrong time type entity
with pytest.raises(TypeError):
entityset.entity_from_dataframe("accounts",
accounts_df,
index="id",
time_index="signup_date")
# add non time type as time index
with pytest.raises(TypeError):
entityset.entity_from_dataframe("accounts",
accounts_df_string,
index="id",
time_index="signup_date")
def test_sets_time_when_adding_entity():
transactions_df = pd.DataFrame({"id": [1, 2, 3, 4, 5, 6],
"card_id": [1, 2, 1, 3, 4, 5],
"transaction_time": [10, 12, 13, 20, 21, 20],
"fraud": [True, False, False, False, True, True]})
accounts_df = pd.DataFrame({"id": [3, 4, 5],
"signup_date": [datetime(2002, 5, 1),
datetime(2006, 3, 20),
datetime(2011, 11, 11)]})
accounts_df_string = pd.DataFrame({"id": [3, 4, 5],
"signup_date": ["element",
"exporting",
"editable"]})
# create empty entityset
entityset = EntitySet("fraud")
# assert it's not set
assert getattr(entityset, "time_type", None) is None
# add entity
entityset.entity_from_dataframe("transactions",
transactions_df,
index="id",
time_index="transaction_time")
# assert time_type is set
assert entityset.time_type == variable_types.NumericTimeIndex
# add another entity
entityset.normalize_entity("transactions",
"cards",
"card_id",
make_time_index=True)
# assert time_type unchanged
assert entityset.time_type == variable_types.NumericTimeIndex
# add wrong time type entity
error_text = "accounts time index is <class 'featuretools.variable_types.variable.DatetimeTimeIndex'> type which differs from other entityset time indexes"
with pytest.raises(TypeError, match=error_text):
entityset.entity_from_dataframe("accounts",
accounts_df,
index="id",
time_index="signup_date")
# add non time type as time index
error_text = "Attempted to convert all string column signup_date to numeric"
with pytest.raises(TypeError, match=error_text):
entityset.entity_from_dataframe("accounts",
accounts_df_string,
index="id",
time_index="signup_date")
def test_sets_time_when_adding_entity(self):
transactions_df = pd.DataFrame({"id": [1, 2, 3, 4, 5, 6],
"card_id": [1, 2, 1, 3, 4, 5],
"transaction_time": [10, 12, 13, 20, 21, 20],
"fraud": [True, False, False, False, True, True]})
accounts_df = pd.DataFrame({"id": [3, 4, 5],
"signup_date": [datetime(2002, 5, 1),
datetime(2006, 3, 20),
datetime(2011, 11, 11)]})
accounts_df_string = pd.DataFrame({"id": [3, 4, 5],
"signup_date": ["element",
"exporting",
"editable"]})
# create empty entityset
entityset = EntitySet("fraud")
# assert it's not set
assert getattr(entityset, "time_type", None) is None
# add entity
entityset.entity_from_dataframe("transactions",
transactions_df,
index="id",
time_index="transaction_time")
# assert time_type is set
assert entityset.time_type == variable_types.NumericTimeIndex
# add another entity
entityset.normalize_entity("transactions",
"cards",
"card_id",
make_time_index=True)
# assert time_type unchanged
assert entityset.time_type == variable_types.NumericTimeIndex
# add wrong time type entity
with pytest.raises(TypeError):
entityset.entity_from_dataframe("accounts",
accounts_df,
index="id",
time_index="signup_date")
# add non time type as time index
with pytest.raises(TypeError):
entityset.entity_from_dataframe("accounts",
accounts_df_string,
index="id",
time_index="signup_date")
def test_single_table_ks_entityset_cutoff_time_df():
primitives_list = [
'absolute', 'is_weekend', 'year', 'day', 'num_characters', 'num_words'
]
ks_es = EntitySet(id="ks_es")
df = pd.DataFrame({
"id": [0, 1, 2],
"values": [1, 12, -34],
"dates": [
pd.to_datetime('2019-01-10'),
pd.to_datetime('2019-02-03'),
pd.to_datetime('2019-01-01')
],
"strings": ["I am a string", "23", "abcdef ghijk"]
})
values_dd = ks.from_pandas(df)
vtypes = {
"id": ft.variable_types.Id,
"values": ft.variable_types.Numeric,
"dates": ft.variable_types.Datetime,
"strings": ft.variable_types.NaturalLanguage
}
ks_es.entity_from_dataframe(entity_id="data",
dataframe=values_dd,
index="id",
time_index="dates",
variable_types=vtypes)
ids = [0, 1, 2, 0]
times = [
pd.Timestamp("2019-01-05 04:00"),
pd.Timestamp("2019-01-05 04:00"),
pd.Timestamp("2019-01-05 04:00"),
pd.Timestamp("2019-01-15 04:00")
]
labels = [True, False, True, False]
cutoff_times = pd.DataFrame({
"id": ids,
"time": times,
"labels": labels
},
columns=["id", "time", "labels"])
ks_fm, _ = ft.dfs(entityset=ks_es,
target_entity="data",
trans_primitives=primitives_list,
cutoff_time=cutoff_times)
pd_es = ft.EntitySet(id="pd_es")
pd_es.entity_from_dataframe(
entity_id="data",
dataframe=df,
index="id",
time_index="dates",
variable_types={"strings": ft.variable_types.NaturalLanguage})
fm, _ = ft.dfs(entityset=pd_es,
target_entity="data",
trans_primitives=primitives_list,
cutoff_time=cutoff_times)
# Because row ordering with koalas is not guaranteed, `we need to sort on two columns to make sure that values
# for instance id 0 are compared correctly. Also, make sure the boolean column has the same dtype.
fm = fm.sort_values(['id', 'labels'])
ks_fm = ks_fm.to_pandas().set_index('id').sort_values(['id', 'labels'])
ks_fm['IS_WEEKEND(dates)'] = ks_fm['IS_WEEKEND(dates)'].astype(
fm['IS_WEEKEND(dates)'].dtype)
pd.testing.assert_frame_equal(fm, ks_fm)
def test_add_last_time_indexes():
pd_es = EntitySet(id="pd_es")
dask_es = EntitySet(id="dask_es")
sessions = pd.DataFrame({
"id": [0, 1, 2, 3],
"user": [1, 2, 1, 3],
"time": [
pd.to_datetime('2019-01-10'),
pd.to_datetime('2019-02-03'),
pd.to_datetime('2019-01-01'),
pd.to_datetime('2017-08-25')
],
"strings": ["I am a string", "23", "abcdef ghijk", ""]
})
sessions_dask = dd.from_pandas(sessions, npartitions=2)
sessions_vtypes = {
"id": ft.variable_types.Id,
"user": ft.variable_types.Id,
"time": ft.variable_types.DatetimeTimeIndex,
"strings": ft.variable_types.NaturalLanguage
}
transactions = pd.DataFrame({
"id": [0, 1, 2, 3, 4, 5],
"session_id": [0, 0, 1, 2, 2, 3],
"amount": [1.23, 5.24, 123.52, 67.93, 40.34, 50.13],
"time": [
pd.to_datetime('2019-01-10 03:53'),
pd.to_datetime('2019-01-10 04:12'),
pd.to_datetime('2019-02-03 10:34'),
pd.to_datetime('2019-01-01 12:35'),
pd.to_datetime('2019-01-01 12:49'),
pd.to_datetime('2017-08-25 04:53')
]
})
transactions_dask = dd.from_pandas(transactions, npartitions=2)
transactions_vtypes = {
"id": ft.variable_types.Id,
"session_id": ft.variable_types.Id,
"amount": ft.variable_types.Numeric,
"time": ft.variable_types.DatetimeTimeIndex,
}
pd_es.entity_from_dataframe(entity_id="sessions",
dataframe=sessions,
index="id",
time_index="time")
dask_es.entity_from_dataframe(entity_id="sessions",
dataframe=sessions_dask,
index="id",
time_index="time",
variable_types=sessions_vtypes)
pd_es.entity_from_dataframe(entity_id="transactions",
dataframe=transactions,
index="id",
time_index="time")
dask_es.entity_from_dataframe(entity_id="transactions",
dataframe=transactions_dask,
index="id",
time_index="time",
variable_types=transactions_vtypes)
new_rel = Relationship(pd_es["sessions"]["id"],
pd_es["transactions"]["session_id"])
dask_rel = Relationship(dask_es["sessions"]["id"],
dask_es["transactions"]["session_id"])
pd_es = pd_es.add_relationship(new_rel)
dask_es = dask_es.add_relationship(dask_rel)
assert pd_es['sessions'].last_time_index is None
assert dask_es['sessions'].last_time_index is None
pd_es.add_last_time_indexes()
dask_es.add_last_time_indexes()
pd.testing.assert_series_equal(
pd_es['sessions'].last_time_index.sort_index(),
dask_es['sessions'].last_time_index.compute(),
check_names=False)