def test_replace_dataframe_different_dataframe_types():
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_logical_types = {
"id": Integer,
"user": Integer,
"time": Datetime,
"strings": NaturalLanguage
}
sessions_semantic_tags = {'user': '******'}
dask_es.add_dataframe(dataframe_name="sessions",
dataframe=sessions_dask,
index="id",
time_index="time",
logical_types=sessions_logical_types,
semantic_tags=sessions_semantic_tags)
with pytest.raises(TypeError, match='Incorrect DataFrame type used'):
dask_es.replace_dataframe('sessions', sessions)
def test_replace_dataframe():
df = pd.DataFrame({
'id':
range(4),
'full_name':
['Mr. John Doe', 'Doe, Mrs. Jane', 'James Brown', 'Ms. Paige Turner'],
'email': [
'*****@*****.**', np.nan, '*****@*****.**',
'*****@*****.**'
],
'phone_number':
['5555555555', '555-555-5555', '1-(555)-555-5555', '555-555-5555'],
'age':
pd.Series([33, None, 33, 57], dtype='Int64'),
'signup_date': [pd.to_datetime('2020-09-01')] * 4,
'is_registered':
pd.Series([True, False, True, None], dtype='boolean'),
})
df.ww.init(name='table', index='id')
es = EntitySet('es')
es.add_dataframe(df)
original_schema = es['table'].ww.schema
new_df = df.iloc[2:]
es.replace_dataframe('table', new_df)
assert len(es['table']) == 2
assert es['table'].ww.schema == original_schema
def test_replace_dataframe_data_transformation(latlong_df):
initial_df = latlong_df.copy()
initial_df.ww.init(
name='latlongs',
index='string_tuple',
logical_types={col_name: 'LatLong'
for col_name in initial_df.columns})
es = EntitySet()
es.add_dataframe(dataframe=initial_df)
df = to_pandas(es['latlongs'])
expected_val = (1, 2)
if ks and isinstance(es['latlongs'], ks.DataFrame):
expected_val = [1, 2]
for col in latlong_df.columns:
series = df[col]
assert series.iloc[0] == expected_val
es.replace_dataframe('latlongs', latlong_df)
df = to_pandas(es['latlongs'])
expected_val = (3, 4)
if ks and isinstance(es['latlongs'], ks.DataFrame):
expected_val = [3, 4]
for col in latlong_df.columns:
series = df[col]
assert series.iloc[-1] == expected_val
def test_replace_dataframe():
df = pd.DataFrame({
"id":
range(4),
"full_name": [
"Mr. John Doe",
"Doe, Mrs. Jane",
"James Brown",
"Ms. Paige Turner",
],
"email": [
"*****@*****.**",
np.nan,
"*****@*****.**",
"*****@*****.**",
],
"phone_number": [
"5555555555",
"555-555-5555",
"1-(555)-555-5555",
"555-555-5555",
],
"age":
pd.Series([33, None, 33, 57], dtype="Int64"),
"signup_date": [pd.to_datetime("2020-09-01")] * 4,
"is_registered":
pd.Series([True, False, True, None], dtype="boolean"),
})
df.ww.init(name="table", index="id")
es = EntitySet("es")
es.add_dataframe(df)
original_schema = es["table"].ww.schema
new_df = df.iloc[2:]
es.replace_dataframe("table", new_df)
assert len(es["table"]) == 2
assert es["table"].ww.schema == original_schema