def test_converts_variable_type_after_init(self):
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.get_dataframe('test_entity')
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_converts_variable_type_after_init(self):
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.get_dataframe('test_entity')
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_converts_variable_types_on_init(self):
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.get_dataframe('test_entity')
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 test_converts_variable_types_on_init(self):
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.get_dataframe('test_entity')
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)