def _update_type(df, added_cols):
indices = list()
for key in added_cols:
indices.append(df.columns.get_loc(key))
for idx in indices:
old_metadata = dict(df.metadata.query((mbase.ALL_ELEMENTS, idx)))
numerics = pd.to_numeric(df.iloc[:, idx], errors='coerce')
length = numerics.shape[0]
nans = numerics.isnull().sum()
if nans / length > 0.9:
if HelperFunction.is_categorical(df.iloc[:, idx]):
old_metadata['semantic_types'] = (
"https://metadata.datadrivendiscovery.org/types/CategoricalData",)
else:
old_metadata['semantic_types'] = ("http://schema.org/Text",)
old_metadata['structural_type'] = type("type")
else:
intcheck = (numerics % 1) == 0
if np.sum(intcheck) / length > 0.9:
old_metadata['semantic_types'] = ("http://schema.org/Integer",)
old_metadata['structural_type'] = type(10)
else:
old_metadata['semantic_types'] = ("http://schema.org/Float",)
old_metadata['structural_type'] = type(10.1)
old_metadata['semantic_types'] += ("https://metadata.datadrivendiscovery.org/types/Attribute",)
df.metadata = df.metadata.update((mbase.ALL_ELEMENTS, idx), old_metadata)
return df
def update_types(self, col_name):
old_metadata = dict(
self.df.metadata.query(
(mbase.ALL_ELEMENTS, self.df.columns.get_loc(col_name))))
numerics = pd.to_numeric(self.df[col_name], errors='coerce')
length = numerics.shape[0]
nans = numerics.isnull().sum()
if nans / length > 0.9:
if HelperFunction.is_categorical(self.df[col_name]):
old_metadata['semantic_types'] = (
"https://metadata.datadrivendiscovery.org/types/CategoricalData",
)
else:
old_metadata['semantic_types'] = ("http://schema.org/Text", )
else:
intcheck = (numerics % 1) == 0
if np.sum(intcheck) / length > 0.9:
old_metadata['semantic_types'] = (
"http://schema.org/Integer", )
else:
old_metadata['semantic_types'] = ("http://schema.org/Float", )
old_metadata['semantic_types'] += \
("https://metadata.datadrivendiscovery.org/types/Attribute",)
self.df.metadata = self.df.metadata.update(
(mbase.ALL_ELEMENTS, self.df.columns.get_loc(col_name)),
old_metadata)
def _relabel_categorical(inputs: Input) -> Output:
for col in range(inputs.shape[1]):
old_metadata = dict(inputs.metadata.query((mbase.ALL_ELEMENTS, col)))
semantic_type = old_metadata.get('semantic_types', [])
if 'https://metadata.datadrivendiscovery.org/types/CategoricalData' in semantic_type:
if not HelperFunction.is_categorical(inputs.iloc[:, col]):
old_metadata['semantic_types'] = tuple(i for i in old_metadata['semantic_types'] if
i != 'https://metadata.datadrivendiscovery.org/types/CategoricalData')
numerics = pd.to_numeric(inputs.iloc[:, col], errors='coerce')
length = numerics.shape[0]
nans = numerics.isnull().sum()
if nans / length > 0.9:
if "http://schema.org/Text" not in old_metadata['semantic_types']:
old_metadata['semantic_types'] += ("http://schema.org/Text",)
else:
intcheck = (numerics % 1) == 0
if np.sum(intcheck) / length > 0.9:
if "http://schema.org/Integer" not in old_metadata['semantic_types']:
old_metadata['semantic_types'] += ("http://schema.org/Integer",)
# old_metadata['structural_type'] = type(10)
# inputs.iloc[:, col] = numerics
else:
if "http://schema.org/Float" not in old_metadata['semantic_types']:
old_metadata['semantic_types'] += ("http://schema.org/Float",)
# old_metadata['structural_type'] = type(10.2)
# inputs.iloc[:, col] = numerics
inputs.metadata = inputs.metadata.update((mbase.ALL_ELEMENTS, col), old_metadata)
return inputs
def _update_structural_type(self):
for col in range(self._input_data_copy.shape[1]):
old_metadata = dict(
self._input_data_copy.metadata.query(
(mbase.ALL_ELEMENTS, col)))
semantic_type = old_metadata.get('semantic_types', None)
if not semantic_type:
numerics = pd.to_numeric(self._input_data_copy.iloc[:, col],
errors='coerce')
length = numerics.shape[0]
nans = numerics.isnull().sum()
if nans / length > 0.9:
if HelperFunction.is_categorical(
self._input_data_copy.iloc[:, col]):
old_metadata['semantic_types'] = (
"https://metadata.datadrivendiscovery.org/types/CategoricalData",
)
else:
old_metadata['semantic_types'] = (
"http://schema.org/Text", )
else:
intcheck = (numerics % 1) == 0
if np.sum(intcheck) / length > 0.9:
old_metadata['semantic_types'] = (
"http://schema.org/Integer", )
old_metadata['structural_type'] = type(10)
self._input_data_copy.iloc[:, col] = numerics
else:
old_metadata['semantic_types'] = (
"http://schema.org/Float", )
old_metadata['structural_type'] = type(10.2)
self._input_data_copy.iloc[:, col] = numerics
old_metadata['semantic_types'] += (
"https://metadata.datadrivendiscovery.org/types/Attribute",
)
else:
if "http://schema.org/Integer" in semantic_type:
self._input_data_copy.iloc[:, col] = pd.to_numeric(
self._input_data_copy.iloc[:, col], errors='coerce')
old_metadata['structural_type'] = type(10)
elif "http://schema.org/Float" in semantic_type:
self._input_data_copy.iloc[:, col] = pd.to_numeric(
self._input_data_copy.iloc[:, col], errors='coerce')
old_metadata['structural_type'] = type(10.2)
self._input_data_copy.metadata = self._input_data_copy.metadata.update(
(mbase.ALL_ELEMENTS, col), old_metadata)
def update_type(extends, df_origin):
extends_df = pd.DataFrame.from_dict(extends)
extends_df = d3m_DataFrame(extends_df, generate_metadata=True)
if extends != {}:
extends_df.index = df_origin.index.copy()
new_df = d3m_DataFrame.append_columns(df_origin, extends_df)
indices = list()
for key in extends:
indices.append(new_df.columns.get_loc(key))
for idx in indices:
old_metadata = dict(new_df.metadata.query((mbase.ALL_ELEMENTS, idx)))
numerics = pd.to_numeric(new_df.iloc[:, idx], errors='coerce')
length = numerics.shape[0]
nans = numerics.isnull().sum()
if nans / length > 0.9:
if HelperFunction.is_categorical(new_df.iloc[:, idx]):
old_metadata['semantic_types'] = (
"https://metadata.datadrivendiscovery.org/types/CategoricalData",
)
else:
old_metadata['semantic_types'] = ("http://schema.org/Text", )
else:
intcheck = (numerics % 1) == 0
if np.sum(intcheck) / length > 0.9:
old_metadata['semantic_types'] = (
"http://schema.org/Integer", )
else:
old_metadata['semantic_types'] = ("http://schema.org/Float", )
old_metadata['semantic_types'] += (
"https://metadata.datadrivendiscovery.org/types/Attribute", )
new_df.metadata = new_df.metadata.update((mbase.ALL_ELEMENTS, idx),
old_metadata)
return new_df
