class SimpleImputer(Imputer):
r"""Implementation of simple imputer.
Date:
2020
Author:
Luka Pečnik
License:
MIT
Documentation:
https://scikit-learn.org/stable/modules/generated/sklearn.impute.SimpleImputer.html
See Also:
* :class:`niaaml.preprocessing.imputation.Imputer`
"""
Name = 'Simple Imputer'
def __init__(self, **kwargs):
r"""Initialize imputer.
"""
self.__simple_imputer = SI(missing_values=np.nan)
def fit(self, feature):
r"""Fit imputer.
Arguments:
feature (pandas.core.frame.DataFrame): A column from DataFrame of features.
"""
if feature.dtypes.iloc[0] != np.dtype(
'int64') or feature.dtypes.iloc[0] != np.dtype('float64'):
replacement_val = feature.mode().iloc[0, 0]
self.__simple_imputer.set_params(**{
'fill_value': replacement_val,
'strategy': 'constant'
})
self.__simple_imputer.fit(feature)
else:
self.__simple_imputer.fit(feature)
def transform(self, feature):
r"""Transform feature's values.
Arguments:
feature (pandas.core.frame.DataFrame): A column from DataFrame of features.
Returns:
pandas.core.frame.DataFrame: A transformed column.
"""
return self.__simple_imputer.transform(feature)
def to_string(self):
r"""User friendly representation of the object.
Returns:
str: User friendly representation of the object.
"""
return Imputer.to_string(self).format(name=self.Name)
def predictor_from_file(config_path, model_path):
with open(config_path, "rb") as f:
config_dict = json.load(f)
if config_dict["model_type"] == "neural_bandit":
# initialize the pytorch model and put it in `eval` mode
model = embed_dnn.EmbedDnn(**config_dict["model_spec"])
model.load_state_dict(torch.load(model_path))
model.eval()
else:
with open(model_path, "rb") as f:
model = pickle.load(f)
# initialize transforms
transforms = {}
for feature_name, transform_spec in config_dict["transforms"].items():
if transform_spec is None:
# id lists don't have transforms
transform = None
elif transform_spec["name"] == "StandardScaler":
transform = preprocessing.StandardScaler()
transform.mean_ = np.array(transform_spec["mean"])
transform.scale_ = np.array(transform_spec["scale"])
transform.var_ = np.array(transform_spec["var"])
elif transform_spec["name"] == "OneHotEncoder":
transform = preprocessing.OneHotEncoder()
transform.sparse = transform_spec["sparse"]
transform.categories_ = np.array(transform_spec["categories"])
else:
raise Exception(
f"Don't know how to load transform_spec of type {transform_spec['name']}"
)
transforms[feature_name] = transform
# initialize imputers
imputers = {}
for feature_name, imputer_spec in config_dict["imputers"].items():
if imputer_spec is None:
# categoricals & id lists don't have imputers
imputer = None
else:
imputer = SimpleImputer()
imputer.set_params(**imputer_spec["parameters"])
imputer.statistics_ = np.array(imputer_spec["statistics"])
imputers[feature_name] = imputer
return BanditPredictor(
feature_config=config_dict["feature_config"],
float_feature_order=config_dict["float_feature_order"],
id_feature_order=config_dict["id_feature_order"],
id_feature_str_to_int_map=config_dict["id_feature_str_to_int_map"],
transforms=transforms,
imputers=imputers,
model=model,
model_type=config_dict["model_type"],
reward_type=config_dict["reward_type"],
model_spec=config_dict["model_spec"],
dense_features_to_use=config_dict["dense_features_to_use"],
)
def get_imputer(self):
imputer = self.kwargs.get("imputer", self.IMPUTER)
if imputer == "SimpleImputer":
imputer_use = SimpleImputer()
if imputer == "KNNImputer":
imputer_use = KNNImputer()
imputer_params = self.kwargs.get("imputer_params", {})
self.mlflow_log_param("imputer", imputer)
imputer_use.set_params(**imputer_params)
print(colored(imputer_use.__class__.__name__, "blue"))
return imputer_use
def predictor_from_file(config_path, net_path):
with open(config_path, "rb") as f:
config_dict = json.load(f)
# initialize the pytorch model and put it in `eval` mode
net = embed_dnn.EmbedDnn(**config_dict["net_spec"])
net.load_state_dict(torch.load(net_path))
net.eval()
# initialize transforms
transforms = {}
for feature_name, transform_spec in config_dict["transforms"].items():
if transform_spec is None:
# id lists don't have transforms
transform = None
elif transform_spec["name"] == "StandardScaler":
transform = preprocessing.StandardScaler()
transform.mean_ = np.array(transform_spec["mean"])
transform.scale_ = np.array(transform_spec["scale"])
transform.var_ = np.array(transform_spec["var"])
elif transform_spec["name"] == "OneHotEncoder":
transform = preprocessing.OneHotEncoder()
transform.sparse = transform_spec["sparse"]
transform.categories_ = np.array(transform_spec["categories"])
else:
raise Exception(
f"Don't know how to load transform_spec of type {transform_spec['name']}"
)
transforms[feature_name] = transform
# initialize imputers
imputers = {}
for feature_name, imputer_spec in config_dict["imputers"].items():
if imputer_spec is None:
# id lists don't have imputers
imputer = None
else:
imputer = SimpleImputer()
imputer.set_params(**imputer_spec["parameters"])
imputer.statistics_ = np.array(imputer_spec["statistics"])
imputers[feature_name] = imputer
return BanditPredictor(
experiment_specific_params=config_dict["experiment_specific_params"],
float_feature_order=config_dict["float_feature_order"],
id_feature_order=config_dict["id_feature_order"],
transforms=transforms,
imputers=imputers,
net=net,
net_spec=config_dict["net_spec"],
)
class PandasSimpleImputer(TransformerMixin):
'''
Класс, представляющий имплементацию sklearn.impute.SimpleImputer,
которая возвращает pandas.DataFrame
'''
def __init__(self, *args, **kwargs):
self.imputer = SimpleImputer(*args, **kwargs)
def fit(self, X, y=None):
self.imputer.fit(X)
return self
def transform(self, X, y=None):
X[:] = self.imputer.transform(X)
return X
def fit_transform(self, X, y=None):
return self.fit(X).transform(X)
def set_params(self, **params):
self.imputer.set_params(**params)
return self
