def test_transform(self):
"""
Check transform
"""
# training data
d = {
"col1": [1, 2, 3, np.nan, np.nan],
"col2": ["a", "a", np.nan, "a", "c"],
"col3": [1, 1, 3, 1, 1],
"col4": ["a", "a", "a", "c", "a"],
}
df = pd.DataFrame(data=d)
# test data
d_test = {
"col1": [1, 2, 3, np.nan, np.nan],
"col2": ["b", "b", np.nan, "b", "c"],
"col3": [1, 2, 2, np.nan, 2],
"col4": ["b", "b", np.nan, "b", "c"],
}
df_test = pd.DataFrame(data=d_test)
# fill with median
preprocess_missing = PreprocessingMissingValues(
df.columns, PreprocessingMissingValues.FILL_NA_MEDIAN)
preprocess_missing.fit(df)
self.assertEqual(2, len(preprocess_missing._na_fill_params)
) # there should be only two columns
df_transformed = preprocess_missing.transform(df_test)
self.assertTrue(np.isnan(
df.loc[3, "col1"])) # training data frame is not filled
self.assertEqual(
2, df_test.loc[3, "col1"]) # data frame is filled after transform
self.assertEqual("a", df_test.loc[2, "col2"])
def from_json(self, data_json):
if "remove_columns" in data_json:
self._remove_columns = data_json.get("remove_columns", [])
if "missing_values" in data_json:
self._missing_values = []
for mv_data in data_json["missing_values"]:
mv = PreprocessingMissingValues()
mv.from_json(mv_data)
self._missing_values += [mv]
if "categorical" in data_json:
self._categorical = []
for cat_data in data_json["categorical"]:
cat = PreprocessingCategorical()
cat.from_json(cat_data)
self._categorical += [cat]
if "scale" in data_json:
self._scale = []
for scale_data in data_json["scale"]:
sc = Scale()
sc.from_json(scale_data)
self._scale += [sc]
if "categorical_y" in data_json:
if "new_columns" in data_json["categorical_y"]:
self._categorical_y = LabelBinarizer()
else:
self._categorical_y = LabelEncoder()
self._categorical_y.from_json(data_json["categorical_y"])
if "scale_y" in data_json:
self._scale_y = Scale()
self._scale_y.from_json(data_json["scale_y"])
if "ml_task" in data_json:
self._params["ml_task"] = data_json["ml_task"]
def from_json(self, data_json):
self._params = data_json.get("params", self._params)
if "remove_columns" in data_json:
self._remove_columns = data_json.get("remove_columns", [])
if "missing_values" in data_json:
self._missing_values = []
for mv_data in data_json["missing_values"]:
mv = PreprocessingMissingValues()
mv.from_json(mv_data)
self._missing_values += [mv]
if "categorical" in data_json:
self._categorical = []
for cat_data in data_json["categorical"]:
cat = PreprocessingCategorical()
cat.from_json(cat_data)
self._categorical += [cat]
if "datetime_transforms" in data_json:
self._datetime_transforms = []
for dtt_params in data_json["datetime_transforms"]:
dtt = DateTimeTransformer()
dtt.from_json(dtt_params)
self._datetime_transforms += [dtt]
if "text_transforms" in data_json:
self._text_transforms = []
for tt_params in data_json["text_transforms"]:
tt = TextTransformer()
tt.from_json(tt_params)
self._text_transforms += [tt]
if "golden_features" in data_json:
self._golden_features = GoldenFeaturesTransformer()
self._golden_features.from_json(data_json["golden_features"])
if "scale" in data_json:
self._scale = []
for scale_data in data_json["scale"]:
sc = Scale()
sc.from_json(scale_data)
self._scale += [sc]
if "categorical_y" in data_json:
if "new_columns" in data_json["categorical_y"]:
self._categorical_y = LabelBinarizer()
else:
self._categorical_y = LabelEncoder()
self._categorical_y.from_json(data_json["categorical_y"])
if "scale_y" in data_json:
self._scale_y = Scale()
self._scale_y.from_json(data_json["scale_y"])
if "ml_task" in data_json:
self._params["ml_task"] = data_json["ml_task"]
self._add_random_feature = data_json.get("add_random_feature", False)
self._drop_features = data_json.get("drop_features", [])
def test_get_fill_value(self):
"""
Check if correct value is returned for filling in case of different
column type and fill method
"""
d = {
"col1": [1, 2, 3, np.nan, np.nan],
"col2": ["a", "a", np.nan, "b", "c"]
}
df = pd.DataFrame(data=d)
# fill with median
preprocess_missing = PreprocessingMissingValues(
df.columns, PreprocessingMissingValues.FILL_NA_MEDIAN)
self.assertEqual(preprocess_missing._get_fill_value(df["col1"]), 2)
self.assertEqual(preprocess_missing._get_fill_value(df["col2"]), "a")
# fill with mean
preprocess_missing = PreprocessingMissingValues(
df.columns, PreprocessingMissingValues.FILL_NA_MEDIAN)
self.assertEqual(preprocess_missing._get_fill_value(df["col1"]), 2)
self.assertEqual(preprocess_missing._get_fill_value(df["col2"]), "a")
# fill with min
preprocess_missing = PreprocessingMissingValues(
df.columns, PreprocessingMissingValues.FILL_NA_MIN)
self.assertEqual(preprocess_missing._get_fill_value(df["col1"]), 0)
self.assertEqual(preprocess_missing._get_fill_value(df["col2"]),
"_missing_value_") # added new value
def test_preprocessing_constructor(self):
"""
Check if PreprocessingMissingValues object is properly initialized
"""
preprocess_missing = PreprocessingMissingValues(
PreprocessingMissingValues.FILL_NA_MEDIAN)
self.assertEqual(
preprocess_missing._na_fill_method,
PreprocessingMissingValues.FILL_NA_MEDIAN,
)
self.assertEqual(preprocess_missing._na_fill_params, {})
def test_transform_on_new_data(self):
# training data
d = {
"col1": [1, 1, np.nan, 3],
"col2": ["a", "a", np.nan, "a"],
"col3": [1, 1, 1, 3],
"col4": ["a", "a", "b", "c"],
"y": [0, 1, 1, 1],
}
df = pd.DataFrame(data=d)
X_train = df.loc[:, ["col1", "col2", "col3", "col4"]]
y_train = df.loc[:, "y"]
d_test = {
"col1": [1, 1, np.nan, 3],
"col2": ["a", "a", np.nan, "a"],
"col3": [1, 1, 1, 3],
"col4": ["a", "a", "b", "c"],
"y": [np.nan, 1, np.nan, 1],
}
df_test = pd.DataFrame(data=d_test)
X_test = df_test.loc[:, ["col1", "col2", "col3", "col4"]]
y_test = df_test.loc[:, "y"]
pm = PreprocessingMissingValues(
X_train.columns, PreprocessingMissingValues.FILL_NA_MEDIAN)
pm.fit(X_train)
X_train = pm.transform(X_train)
X_test = pm.transform(X_test)
self.assertEqual(1, X_test.loc[2, "col1"])
self.assertEqual("a", X_test.loc[2, "col2"])
def fit_and_transform(self, X_train, y_train):
logger.debug("Preprocessing.fit_and_transform")
if y_train is not None:
# target preprocessing
# this must be used first, maybe we will drop some rows because of missing target values
target_preprocessing = self._params.get("target_preprocessing")
logger.debug(
"target_preprocessing params: {}".format(target_preprocessing))
X_train, y_train = ExcludeRowsMissingTarget.transform(
X_train, y_train)
if PreprocessingCategorical.CONVERT_INTEGER in target_preprocessing:
logger.debug("Convert target to integer")
self._categorical_y = LabelEncoder()
self._categorical_y.fit(y_train)
y_train = pd.Series(self._categorical_y.transform(y_train))
if PreprocessingCategorical.CONVERT_ONE_HOT in target_preprocessing:
logger.debug("Convert target to one-hot coding")
self._categorical_y = LabelBinarizer()
self._categorical_y.fit(pd.DataFrame({"target": y_train}),
"target")
y_train = self._categorical_y.transform(
pd.DataFrame({"target": y_train}), "target")
if Scale.SCALE_LOG_AND_NORMAL in target_preprocessing:
logger.debug("Scale log and normal")
self._scale_y = Scale(["target"],
scale_method=Scale.SCALE_LOG_AND_NORMAL)
y_train = pd.DataFrame({"target": y_train})
self._scale_y.fit(y_train)
y_train = self._scale_y.transform(y_train)
y_train = y_train["target"]
if Scale.SCALE_NORMAL in target_preprocessing:
logger.debug("Scale normal")
self._scale_y = Scale(["target"],
scale_method=Scale.SCALE_NORMAL)
y_train = pd.DataFrame({"target": y_train})
self._scale_y.fit(y_train)
y_train = self._scale_y.transform(y_train)
y_train = y_train["target"]
# columns preprocessing
columns_preprocessing = self._params.get("columns_preprocessing")
for column in columns_preprocessing:
transforms = columns_preprocessing[column]
# logger.debug("Preprocess column {} with: {}".format(column, transforms))
# remove empty or constant columns
cols_to_remove = list(
filter(
lambda k: "remove_column" in columns_preprocessing[k],
columns_preprocessing,
))
if X_train is not None:
X_train.drop(cols_to_remove, axis=1, inplace=True)
self._remove_columns = cols_to_remove
for missing_method in [PreprocessingMissingValues.FILL_NA_MEDIAN]:
cols_to_process = list(
filter(
lambda k: missing_method in columns_preprocessing[k],
columns_preprocessing,
))
missing = PreprocessingMissingValues(cols_to_process,
missing_method)
missing.fit(X_train)
X_train = missing.transform(X_train)
self._missing_values += [missing]
for convert_method in [PreprocessingCategorical.CONVERT_INTEGER]:
cols_to_process = list(
filter(
lambda k: convert_method in columns_preprocessing[k],
columns_preprocessing,
))
convert = PreprocessingCategorical(cols_to_process, convert_method)
convert.fit(X_train)
X_train = convert.transform(X_train)
self._categorical += [convert]
# SCALE
for scale_method in [Scale.SCALE_NORMAL, Scale.SCALE_LOG_AND_NORMAL]:
cols_to_process = list(
filter(
lambda k: scale_method in columns_preprocessing[k],
columns_preprocessing,
))
if len(cols_to_process):
scale = Scale(cols_to_process)
scale.fit(X_train)
X_train = scale.transform(X_train)
self._scale += [scale]
return X_train, y_train
def transform(self, X_validation, y_validation):
logger.debug("Preprocessing.transform")
# doing copy to avoid SettingWithCopyWarning
if X_validation is not None:
X_validation = X_validation.copy(deep=False)
if y_validation is not None:
y_validation = y_validation.copy(deep=False)
# target preprocessing
# this must be used first, maybe we will drop some rows because of missing target values
if y_validation is not None:
target_preprocessing = self._params.get("target_preprocessing")
logger.debug(
"target_preprocessing -> {}".format(target_preprocessing))
X_validation, y_validation = ExcludeRowsMissingTarget.transform(
X_validation, y_validation)
if PreprocessingCategorical.CONVERT_INTEGER in target_preprocessing:
if y_validation is not None and self._categorical_y is not None:
y_validation = pd.Series(
self._categorical_y.transform(y_validation))
if PreprocessingCategorical.CONVERT_ONE_HOT in target_preprocessing:
if y_validation is not None and self._categorical_y is not None:
y_validation = self._categorical_y.transform(
pd.DataFrame({"target": y_validation}), "target")
if Scale.SCALE_LOG_AND_NORMAL in target_preprocessing:
if self._scale_y is not None and y_validation is not None:
logger.debug("Transform log and normalize")
y_validation = pd.DataFrame({"target": y_validation})
y_validation = self._scale_y.transform(y_validation)
y_validation = y_validation["target"]
if Scale.SCALE_NORMAL in target_preprocessing:
if self._scale_y is not None and y_validation is not None:
logger.debug("Transform normalize")
y_validation = pd.DataFrame({"target": y_validation})
y_validation = self._scale_y.transform(y_validation)
y_validation = y_validation["target"]
# columns preprocessing
if len(self._remove_columns) and X_validation is not None:
cols_to_remove = [
col for col in X_validation.columns
if col in self._remove_columns
]
X_validation.drop(cols_to_remove, axis=1, inplace=True)
for missing in self._missing_values:
if X_validation is not None and missing is not None:
X_validation = missing.transform(X_validation)
# to be sure that all missing are filled
# in case new data there can be gaps!
if (X_validation is not None
and np.sum(np.sum(pd.isnull(X_validation))) > 0
and len(self._params["columns_preprocessing"]) > 0):
# there is something missing, fill it
# we should notice user about it!
warnings.warn(
"There are columns {} with missing values which didnt have missing values in train dataset."
.format(
list(X_validation.columns[np.where(
np.sum(pd.isnull(X_validation)))])))
missing = PreprocessingMissingValues(
X_validation.columns,
PreprocessingMissingValues.FILL_NA_MEDIAN)
missing.fit(X_validation)
X_validation = missing.transform(X_validation)
for convert in self._categorical:
if X_validation is not None and convert is not None:
X_validation = convert.transform(X_validation)
for scale in self._scale:
if X_validation is not None and scale is not None:
X_validation = scale.transform(X_validation)
return X_validation, y_validation
def run(self, train_data=None, validation_data=None):
log.debug("PreprocessingStep.run")
X_train, y_train = None, None
if train_data is not None:
if "X" in train_data:
X_train = train_data.get("X").copy()
if "y" in train_data:
y_train = train_data.get("y").copy()
X_validation, y_validation = None, None
if validation_data is not None:
if "X" in validation_data:
X_validation = validation_data.get("X").copy()
if "y" in validation_data:
y_validation = validation_data.get("y").copy()
if y_train is not None:
# target preprocessing
# this must be used first, maybe we will drop some rows because of missing target values
target_preprocessing = self._params.get("target_preprocessing")
log.debug(
"target_preprocessing -> {}".format(target_preprocessing))
# if PreprocessingMissingValues.NA_EXCLUDE in target_preprocessing:
X_train, y_train = PreprocessingExcludeMissingValues.transform(
X_train, y_train)
if validation_data is not None:
X_validation, y_validation = PreprocessingExcludeMissingValues.transform(
X_validation, y_validation)
if PreprocessingCategorical.CONVERT_INTEGER in target_preprocessing:
self._categorical_y = LabelEncoder()
self._categorical_y.fit(y_train)
y_train = pd.Series(self._categorical_y.transform(y_train))
if y_validation is not None and self._categorical_y is not None:
y_validation = pd.Series(
self._categorical_y.transform(y_validation))
if PreprocessingScale.SCALE_LOG_AND_NORMAL in target_preprocessing:
log.error("not implemented SCALE_LOG_AND_NORMAL")
raise Exception("not implemented SCALE_LOG_AND_NORMAL")
if PreprocessingScale.SCALE_NORMAL in target_preprocessing:
log.error("not implemented SCALE_NORMAL")
raise Exception("not implemented SCALE_NORMAL")
# columns preprocessing
columns_preprocessing = self._params.get("columns_preprocessing")
for column in columns_preprocessing:
transforms = columns_preprocessing[column]
log.debug("Preprocess column -> {}, {}".format(column, transforms))
# remove empty or constant columns
cols_to_remove = list(
filter(
lambda k: "remove_column" in columns_preprocessing[k],
columns_preprocessing,
))
if X_train is not None:
X_train.drop(cols_to_remove, axis=1, inplace=True)
if X_validation is not None:
X_validation.drop(cols_to_remove, axis=1, inplace=True)
self._remove_columns = cols_to_remove
for missing_method in [PreprocessingMissingValues.FILL_NA_MEDIAN]:
cols_to_process = list(
filter(
lambda k: missing_method in columns_preprocessing[k],
columns_preprocessing,
))
missing = PreprocessingMissingValues(cols_to_process,
missing_method)
missing.fit(X_train)
X_train = missing.transform(X_train)
if X_validation is not None:
X_validation = missing.transform(X_validation)
self._missing_values += [missing]
for convert_method in [PreprocessingCategorical.CONVERT_INTEGER]:
cols_to_process = list(
filter(
lambda k: convert_method in columns_preprocessing[k],
columns_preprocessing,
))
convert = PreprocessingCategorical(cols_to_process, convert_method)
convert.fit(X_train)
X_train = convert.transform(X_train)
if X_validation is not None:
X_validation = convert.transform(X_validation)
self._categorical += [convert]
# SCALE
for scale_method in [PreprocessingScale.SCALE_NORMAL]:
cols_to_process = list(
filter(
lambda k: scale_method in columns_preprocessing[k],
columns_preprocessing,
))
if len(cols_to_process):
scale = PreprocessingScale(cols_to_process)
scale.fit(X_train)
X_train = scale.transform(X_train)
if X_validation is not None:
X_validation = scale.transform(X_validation)
self._scale += [scale]
return {
"X": X_train,
"y": y_train
}, {
"X": X_validation,
"y": y_validation
}
def transform(self, validation_data=None):
log.debug("PreprocessingStep.transform")
X_validation, y_validation = None, None
if validation_data is not None:
if "X" in validation_data:
X_validation = validation_data.get("X").copy()
if "y" in validation_data:
y_validation = validation_data.get("y").copy()
# target preprocessing
# this must be used first, maybe we will drop some rows because of missing target values
target_preprocessing = self._params.get("target_preprocessing")
log.debug("target_preprocessing -> {}".format(target_preprocessing))
if validation_data is not None:
X_validation, y_validation = PreprocessingExcludeMissingValues.transform(
X_validation, y_validation)
if PreprocessingCategorical.CONVERT_INTEGER in target_preprocessing:
if y_validation is not None and self._categorical_y is not None:
y_validation = pd.Series(
self._categorical_y.transform(y_validation))
if PreprocessingScale.SCALE_LOG_AND_NORMAL in target_preprocessing:
log.error("not implemented SCALE_LOG_AND_NORMAL")
raise Exception("not implemented SCALE_LOG_AND_NORMAL")
if PreprocessingScale.SCALE_NORMAL in target_preprocessing:
log.error("not implemented SCALE_NORMAL")
raise Exception("not implemented SCALE_NORMAL")
# columns preprocessing
if len(self._remove_columns) and X_validation is not None:
cols_to_remove = [
col for col in X_validation.columns
if col in self._remove_columns
]
X_validation.drop(cols_to_remove, axis=1, inplace=True)
for missing in self._missing_values:
if X_validation is not None and missing is not None:
X_validation = missing.transform(X_validation)
# to be sure that all missing are filled
# in case new data there can be gaps!
if np.sum(np.sum(pd.isnull(X_validation))) > 0:
# there is something missing, fill it
# we should notice user about it!
warnings.warn(
"There are columns {} with missing values which didnt have missing values in train dataset."
.format(
list(X_validation.columns[np.where(
np.sum(pd.isnull(X_validation)))])))
missing = PreprocessingMissingValues(
X_validation.columns,
PreprocessingMissingValues.FILL_NA_MEDIAN)
missing.fit(X_validation)
X_validation = missing.transform(X_validation)
for convert in self._categorical:
if X_validation is not None and convert is not None:
X_validation = convert.transform(X_validation)
for scale in self._scale:
if X_validation is not None and scale is not None:
X_validation = scale.transform(X_validation)
return {"X": X_validation, "y": y_validation}
def fit_and_transform(self, X_train, y_train, sample_weight=None):
logger.debug("Preprocessing.fit_and_transform")
if y_train is not None:
# target preprocessing
# this must be used first, maybe we will drop some rows because of missing target values
target_preprocessing = self._params.get("target_preprocessing")
logger.debug(
"target_preprocessing params: {}".format(target_preprocessing))
X_train, y_train, sample_weight = ExcludeRowsMissingTarget.transform(
X_train, y_train, sample_weight)
if PreprocessingCategorical.CONVERT_INTEGER in target_preprocessing:
logger.debug("Convert target to integer")
self._categorical_y = LabelEncoder(try_to_fit_numeric=True)
self._categorical_y.fit(y_train)
y_train = pd.Series(self._categorical_y.transform(y_train))
if PreprocessingCategorical.CONVERT_ONE_HOT in target_preprocessing:
logger.debug("Convert target to one-hot coding")
self._categorical_y = LabelBinarizer()
self._categorical_y.fit(pd.DataFrame({"target": y_train}),
"target")
y_train = self._categorical_y.transform(
pd.DataFrame({"target": y_train}), "target")
if Scale.SCALE_LOG_AND_NORMAL in target_preprocessing:
logger.debug("Scale log and normal")
self._scale_y = Scale(["target"],
scale_method=Scale.SCALE_LOG_AND_NORMAL)
y_train = pd.DataFrame({"target": y_train})
self._scale_y.fit(y_train)
y_train = self._scale_y.transform(y_train)
y_train = y_train["target"]
if Scale.SCALE_NORMAL in target_preprocessing:
logger.debug("Scale normal")
self._scale_y = Scale(["target"],
scale_method=Scale.SCALE_NORMAL)
y_train = pd.DataFrame({"target": y_train})
self._scale_y.fit(y_train)
y_train = self._scale_y.transform(y_train)
y_train = y_train["target"]
# columns preprocessing
columns_preprocessing = self._params.get("columns_preprocessing")
for column in columns_preprocessing:
transforms = columns_preprocessing[column]
# logger.debug("Preprocess column {} with: {}".format(column, transforms))
# remove empty or constant columns
cols_to_remove = list(
filter(
lambda k: "remove_column" in columns_preprocessing[k],
columns_preprocessing,
))
if X_train is not None:
X_train.drop(cols_to_remove, axis=1, inplace=True)
self._remove_columns = cols_to_remove
numeric_cols = [] # get numeric cols before text transformations
# needed for golden features
if X_train is not None and ("golden_features" in self._params
or "kmeans_features" in self._params):
numeric_cols = X_train.select_dtypes(
include="number").columns.tolist()
# there can be missing values in the text data,
# but we don't want to handle it by fill missing methods
# zeros will be imputed by text_transform method
cols_to_process = list(
filter(
lambda k: "text_transform" in columns_preprocessing[k],
columns_preprocessing,
))
new_text_columns = []
for col in cols_to_process:
t = TextTransformer()
t.fit(X_train, col)
X_train = t.transform(X_train)
self._text_transforms += [t]
new_text_columns += t._new_columns
# end of text transform
for missing_method in [PreprocessingMissingValues.FILL_NA_MEDIAN]:
cols_to_process = list(
filter(
lambda k: missing_method in columns_preprocessing[k],
columns_preprocessing,
))
missing = PreprocessingMissingValues(cols_to_process,
missing_method)
missing.fit(X_train)
X_train = missing.transform(X_train)
self._missing_values += [missing]
# golden features
golden_columns = []
if "golden_features" in self._params:
results_path = self._params["golden_features"]["results_path"]
ml_task = self._params["golden_features"]["ml_task"]
self._golden_features = GoldenFeaturesTransformer(
results_path, ml_task)
self._golden_features.fit(X_train[numeric_cols], y_train)
X_train = self._golden_features.transform(X_train)
golden_columns = self._golden_features._new_columns
kmeans_columns = []
if "kmeans_features" in self._params:
results_path = self._params["kmeans_features"]["results_path"]
self._kmeans = KMeansTransformer(results_path, self._model_name,
self._k_fold)
self._kmeans.fit(X_train[numeric_cols], y_train)
X_train = self._kmeans.transform(X_train)
kmeans_columns = self._kmeans._new_features
for convert_method in [
PreprocessingCategorical.CONVERT_INTEGER,
PreprocessingCategorical.CONVERT_ONE_HOT,
PreprocessingCategorical.CONVERT_LOO,
]:
cols_to_process = list(
filter(
lambda k: convert_method in columns_preprocessing[k],
columns_preprocessing,
))
convert = PreprocessingCategorical(cols_to_process, convert_method)
convert.fit(X_train, y_train)
X_train = convert.transform(X_train)
self._categorical += [convert]
# datetime transform
cols_to_process = list(
filter(
lambda k: "datetime_transform" in columns_preprocessing[k],
columns_preprocessing,
))
new_datetime_columns = []
for col in cols_to_process:
t = DateTimeTransformer()
t.fit(X_train, col)
X_train = t.transform(X_train)
self._datetime_transforms += [t]
new_datetime_columns += t._new_columns
# SCALE
for scale_method in [Scale.SCALE_NORMAL, Scale.SCALE_LOG_AND_NORMAL]:
cols_to_process = list(
filter(
lambda k: scale_method in columns_preprocessing[k],
columns_preprocessing,
))
if (len(cols_to_process) and len(new_datetime_columns)
and scale_method == Scale.SCALE_NORMAL):
cols_to_process += new_datetime_columns
if (len(cols_to_process) and len(new_text_columns)
and scale_method == Scale.SCALE_NORMAL):
cols_to_process += new_text_columns
if (len(cols_to_process) and len(golden_columns)
and scale_method == Scale.SCALE_NORMAL):
cols_to_process += golden_columns
if (len(cols_to_process) and len(kmeans_columns)
and scale_method == Scale.SCALE_NORMAL):
cols_to_process += kmeans_columns
if len(cols_to_process):
scale = Scale(cols_to_process)
scale.fit(X_train)
X_train = scale.transform(X_train)
self._scale += [scale]
if self._add_random_feature:
# -1, 1, with 0 mean
X_train["random_feature"] = np.random.rand(
X_train.shape[0]) * 2.0 - 1.0
if self._drop_features:
available_cols = X_train.columns.tolist()
drop_cols = [c for c in self._drop_features if c in available_cols]
if len(drop_cols) == X_train.shape[1]:
raise AutoMLException(
"All features are droppped! Your data looks like random data."
)
if drop_cols:
X_train.drop(drop_cols, axis=1, inplace=True)
self._drop_features = drop_cols
if X_train is not None:
# there can be catagorical columns (in CatBoost) which cant be clipped
numeric_cols = X_train.select_dtypes(
include="number").columns.tolist()
X_train[numeric_cols] = X_train[numeric_cols].clip(
lower=np.finfo(np.float32).min + 1000,
upper=np.finfo(np.float32).max - 1000,
)
return X_train, y_train, sample_weight
def transform(self,
X_validation,
y_validation,
sample_weight_validation=None):
logger.debug("Preprocessing.transform")
# doing copy to avoid SettingWithCopyWarning
if X_validation is not None:
X_validation = X_validation.copy(deep=False)
if y_validation is not None:
y_validation = y_validation.copy(deep=False)
# target preprocessing
# this must be used first, maybe we will drop some rows because of missing target values
if y_validation is not None:
target_preprocessing = self._params.get("target_preprocessing")
logger.debug(
"target_preprocessing -> {}".format(target_preprocessing))
(
X_validation,
y_validation,
sample_weight_validation,
) = ExcludeRowsMissingTarget.transform(X_validation, y_validation,
sample_weight_validation)
if PreprocessingCategorical.CONVERT_INTEGER in target_preprocessing:
if y_validation is not None and self._categorical_y is not None:
y_validation = pd.Series(
self._categorical_y.transform(y_validation))
if PreprocessingCategorical.CONVERT_ONE_HOT in target_preprocessing:
if y_validation is not None and self._categorical_y is not None:
y_validation = self._categorical_y.transform(
pd.DataFrame({"target": y_validation}), "target")
if Scale.SCALE_LOG_AND_NORMAL in target_preprocessing:
if self._scale_y is not None and y_validation is not None:
logger.debug("Transform log and normalize")
y_validation = pd.DataFrame({"target": y_validation})
y_validation = self._scale_y.transform(y_validation)
y_validation = y_validation["target"]
if Scale.SCALE_NORMAL in target_preprocessing:
if self._scale_y is not None and y_validation is not None:
logger.debug("Transform normalize")
y_validation = pd.DataFrame({"target": y_validation})
y_validation = self._scale_y.transform(y_validation)
y_validation = y_validation["target"]
# columns preprocessing
if len(self._remove_columns) and X_validation is not None:
cols_to_remove = [
col for col in X_validation.columns
if col in self._remove_columns
]
X_validation.drop(cols_to_remove, axis=1, inplace=True)
# text transform
for tt in self._text_transforms:
if X_validation is not None and tt is not None:
X_validation = tt.transform(X_validation)
for missing in self._missing_values:
if X_validation is not None and missing is not None:
X_validation = missing.transform(X_validation)
# to be sure that all missing are filled
# in case new data there can be gaps!
if (X_validation is not None
and np.sum(np.sum(pd.isnull(X_validation))) > 0
and len(self._params["columns_preprocessing"]) > 0):
# there is something missing, fill it
# we should notice user about it!
# warnings should go to the separate file ...
# warnings.warn(
# "There are columns {} with missing values which didnt have missing values in train dataset.".format(
# list(
# X_validation.columns[np.where(np.sum(pd.isnull(X_validation)))]
# )
# )
# )
missing = PreprocessingMissingValues(
X_validation.columns,
PreprocessingMissingValues.FILL_NA_MEDIAN)
missing.fit(X_validation)
X_validation = missing.transform(X_validation)
# golden features
if self._golden_features is not None:
X_validation = self._golden_features.transform(X_validation)
if self._kmeans is not None:
X_validation = self._kmeans.transform(X_validation)
for convert in self._categorical:
if X_validation is not None and convert is not None:
X_validation = convert.transform(X_validation)
for dtt in self._datetime_transforms:
if X_validation is not None and dtt is not None:
X_validation = dtt.transform(X_validation)
for scale in self._scale:
if X_validation is not None and scale is not None:
X_validation = scale.transform(X_validation)
if self._add_random_feature:
# -1, 1, with 0 mean
X_validation["random_feature"] = (
np.random.rand(X_validation.shape[0]) * 2.0 - 1.0)
if self._drop_features and X_validation is not None:
X_validation.drop(self._drop_features, axis=1, inplace=True)
if X_validation is not None:
# there can be catagorical columns (in CatBoost) which cant be clipped
numeric_cols = X_validation.select_dtypes(
include="number").columns.tolist()
X_validation[numeric_cols] = X_validation[numeric_cols].clip(
lower=np.finfo(np.float32).min + 1000,
upper=np.finfo(np.float32).max - 1000,
)
return X_validation, y_validation, sample_weight_validation
def test_fit_na_fill(self):
"""
Check fit private method
"""
d = {
"col1": [1, 2, 3, np.nan, np.nan],
"col2": ["a", "a", np.nan, "b", "c"],
"col3": ["a", "a", "d", "b", "c"],
}
df = pd.DataFrame(data=d)
# fill with median
preprocess_missing = PreprocessingMissingValues(
df.columns, PreprocessingMissingValues.FILL_NA_MEDIAN)
preprocess_missing._fit_na_fill(df)
self.assertTrue("col1" in preprocess_missing._na_fill_params)
self.assertTrue("col2" in preprocess_missing._na_fill_params)
self.assertTrue("col3" not in preprocess_missing._na_fill_params)
self.assertEqual(2, preprocess_missing._na_fill_params["col1"])
self.assertEqual("a", preprocess_missing._na_fill_params["col2"])
# fill with mean
preprocess_missing = PreprocessingMissingValues(
df.columns, PreprocessingMissingValues.FILL_NA_MEAN)
preprocess_missing._fit_na_fill(df)
self.assertTrue("col1" in preprocess_missing._na_fill_params)
self.assertTrue("col2" in preprocess_missing._na_fill_params)
self.assertTrue("col3" not in preprocess_missing._na_fill_params)
self.assertEqual(2, preprocess_missing._na_fill_params["col1"])
self.assertEqual("a", preprocess_missing._na_fill_params["col2"])
# fill with min
preprocess_missing = PreprocessingMissingValues(
df.columns, PreprocessingMissingValues.FILL_NA_MIN)
preprocess_missing._fit_na_fill(df)
self.assertTrue("col1" in preprocess_missing._na_fill_params)
self.assertTrue("col2" in preprocess_missing._na_fill_params)
self.assertTrue("col3" not in preprocess_missing._na_fill_params)
self.assertEqual(0, preprocess_missing._na_fill_params["col1"])
self.assertEqual("_missing_value_",
preprocess_missing._na_fill_params["col2"])
def fit_and_transform(self, X_train, y_train):
logger.debug("Preprocessing.fit_and_transform")
if y_train is not None:
# target preprocessing
# this must be used first, maybe we will drop some rows because of missing target values
target_preprocessing = self._params.get("target_preprocessing")
logger.debug("target_preprocessing params: {}".format(target_preprocessing))
X_train, y_train = ExcludeRowsMissingTarget.transform(X_train, y_train)
if PreprocessingCategorical.CONVERT_INTEGER in target_preprocessing:
logger.debug("Convert target to integer")
self._categorical_y = LabelEncoder()
self._categorical_y.fit(y_train)
y_train = pd.Series(self._categorical_y.transform(y_train))
if PreprocessingCategorical.CONVERT_ONE_HOT in target_preprocessing:
logger.debug("Convert target to one-hot coding")
self._categorical_y = LabelBinarizer()
self._categorical_y.fit(pd.DataFrame({"target": y_train}), "target")
y_train = self._categorical_y.transform(
pd.DataFrame({"target": y_train}), "target"
)
if Scale.SCALE_LOG_AND_NORMAL in target_preprocessing:
logger.debug("Scale log and normal")
self._scale_y = Scale(
["target"], scale_method=Scale.SCALE_LOG_AND_NORMAL
)
y_train = pd.DataFrame({"target": y_train})
self._scale_y.fit(y_train)
y_train = self._scale_y.transform(y_train)
y_train = y_train["target"]
if Scale.SCALE_NORMAL in target_preprocessing:
logger.debug("Scale normal")
self._scale_y = Scale(["target"], scale_method=Scale.SCALE_NORMAL)
y_train = pd.DataFrame({"target": y_train})
self._scale_y.fit(y_train)
y_train = self._scale_y.transform(y_train)
y_train = y_train["target"]
# columns preprocessing
columns_preprocessing = self._params.get("columns_preprocessing")
for column in columns_preprocessing:
transforms = columns_preprocessing[column]
# logger.debug("Preprocess column {} with: {}".format(column, transforms))
# remove empty or constant columns
cols_to_remove = list(
filter(
lambda k: "remove_column" in columns_preprocessing[k],
columns_preprocessing,
)
)
if X_train is not None:
X_train.drop(cols_to_remove, axis=1, inplace=True)
self._remove_columns = cols_to_remove
# there can be missing values in the text data,
# but we don't want to handle it by fill missing methods
# zeros will be imputed by text_transform method
cols_to_process = list(
filter(
lambda k: "text_transform" in columns_preprocessing[k],
columns_preprocessing,
)
)
new_text_columns = []
for col in cols_to_process:
t = TextTransformer()
t.fit(X_train, col)
X_train = t.transform(X_train)
self._text_transforms += [t]
new_text_columns += t._new_columns
# end of text transform
for missing_method in [PreprocessingMissingValues.FILL_NA_MEDIAN]:
cols_to_process = list(
filter(
lambda k: missing_method in columns_preprocessing[k],
columns_preprocessing,
)
)
missing = PreprocessingMissingValues(cols_to_process, missing_method)
missing.fit(X_train)
X_train = missing.transform(X_train)
self._missing_values += [missing]
for convert_method in [
PreprocessingCategorical.CONVERT_INTEGER,
PreprocessingCategorical.CONVERT_ONE_HOT,
]:
cols_to_process = list(
filter(
lambda k: convert_method in columns_preprocessing[k],
columns_preprocessing,
)
)
convert = PreprocessingCategorical(cols_to_process, convert_method)
convert.fit(X_train)
X_train = convert.transform(X_train)
self._categorical += [convert]
# datetime transform
cols_to_process = list(
filter(
lambda k: "datetime_transform" in columns_preprocessing[k],
columns_preprocessing,
)
)
new_datetime_columns = []
for col in cols_to_process:
t = DateTimeTransformer()
t.fit(X_train, col)
X_train = t.transform(X_train)
self._datetime_transforms += [t]
new_datetime_columns += t._new_columns
# SCALE
for scale_method in [Scale.SCALE_NORMAL, Scale.SCALE_LOG_AND_NORMAL]:
cols_to_process = list(
filter(
lambda k: scale_method in columns_preprocessing[k],
columns_preprocessing,
)
)
if (
len(cols_to_process)
and len(new_datetime_columns)
and scale_method == Scale.SCALE_NORMAL
):
cols_to_process += new_datetime_columns
if (
len(cols_to_process)
and len(new_text_columns)
and scale_method == Scale.SCALE_NORMAL
):
cols_to_process += new_text_columns
if len(cols_to_process):
scale = Scale(cols_to_process)
scale.fit(X_train)
X_train = scale.transform(X_train)
self._scale += [scale]
return X_train, y_train
