def partial_fit(self, df, options):
# Make a copy of data, to not alter original dataframe
X = df.copy()
X, _, columns = df_util.prepare_features(X, self.feature_variables)
if self.columns is not None:
df_util.handle_new_categorical_values(X, None, options,
self.columns)
if X.empty:
return
else:
self.columns = columns
self.estimator.partial_fit(X)
def partial_fit(self, df, options):
# Handle backwards compatibility.
add_missing_attr(self.estimator,
attr='max_iter',
value=5,
param_key='n_iter')
add_missing_attr(self.estimator, attr='tol', value=None)
# Make a copy of data, to not alter original dataframe
X = df.copy()
relevant_variables = self.feature_variables + [self.target_variable]
X, y, columns = df_util.prepare_features_and_target(
X=X,
variables=relevant_variables,
target=self.target_variable,
mlspl_limits=options.get('mlspl_limits'),
)
if self.columns is not None:
X, y = df_util.handle_new_categorical_values(
X, y, options, self.columns)
if X.empty:
return
else:
self.columns = columns
self.scaler.partial_fit(X.values)
scaled_X = self.scaler.transform(X.values)
self.estimator.partial_fit(scaled_X, y)
cexc.messages.warn('n_iter is set to 1 when partial fit is performed')
def partial_fit(self, df, options):
# Make a copy of data, to not alter original dataframe
X = df.copy()
algo_util.assert_estimator_supports_partial_fit(self.estimator)
X, _, columns = df_util.prepare_features(
X=X,
variables=self.feature_variables,
mlspl_limits=options.get('mlspl_limits'),
)
if getattr(self, 'columns', None):
df_util.handle_new_categorical_values(X, None, options,
self.columns)
if X.empty:
return
else:
self.columns = columns
self.estimator.partial_fit(X)
def partial_fit(self, df, options):
# Handle backwards compatibility.
add_missing_attr(self.estimator,
attr='max_iter',
value=5,
param_key='n_iter')
add_missing_attr(self.estimator, attr='tol', value=None)
# Check target variable
df[self.target_variable] = df_util.check_and_convert_target_variable(
df, self.target_variable)
# Make a copy of data, to not alter original dataframe
X = df.copy()
relevant_variables = self.feature_variables + [self.target_variable]
mlspl_limits = options.get('mlspl_limits', {})
max_classes = int(
mlspl_limits.get('max_distinct_cat_values_for_classifier', 100))
df_util.limit_classes_for_classifier(X, self.target_variable,
max_classes)
X, y, columns = df_util.prepare_features_and_target(
X=X,
variables=relevant_variables,
target=self.target_variable,
mlspl_limits=mlspl_limits,
)
if self.classes is None:
self.classes = np.unique(y)
scaled_X = self.scaler.fit_transform(X.values)
self.estimator.partial_fit(scaled_X, y, classes=self.classes)
self.columns = columns
else:
X, y = df_util.handle_new_categorical_values(
X, y, options, self.columns, self.classes)
if X.empty:
return
self.scaler.partial_fit(X.values)
scaled_X = self.scaler.transform(X.values)
self.estimator.partial_fit(scaled_X, y)
def partial_fit(self, df, options):
# Check target variable
df[self.target_variable] = df_util.check_and_convert_target_variable(
df, self.target_variable)
# Make a copy of data, to not alter original dataframe
X = df.copy()
# Ensure that partial_fit method is defined for the estimator
algo_util.assert_estimator_supports_partial_fit(self.estimator)
# Ensure there aren't too many classes
mlspl_limits = options.get('mlspl_limits', {})
max_classes = int(
mlspl_limits.get('max_distinct_cat_values_for_classifiers', 100))
df_util.limit_classes_for_classifier(X, self.target_variable,
max_classes)
# Use all the variables
used_variables = self.feature_variables + [self.target_variable]
# Prepare the dataset
X, y, columns = df_util.prepare_features_and_target(
X=X,
variables=used_variables,
target=self.target_variable,
mlspl_limits=mlspl_limits,
)
# On the very first partial call
if self.classes is None:
self.classes = np.unique(y)
self.estimator.partial_fit(X.values, y.values, self.classes)
self.columns = columns
# On subsequent partial_fit calls
else:
X, y = df_util.handle_new_categorical_values(
X, y, options, self.columns, self.classes)
if not X.empty:
self.estimator.partial_fit(X.values, y.values)
def partial_fit(self, df, options):
# Make a copy of data, to not alter original dataframe
X = df.copy()
relevant_variables = self.feature_variables + [self.target_variable]
X, y, columns = df_util.prepare_features_and_target(
X=X,
variables=relevant_variables,
target=self.target_variable,
)
if self.columns is not None:
X, y = df_util.handle_new_categorical_values(
X, y, options, self.columns)
if X.empty:
return
else:
self.columns = columns
self.scaler.partial_fit(X.values)
scaled_X = self.scaler.transform(X.values)
self.estimator.partial_fit(scaled_X, y)
cexc.messages.warn('n_iter is set to 1 when partial fit is performed')
def partial_fit(self, df, options):
# Make a copy of data, to not alter original dataframe
X = df.copy()
relevant_variables = self.feature_variables + [self.target_variable]
df_util.limit_classes_for_classifier(X, self.target_variable)
X, y, columns = df_util.prepare_features_and_target(
X=X,
variables=relevant_variables,
target=self.target_variable,
)
if self.classes is None:
self.classes = np.unique(y)
scaled_X = self.scaler.fit_transform(X.values)
self.estimator.partial_fit(scaled_X, y, classes=self.classes)
self.columns = columns
else:
X, y = df_util.handle_new_categorical_values(X, y, options, self.columns, self.classes)
if X.empty:
return
self.scaler.partial_fit(X.values)
scaled_X = self.scaler.transform(X.values)
self.estimator.partial_fit(scaled_X, y)