def transformer(self, value):
"""Validate transformer initialization.
Args:
value (object): The selected transformer that SmartTransformer
should use.
Raises:
ValueError: If input is neither a valid foreshadow wrapped
transformer, scikit-learn Pipeline, scikit-learn FeatureUnion,
nor None.
"""
if isinstance(value, str):
value = get_transformer(value)(**self.kwargs)
self.unset_resolve()
# Check transformer type
is_trans = is_transformer(value)
trans_wrapped = (is_wrapped(value)
if getattr(self, "check_wrapped", True) else True)
# True by default passes this check if we don't want it.
is_pipe = isinstance(value, Pipeline)
is_none = value is None
checks = [is_trans, is_pipe, is_none, trans_wrapped]
# Check the transformer inheritance status
if not any(checks):
logging.error("transformer: {} failed checks: {}".format(
value, checks))
raise ValueError(
"{} is neither a scikit-learn Pipeline, FeatureUnion, a "
"wrapped foreshadow transformer, nor None.".format(value))
self._transformer = value
def _get_modules(classes, globals_, mname): # TODO auto import all
# TODO sklearn transformers and test each one generically.
"""Import sklearn transformers from transformers directory.
Searches transformers directory for classes implementing BaseEstimator and
TransformerMixin and duplicates them, wraps their init methods and public
functions to support pandas dataframes, and exposes them as
foreshadow.transformers.[name]
Args:
classes: A list of classes
globals_: The globals in the callee's context
mname: The module name
Returns:
The list of wrapped transformers.
"""
transformers = [
cls for cls in classes
if is_transformer(cls, method="issubclass") # noqa: F821
] # flake does not detect due to del.
for t in transformers:
copied_t = type(t.__name__, (t, *t.__bases__), dict(t.__dict__))
copied_t.__module__ = mname
globals_[copied_t.__name__] = pandas_wrap( # noqa: F821
copied_t # noqa: F821
)
# flake does not detect due to del.
return [t.__name__ for t in transformers]
def inverse_transform(self, X, *args, **kwargs):
"""Give original inputs using fitted transformer. Pandas enabled.
See transformer
Args:
X: transformed inputs
*args: arguments to transformer
**kwargs: keyword arguments to transformer
Returns:
original inputs
Raises:
ValueError: If not a valid output type from transformer.
"""
df = check_df(X)
init_cols = [str(col) for col in df]
func = super(DFTransformer, self).inverse_transform
out = func(df, *args, **kwargs)
# determine name of new columns
name = getattr(self, "name", type(self).__name__)
out_is_transformer = hasattr(out, "__class__") and is_transformer(
out.__class__, method="issubclass") # noqa: E127
# check if the output
# returned by the scikit-learn public function is a transformer or
# not. It will be a transformer in fit calls.
if not (out_is_transformer):
# if the output is a transformer, we do nothing.
if isinstance(out,
pd.DataFrame): # custom handling based on the
# type returned by the sklearn transformer function call
out, graph = _df_post_process(out, init_cols, name)
elif isinstance(out, np.ndarray):
out, graph = _ndarray_post_process(out, df, init_cols,
name)
elif scipy.sparse.issparse(out):
out = out.toarray()
out, graph = _ndarray_post_process(out, df, init_cols,
name)
elif isinstance(out, pd.Series):
graph = [] # just return the series
else:
raise ValueError("undefined input {0}".format(type(out)))
if getattr(self, "keep_columns", False):
out = _keep_columns_process(out, df, name, graph)
if getattr(self, "cache_manager", None) is not None: # only
# used when part of the Foreshadow flow.
for column in X:
self.cache_manager["graph", column] = graph
else:
logging.debug("cache_manager is not set for: "
"{}".format(self))
return out # TODO output is a DataFrame, make it detect based
def fit_transform(self, X, *args, **kwargs):
df = check_df(X)
kwargs.pop("full_df", None)
init_cols = [str(col) for col in df]
func = super(DFTransformer, self).fit_transform
out = func(df, *args, **kwargs)
# determine name of new columns
name = getattr(self, "name", type(self).__name__)
out_is_transformer = hasattr(out, "__class__") and is_transformer(
out.__class__, method="issubclass") # noqa: E127
# check if the output returned by the scikit-learn public function
# is a transformer or not. It will be a transformer in fit calls.
if not (out_is_transformer) and not isinstance(out, pd.DataFrame):
# out_is_transformer: if the output is a transformer,
# we do nothing.
# pd.DataFrame: fit_transform will likely be
# passed to the TransformerMixin fit_transform, which just
# calls .fit and .transform. Processing will be handled
# there
if isinstance(out, np.ndarray): # output was not yet
# transformed to DataFrame
out, graph = _ndarray_post_process(out, df, init_cols,
name)
elif scipy.sparse.issparse(out):
out = out.toarray()
out, graph = _ndarray_post_process(out, df, init_cols,
name)
elif isinstance(out, pd.Series):
graph = [] # just return the series
else:
raise ValueError("undefined input {0}".format(type(out)))
if getattr(self, "keep_columns", False):
out = _keep_columns_process(out, df, name, graph)
if getattr(self, "cache_manager", None) is not None: # only
# used when part of the Foreshadow flow.
for column in X:
self.cache_manager["graph", column] = graph
else:
logging.debug("cache_manager is not set for: "
"{}".format(self))
return out