def test_slice_columns():
columns = [2, 3]
df2 = slice_columns(df, columns)
X2 = slice_columns(X, columns)
assert list(df2.columns) == columns
assert_eq_df(df[columns].compute(), df2.compute())
assert_eq_ar(X.compute(), X2.compute())
def fit(self, X, y=None):
self._reset()
to_persist = OrderedDict()
feature_range = self.feature_range
if feature_range[0] >= feature_range[1]:
raise ValueError("Minimum of desired feature "
"range must be smaller than maximum.")
_X = slice_columns(X, self.columns)
data_min = _X.min(0)
data_max = _X.max(0)
data_range = data_max - data_min
scale = ((feature_range[1] - feature_range[0]) /
handle_zeros_in_scale(data_range))
to_persist["data_min_"] = data_min
to_persist["data_max_"] = data_max
to_persist["data_range_"] = data_range
to_persist["scale_"] = scale
to_persist["min_"] = feature_range[0] - data_min * scale
to_persist["n_samples_seen_"] = np.nan
values = persist(*to_persist.values())
for k, v in zip(to_persist, values):
setattr(self, k, v)
return self
def transform(self, X, y=None, copy=None):
_X = slice_columns(X, self.columns)
_X *= self.scale_
_X += self.min_
if isinstance(_X, dd.DataFrame) and self.columns:
for column in self.columns:
X[column] = _X[column]
return X
else:
return _X
def inverse_transform(self, X, y=None, copy=None):
if not hasattr(self, "scale_"):
raise Exception("This %(name)s instance is not fitted yet. "
"Call 'fit' with appropriate arguments before "
"using this method.")
_X = slice_columns(X, self.columns)
_X -= self.min_
_X /= self.scale_
if isinstance(_X, dd.DataFrame) and self.columns:
for column in self.columns:
X[column] = _X[column]
return X
else:
return _X
