def fit(self, X, y=None):
self._reset()
attributes = 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.")
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)
attributes["data_min_"] = data_min
attributes["data_max_"] = data_max
attributes["data_range_"] = data_range
attributes["scale_"] = scale
attributes["min_"] = feature_range[0] - data_min * scale
attributes["n_samples_seen_"] = np.nan
values = compute(*attributes.values())
for k, v in zip(attributes, values):
setattr(self, k, v)
return self
def fit(
self,
X: Union[ArrayLike, DataFrameType],
y: Optional[Union[ArrayLike, SeriesType]] = None,
) -> "MinMaxScaler":
self._reset()
attributes = 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.")
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)
attributes["data_min_"] = data_min
attributes["data_max_"] = data_max
attributes["data_range_"] = data_range
attributes["scale_"] = scale
attributes["min_"] = feature_range[0] - data_min * scale
attributes["n_samples_seen_"] = X.shape[0]
values = compute(*attributes.values())
for k, v in zip(attributes, values):
setattr(self, k, v)
self.n_features_in_: int = X.shape[1]
return self
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 test_handle_zeros_in_scale():
s2 = handle_zeros_in_scale(s)
a2 = handle_zeros_in_scale(a)
assert list(s2.compute()) == [1, 1, 2, 3, 1]
assert list(a2.compute()) == [1, 1, 2, 3, 1]
x = np.array([1, 2, 3, 0], dtype="f8")
expected = np.array([1, 2, 3, 1], dtype="f8")
result = handle_zeros_in_scale(x)
np.testing.assert_array_equal(result, expected)
x = pd.Series(x)
expected = pd.Series(expected)
result = handle_zeros_in_scale(x)
tm.assert_series_equal(result, expected)
x = da.from_array(x.values, chunks=2)
expected = expected.values
result = handle_zeros_in_scale(x)
assert_eq_ar(result, expected)
x = dd.from_dask_array(x)
expected = pd.Series(expected)
result = handle_zeros_in_scale(x)
assert_eq_df(result, expected)
def fit(
self,
X,
y=None,
):
from dask_ml.utils import handle_zeros_in_scale
self._reset()
if isinstance(X, (pd.DataFrame, np.ndarray)):
return super().fit(X, y)
max_abs = X.reduction(lambda x: x.abs().max(),
aggregate=lambda x: x.max(),
token=self.__class__.__name__).compute()
scale = handle_zeros_in_scale(max_abs)
setattr(self, 'max_abs_', max_abs)
setattr(self, 'scale_', scale)
setattr(self, 'n_samples_seen_', 0)
self.n_features_in_ = X.shape[1]
return self
def test_handle_zeros_in_scale():
s2 = handle_zeros_in_scale(s)
a2 = handle_zeros_in_scale(a)
assert list(s2.compute()) == [1, 1, 2, 3, 1]
assert list(a2.compute()) == [1, 1, 2, 3, 1]
