def test_nan():
x = np.array([[1, np.nan, 3, 4], [5, 6, 7, np.nan], [9, 10, 11, 12]])
d = da.from_array(x, chunks=(2, 2))
assert_eq(np.nansum(x), da.nansum(d))
assert_eq(np.nansum(x, axis=0), da.nansum(d, axis=0))
assert_eq(np.nanmean(x, axis=1), da.nanmean(d, axis=1))
assert_eq(np.nanmin(x, axis=1), da.nanmin(d, axis=1))
assert_eq(np.nanmax(x, axis=(0, 1)), da.nanmax(d, axis=(0, 1)))
assert_eq(np.nanvar(x), da.nanvar(d))
assert_eq(np.nanstd(x, axis=0), da.nanstd(d, axis=0))
assert_eq(np.nanargmin(x, axis=0), da.nanargmin(d, axis=0))
assert_eq(np.nanargmax(x, axis=0), da.nanargmax(d, axis=0))
assert_eq(np.nanprod(x), da.nanprod(d))
def test_nan():
x = np.array([[1, np.nan, 3, 4], [5, 6, 7, np.nan], [9, 10, 11, 12]])
d = da.from_array(x, blockshape=(2, 2))
assert eq(np.nansum(x), da.nansum(d))
assert eq(np.nansum(x, axis=0), da.nansum(d, axis=0))
assert eq(np.nanmean(x, axis=1), da.nanmean(d, axis=1))
assert eq(np.nanmin(x, axis=1), da.nanmin(d, axis=1))
assert eq(np.nanmax(x, axis=(0, 1)), da.nanmax(d, axis=(0, 1)))
assert eq(np.nanvar(x), da.nanvar(d))
assert eq(np.nanstd(x, axis=0), da.nanstd(d, axis=0))
assert eq(np.nanargmin(x, axis=0), da.nanargmin(d, axis=0))
assert eq(np.nanargmax(x, axis=0), da.nanargmax(d, axis=0))
with ignoring(AttributeError):
assert eq(np.nanprod(x), da.nanprod(d))
def test_nan():
x = np.array([[1, np.nan, 3, 4],
[5, 6, 7, np.nan],
[9, 10, 11, 12]])
d = da.from_array(x, chunks=(2, 2))
assert_eq(np.nansum(x), da.nansum(d))
assert_eq(np.nansum(x, axis=0), da.nansum(d, axis=0))
assert_eq(np.nanmean(x, axis=1), da.nanmean(d, axis=1))
assert_eq(np.nanmin(x, axis=1), da.nanmin(d, axis=1))
assert_eq(np.nanmax(x, axis=(0, 1)), da.nanmax(d, axis=(0, 1)))
assert_eq(np.nanvar(x), da.nanvar(d))
assert_eq(np.nanstd(x, axis=0), da.nanstd(d, axis=0))
assert_eq(np.nanargmin(x, axis=0), da.nanargmin(d, axis=0))
assert_eq(np.nanargmax(x, axis=0), da.nanargmax(d, axis=0))
assert_eq(nanprod(x), da.nanprod(d))
def test_nan():
x = np.array([[1, np.nan, 3, 4],
[5, 6, 7, np.nan],
[9, 10, 11, 12]])
d = da.from_array(x, blockshape=(2, 2))
assert eq(np.nansum(x), da.nansum(d))
assert eq(np.nansum(x, axis=0), da.nansum(d, axis=0))
assert eq(np.nanmean(x, axis=1), da.nanmean(d, axis=1))
assert eq(np.nanmin(x, axis=1), da.nanmin(d, axis=1))
assert eq(np.nanmax(x, axis=(0, 1)), da.nanmax(d, axis=(0, 1)))
assert eq(np.nanvar(x), da.nanvar(d))
assert eq(np.nanstd(x, axis=0), da.nanstd(d, axis=0))
assert eq(np.nanargmin(x, axis=0), da.nanargmin(d, axis=0))
assert eq(np.nanargmax(x, axis=0), da.nanargmax(d, axis=0))
with ignoring(AttributeError):
assert eq(np.nanprod(x), da.nanprod(d))
def test_reductions():
x = np.arange(5).astype('f4')
a = da.from_array(x, chunks=(2,))
assert eq(da.all(a), np.all(x))
assert eq(da.any(a), np.any(x))
assert eq(da.argmax(a, axis=0), np.argmax(x, axis=0))
assert eq(da.argmin(a, axis=0), np.argmin(x, axis=0))
assert eq(da.max(a), np.max(x))
assert eq(da.mean(a), np.mean(x))
assert eq(da.min(a), np.min(x))
assert eq(da.nanargmax(a, axis=0), np.nanargmax(x, axis=0))
assert eq(da.nanargmin(a, axis=0), np.nanargmin(x, axis=0))
assert eq(da.nanmax(a), np.nanmax(x))
assert eq(da.nanmin(a), np.nanmin(x))
assert eq(da.nansum(a), np.nansum(x))
assert eq(da.nanvar(a), np.nanvar(x))
assert eq(da.nanstd(a), np.nanstd(x))
def test_reductions():
x = np.arange(5).astype('f4')
a = da.from_array(x, blockshape=(2, ))
assert eq(da.all(a), np.all(x))
assert eq(da.any(a), np.any(x))
assert eq(da.argmax(a, axis=0), np.argmax(x, axis=0))
assert eq(da.argmin(a, axis=0), np.argmin(x, axis=0))
assert eq(da.max(a), np.max(x))
assert eq(da.mean(a), np.mean(x))
assert eq(da.min(a), np.min(x))
assert eq(da.nanargmax(a, axis=0), np.nanargmax(x, axis=0))
assert eq(da.nanargmin(a, axis=0), np.nanargmin(x, axis=0))
assert eq(da.nanmax(a), np.nanmax(x))
assert eq(da.nanmin(a), np.nanmin(x))
assert eq(da.nansum(a), np.nansum(x))
assert eq(da.nanvar(a), np.nanvar(x))
assert eq(da.nanstd(a), np.nanstd(x))
def fit(self, X, y=None):
self._reset()
attributes = OrderedDict()
if isinstance(X, (pd.DataFrame, dd.DataFrame)):
X = X.values
if self.with_mean:
mean_ = nanmean(X, 0)
attributes["mean_"] = mean_
if self.with_std:
var_ = nanvar(X, 0)
scale_ = var_.copy()
scale_[scale_ == 0] = 1
scale_ = da.sqrt(scale_)
attributes["scale_"] = scale_
attributes["var_"] = var_
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,
) -> "StandardScaler":
self._reset()
X = self._validate_data(
X,
estimator=self,
accept_dask_array=True,
accept_dask_dataframe=True,
accept_unknown_chunks=True,
preserve_pandas_dataframe=True,
)
attributes = OrderedDict()
if isinstance(X, (pd.DataFrame, dd.DataFrame)):
X = X.values
if self.with_mean:
mean_ = nanmean(X, 0)
attributes["mean_"] = mean_
if self.with_std:
var_ = nanvar(X, 0)
scale_ = var_.copy()
scale_[scale_ == 0] = 1
scale_ = da.sqrt(scale_)
attributes["scale_"] = scale_
attributes["var_"] = var_
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
