def test_basic(self):
a = dpp.StandardScaler()
b = spp.StandardScaler()
a.fit(X)
b.fit(X.compute())
assert_estimator_equal(a, b)
def test_basic(self):
a = dpp.StandardScaler()
b = spp.StandardScaler()
a.fit(X)
b.fit(X.compute())
assert_estimator_equal(a, b, exclude="n_samples_seen_")
def test_nan(self, pandas_df):
pandas_df = pandas_df.copy()
pandas_df.iloc[0] = np.nan
dask_nan_df = dd.from_pandas(pandas_df, npartitions=5)
a = dpp.StandardScaler()
a.fit(dask_nan_df.values)
assert np.isnan(a.mean_).sum() == 0
assert np.isnan(a.var_).sum() == 0
def test_input_types(self, dask_df, pandas_df):
a = dpp.StandardScaler()
b = spp.StandardScaler()
assert_estimator_equal(a.fit(dask_df.values),
a.fit(dask_df),
exclude="n_samples_seen_")
assert_estimator_equal(a.fit(dask_df),
b.fit(pandas_df),
exclude="n_samples_seen_")
assert_estimator_equal(a.fit(dask_df.values),
b.fit(pandas_df),
exclude="n_samples_seen_")
assert_estimator_equal(a.fit(dask_df),
b.fit(pandas_df.values),
exclude="n_samples_seen_")
assert_estimator_equal(a.fit(dask_df.values),
b.fit(pandas_df.values),
exclude="n_samples_seen_")
def test_inverse_transform(self):
a = dpp.StandardScaler()
assert_eq_ar(
a.inverse_transform(a.fit_transform(X)).compute(), X.compute())
def test_inverse_transform(self):
a = dpp.StandardScaler()
result = a.inverse_transform(a.fit_transform(X))
assert dask.is_dask_collection(result)
assert_eq_ar(result, X)