def test_df_values(self):
est1 = dpp.MinMaxScaler()
est2 = dpp.MinMaxScaler()
result_ar = est1.fit_transform(X)
result_df = est2.fit_transform(df)
for attr in ["data_min_", "data_max_", "data_range_", "scale_", "min_"]:
assert_eq_ar(getattr(est1, attr), getattr(est2, attr).values)
assert_eq_ar(est1.transform(X), est2.transform(df).values)
if hasattr(result_df, "values"):
result_df = result_df.values
assert_eq_ar(result_ar, result_df)
def test_basic(self):
a = dpp.MinMaxScaler()
b = spp.MinMaxScaler()
a.fit(X)
b.fit(X.compute())
assert_estimator_equal(a, b, exclude='n_samples_seen_')
def test_df_values(self):
est1 = dpp.MinMaxScaler()
est2 = dpp.MinMaxScaler()
result_ar = est1.fit_transform(X)
result_df = est2.fit_transform(df)
for attr in [
'data_min_', 'data_max_', 'data_range_', 'scale_', 'min_'
]:
assert_eq_ar(getattr(est1, attr), getattr(est2, attr).values)
assert_eq_ar(est1.transform(X), est2.transform(X))
assert_eq_ar(est1.transform(df).values, est2.transform(X))
assert_eq_ar(est1.transform(X), est2.transform(df).values)
assert_eq_ar(result_ar, result_df.values)
def test_df_column_slice(self):
mask = ["3", "4"]
mask_ix = [mask.index(x) for x in mask]
a = dpp.MinMaxScaler(columns=mask)
b = spp.MinMaxScaler()
dfa = a.fit_transform(df2).compute()
mxb = b.fit_transform(df2.compute())
assert isinstance(dfa, pd.DataFrame)
assert_eq_ar(dfa[mask].values, mxb[:, mask_ix])
assert_eq_df(dfa.drop(mask, axis=1), df2.drop(mask, axis=1).compute())
def test_df_inverse_transform(self):
mask = ["3", "4"]
a = dpp.MinMaxScaler(columns=mask)
assert_eq_df(
a.inverse_transform(a.fit_transform(df2)).compute(), df2.compute())
def test_inverse_transform(self):
a = dpp.MinMaxScaler()
assert_eq_ar(
a.inverse_transform(a.fit_transform(X)).compute(), X.compute())
def dataScaling(users_genres):
scaler = preprocessing.MinMaxScaler()
scaler.fit(users_genres)
return scaler.transform(users_genres)
def test_df_values(self):
a = dpp.MinMaxScaler()
assert_eq_ar(
a.fit_transform(X).compute(),
a.fit_transform(df).compute().as_matrix())
def test_df_inverse_transform(self):
mask = ["3", "4"]
a = dpp.MinMaxScaler(columns=mask)
result = a.inverse_transform(a.fit_transform(df2))
assert dask.is_dask_colelction(result)
assert_eq_df(result, df2)
def test_inverse_transform(self):
a = dpp.MinMaxScaler()
result = a.inverse_transform(a.fit_transform(X))
assert dask.is_dask_collection(result)
assert_eq_ar(result, X)