def test_cross_val_stack(self):
x, y = DataGenerator.get_digits_data()
# In order to obtain some categorical columns
x['i63'] = x['i63'].map(str)
x['i62'] = x['i62'].map(str)
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.33,
random_state=42)
dic = {}
x_shadow = x_train.copy()
x_train.loc[:, 'source'] = 0
x_shadow.loc[:, 'source'] = 1
x_all = pd.concat([x_train, x_shadow])
shadow_selector = x_all['source'] == 0
ChaosGeneration.chaos_feature_importance(x_all,
y_train,
shadow_selector,
feat_dic=dic,
feat_iter=10,
nb_features=20,
chaos_gen_iter=30)
sorted_x = sorted(dic.items(), key=operator.itemgetter(1))
self.assertGreater(len(dic), len(x_train.columns))
self.assertGreater(len(dic), len(x_shadow.columns))
def chaosize(x_feat, x_train1, x_valid, y_feat, **chaos_args):
x_feat.loc[:, 'source'] = 0
x_train1.loc[:, 'source'] = 1
x_valid.loc[:, 'source'] = 2
x_all = pd.concat([x_feat, x_train1, x_valid])
Cg.chaos_feature_importance(x_all, y_feat, x_all['source'] == 0, **chaos_args)
x_train_res = x_all[x_all['source'] == 1].drop(['source'], axis=1)
x_valid_res = x_all[x_all['source'] == 2].drop(['source'], axis=1)
return x_train_res, x_valid_res
def chaosize(x_feat, x_mirror, x_valid, y_feat, **chaos_args):
x_feat.loc[:, 'source'] = 0
x_mirror.loc[:, 'source'] = 1
x_valid.loc[:, 'source'] = 2
x_all = pd.concat([x_feat, x_mirror, x_valid])
Cg.chaos_feature_importance(x_all, y_feat, x_all['source'] == 0,
**chaos_args)
x_train_res = x_all[x_all['source'] == 1].drop(['source'], axis=1)
x_valid_res = x_all[x_all['source'] == 2].drop(['source'], axis=1)
return x_train_res, x_valid_res
def test_cross_val_stack_none(self):
x, y = DataGenerator.get_digits_data()
# In order to obtain some categorical columns
x["i63"] = x["i63"].map(str)
x["i62"] = x["i62"].map(str)
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.33, random_state=42)
dic = {}
x_train.loc[:, "source"] = 0
shadow_selector = x_train["source"] == 0
ChaosGeneration.chaos_feature_importance(
x_train, y_train, shadow_selector, feat_dic=dic, feat_iter=10, nb_features=20, chaos_gen_iter=30
)
sorted_x = sorted(dic.items(), key=operator.itemgetter(1))
self.assertGreater(len(dic), len(x_train.columns))
def test_handle_nocategoric_nonreg(self):
x, y = DataGenerator.get_digits_data()
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.33,
random_state=42)
dic = {}
x_train.loc[:, 'source'] = 0
shadow_selector = x_train['source'] == 0
ChaosGeneration.chaos_feature_importance(x_train,
y_train,
shadow_selector,
feat_dic=dic,
feat_iter=10,
nb_features=20,
chaos_gen_iter=30)
self.assertGreater(len(dic), len(x_train.columns))