def test_card_combiner_str_not_match():
c = combiner.export()
c['C'] = [['A'], ['B'], ['C']]
com = Combiner().load(c)
bins = com.transform(df)
woe_transer = WOETransformer()
woe = woe_transer.fit_transform(bins, target)
card = ScoreCard(
combiner=com,
transer=woe_transer,
)
with pytest.raises(Exception) as e:
# will raise an exception when fitting a card
card.fit(woe, target)
assert '\'C\' is not matched' in str(e.value)
def test_card_combiner_str_not_match():
c = combiner.export()
c['C'] = [['A'], ['B'], ['C']]
com = Combiner().set_rules(c)
bins = com.transform(df)
woe_transer = WOETransformer()
woe = woe_transer.fit_transform(bins, target)
model = LogisticRegression()
model.fit(woe, target)
with pytest.raises(Exception) as e:
# will raise an exception when create a card
card = ScoreCard(
combiner=com,
transer=woe_transer,
model=model,
)
assert '\'C\' is not matched' in str(e.value)
def test_combiner_labels_with_empty():
combiner = Combiner().fit(df, 'target', n_bins = 4, empty_separate = True)
res = combiner.transform(df, labels = True)
assert res.loc[2, 'D'] == '4.nan'
def test_combiner_labels():
combiner = Combiner().fit(df, target)
res = combiner.transform(df, labels = True)
assert res.loc[451, 'A'] == '3.[3 ~ 4)'
bin_plot(data_c, x=i, target=target)
plt.show()
# combine(train_s, target='loan_status', columns=columns, exclude=['loan_status'])
comb.fit(train_s, y='loan_status', method='chi', min_samples=0.1)
rules = {
'emp_length': [['< 1 year'], ['1 year', '2 years', '3 years'],
['4 years', '5 years', '6 years', '7 years', '8 years'],
['9 years', '10+ years']],
'percent_bc_gt_75': [11.1, 25.9, 52.0],
'avg_cur_bal': [6515.0, 10622.0, 19486.0, 36453.0]
}
comb.set_rules(rules)
train_b = comb.transform(train_s, labels=True)
test_b = comb.transform(test_s, labels=True)
for i in columns[~columns.isin(['split', 'loan_status'])]:
data_i = pd.concat([train_b[i], train_s['loan_status']], axis=1)
bin_plot(data_i, x=i, target='loan_status')
plt.show()
print('分箱完成', '\n' * 2)
# ----------------------------------------------------------------------------------------------------------------------------------------------------
# WOE编码
print('WOE编码'.center(62, '—'))
WOE = WOETransformer()
train_w = WOE.fit_transform(train_b, y='loan_status')
test_w = WOE.fit_transform(test_b, y='loan_status')
print('WOE编码完成', '\n' * 2)
train_w.to_csv('train_w.csv', index=False)
