def Multiply_Divide(train, test, features):
"""
combinations:
combinations(['A', 'B','C'],2) retrun AB AC BC
combinations(range(4), 3) --> 012 013 023 123
"""
feature_names= []
for e, (x, y) in enumerate(combinations(features, 2)):
train, test, feature_name= interaction_features(train, test, x, y, e)
for name in feature_name:
feature_names.append(name)
return train, test, feature_names
test_id = test['id']
del test['id']
cat_fea = [x for x in list(train) if 'cat' in x]
bin_fea = [x for x in list(train) if 'bin' in x]
train['missing'] = (train == -1).sum(axis=1).astype(float)
test['missing'] = (test == -1).sum(axis=1).astype(float)
# include interactions
for e, (x, y) in enumerate(
combinations([
'ps_car_13', 'ps_ind_03', 'ps_reg_03', 'ps_ind_15', 'ps_reg_01',
'ps_ind_01'
], 2)):
train, test = interaction_features(train, test, x, y, e)
num_features = [c for c in list(train) if ('cat' not in c and 'calc' not in c)]
num_features.append('missing')
inter_fea = [x for x in list(train) if 'inter' in x]
#train['cat_sum'] = train[cat_fea].sum(axis=1)
#test['cat_sum'] = test[cat_fea].sum(axis=1)
#X = train.as_matrix()
#X_test = test.as_matrix()
#print(X.shape, X_test.shape)
#ohe
ohe = OneHotEncoder(sparse=True)
train_cat = train[cat_fea].as_matrix()
train_num = train[[x for x in list(train) if x in num_features]]
train_id = train['id']
del train['target'], train['id']
test = pd.read_csv("../input/test.csv")
test_id = test['id']
del test['id']
cat_fea = [x for x in list(train) if 'cat' in x]
bin_fea = [x for x in list(train) if 'bin' in x]
train['missing'] = (train==-1).sum(axis=1).astype(float)
test['missing'] = (test==-1).sum(axis=1).astype(float)
# include interactions
for e, (x, y) in enumerate(combinations(['ps_car_13', 'ps_ind_03', 'ps_reg_03', 'ps_ind_15', 'ps_reg_01', 'ps_ind_01'], 2)):
train, test = interaction_features(train, test, x, y, e)
num_features = [c for c in list(train) if ('cat' not in c and 'calc' not in c)]
num_features.append('missing')
inter_fea = [x for x in list(train) if 'inter' in x]
#train['cat_sum'] = train[cat_fea].sum(axis=1)
#test['cat_sum'] = test[cat_fea].sum(axis=1)
path = "../input/"
num_features_comb = []
for p in os.listdir(path):
if 'ps_reg_02___ps_car_07_cat' in p or 'ps_reg_01___ps_car_13___ps_car_15' in p:
print(p)
x,xt = pd.read_pickle(path+p)
train[p] = x
test[p] = xt