X = pd.concat([X_cat_dummies, X_num, X_survey], axis=1)
if TEST == True:
n = X.shape[0]
test_size = np.floor(n * 0.1)
X = X.loc[0:test_size, :]
ys = ys.loc[0:test_size, :]
all_scores = {}
for dependent_variable in y_variables:
print('Running variables: ' + dependent_variable)
y = ys[dependent_variable].values
print('Running Linear Regression')
# Linear Regression
lr_cv_train_scores, lr_cv_test_scores = models.lr_model(
X, y, dummies, num_demo + data_sets[key])
all_scores['lr_train_' + dependent_variable] = lr_cv_train_scores
all_scores['lr_test_' + dependent_variable] = lr_cv_test_scores
print('Running Random Forest')
#Random Forest
if TEST == True:
param_grid = {
'max_depth': [15],
'min_samples_leaf': [20],
'min_samples_split': [20],
'n_estimators': [500]
}
else:
print("被筛选的特征数量", selector.n_features_)
print("特征排名", selector.ranking_)
columns = x_train.columns
selects = [columns[i] for i, j in enumerate(selector.support_) if j]
cat_features = [
"is_festival_user",
"is_LAST_2YEAR_DD_ACTIVE",
"cafe_tag_is_mop_available",
"IS_SR_KIT_USER",
]
x_train = x_train[selects]
x_test = x_test[selects]
x_btest = df_btest[selects]
adaboost_model(x_train, x_test, y_train, y_test, x_btest, df_btest[labels])
lr_model(x_train, x_test, y_train, y_test, x_btest, df_btest[labels])
gbdt_mdoel(x_train, x_test, y_train, y_test, x_btest, df_btest[labels])
xgb_model(x_train, x_test, y_train, y_test, x_btest, df_btest[labels])
lgb_model(x_train, x_test, y_train, y_test, x_btest, df_btest[labels])
cat_boost_model(x_train,
x_test,
y_train,
y_test,
x_btest,
df_btest[labels],
cat_features=cat_features)
# from sklearn.feature_selection import RFECV
# x = df_train.copy()
# clf1 = RandomForestClassifier()
# x1 = X_train_tra[X_train_tra[labels] == 1]
# x0 = x0.sample(n=None, frac=0.33, replace=False, weights=None, random_state=0, axis=0)
# X_train_tra = pd.concat([x0, x1], axis=0)
# 划分label
x_train, y_train = seperate_label(X_train_tra, label=labels)
x_test, y_test = seperate_label(X_test_tra, label=labels)
print("x_train", x_train.shape)
# #模型训练
# adaboost模型
adaboost_model(x_train, x_test, y_train, y_test,
df_btest.drop(labels, axis=1), df_btest[labels])
# LR模型
lr_model(x_train, x_test, y_train, y_test, df_btest.drop(labels, axis=1),
df_btest[labels])
# # rf模型
rf_mdoel(x_train, x_test, y_train, y_test, df_btest.drop(labels, axis=1),
df_btest[labels])
# # #
# # gbdt模型
gbdt_mdoel(x_train, x_test, y_train, y_test, df_btest.drop(labels, axis=1),
df_btest[labels])
# xgb模型
xgb_model(x_train, x_test, y_train, y_test, df_btest.drop(labels, axis=1),
df_btest[labels])
# lgb模型
lgb_model(x_train,
x_test,