|
|
@@ -0,0 +1,76 @@
|
|
|
+import datetime
|
|
|
+import pandas as pd
|
|
|
+from xgboost.sklearn import XGBClassifier
|
|
|
+from sklearn.model_selection import GridSearchCV
|
|
|
+from sklearn import metrics
|
|
|
+
|
|
|
+
|
|
|
+now_date = datetime.datetime.today()
|
|
|
+dt = datetime.datetime.strftime(now_date, '%Y%m%d')
|
|
|
+# 1. 读取数据
|
|
|
+train_data = pd.read_csv(f'./data/train_test_data/train_{dt}.csv')
|
|
|
+print(train_data.shape)
|
|
|
+test_data = pd.read_csv(f'./data/train_test_data/test_{dt}.csv')
|
|
|
+print(test_data.shape)
|
|
|
+# 2. 划分x和y
|
|
|
+data_columns = train_data.columns.values.tolist()
|
|
|
+x_train = train_data[data_columns[:-1]]
|
|
|
+y_train = train_data[data_columns[-1]]
|
|
|
+x_test = test_data[data_columns[:-1]]
|
|
|
+y_test = test_data[data_columns[-1]]
|
|
|
+print(f"x_train_shape: {x_train.shape}")
|
|
|
+print(f"x_test_shape: {x_test.shape}")
|
|
|
+
|
|
|
+parameters = {
|
|
|
+ 'max_depth': range(3, 10, 2), # 树的最大深度
|
|
|
+ 'learning_rate': [i/10 for i in range(1, 5)], # 学习率
|
|
|
+ 'n_estimators': range(50, 500, 50), # 最大迭代次数
|
|
|
+ 'min_child_weight': range(1, 6, 2), # 叶子结点的最小权重
|
|
|
+}
|
|
|
+
|
|
|
+grid = GridSearchCV(
|
|
|
+ estimator=XGBClassifier(
|
|
|
+ learning_rate=0.1, # 学习率，控制每次迭代更新权重时的步长，默认0.3;调参：值越小，训练越慢;典型值为0.01-0.2
|
|
|
+ n_estimators=50, # 总共迭代的次数，即决策树的个数
|
|
|
+ max_depth=3, # 树的深度,默认值为6，典型值3-10;调参：值越大，越容易过拟合；值越小，越容易欠拟合
|
|
|
+ min_child_weight=5, # 叶子节点最小权重;默认值为1;调参：值越大，越容易欠拟合；值越小，越容易过拟合
|
|
|
+ objective='binary:logistic',
|
|
|
+ eval_metric=['error', 'auc']
|
|
|
+ ),
|
|
|
+ param_grid=parameters,
|
|
|
+ scoring='roc_auc',
|
|
|
+ n_jobs=4,
|
|
|
+ iid=False,
|
|
|
+ cv=5)
|
|
|
+grid.fit(x_train, y_train)
|
|
|
+
|
|
|
+print(f"grid.best_params_: {grid.best_params_}")
|
|
|
+print(f"grid.best_score_: {grid.best_score_}")
|
|
|
+
|
|
|
+clf = grid.best_estimator_
|
|
|
+print(f"grid.best_estimator_: {grid.best_estimator_}")
|
|
|
+
|
|
|
+clf.fit(x_train, y_train)
|
|
|
+y_train_pred = clf.predict(x_train)
|
|
|
+train_accuracy = metrics.accuracy_score(y_train, y_train_pred)
|
|
|
+train_auc = metrics.roc_auc_score(y_train, y_train_pred)
|
|
|
+train_recall = metrics.recall_score(y_train, y_train_pred)
|
|
|
+train_f1 = metrics.f1_score(y_train, y_train_pred)
|
|
|
+train_precision = metrics.precision_score(y_train, y_train_pred)
|
|
|
+print(f"Train Accuracy: {train_accuracy * 100.0}.2f%%, "
|
|
|
+ f"auc: {train_auc}.2f, "
|
|
|
+ f"recall: {train_recall * 100.0}.2f%%, "
|
|
|
+ f"f1: {train_f1 * 100.0}.2f%%, "
|
|
|
+ f"precision: {train_precision * 100.0}.2f%%")
|
|
|
+
|
|
|
+y_test_pred = clf.predict(x_test)
|
|
|
+test_accuracy = metrics.accuracy_score(y_test, y_test_pred)
|
|
|
+test_auc = metrics.roc_auc_score(y_test, y_test_pred)
|
|
|
+test_recall = metrics.recall_score(y_test, y_test_pred)
|
|
|
+test_f1 = metrics.f1_score(y_test, y_test_pred)
|
|
|
+test_precision = metrics.precision_score(y_test, y_test_pred)
|
|
|
+print(f"Test Accuracy: {test_accuracy * 100.0}.2f%%, "
|
|
|
+ f"auc: {test_auc}.2f, "
|
|
|
+ f"recall: {test_recall * 100.0}.2f%%, "
|
|
|
+ f"f1: {test_f1 * 100.0}.2f%%, "
|
|
|
+ f"precision: {test_precision * 100.0}.2f%%")
|
