测试提交

functions/odps_function.py

@@ -0,0 +1,34 @@
+"""
+python ODPS class
+"""
+from odps import ODPS
+
+
+class PyODPS(object):
+    """
+    PyODPS class, get data from odps server
+    """
+
+    def __init__(self):
+        self.endpoint = "http://service.cn.maxcompute.aliyun.com/api"
+        self.access_id = "LTAIWYUujJAm7CbH"
+        self.access_key = "RfSjdiWwED1sGFlsjXv0DlfTnZTG1P"
+        self.project = "loghubods"
+
+        self.od = ODPS(
+            access_id=self.access_id,
+            secret_access_key=self.access_key,
+            endpoint=self.endpoint,
+            project=self.project,
+        )
+
+    def select(self, sql):
+        """
+        :param sql: 查询语句
+        :return: odps_obj{}
+        """
+        result = []
+        with self.od.execute_sql(sql).open_reader() as reader:
+            for record in reader:
+                result.append(record)
+        return result

main.py

@@ -0,0 +1,39 @@
+import numpy as np
+import lightgbm as lgb
+from sklearn.model_selection import train_test_split
+from sklearn.datasets import make_classification
+from sklearn.metrics import accuracy_score
+
+# 生成模拟数据
+X, y = make_classification(n_samples=1000, n_features=20, n_classes=2, random_state=42)
+
+# 分割数据集
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# 创建LightGBM数据集
+train_data = lgb.Dataset(X_train, label=y_train)
+test_data = lgb.Dataset(X_test, label=y_test, reference=train_data)
+
+# 设置模型的参数
+params = {
+    'objective': 'binary',       # 指定二分类任务
+    'metric': 'binary_logloss',  # 评估指标为二分类的log损失
+    'num_leaves': 31,            # 叶子节点数
+    'learning_rate': 0.05,       # 学习率
+    'bagging_fraction': 0.9,     # 建树的样本采样比例
+    'feature_fraction': 0.8,     # 建树的特征选择比例
+    'bagging_freq': 5,           # k 意味着每 k 次迭代执行bagging
+}
+
+# 训练模型
+num_round = 100
+bst = lgb.train(params, train_data, num_round, valid_sets=[test_data], early_stopping_rounds=10)
+
+# 预测
+y_pred = bst.predict(X_test, num_iteration=bst.best_iteration)
+# 转换为二进制输出
+y_pred_binary = np.where(y_pred > 0.5, 1, 0)
+
+# 评估模型
+accuracy = accuracy_score(y_test, y_pred_binary)
+print(f'Accuracy: {accuracy}')