generate label for mysql

main_userupload.py

@@ -1,20 +1,23 @@
 """
-针对爬虫类型数据单独训练模型
+针对用户类型数据单独训练模型
 """
 import os
 import sys
 import json
 import optuna
+import numpy as np
 
-from sklearn.linear_model import LogisticRegression
+from sklearn.preprocessing import LabelEncoder
 
 sys.path.append(os.getcwd())
 
-import numpy as np
 import pandas as pd
 import lightgbm as lgb
-from sklearn.preprocessing import LabelEncoder
-from sklearn.metrics import accuracy_score
+
+from scipy.stats import randint as sp_randint
+from scipy.stats import uniform as sp_uniform
+from sklearn.model_selection import RandomizedSearchCV, train_test_split
+from sklearn.metrics import roc_auc_score, accuracy_score
 
 
 class LightGBM(object):
@@ -25,123 +28,127 @@ class LightGBM(object):
     def __init__(self, flag, dt):
         self.label_encoder = LabelEncoder()
         self.my_c = [
-            "uid",
             "channel",
-            "fans",
-            "view_count_user_30days",
-            "share_count_user_30days",
-            "return_count_user_30days",
-            "rov_user",
-            "str_user",
+            "user_fans",
+            "user_view_30",
+            "user_share_30",
+            "user_return_30",
+            "user_rov",
+            "user_str",
+            "user_return_videos_30",
+            "user_return_videos_3",
+            "user_return_3",
+            "user_view_3",
+            "user_share_3",
+            "address",
             "tag1",
             "tag2",
             "tag3"
         ]
-        self.str_columns = ["channel", "uid", "tag1", "tag2", "tag3"]
+        self.str_columns = ["channel", "address", "tag1", "tag2", "tag3"]
         self.float_columns = [
-            "fans",
-            "view_count_user_30days",
-            "share_count_user_30days",
-            "return_count_user_30days",
-            "rov_user",
-            "str_user",
+            "user_fans",
+            "user_view_30",
+            "user_share_30",
+            "user_return_30",
+            "user_rov",
+            "user_str",
+            "user_return_videos_30",
+            "user_return_videos_3",
+            "user_return_3",
+            "user_share_3",
+            "user_view_3"
         ]
         self.split_c = 0.7
         self.yc = 0.8
-        self.model = "lightgbm_0326_user.bin"
+        self.model = "models/lightgbm_0402_user.bin"
         self.flag = flag
         self.dt = dt
 
-    def bays_params(self, trial):
-        """
-        Bayesian parameters for
-        :return: best parameters
+    def read_data(self, path):
         """
-        # 定义搜索空间
-        param = {
-            'objective': 'binary',
-            'metric': 'binary_logloss',
-            'verbosity': -1,
-            'boosting_type': 'gbdt',
-            'num_leaves': trial.suggest_int('num_leaves', 20, 40),
-            'learning_rate': trial.suggest_loguniform('learning_rate', 1e-8, 1.0),
-            'feature_fraction': trial.suggest_uniform('feature_fraction', 0.4, 1.0),
-            'bagging_fraction': trial.suggest_uniform('bagging_fraction', 0.4, 1.0),
-            'bagging_freq': trial.suggest_int('bagging_freq', 1, 7),
-            'min_child_samples': trial.suggest_int('min_child_samples', 5, 100),
-            "num_threads": 16,  # 线程数量
-        }
-        X_train, X_test = self.generate_x_data()
-        Y_train, Y_test = self.generate_y_data()
-        train_data = lgb.Dataset(
-            X_train,
-            label=Y_train,
-            categorical_feature=["channel", "uid", "tag1", "tag2", "tag3"],
-        )
-        test_data = lgb.Dataset(X_test, label=Y_test, reference=train_data)
-        gbm = lgb.train(param, train_data, num_boost_round=100, valid_sets=[test_data])
-        preds = gbm.predict(X_test)
-        pred_labels = np.rint(preds)
-        accuracy = accuracy_score(Y_test, pred_labels)
-        return accuracy
-
-    def generate_x_data(self):
-        """
-        Generate data for feature engineering
+        Read data from local
         :return:
         """
-        with open("data/produce_data/x_data_total_return_{}_{}_user.json".format(self.flag, self.dt)) as f1:
-            x_list = json.loads(f1.read())
-        index_t = int(len(x_list) * self.split_c)
-        X_train = pd.DataFrame(x_list[:index_t], columns=self.my_c)
-        for key in self.str_columns:
-            X_train[key] = self.label_encoder.fit_transform(X_train[key])
+        df = pd.read_json(path)
+        df = df.dropna(subset=['label'])
+        labels = df['label']
+        temp = sorted(labels)
+        yc = temp[int(len(temp) * 0.7)]
+        print("阈值", yc)
+        labels = [0 if i < yc else 1 for i in labels]
+        features = df.drop("label", axis=1)
         for key in self.float_columns:
-            X_train[key] = pd.to_numeric(X_train[key], errors="coerce")
-        X_test = pd.DataFrame(x_list[index_t:], columns=self.my_c)
+            features[key] = pd.to_numeric(features[key], errors="coerce")
         for key in self.str_columns:
-            X_test[key] = self.label_encoder.fit_transform(X_test[key])
-        for key in self.float_columns:
-            X_test[key] = pd.to_numeric(X_test[key], errors="coerce")
-        return X_train, X_test
+            features[key] = self.label_encoder.fit_transform(features[key])
+        return features, labels
+
+    def best_params(self):
+        path = "data/train_data/spider_train_20240402"
+        X, y = self.read_data(path)
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+        lgbm = lgb.LGBMClassifier(objective='binary')
+
+        # 设置搜索的参数范围
+        param_dist = {
+            'num_leaves': sp_randint(20, 40),
+            'learning_rate': sp_uniform(0.001, 0.1),
+            'feature_fraction': sp_uniform(0.5, 0.9),
+            'bagging_fraction': sp_uniform(0.5, 0.9),
+            'bagging_freq': sp_randint(1, 10),
+            'min_child_samples': sp_randint(5, 100),
+        }
 
-    def generate_y_data(self):
-        """
-        Generate data for label
-        :return:
-        """
-        with open("data/produce_data/y_data_total_return_{}_{}_user.json".format(self.flag, self.dt)) as f2:
-            y_list = json.loads(f2.read())
-        index_t = int(len(y_list) * self.split_c)
-        temp = sorted(y_list)
-        yuzhi = temp[int(len(temp) * self.yc) - 1]
-        print("阈值是: {}".format(yuzhi))
-        y__list = [0 if i <= yuzhi else 1 for i in y_list]
-        y_train = np.array(y__list[:index_t])
-        y_test = np.array(y__list[index_t:])
-        return y_train, y_test
+        # 定义 RandomizedSearchCV
+        rsearch = RandomizedSearchCV(
+            estimator=lgbm,
+            param_distributions=param_dist,
+            n_iter=100,
+            cv=3,
+            scoring='roc_auc',
+            random_state=42, verbose=2
+        )
+
+        # 开始搜索
+        rsearch.fit(X_train, y_train)
+
+        # 打印最佳参数和对应的AUC得分
+        print("Best parameters found: ", rsearch.best_params_)
+        print("Best AUC found: ", rsearch.best_score_)
+
+        # 使用最佳参数在测试集上的表现
+        best_model = rsearch.best_estimator_
+        y_pred = best_model.predict_proba(X_test)[:, 1]
+        auc = roc_auc_score(y_test, y_pred)
+        print("AUC on test set: ", auc)
 
     def train_model(self):
         """
         Load dataset
         :return:
         """
-        X_train, X_test = self.generate_x_data()
-        Y_train, Y_test = self.generate_y_data()
+        path = "data/train_data/spider_train_20240402"
+        x, y = self.read_data(path)
+        train_size = int(len(x) * self.split_c)
+        X_train, X_test = x[:train_size], x[train_size:]
+        Y_train, Y_test = y[:train_size], y[train_size:]
         train_data = lgb.Dataset(
             X_train,
             label=Y_train,
-            categorical_feature=["channel", "uid", "tag1", "tag2", "tag3"],
+            categorical_feature=self.str_columns,
         )
         test_data = lgb.Dataset(X_test, label=Y_test, reference=train_data)
         params = {
-            'num_leaves': 29,
-            'learning_rate': 0.0005153812869522004,
-            'feature_fraction': 0.7460901121756344,
-            'bagging_fraction': 0.5744390458938479,
-            'bagging_freq': 1,
-            "num_threads": 16,
-            }
+            'bagging_fraction': 0.7938866919252519,
+            'bagging_freq': 7,
+            'feature_fraction': 0.9687508340232414,
+            'learning_rate': 0.09711720243493492,
+            'min_child_samples': 89,
+            'num_leaves': 35,
+            'num_threads': 16
+        }
 
         # 训练模型
         num_round = 100
@@ -155,30 +162,18 @@ class LightGBM(object):
         评估模型性能
         :return:
         """
-        fw = open("summary_tag_03{}_user.txt".format(self.dt), "a+", encoding="utf-8")
-        # 测试数据
-        with open("data/produce_data/x_data_total_return_predict_{}_user.json".format(self.dt)) as f1:
-            x_list = json.loads(f1.read())
-
-        # 测试 label
-        with open("data/produce_data/y_data_total_return_predict_{}_user.json".format(self.dt)) as f2:
-            Y_test = json.loads(f2.read())
-
-        Y_test = [0 if i <= 31 else 1 for i in Y_test]
-        X_test = pd.DataFrame(x_list, columns=self.my_c)
-        for key in self.str_columns:
-            X_test[key] = self.label_encoder.fit_transform(X_test[key])
-        for key in self.float_columns:
-            X_test[key] = pd.to_numeric(X_test[key], errors="coerce")
+        fw = open("result/summary_{}.txt".format(dt), "a+", encoding="utf-8")
+        path = 'data/predict_data/predict_{}.json'.format(dt)
+        x, y = self.read_data(path)
         bst = lgb.Booster(model_file=self.model)
-        y_pred = bst.predict(X_test, num_iteration=bst.best_iteration)
+        y_pred = bst.predict(x, num_iteration=bst.best_iteration)
         temp = sorted(list(y_pred))
         yuzhi = temp[int(len(temp) * 0.7) - 1]
         y_pred_binary = [0 if i <= yuzhi else 1 for i in list(y_pred)]
         # 转换为二进制输出
         score_list = []
         for index, item in enumerate(list(y_pred)):
-            real_label = Y_test[index]
+            real_label = y[index]
             score = item
             prid_label = y_pred_binary[index]
             print(real_label, "\t", prid_label, "\t", score)
@@ -189,7 +184,7 @@ class LightGBM(object):
         print("统计 score 信息")
         print(data_series.describe())
         # 评估模型
-        accuracy = accuracy_score(Y_test, y_pred_binary)
+        accuracy = accuracy_score(y, y_pred_binary)
         print(f"Accuracy: {accuracy}")
         fw.close()
 
@@ -217,12 +212,10 @@ if __name__ == "__main__":
         L.train_model()
     elif i == 2:
         f = "predict"
-        dt = int(input("输入日期， 16-21:\n"))
+        dt = int(input("输入日期， 20240316-21:\n"))
         L = LightGBM(flag=f, dt=dt)
         L.evaluate_model()
         L.feature_importance()
-    # L = LightGBM("train", "whole")
-    # study = optuna.create_study(direction='maximize')
-    # study.optimize(L.bays_params, n_trials=100)
-    # print('Number of finished trials:', len(study.trials))
-    # print('Best trial:', study.best_trial.params)
+    elif i == 3:
+        L = LightGBM("train", "whole")
+        L.best_params()

process_data.py

@@ -243,10 +243,10 @@ class UserProcess(object):
         temp_time = three_date_before.strftime("%Y%m%d")
         if flag == "train":
             sql = "select video_title, label, user_id, channel, user_fans, user_view_30, user_share_30, user_return_30, user_rov, user_str, user_return_videos_30, user_return_videos_3, user_return_3, user_view_3, user_share_3, address from lightgbm_data where type = 'userupload' and daily_dt_str >= '20240305';"
-            des_path = "data/train_data/spider_train_{}".format(datetime.datetime.today().strftime("%Y%m%d"))
+            des_path = "data/train_data/user_train_{}.json".format(datetime.datetime.today().strftime("%Y%m%d"))
         elif flag == "predict":
             sql = f"""select video_title, label, user_id, channel, user_fans, user_view_30, user_share_30, user_return_30, user_rov, user_str, user_return_videos_30, user_return_videos_3, user_return_3, user_view_3, user_share_3, address from lightgbm_data where type = 'userupload' and daily_dt_str = '{temp_time}';"""
-            des_path = "data/predict_data/predict_{}.json".format(dt_time.strftime("%Y%m%d"))
+            des_path = "data/predict_data/user_predict_{}.json".format(dt_time.strftime("%Y%m%d"))
         else:
             return
         dt_list = self.client_spider.select(sql)