alg/main.py

import os
import sys
import json

from sklearn.linear_model import LogisticRegression

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


class LightGBM(object):
    """
    LightGBM model for classification
    """

    def __init__(self):
        self.label_encoder = LabelEncoder()
        self.my_c = [
            "uid",
            "type",
            "channel",
            "fans",
            "view_count_user_30days",
            "share_count_user_30days",
            "return_count_user_30days",
            "rov_user",
            "str_user",
            "out_user_id",
            "mode",
            "out_play_cnt",
            "out_like_cnt",
            "out_share_cnt",
            "out_collection_cnt",
            "tag1",
            "tag2",
            "tag3"
        ]
        self.str_columns = ["uid", "type", "channel", "mode", "out_user_id", "tag1", "tag2", "tag3"]
        self.float_columns = [
            "fans",
            "view_count_user_30days",
            "share_count_user_30days",
            "return_count_user_30days",
            "rov_user",
            "str_user",
            "out_play_cnt",
            "out_like_cnt",
            "out_share_cnt",
            "out_collection_cnt",
        ]
        self.split_c = 0.98
        self.yc = 0.8
        self.model = "lightgbm_tag_train_01.bin"

    def generate_x_data(self):
        """
        Generate data for feature engineering
        :return:
        """
        with open("produce_data/x_data_total_return_train.json") 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])
        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)
        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

    def generate_y_data(self):
        """
        Generate data for label
        :return:
        """
        with open("produce_data/y_data_total_return_train.json") 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

    def train_model(self):
        """
        Load dataset
        :return:
        """
        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=["uid", "type", "channel", "mode", "out_user_id", "tag1", "tag2", "tag3"],
        )
        test_data = lgb.Dataset(X_test, label=Y_test, reference=train_data)
        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": 0.01,  # 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
            "num_threads": 4,  # 线程数量
        }
        # 训练模型
        num_round = 500
        print("开始训练......")
        bst = lgb.train(params, train_data, num_round, valid_sets=[test_data])
        bst.save_model(self.model)
        print("模型训练完成✅")

    def evaluate_model(self):
        """
        评估模型性能
        :return:
        """
        fw = open("summary_tag_01.txt", "a+", encoding="utf-8")
        # 测试数据
        with open("produce_data/x_data_total_return_predict.json") as f1:
            x_list = json.loads(f1.read())

        # 测试 label
        with open("produce_data/y_data_total_return_predict.json") as f2:
            Y_test = json.loads(f2.read())

        Y_test = [0 if i <= 26 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")
        bst = lgb.Booster(model_file=self.model)
        y_pred = bst.predict(X_test, num_iteration=bst.best_iteration)
        y_pred_binary = [0 if i <= 0.158550 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]
            score = item
            prid_label = y_pred_binary[index]
            print(real_label, "\t", prid_label, "\t", score)
            fw.write("{}\t{}\t{}\n".format(real_label, prid_label, score))
            score_list.append(score)
        print("预测样本总量: {}".format(len(score_list)))
        data_series = pd.Series(score_list)
        print("统计 score 信息")
        print(data_series.describe())
        # 评估模型
        accuracy = accuracy_score(Y_test, y_pred_binary)
        print(f"Accuracy: {accuracy}")
        fw.close()

    def feature_importance(self):
        """
        Get the importance of each feature
        :return:
        """
        lgb_model = lgb.Booster(model_file=self.model)
        importance = lgb_model.feature_importance(importance_type='split')
        feature_name = lgb_model.feature_name()
        feature_importance = sorted(zip(feature_name, importance), key=lambda x: x[1], reverse=True)

        # 打印特征重要性
        for name, imp in feature_importance:
            print(name, imp)


if __name__ == "__main__":
    L = LightGBM()
    # L.train_model()
    L.evaluate_model()
    # L.feature_importance()