使用词向量特征建模-逻辑回归

最新推荐文章于 2025-12-18 17:00:31 发布

原创

最新推荐文章于 2025-12-18 17:00:31 发布 · 129 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#逻辑回归 #算法 #机器学习

import time
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split  # 划分数据
from sklearn.metrics import classification_report, auc, roc_auc_score  # F1/AUC #精确率召回率
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import roc_curve
import joblib
import sys
from pyspark.sql import SparkSession
import os
import datetime

start_time = datetime.datetime.now()
# 配置环境变量，否则报错python3找不到
os.environ['PYSPARK_PYTHON'] = sys.executable
os.environ['PYSPARK_DRIVER_PYTHON'] = sys.executable
spark = SparkSession.builder.config("spark.metrics.conf",
                                    "/opt/mobdata/spark/spark-2.4.3.mob1-bin-2.6.5/conf/metrics.properties") \
    .config("spark.driver.memory", "24g") \
    .config("spark.driver.maxResultSize", "8g") \
    .appName("jw_zhihui_yc0202_all_loan_uv") \
    .enableHiveSupport() \
    .getOrCreate()

sql_pos_uv = """select pid,avg_embedding from database.table1"""
df_p