分布式day09_04.服务器集群Session共享问题

分布式Session管理
本文介绍了一个基于Spring Boot的应用如何通过HTTP Session实现分布式环境下的Session管理。包括Session的创建、存储及检索过程,展示了如何在不同服务器间共享Session信息,解决分布式环境下Session同步的问题。

 


package com.itmayiedu.controller;

import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpSession;

import org.springframework.beans.factory.annotation.Value;
import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.RestController;


@SpringBootApplication
@RestController
public class TestSessionController {
	@Value("${server.port}")
	private String serverPort;

	@RequestMapping("/")
	public String index() {
		return serverPort;
	}

	// 创建session 会话
	@RequestMapping("/createSession")
	public String createSession(HttpServletRequest request, String nameValue) {
		HttpSession session = request.getSession();
		System.out.println(
				"存入Session  sessionid:信息" + session.getId() + ",nameValue:" + nameValue + ",serverPort:" + serverPort);
		session.setAttribute("name", nameValue);
		return "success-" + serverPort;
	}

	// 获取session 会话
	@RequestMapping("/getSession")
	public Object getSession(HttpServletRequest request) {
		HttpSession session = request.getSession(false);
		if (session == null) {
			return serverPort + "-" + "没有找到对应的session值";
		}
		System.out.println("获取Session sessionid:信息" + session.getId() + "serverPort:" + serverPort);
		Object value = session.getAttribute("name");
		return serverPort + "-" + value;
	}

}

package com.itmayiedu;

import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;


@SpringBootApplication
public class AppSession {

	public static void main(String[] args) {
		SpringApplication.run(AppSession.class, args);
	}

}

 

server:
  port: 8081
spring:
  redis:
    database: 0
    host: 192.168.144.150
    port: 6379
    password: 123456
    jedis:
      pool:
        max-active: 8
        max-wait: -1
        max-idle: 8
        min-idle: 0
    timeout: 10000
redis:
 hostname: 192.168.144.150
 port: 6379
 password: 123456
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
	xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
	<modelVersion>4.0.0</modelVersion>
	<groupId>com.itmayiedu</groupId>
	<artifactId>itmayiedu_session</artifactId>
	<version>0.0.1-SNAPSHOT</version>
	<parent>
		<groupId>org.springframework.boot</groupId>
		<artifactId>spring-boot-starter-parent</artifactId>
		<version>2.0.0.RELEASE</version>
		<relativePath /> <!-- lookup parent from repository -->
	</parent>
	<properties>
		<weixin-java-mp.version>2.8.0</weixin-java-mp.version>
		<maven.compiler.source>1.8</maven.compiler.source>
		<maven.compiler.target>1.8</maven.compiler.target>
		<maven.compiler.encoding>UTF-8</maven.compiler.encoding>
		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
		<project.build.locales>zh_CN</project.build.locales>
	</properties>

	<dependencies>
		<dependency>
			<groupId>org.projectlombok</groupId>
			<artifactId>lombok</artifactId>
		</dependency>
		<dependency>
			<groupId>org.springframework.boot</groupId>
			<artifactId>spring-boot-starter-web</artifactId>
			<!-- <exclusions> <exclusion> <groupId>com.fasterxml.jackson.core</groupId> 
				<artifactId>jackson-databind</artifactId> </exclusion> </exclusions> -->
		</dependency>
		<!-- https://mvnrepository.com/artifact/com.alibaba/fastjson -->
		<dependency>
			<groupId>com.alibaba</groupId>
			<artifactId>fastjson</artifactId>
			<version>1.2.47</version>
		</dependency>
		<!-- Testing Dependencies -->
		<dependency>
			<groupId>org.springframework.boot</groupId>
			<artifactId>spring-boot-starter-test</artifactId>
			<scope>test</scope>
		</dependency>
<!-- 		<dependency> -->
<!-- 			<groupId>org.springframework.boot</groupId> -->
<!-- 			<artifactId>spring-boot-starter-data-redis</artifactId> -->
<!-- 		</dependency> -->
		<!--spring session 与redis应用基本环境配置,需要开启redis后才可以使用,不然启动Spring boot会报错 -->
<!-- 		<dependency> -->
<!-- 			<groupId>org.springframework.session</groupId> -->
<!-- 			<artifactId>spring-session-data-redis</artifactId> -->
<!-- 		</dependency> -->
		<dependency>
			<groupId>org.apache.commons</groupId>
			<artifactId>commons-pool2</artifactId>
		</dependency>
		<dependency>
			<groupId>redis.clients</groupId>
			<artifactId>jedis</artifactId>
		</dependency>

	</dependencies>
	<build>
		<plugins>
			<plugin>
				<groupId>org.apache.maven.plugins</groupId>
				<artifactId>maven-compiler-plugin</artifactId>
				<configuration>
					<source>1.8</source>
					<target>1.8</target>
				</configuration>
			</plugin>
			<plugin>
				<groupId>org.springframework.boot</groupId>
				<artifactId>spring-boot-maven-plugin</artifactId>
				<configuration>
					<maimClass>com.meiteedu.WxMpApplication</maimClass>
				</configuration>
				<executions>
					<execution>
						<goals>
							<goal>repackage</goal>
						</goals>
					</execution>
				</executions>

			</plugin>
		</plugins>
	</build>


</project>

启动nginx,再启动redis

再浏览器看效果

先是存入session

再第一次获取session

轮训到8081服务器,没有找到session的值

再刷新一次

这就出现了分布式session的问题了

import streamlit as st import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns from pyspark.sql import SparkSession from pyspark.ml.feature import VectorAssembler, StringIndexer, OneHotEncoder from pyspark.ml import Pipeline from pyspark.ml.classification import LogisticRegression, DecisionTreeClassifier, RandomForestClassifier from pyspark.ml.evaluation import BinaryClassificationEvaluator, MulticlassClassificationEvaluator import os import time import warnings import tempfile import subprocess import sys import shutil 忽略警告 warnings.filterwarnings(“ignore”) 设置中文字体 plt.rcParams[‘font.sans-serif’] = [‘SimHei’] plt.rcParams[‘axes.unicode_minus’] = False 页面设置 st.set_page_config( page_title=“精准营销系统”, page_icon=“📊”, layout=“wide”, initial_sidebar_state=“expanded” ) 自定义CSS样式 st.markdown(“”" <style> .stApp { background: linear-gradient(135deg, #f8f9fa 0%, #e9ecef 100%); font-family: 'Helvetica Neue', Arial, sans-serif; } .header { background: linear-gradient(90deg, #1a237e 0%, #283593 100%); color: white; padding: 1.5rem; border-radius: 0.75rem; box-shadow: 0 4px 12px rgba(0,0,0,0.1); margin-bottom: 2rem; } .card { background: white; border-radius: 0.75rem; padding: 1rem; margin-bottom: 1.5rem; box-shadow: 0 4px 12px transition: transform 0.3s ease; } .card:hover { transform: translateY(-5px); box-shadow: 0 6px 16px rgba(0,0,0,0.12); } .stButton button { background: linear-gradient(90deg, #3949ab 0%, #1a237e 100%) !important; color: white !important; border: none !important; border-radius: 0.5rem; padding: 0.75rem 1.5rem; font-size: 1rem; font-weight: 600; transition: all 0.3s ease; width: 100%; } .stButton button:hover { transform: scale(1.05); box-shadow: 0 4px 8px rgba(57, 73, 171, 0.4); } .feature-box { background: linear-gradient(135deg, #e3f2fd 0%, #bbdefb 100%); border-radius: 0.75rem; padding: 1.5rem; margin-bottom: 1.5rem; } .result-box { background: linear-gradient(135deg, #e8f5e9 0%, #c8e6c9 100%); border-radius: 0.75rem; padding: 1.5rem; margin-top: 1.5rem; } .model-box { background: linear-gradient(135deg, #fff3e0 0%, #ffe0b2 100%); border-radius: 0.75rem; padding: 1.5rem; margin-top: 1.5rem; } .stProgress > div > div > div { background: linear-gradient(90deg, #2ecc71 0%, #27ae60 100%) !important; } .metric-card { background: white; border-radius: 0.75rem; padding: 1rem; text-align: center; box-shadow: 0 4px 8px rgba(0,0,0,0.06); } .metric-value { font-size: 1.8rem; font-weight: 700; color: #1a237e; } .metric-label { font-size: 0.9rem; color: #5c6bc0; margin-top: 0.5rem; } .highlight { background: linear-gradient(90deg, #ffeb3b 0%, #fbc02d 100%); padding: 0.2rem 0.5rem; border-radius: 0.25rem; font-weight: 600; } .stDataFrame { border-radius: 0.75rem; box-shadow: 0 4px 8px rgba(0,0,0,0.06); } .convert-high { background-color: #c8e6c9 !important; color: #388e3c !important; font-weight: 700; } .convert-low { background-color: #ffcdd2 !important; color: #c62828 !important; font-weight: 600; } .java-success { background-color: #d4edda; border-left: 4px solid #28a745; padding: 1rem; margin-bottom: 1.5rem; border-radius: 0 0.25rem 0.25rem 0; } </style> “”", unsafe_allow_html=True) 创建优化的Spark会话 def create_spark_session(): “”“创建优化的Spark会话,使用高效的配置参数”“” try: # 基础配置 - 优化资源使用 builder = SparkSession.builder .appName(“TelecomPrecisionMarketing”) .config(“spark.driver.memory”, “1g”) .config(“spark.executor.memory”, “1g”) .config(“spark.sql.shuffle.partitions”, “4”) .config(“spark.network.timeout”, “800s”) .config(“spark.executor.heartbeatInterval”, “60s”) .config(“spark.sql.legacy.allowUntypedScalaUDF”, “true”) .config(“spark.serializer”, “org.apache.spark.serializer.KryoSerializer”) .config(“spark.kryoserializer.buffer.max”, “128m”) .config(“spark.driver.maxResultSize”, “1g”) .config(“spark.sql.execution.arrow.pyspark.enabled”, “true”) .config(“spark.ui.showConsoleProgress”, “false”) # 创建会话 spark = builder.getOrCreate() # 验证会话 try: # 创建测试DataFrame验证会话是否正常工作 test_df = spark.createDataFrame([(1, "test"), (2, "session")], ["id", "name"]) test_df_count = test_df.count() if test_df_count == 2: st.success("Spark会话创建成功并验证通过") else: st.warning(f"Spark会话验证异常,返回记录数: {test_df_count}") except Exception as e: st.error(f"Spark会话验证失败: {str(e)}") spark.stop() raise return spark except Exception as e: st.error(f"创建Spark会话失败: {str(e)}") st.error("请检查Java版本和Spark配置") st.stop() 数据预处理函数 def preprocess_data(df): “”“优化后的数据预处理函数”“” # 1. 选择关键特征 available_features = [col for col in df.columns if col in [ ‘AGE’, ‘GENDER’, ‘ONLINE_DAY’, ‘TERM_CNT’, ‘IF_YHTS’, ‘MKT_STAR_GRADE_NAME’, ‘PROM_AMT_MONTH’, ‘is_rh_next’ # 目标变量 ]] # 确保目标变量存在 if 'is_rh_next' not in available_features: st.error("错误:数据集中缺少目标变量 'is_rh_next'") return df # 只保留需要的列 df = df[available_features].copy() # 2. 处理缺失值 numeric_cols = ['AGE', 'ONLINE_DAY', 'TERM_CNT', 'PROM_AMT_MONTH'] for col in numeric_cols: if col in df.columns: median_val = df[col].median() df[col].fillna(median_val, inplace=True) categorical_cols = ['GENDER', 'MKT_STAR_GRADE_NAME', 'IF_YHTS'] for col in categorical_cols: if col in df.columns: mode_val = df[col].mode()[0] if not df[col].mode().empty else '未知' df[col].fillna(mode_val, inplace=True) # 3. 异常值处理 def handle_outliers(series): Q1 = series.quantile(0.25) Q3 = series.quantile(0.75) IQR = Q3 - Q1 lower_bound = Q1 - 1.5 * IQR upper_bound = Q3 + 1.5 * IQR return series.clip(lower_bound, upper_bound) for col in numeric_cols: if col in df.columns: df[col] = handle_outliers(df[col]) return df 标题区域 st.markdown(“”" <div class="header"> <h1 style='text-align: center; margin: 0;'>精准营销系统</h1> <p style='text-align: center; margin: 0.5rem 0 0; font-size: 1.1rem;'>基于机器学习的单宽转融预测</p> </div> """, unsafe_allow_html=True) 页面布局 col1, col2 = st.columns([1, 1.5]) 左侧区域 - 图片和简介 with col1: st.markdown(“”" 📱 智能营销系统 预测单宽带用户转化为融合套餐用户的可能性 “”", unsafe_allow_html=True) # 使用在线图片作为占位符 st.image("https://images.unsplash.com/photo-1551836022-d5d88e9218df?ixlib=rb-4.0.3&ixid=M3wxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8fA%3D%3D&auto=format&fit=crop&w=1200&q=80", caption="精准营销系统示意图", use_column_width=True) st.markdown(""" <div class="card"> <h4>📈 系统功能</h4> <ul> <li>用户转化可能性预测</li> <li>高精度机器学习模型</li> <li>可视化数据分析</li> <li>精准营销策略制定</li> </ul> </div> """, unsafe_allow_html=True) 右侧区域 - 功能选择 with col2: st.markdown(“”" 📋 请选择操作类型 您可以选择数据分析或使用模型进行预测 “”", unsafe_allow_html=True) # 功能选择 option = st.radio("操作类型", ["📊 数据分析 - 探索数据并训练模型", "🔍 预测分析 - 预测用户转化可能性"], index=0) # 数据分析部分 if "数据分析" in option: st.markdown(""" <div class="card"> <h3>数据分析与模型训练</h3> <p>上传数据并训练预测模型</p> </div> """, unsafe_allow_html=True) # 上传训练数据 train_file = st.file_uploader("上传数据集 (CSV格式, GBK编码)", type=["csv"]) if train_file is not None: try: # 读取数据 train_data = pd.read_csv(train_file, encoding='GBK') # 显示数据预览 with st.expander("数据预览", expanded=True): st.dataframe(train_data.head()) col1, col2 = st.columns(2) col1.metric("总样本数", train_data.shape[0]) col2.metric("特征数量", train_data.shape[1] - 1) # 数据预处理 st.subheader("数据预处理") with st.spinner("数据预处理中..."): processed_data = preprocess_data(train_data) st.success("✅ 数据预处理完成") # 可视化数据分布 st.subheader("数据分布分析") # 目标变量分布 st.markdown("**目标变量分布 (is_rh_next)**") fig, ax = plt.subplots(figsize=(8, 5)) sns.countplot(x='is_rh_next', data=processed_data, palette='viridis') plt.title('用户转化分布 (0:未转化, 1:转化)') plt.xlabel('是否转化') plt.ylabel('用户数量') st.pyplot(fig) # 数值特征分布 st.markdown("**数值特征分布**") numeric_cols = ['AGE', 'ONLINE_DAY', 'TERM_CNT', 'PROM_AMT_MONTH'] # 动态计算子图布局 num_features = len(numeric_cols) if num_features > 0: ncols = 2 nrows = (num_features + ncols - 1) // ncols fig, axes = plt.subplots(nrows, ncols, figsize=(14, 4*nrows)) if nrows > 1 or ncols > 1: axes = axes.flatten() else: axes = [axes] for i, col in enumerate(numeric_cols): if col in processed_data.columns and i < len(axes): sns.histplot(processed_data[col], kde=True, ax=axes[i], color='skyblue') axes[i].set_title(f'{col}分布') axes[i].set_xlabel('') for j in range(i+1, len(axes)): axes[j].set_visible(False) plt.tight_layout() st.pyplot(fig) else: st.warning("没有可用的数值特征") # 特征相关性分析 st.markdown("**特征相关性热力图**") corr_cols = numeric_cols + ['is_rh_next'] if len(corr_cols) > 1: corr_data = processed_data[corr_cols].corr() fig, ax = plt.subplots(figsize=(12, 8)) sns.heatmap(corr_data, annot=True, fmt=".2f", cmap='coolwarm', ax=ax) plt.title('特征相关性热力图') st.pyplot(fig) else: st.warning("特征不足,无法生成相关性热力图") # 模型训练 st.subheader("模型训练") # 训练参数设置 col1, col2 = st.columns(2) test_size = col1.slider("测试集比例", 0.1, 0.4, 0.2, 0.05) random_state = col2.number_input("随机种子", 0, 100, 42) # 开始训练按钮 if st.button("开始训练模型", use_container_width=True): # 创建临时目录用于存储模型 with tempfile.TemporaryDirectory() as tmp_dir: # 修复路径问题:使用绝对路径 model_path = os.path.abspath(os.path.join(tmp_dir, "best_model")) progress_bar = st.progress(0) status_text = st.empty() # 步骤1: 创建Spark会话 status_text.text("步骤1/7: 初始化Spark会话...") spark = create_spark_session() progress_bar.progress(15) # 步骤2: 转换为Spark DataFrame status_text.text("步骤2/7: 转换数据为Spark格式...") spark_df = spark.createDataFrame(processed_data) progress_bar.progress(30) # 步骤3: 划分训练集和测试集 status_text.text("步骤3/7: 划分训练集和测试集...") train_df, test_df = spark_df.randomSplit([1.0 - test_size, test_size], seed=random_state) progress_bar.progress(40) # 步骤4: 特征工程 status_text.text("步骤4/7: 特征工程处理...") categorical_cols = ['GENDER', 'MKT_STAR_GRADE_NAME', 'IF_YHTS'] existing_cat_cols = [col for col in categorical_cols if col in processed_data.columns] # 创建特征处理管道 indexers = [StringIndexer(inputCol=col, outputCol=col+"_index") for col in existing_cat_cols] encoders = [OneHotEncoder(inputCol=col+"_index", outputCol=col+"_encoded") for col in existing_cat_cols] numeric_cols = ['AGE', 'ONLINE_DAY', 'TERM_CNT', 'PROM_AMT_MONTH'] feature_cols = numeric_cols + [col+"_encoded" for col in existing_cat_cols] assembler = VectorAssembler(inputCols=feature_cols, outputCol="features") label_indexer = StringIndexer(inputCol="is_rh_next", outputCol="label") progress_bar.progress(50) # 步骤5: 构建模型 status_text.text("步骤5/7: 构建和训练模型...") # 使用优化的模型配置 rf = RandomForestClassifier( featuresCol="features", labelCol="label", numTrees=50, # 增加树的数量提高精度 maxDepth=5, # 适当增加深度 seed=random_state, featureSubsetStrategy="auto", # 自动选择特征子集策略 impurity="gini" # 使用基尼不纯度 ) pipeline = Pipeline(stages=indexers + encoders + [assembler, label_indexer, rf]) model = pipeline.fit(train_df) progress_bar.progress(80) # 步骤6: 评估模型 status_text.text("步骤6/7: 评估模型性能...") predictions = model.transform(test_df) evaluator_auc = BinaryClassificationEvaluator(labelCol="label", rawPredictionCol="rawPrediction") evaluator_acc = MulticlassClassificationEvaluator(labelCol="label", predictionCol="prediction", metricName="accuracy") evaluator_f1 = MulticlassClassificationEvaluator(labelCol="label", predictionCol="prediction", metricName="f1") auc = evaluator_auc.evaluate(predictions) acc = evaluator_acc.evaluate(predictions) f1 = evaluator_f1.evaluate(predictions) results = { "Random Forest": {"AUC": auc, "Accuracy": acc, "F1 Score": f1} } progress_bar.progress(95) # 步骤7: 保存结果 status_text.text("步骤7/7: 保存模型和结果...") # 确保目录存在 os.makedirs(model_path, exist_ok=True) model.write().overwrite().save(model_path) st.session_state.model_results = results st.session_state.best_model = model st.session_state.model_path = model_path st.session_state.spark = spark progress_bar.progress(100) st.success("🎉 模型训练完成!") # 显示模型性能 st.subheader("模型性能评估") results_df = pd.DataFrame(results).T st.dataframe(results_df.style.format("{:.4f}").background_gradient(cmap='Blues')) # 特征重要性 st.subheader("特征重要性") rf_model = model.stages[-1] feature_importances = rf_model.featureImportances.toArray() importance_df = pd.DataFrame({ "Feature": feature_cols, "Importance": feature_importances }).sort_values("Importance", ascending=False).head(10) fig, ax = plt.subplots(figsize=(10, 6)) sns.barplot(x="Importance", y="Feature", data=importance_df, palette="viridis", ax=ax) plt.title('Top 10 重要特征') st.pyplot(fig) except Exception as e: st.error(f"模型训练错误: {str(e)}") st.error("提示:请检查数据格式和特征列名") # 预测分析部分 else: st.markdown(""" <div class="card"> <h3>用户转化预测</h3> <p>预测单宽带用户转化为融合套餐的可能性</p> </div> """, unsafe_allow_html=True) # 上传预测数据 predict_file = st.file_uploader("上传预测数据 (CSV格式, GBK编码)", type=["csv"]) if predict_file is not None: try: # 读取数据 predict_data = pd.read_csv(predict_file, encoding='GBK') # 显示数据预览 with st.expander("数据预览", expanded=True): st.dataframe(predict_data.head()) # 检查是否有模型 if "model_path" not in st.session_state: st.warning("⚠️ 未找到训练好的模型,请先训练模型") st.stop() # 开始预测按钮 if st.button("开始预测", use_container_width=True): progress_bar = st.progress(0) status_text = st.empty() # 步骤1: 数据预处理 status_text.text("步骤1/4: 数据预处理中...") processed_data = preprocess_data(predict_data) progress_bar.progress(25) # 步骤2: 创建Spark会话 status_text.text("步骤2/4: 初始化Spark会话...") if "spark" not in st.session_state: spark = create_spark_session() st.session_state.spark = spark else: spark = st.session_state.spark progress_bar.progress(50) # 步骤3: 预测 status_text.text("步骤3/4: 进行预测...") spark_df = spark.createDataFrame(processed_data) best_model = st.session_state.best_model predictions = best_model.transform(spark_df) progress_bar.progress(75) # 步骤4: 处理结果 status_text.text("步骤4/4: 处理预测结果...") predictions_df = predictions.select( "CCUST_ROW_ID", "probability", "prediction" ).toPandas() # 解析概率值 predictions_df['转化概率'] = predictions_df['probability'].apply(lambda x: float(x[1])) predictions_df['预测结果'] = predictions_df['prediction'].apply(lambda x: "可能转化" if x == 1.0 else "可能不转化") # 添加转化可能性等级 predictions_df['转化可能性'] = pd.cut( predictions_df['转化概率'], bins=[0, 0.3, 0.7, 1], labels=["低可能性", "中可能性", "高可能性"] ) # 保存结果 st.session_state.prediction_results = predictions_df progress_bar.progress(100) st.success("✅ 预测完成!") except Exception as e: st.error(f"预测错误: {str(e)}") # 显示预测结果 if "prediction_results" in st.session_state: st.markdown(""" <div class="card"> <h3>预测结果</h3> <p>用户转化可能性评估报告</p> </div> """, unsafe_allow_html=True) result_df = st.session_state.prediction_results # 转化可能性分布 st.subheader("转化可能性分布概览") col1, col2, col3 = st.columns(3) high_conv = (result_df["转化可能性"] == "高可能性").sum() med_conv = (result_df["转化可能性"] == "中可能性").sum() low_conv = (result_df["转化可能性"] == "低可能性").sum() col1.markdown(f""" <div class="metric-card"> <div class="metric-value">{high_conv}</div> <div class="metric-label">高可能性用户</div> </div> """, unsafe_allow_html=True) col2.markdown(f""" <div class="metric-card"> <div class="metric-value">{med_conv}</div> <div class="metric-label">中可能性用户</div> </div> """, unsafe_allow_html=True) col3.markdown(f""" <div class="metric-card"> <div class="metric-value">{low_conv}</div> <div class="metric-label">低可能性用户</div> </div> """, unsafe_allow_html=True) # 转化可能性分布图 fig, ax = plt.subplots(figsize=(8, 5)) conv_counts = result_df["转化可能性"].value_counts() conv_counts.plot(kind='bar', color=['#4CAF50', '#FFC107', '#F44336'], ax=ax) plt.title('用户转化可能性分布') plt.xlabel('可能性等级') plt.ylabel('用户数量') st.pyplot(fig) # 详细预测结果 st.subheader("详细预测结果") # 样式函数 def color_convert(val): if val == "高可能性": return "background-color: #c8e6c9; color: #388e3c;" elif val == "中可能性": return "background-color: #fff9c4; color: #f57f17;" else: return "background-color: #ffcdd2; color: #c62828;" # 格式化显示 display_df = result_df[["CCUST_ROW_ID", "转化概率", "预测结果", "转化可能性"]] styled_df = display_df.style.format({ "转化概率": "{:.2%}" }).applymap(color_convert, subset=["转化可能性"]) st.dataframe(styled_df, height=400) # 下载结果 csv = display_df.to_csv(index=False).encode("utf-8") st.download_button( label="下载预测结果", data=csv, file_name="用户转化预测结果.csv", mime="text/csv", use_container_width=True ) 页脚 st.markdown(“—”) st.markdown(“”" <div style="text-align: center; color: #5c6bc0; font-size: 0.9rem; padding: 1rem;"> © 2023 精准营销系统 | 基于Spark和Streamlit开发 | 优化版Spark连接 </div> """, unsafe_allow_html=True) 执行上述代码提示系统找不到指定的路径,给出修改后完整代码
最新发布
07-02
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值