前言

💖💖作者：计算机程序员小杨
💙💙个人简介：我是一名计算机相关专业的从业者，擅长Java、微信小程序、Python、Golang、安卓Android等多个IT方向。会做一些项目定制化开发、代码讲解、答辩教学、文档编写、也懂一些降重方面的技巧。热爱技术，喜欢钻研新工具和框架，也乐于通过代码解决实际问题，大家有技术代码这一块的问题可以问我！
💛💛想说的话：感谢大家的关注与支持！
💕💕文末获取源码联系 计算机程序员小杨
💜💜
网站实战项目
安卓/小程序实战项目
大数据实战项目
深度学习实战项目
计算机毕业设计选题
💜💜

一.开发工具简介

大数据框架：Hadoop+Spark（本次没用Hive，支持定制）
开发语言：Python+Java（两个版本都支持）
后端框架：Django+Spring Boot(Spring+SpringMVC+Mybatis)（两个版本都支持）
前端：Vue+ElementUI+Echarts+HTML+CSS+JavaScript+jQuery
详细技术点：Hadoop、HDFS、Spark、Spark SQL、Pandas、NumPy
数据库：MySQL

二.系统内容简介

《BOSS直聘就业岗位数据可视化分析系统》是一个基于大数据技术的就业市场分析平台，采用Hadoop+Spark大数据框架作为核心处理引擎，结合Django后端框架和Vue+ElementUI+Echarts前端技术栈构建。系统通过HDFS分布式存储海量招聘数据，利用Spark SQL进行高效数据处理和分析，配合Pandas、NumPy等数据科学库实现复杂的统计计算。平台提供薪酬水平分析、市场需求分析、技能福利分析、多维交叉分析和可视化大屏五大核心功能模块。薪酬分析模块能够按地区、行业、职位等维度展示薪资分布趋势；市场需求分析通过岗位数量、热门技能等指标反映就业市场动态；技能福利分析帮助求职者了解不同技能对应的薪酬待遇和福利状况；多维交叉分析支持用户自定义筛选条件进行深度数据挖掘；可视化大屏则以直观的图表形式展现各类分析结果，为求职者、企业HR和相关研究人员提供数据驱动的决策支持。

三.系统功能演示

四.系统界面展示

五.系统源码展示

from pyspark.sql import SparkSession
from pyspark.sql.functions import col, avg, count, sum, desc, asc, when, regexp_replace, split
from pyspark.sql.types import StructType, StructField, StringType, IntegerType, FloatType
import pandas as pd
import numpy as np
from django.http import JsonResponse
from django.views.decorators.csrf import csrf_exempt
import json

spark = SparkSession.builder.appName("BOSSJobAnalysis").config("spark.sql.adaptive.enabled", "true").config("spark.sql.adaptive.coalescePartitions.enabled", "true").getOrCreate()

def salary_analysis(request):
    job_data = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/job_analysis").option("dbtable", "job_positions").option("user", "root").option("password", "password").load()
    cleaned_data = job_data.filter(col("salary_min").isNotNull() & col("salary_max").isNotNull() & (col("salary_min") > 0) & (col("salary_max") > 0))
    salary_with_avg = cleaned_data.withColumn("salary_avg", (col("salary_min") + col("salary_max")) / 2)
    city_salary_stats = salary_with_avg.groupBy("city").agg(avg("salary_avg").alias("avg_salary"), count("job_id").alias("job_count"), avg("salary_min").alias("min_salary_avg"), avg("salary_max").alias("max_salary_avg")).orderBy(desc("avg_salary"))
    industry_salary_stats = salary_with_avg.groupBy("industry").agg(avg("salary_avg").alias("avg_salary"), count("job_id").alias("job_count")).orderBy(desc("avg_salary"))
    position_salary_stats = salary_with_avg.groupBy("position_name").agg(avg("salary_avg").alias("avg_salary"), count("job_id").alias("job_count")).filter(col("job_count") >= 10).orderBy(desc("avg_salary"))
    experience_salary = salary_with_avg.groupBy("experience_required").agg(avg("salary_avg").alias("avg_salary"), count("job_id").alias("job_count")).orderBy(desc("avg_salary"))
    education_salary = salary_with_avg.groupBy("education_required").agg(avg("salary_avg").alias("avg_salary"), count("job_id").alias("job_count")).orderBy(desc("avg_salary"))
    salary_range_distribution = salary_with_avg.withColumn("salary_range", when(col("salary_avg") < 8000, "8k以下").when((col("salary_avg") >= 8000) & (col("salary_avg") < 15000), "8k-15k").when((col("salary_avg") >= 15000) & (col("salary_avg") < 25000), "15k-25k").when((col("salary_avg") >= 25000) & (col("salary_avg") < 40000), "25k-40k").otherwise("40k以上")).groupBy("salary_range").count().orderBy("count")
    city_salary_pandas = city_salary_stats.toPandas()
    industry_salary_pandas = industry_salary_stats.toPandas()
    position_salary_pandas = position_salary_stats.head(20).toPandas()
    experience_salary_pandas = experience_salary.toPandas()
    education_salary_pandas = education_salary.toPandas()
    salary_distribution_pandas = salary_range_distribution.toPandas()
    result_data = {"city_salary": city_salary_pandas.to_dict('records'), "industry_salary": industry_salary_pandas.to_dict('records'), "position_salary": position_salary_pandas.to_dict('records'), "experience_salary": experience_salary_pandas.to_dict('records'), "education_salary": education_salary_pandas.to_dict('records'), "salary_distribution": salary_distribution_pandas.to_dict('records')}
    return JsonResponse(result_data)

def market_demand_analysis(request):
    job_data = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/job_analysis").option("dbtable", "job_positions").option("user", "root").option("password", "password").load()
    city_demand = job_data.groupBy("city").agg(count("job_id").alias("job_count"), count("company_name").alias("company_count")).orderBy(desc("job_count"))
    industry_demand = job_data.groupBy("industry").agg(count("job_id").alias("job_count"), count("company_name").alias("company_count")).orderBy(desc("job_count"))
    position_demand = job_data.groupBy("position_name").agg(count("job_id").alias("job_count"), count("company_name").alias("company_count")).orderBy(desc("job_count"))
    company_size_demand = job_data.groupBy("company_size").agg(count("job_id").alias("job_count"), avg("salary_min").alias("avg_min_salary"), avg("salary_max").alias("avg_max_salary")).orderBy(desc("job_count"))
    experience_demand = job_data.groupBy("experience_required").agg(count("job_id").alias("job_count")).orderBy(desc("job_count"))
    education_demand = job_data.groupBy("education_required").agg(count("job_id").alias("job_count")).orderBy(desc("job_count"))
    skills_data = job_data.select("skills").filter(col("skills").isNotNull() & (col("skills") != ""))
    skills_exploded = skills_data.withColumn("skill", split(col("skills"), ",")).select("skill").rdd.flatMap(lambda x: x[0]).filter(lambda x: x is not None and x.strip() != "")
    skills_df = spark.createDataFrame(skills_exploded.map(lambda x: (x.strip(),)), ["skill_name"])
    skills_count = skills_df.groupBy("skill_name").count().orderBy(desc("count"))
    hot_skills = skills_count.head(30)
    trending_positions = job_data.filter(col("publish_date") >= "2023-01-01").groupBy("position_name").agg(count("job_id").alias("recent_count")).orderBy(desc("recent_count")).head(20)
    city_demand_pandas = city_demand.head(20).toPandas()
    industry_demand_pandas = industry_demand.toPandas()
    position_demand_pandas = position_demand.head(30).toPandas()
    company_size_pandas = company_size_demand.toPandas()
    experience_demand_pandas = experience_demand.toPandas()
    education_demand_pandas = education_demand.toPandas()
    hot_skills_pandas = pd.DataFrame(hot_skills, columns=["skill_name", "count"])
    trending_positions_pandas = pd.DataFrame(trending_positions, columns=["position_name", "recent_count"])
    result_data = {"city_demand": city_demand_pandas.to_dict('records'), "industry_demand": industry_demand_pandas.to_dict('records'), "position_demand": position_demand_pandas.to_dict('records'), "company_size_demand": company_size_pandas.to_dict('records'), "experience_demand": experience_demand_pandas.to_dict('records'), "education_demand": education_demand_pandas.to_dict('records'), "hot_skills": hot_skills_pandas.to_dict('records'), "trending_positions": trending_positions_pandas.to_dict('records')}
    return JsonResponse(result_data)

def skills_benefits_analysis(request):
    job_data = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/job_analysis").option("dbtable", "job_positions").option("user", "root").option("password", "password").load()
    benefits_data = job_data.select("benefits").filter(col("benefits").isNotNull() & (col("benefits") != ""))
    benefits_exploded = benefits_data.withColumn("benefit", split(col("benefits"), ",")).select("benefit").rdd.flatMap(lambda x: x[0]).filter(lambda x: x is not None and x.strip() != "")
    benefits_df = spark.createDataFrame(benefits_exploded.map(lambda x: (x.strip(),)), ["benefit_name"])
    benefits_count = benefits_df.groupBy("benefit_name").count().orderBy(desc("count"))
    skills_salary_data = job_data.select("skills", "salary_min", "salary_max").filter(col("skills").isNotNull() & (col("skills") != "") & col("salary_min").isNotNull() & col("salary_max").isNotNull())
    skills_with_avg_salary = skills_salary_data.withColumn("salary_avg", (col("salary_min") + col("salary_max")) / 2)
    skills_exploded_salary = skills_with_avg_salary.withColumn("skill", split(col("skills"), ",")).select("skill", "salary_avg").rdd.flatMap(lambda row: [(skill.strip(), row[1]) for skill in row[0] if skill.strip() != ""])
    skills_salary_df = spark.createDataFrame(skills_exploded_salary, ["skill_name", "salary_avg"])
    skills_salary_stats = skills_salary_df.groupBy("skill_name").agg(avg("salary_avg").alias("avg_salary"), count("skill_name").alias("skill_count")).filter(col("skill_count") >= 5).orderBy(desc("avg_salary"))
    benefits_salary_data = job_data.select("benefits", "salary_min", "salary_max").filter(col("benefits").isNotNull() & (col("benefits") != "") & col("salary_min").isNotNull() & col("salary_max").isNotNull())
    benefits_with_avg_salary = benefits_salary_data.withColumn("salary_avg", (col("salary_min") + col("salary_max")) / 2)
    benefits_exploded_salary = benefits_with_avg_salary.withColumn("benefit", split(col("benefits"), ",")).select("benefit", "salary_avg").rdd.flatMap(lambda row: [(benefit.strip(), row[1]) for benefit in row[0] if benefit.strip() != ""])
    benefits_salary_df = spark.createDataFrame(benefits_exploded_salary, ["benefit_name", "salary_avg"])
    benefits_salary_stats = benefits_salary_df.groupBy("benefit_name").agg(avg("salary_avg").alias("avg_salary"), count("benefit_name").alias("benefit_count")).filter(col("benefit_count") >= 10).orderBy(desc("avg_salary"))
    skill_benefit_correlation = job_data.select("skills", "benefits").filter(col("skills").isNotNull() & (col("skills") != "") & col("benefits").isNotNull() & (col("benefits") != ""))
    high_salary_skills = skills_salary_stats.head(20)
    high_value_benefits = benefits_salary_stats.head(15)
    popular_benefits = benefits_count.head(20)
    benefits_count_pandas = pd.DataFrame(popular_benefits, columns=["benefit_name", "count"])
    skills_salary_pandas = pd.DataFrame(high_salary_skills, columns=["skill_name", "avg_salary", "skill_count"])
    benefits_salary_pandas = pd.DataFrame(high_value_benefits, columns=["benefit_name", "avg_salary", "benefit_count"])
    result_data = {"popular_benefits": benefits_count_pandas.to_dict('records'), "high_salary_skills": skills_salary_pandas.to_dict('records'), "high_value_benefits": benefits_salary_pandas.to_dict('records')}
    return JsonResponse(result_data)

六.系统文档展示

结束

💕💕文末获取源码联系 计算机程序员小杨