💖💖作者：计算机编程小咖 💙💙个人简介：曾长期从事计算机专业培训教学，本人也热爱上课教学，语言擅长Java、微信小程序、Python、Golang、安卓Android等，开发项目包括大数据、深度学习、网站、小程序、安卓、算法。平常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。平常喜欢分享一些自己开发中遇到的问题的解决办法，也喜欢交流技术，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！ 💜💜 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
@TOC
懂车帝二手车数据分析系统介绍
基于大数据的懂车帝二手车数据分析系统是一个集数据采集、存储、处理和分析于一体的综合性大数据应用项目，该系统采用Hadoop分布式存储框架作为底层数据存储基础，结合Spark大数据处理引擎实现海量二手车数据的高效计算和分析。系统后端采用Spring Boot框架构建RESTful API服务，前端基于Vue.js框架结合ElementUI组件库和Echarts可视化图表库打造现代化的用户交互界面，数据库采用MySQL进行结构化数据存储管理。在功能架构上，系统提供了完整的用户权限管理模块，包括个人中心、用户管理和系统管理等基础功能，核心业务模块围绕二手车数据展开深度分析，通过数据看板实现关键指标的可视化展示，市场宏观特征分析模块运用Spark SQL和Pandas进行大规模数据统计分析，价值影响因素分析模块基于NumPy数学计算库挖掘影响二手车价格的关键因素，品牌竞争力分析模块通过多维度数据对比评估各汽车品牌在二手车市场的表现，市场供给画像与聚类分析模块利用机器学习算法对二手车供给方进行精准画像和智能分类，整个系统充分体现了大数据技术在实际业务场景中的应用价值，为二手车市场参与者提供科学的数据支撑和决策依据。
懂车帝二手车数据分析系统演示视频
懂车帝二手车数据分析系统演示图片
懂车帝二手车数据分析系统代码展示
from pyspark.sql import SparkSession
from pyspark.sql.functions import *
from pyspark.ml.clustering import KMeans
from pyspark.ml.feature import VectorAssembler
import pandas as pd
import numpy as np
from django.http import JsonResponse
spark = SparkSession.builder.appName("CarDataAnalysis").config("spark.sql.adaptive.enabled", "true").getOrCreate()
def market_macro_analysis(request):
df = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/cardata").option("dbtable", "car_info").option("user", "root").option("password", "123456").load()
total_cars = df.count()
avg_price = df.agg(avg("price").alias("avg_price")).collect()[0]["avg_price"]
brand_count = df.groupBy("brand").count().orderBy(desc("count"))
city_distribution = df.groupBy("city").agg(count("*").alias("car_count"), avg("price").alias("avg_city_price")).orderBy(desc("car_count"))
year_trend = df.groupBy("year").agg(count("*").alias("yearly_count"), avg("price").alias("yearly_avg_price")).orderBy("year")
mileage_stats = df.agg(min("mileage").alias("min_mileage"), max("mileage").alias("max_mileage"), avg("mileage").alias("avg_mileage")).collect()[0]
price_range = df.select(when(col("price") < 50000, "低价区").when((col("price") >= 50000) & (col("price") < 150000), "中价区").otherwise("高价区").alias("price_category")).groupBy("price_category").count()
fuel_type_analysis = df.groupBy("fuel_type").agg(count("*").alias("count"), avg("price").alias("avg_fuel_price")).orderBy(desc("count"))
transmission_analysis = df.groupBy("transmission").agg(count("*").alias("count"), avg("price").alias("avg_trans_price"))
monthly_trend = df.withColumn("month", month("create_time")).groupBy("month").agg(count("*").alias("monthly_count"), avg("price").alias("monthly_avg"))
condition_analysis = df.groupBy("car_condition").agg(count("*").alias("condition_count"), avg("price").alias("condition_avg_price"))
brand_pandas = brand_count.toPandas()
city_pandas = city_distribution.toPandas()
year_pandas = year_trend.toPandas()
result_data = {"total_cars": total_cars, "avg_price": round(avg_price, 2), "brand_distribution": brand_pandas.to_dict('records'), "city_distribution": city_pandas.to_dict('records'), "year_trend": year_pandas.to_dict('records'), "mileage_stats": dict(mileage_stats.asDict()), "price_range": price_range.toPandas().to_dict('records'), "fuel_analysis": fuel_type_analysis.toPandas().to_dict('records')}
return JsonResponse(result_data)
def brand_competition_analysis(request):
df = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/cardata").option("dbtable", "car_info").option("user", "root").option("password", "123456").load()
brand_market_share = df.groupBy("brand").agg(count("*").alias("car_count")).withColumn("market_share", col("car_count") * 100.0 / df.count()).orderBy(desc("market_share"))
brand_avg_price = df.groupBy("brand").agg(avg("price").alias("avg_price"), min("price").alias("min_price"), max("price").alias("max_price"), stddev("price").alias("price_std"))
brand_age_analysis = df.groupBy("brand").agg(avg("car_age").alias("avg_age"), avg("mileage").alias("avg_mileage"))
brand_condition_score = df.groupBy("brand", "car_condition").count().groupBy("brand").pivot("car_condition").sum("count").fillna(0)
brand_fuel_preference = df.groupBy("brand", "fuel_type").count().withColumn("fuel_ratio", col("count") * 100.0 / sum("count").over(Window.partitionBy("brand")))
brand_city_coverage = df.groupBy("brand").agg(countDistinct("city").alias("city_coverage"), collect_set("city").alias("covered_cities"))
brand_time_trend = df.withColumn("quarter", quarter("create_time")).groupBy("brand", "quarter").count().withColumn("trend_score", col("count") / lag("count").over(Window.partitionBy("brand").orderBy("quarter")))
brand_price_competitiveness = df.groupBy("brand").agg(avg("price").alias("brand_avg")).withColumn("price_rank", row_number().over(Window.orderBy("brand_avg"))).withColumn("competitiveness_score", when(col("price_rank") <= 10, "高性价比").when(col("price_rank") <= 20, "中等竞争力").otherwise("价格偏高"))
luxury_brands = df.filter(col("price") > 200000).groupBy("brand").count().withColumn("luxury_ratio", col("count") * 100.0 / df.filter(col("price") > 200000).count())
brand_satisfaction = df.groupBy("brand").agg(avg("rating").alias("avg_rating"), count("rating").alias("rating_count")).filter(col("rating_count") >= 10)
comprehensive_score = brand_market_share.join(brand_avg_price, "brand").join(brand_satisfaction, "brand", "left").withColumn("comprehensive_score", (col("market_share") * 0.3 + (1000000 - col("avg_price")) / 10000 * 0.4 + coalesce(col("avg_rating"), lit(3.0)) * 20 * 0.3)).orderBy(desc("comprehensive_score"))
brand_growth_potential = df.withColumn("is_recent", when(col("create_time") >= date_sub(current_date(), 90), 1).otherwise(0)).groupBy("brand").agg(sum("is_recent").alias("recent_listings"), count("*").alias("total_listings")).withColumn("growth_rate", col("recent_listings") * 100.0 / col("total_listings")).orderBy(desc("growth_rate"))
result = {"brand_share": brand_market_share.toPandas().to_dict('records'), "price_analysis": brand_avg_price.toPandas().to_dict('records'), "age_analysis": brand_age_analysis.toPandas().to_dict('records'), "comprehensive_ranking": comprehensive_score.toPandas().to_dict('records'), "growth_potential": brand_growth_potential.toPandas().to_dict('records')}
return JsonResponse(result)
def market_supply_clustering_analysis(request):
df = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/cardata").option("dbtable", "car_info").option("user", "root").option("password", "123456").load()
feature_df = df.select("price", "mileage", "car_age", "engine_size", "power").filter(col("price").isNotNull() & col("mileage").isNotNull() & col("car_age").isNotNull())
assembler = VectorAssembler(inputCols=["price", "mileage", "car_age", "engine_size", "power"], outputCol="features")
feature_vector = assembler.transform(feature_df)
kmeans = KMeans(k=5, seed=42, featuresCol="features", predictionCol="cluster")
model = kmeans.fit(feature_vector)
clustered_df = model.transform(feature_vector)
cluster_summary = clustered_df.groupBy("cluster").agg(count("*").alias("cluster_size"), avg("price").alias("avg_price"), avg("mileage").alias("avg_mileage"), avg("car_age").alias("avg_age"), min("price").alias("min_price"), max("price").alias("max_price"))
cluster_characteristics = clustered_df.groupBy("cluster").agg(avg("price").alias("price_center"), avg("mileage").alias("mileage_center"), avg("car_age").alias("age_center")).withColumn("cluster_type", when((col("price_center") > 150000) & (col("age_center") < 3), "高端新车型").when((col("price_center") < 80000) & (col("mileage_center") > 100000), "经济实用型").when(col("age_center") > 8, "老旧车型").when((col("price_center").between(80000, 150000)) & (col("age_center").between(3, 8)), "主流中档型").otherwise("其他类型"))
seller_clustering = df.groupBy("seller_id").agg(count("*").alias("listing_count"), avg("price").alias("avg_listing_price"), countDistinct("brand").alias("brand_variety"), avg("car_age").alias("avg_car_age")).filter(col("listing_count") >= 3)
seller_assembler = VectorAssembler(inputCols=["listing_count", "avg_listing_price", "brand_variety"], outputCol="seller_features")
seller_vector = seller_assembler.transform(seller_clustering)
seller_kmeans = KMeans(k=4, seed=42, featuresCol="seller_features", predictionCol="seller_cluster")
seller_model = seller_kmeans.fit(seller_vector)
seller_clustered = seller_model.transform(seller_vector)
seller_profiles = seller_clustered.groupBy("seller_cluster").agg(count("*").alias("seller_count"), avg("listing_count").alias("avg_listings"), avg("avg_listing_price").alias("price_level"), avg("brand_variety").alias("variety_score")).withColumn("seller_type", when(col("avg_listings") > 50, "大型车商").when((col("avg_listings").between(10, 50)) & (col("variety_score") > 5), "中型经销商").when(col("avg_listings") < 10, "个人卖家").otherwise("小型车商"))
geographic_clustering = df.groupBy("city", "district").agg(count("*").alias("supply_count"), avg("price").alias("regional_avg_price")).filter(col("supply_count") >= 20)
regional_features = VectorAssembler(inputCols=["supply_count", "regional_avg_price"], outputCol="geo_features").transform(geographic_clustering)
geo_kmeans = KMeans(k=6, seed=42, featuresCol="geo_features", predictionCol="geo_cluster").fit(regional_features)
geo_clustered = geo_kmeans.transform(regional_features)
regional_types = geo_clustered.groupBy("geo_cluster").agg(count("*").alias("region_count"), avg("supply_count").alias("avg_supply"), avg("regional_avg_price").alias("avg_regional_price"))
result_data = {"vehicle_clusters": cluster_summary.toPandas().to_dict('records'), "cluster_types": cluster_characteristics.toPandas().to_dict('records'), "seller_profiles": seller_profiles.toPandas().to_dict('records'), "regional_analysis": regional_types.toPandas().to_dict('records')}
return JsonResponse(result_data)
懂车帝二手车数据分析系统文档展示
💖💖作者：计算机编程小咖
💙💙个人简介：曾长期从事计算机专业培训教学，本人也热爱上课教学，语言擅长Java、微信小程序、Python、Golang、安卓Android等，开发项目包括大数据、深度学习、网站、小程序、安卓、算法。平常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。平常喜欢分享一些自己开发中遇到的问题的解决办法，也喜欢交流技术，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！
💜💜
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
