✨作者主页 ：IT毕设梦工厂✨
个人简介：曾从事计算机专业培训教学，擅长Java、Python、PHP、.NET、Node.js、GO、微信小程序、安卓Android等项目实战。接项目定制开发、代码讲解、答辩教学、文档编写、降重等。
☑文末获取源码☑
文章目录
一、前言
《基于大数据的二手车数据可视化分析》是一套面向计算机专业毕业设计的完整系统，主要围绕二手车业务场景，把采集到的二手车信息通过Hadoop与HDFS进行数据存储，再借助Spark和Spark SQL完成数据清洗、统计与指标计算，后端采用Django框架搭建接口服务，数据库使用MySQL保存用户信息、二手车信息以及分析结果，前端通过Vue、ElementUI、Echarts、HTML、CSS、JavaScript和jQuery实现页面展示与图表交互。系统首页提供整体入口，大屏可视化用于集中展示二手车核心指标，用户管理、二手车信息管理、个人信息和修改密码保证系统基础操作完整，数据分析模块则进一步细分为车源分布分析、价格行情分析、品牌格局分析、车龄里程分析、能效成本分析和价值洞察分析，能够从地区、价格、品牌、使用年限、行驶里程、能耗成本以及综合价值等角度对二手车数据进行可视化呈现，帮助用户更直观地了解二手车市场情况，也方便大四学生在毕设中展示大数据处理与可视化分析的完整流程。
二、开发环境
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
三、系统界面展示
- 基于大数据的二手车数据可视化分析系统界面展示：
四、部分代码设计
- 项目实战-代码参考：
python
spark = SparkSession.builder \
.appName("UsedCarBigDataAnalysis") \
.master("local[*]") \
.config("spark.sql.warehouse.dir", "/user/hive/warehouse") \
.enableHiveSupport() \
.getOrCreate()
def analyze_car_source_distribution(request):
city = request.GET.get("city", "").strip()
start_date = request.GET.get("start_date", "").strip()
end_date = request.GET.get("end_date", "").strip()
car_df = spark.read.format("csv") \
.option("header", "true") \
.option("inferSchema", "true") \
.load("hdfs://localhost:9000/usedcar/cleaned/car_info")
car_df.createOrReplaceTempView("car_info")
sql = """
SELECT source_city, COUNT(*) AS car_count,
ROUND(AVG(price), 2) AS avg_price,
ROUND(AVG(mileage), 2) AS avg_mileage
FROM car_info
WHERE source_city IS NOT NULL
"""
if city:
sql += " AND source_city = '%s'" % city
if start_date and end_date:
sql += " AND publish_date >= '%s' AND publish_date <= '%s'" % (start_date, end_date)
sql += " GROUP BY source_city ORDER BY car_count DESC"
result_df = spark.sql(sql)
total_count = result_df.agg({"car_count": "sum"}).collect()[0][0] or 0
rows = result_df.collect()
data_list = []
for row in rows:
item = {
"source_city": row["source_city"],
"car_count": row["car_count"],
"avg_price": row["avg_price"],
"avg_mileage": row["avg_mileage"],
"ratio": round(row["car_count"] / total_count * 100, 2) if total_count else 0
}
data_list.append(item)
top_city = data_list[0]["source_city"] if data_list else ""
top_count = data_list[0]["car_count"] if data_list else 0
return JsonResponse({
"code": 200,
"msg": "车源分布分析成功",
"total": total_count,
"top_city": top_city,
"top_count": top_count,
"data": data_list
})
def analyze_price_market(request):
brand = request.GET.get("brand", "").strip()
price_range = request.GET.get("price_range", "").strip()
car_df = spark.read.format("csv") \
.option("header", "true") \
.option("inferSchema", "true") \
.load("hdfs://localhost:9000/usedcar/cleaned/car_info")
car_df.createOrReplaceTempView("car_info")
base_sql = """
SELECT brand, price, car_age, mileage, source_city
FROM car_info
WHERE price IS NOT NULL AND price > 0
"""
if brand:
base_sql += " AND brand = '%s'" % brand
if price_range == "low":
base_sql += " AND price < 5"
elif price_range == "mid":
base_sql += " AND price >= 5 AND price < 15"
elif price_range == "high":
base_sql += " AND price >= 15"
base_df = spark.sql(base_sql)
base_df.createOrReplaceTempView("price_base")
stat_df = spark.sql("""
SELECT COUNT(*) AS total_count,
ROUND(AVG(price), 2) AS avg_price,
ROUND(MIN(price), 2) AS min_price,
ROUND(MAX(price), 2) AS max_price,
ROUND(PERCENTILE(price, 0.5), 2) AS median_price
FROM price_base
""")
stat_row = stat_df.collect()[0]
segment_df = spark.sql("""
SELECT CASE
WHEN price < 5 THEN '5万以下'
WHEN price >= 5 AND price < 10 THEN '5-10万'
WHEN price >= 10 AND price < 15 THEN '10-15万'
WHEN price >= 15 AND price < 20 THEN '15-20万'
ELSE '20万以上'
END AS price_segment,
COUNT(*) AS segment_count,
ROUND(AVG(mileage), 2) AS avg_mileage
FROM price_base
GROUP BY CASE
WHEN price < 5 THEN '5万以下'
WHEN price >= 5 AND price < 10 THEN '5-10万'
WHEN price >= 10 AND price < 15 THEN '10-15万'
WHEN price >= 15 AND price < 20 THEN '15-20万'
ELSE '20万以上'
END
ORDER BY segment_count DESC
""")
segment_list = []
for row in segment_df.collect():
segment_list.append({
"price_segment": row["price_segment"],
"segment_count": row["segment_count"],
"avg_mileage": row["avg_mileage"]
})
age_price_df = spark.sql("""
SELECT car_age, ROUND(AVG(price), 2) AS avg_price, COUNT(*) AS car_count
FROM price_base
WHERE car_age IS NOT NULL
GROUP BY car_age
ORDER BY car_age ASC
""")
age_price_list = []
for row in age_price_df.collect():
age_price_list.append({
"car_age": row["car_age"],
"avg_price": row["avg_price"],
"car_count": row["car_count"]
})
return JsonResponse({
"code": 200,
"msg": "价格行情分析成功",
"total_count": stat_row["total_count"],
"avg_price": stat_row["avg_price"],
"min_price": stat_row["min_price"],
"max_price": stat_row["max_price"],
"median_price": stat_row["median_price"],
"segment_data": segment_list,
"age_price_data": age_price_list
})
def analyze_brand_pattern(request):
city = request.GET.get("city", "").strip()
top_n = int(request.GET.get("top_n", 10))
car_df = spark.read.format("csv") \
.option("header", "true") \
.option("inferSchema", "true") \
.load("hdfs://localhost:9000/usedcar/cleaned/car_info")
car_df.createOrReplaceTempView("car_info")
sql = """
SELECT brand, COUNT(*) AS car_count,
ROUND(AVG(price), 2) AS avg_price,
ROUND(AVG(mileage), 2) AS avg_mileage,
ROUND(AVG(car_age), 2) AS avg_car_age
FROM car_info
WHERE brand IS NOT NULL AND brand != ''
"""
if city:
sql += " AND source_city = '%s'" % city
sql += " GROUP BY brand ORDER BY car_count DESC LIMIT %d" % top_n
brand_df = spark.sql(sql)
brand_rows = brand_df.collect()
total_df = spark.sql("SELECT COUNT(*) AS total FROM car_info")
total_count = total_df.collect()[0]["total"] or 0
brand_list = []
for row in brand_rows:
brand_list.append({
"brand": row["brand"],
"car_count": row["car_count"],
"avg_price": row["avg_price"],
"avg_mileage": row["avg_mileage"],
"avg_car_age": row["avg_car_age"],
"ratio": round(row["car_count"] / total_count * 100, 2) if total_count else 0
})
price_rank_df = spark.sql("""
SELECT brand, ROUND(AVG(price), 2) AS avg_price, COUNT(*) AS car_count
FROM car_info
WHERE brand IS NOT NULL AND brand != ''
GROUP BY brand
HAVING COUNT(*) >= 5
ORDER BY avg_price DESC
LIMIT %d
""" % top_n)
price_rank_list = []
for row in price_rank_df.collect():
price_rank_list.append({
"brand": row["brand"],
"avg_price": row["avg_price"],
"car_count": row["car_count"]
})
return JsonResponse({
"code": 200,
"msg": "品牌格局分析成功",
"total_count": total_count,
"brand_data": brand_list,
"price_rank_data": price_rank_list
})五、论文参考
- 计算机毕业设计选题推荐-基于大数据的二手车数据可视化分析系统-论文参考：
六、系统视频
- 基于大数据的二手车数据可视化分析系统-项目视频：
项目演示视频
结语
计算机毕业设计选题推荐:基于大数据的二手车数据可视化分析|毕业设计选题|计算机毕设|选题推荐|毕设指导|项目定制|源码|高质量项目
大家可以帮忙点赞、收藏、关注、评论啦～
源码获取：⬇⬇⬇