💖💖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
目录
睡前手机使用行为与睡眠关联性可视化分析系统介绍
本系统名为《基于大数据的睡前手机使用行为与睡眠关联性可视化分析系统》,主要围绕睡前手机使用记录和睡眠记录展开分析,用Hadoop与Spark搭起一套适合毕业设计规模的大数据处理流程,原始数据可存放在HDFS中,借助Spark SQL完成数据清洗、分组聚合、关联统计等处理,并结合Pandas、NumPy做指标整理,后端提供Python+Django和Java+Spring Boot两个版本,数据存储使用MySQL,前端通过Vue、ElementUI、ECharts以及HTML、CSS、JavaScript、jQuery完成页面展示和图表渲染。系统首页用于汇总展示整体数据概况和主要图表入口;手机行为分析功能对睡前使用时长、使用次数、应用类型分布等指标进行统计;睡眠质量分析功能围绕睡眠时长、醒来次数、睡眠评分等指标做汇总和分级展示;关联洞察分析功能把睡前手机使用指标与睡眠指标按用户和日期关联起来,观察使用时长、使用次数与睡眠情况之间的关系;睡前手机睡眠数据功能用于查看和管理用于分析的基础记录;个人信息和修改密码功能用于维护当前用户的基本信息与账号安全。整体上,本系统更关注大数据处理流程和可视化表达,功能范围清晰,适合作为计算机专业本科毕业设计中的数据分析与可视化类系统来使用。
睡前手机使用行为与睡眠关联性可视化分析系统演示视频
睡前手机使用行为与睡眠关联性可视化分析系统演示图片






睡前手机使用行为与睡眠关联性可视化分析系统代码展示
from pyspark.sql import SparkSession
spark = SparkSession.builder.appName("sleep_phone_analysis").master("local[*]").config("spark.sql.shuffle.partitions", "4").getOrCreate()
from django.http import JsonResponse
from pyspark.sql import functions as F
mysql_url = "jdbc:mysql://localhost:3306/sleep_analysis?useSSL=false&serverTimezone=Asia/Shanghai"
mysql_props = {"user": "root", "password": "123456", "driver": "com.mysql.cj.jdbc.Driver"}
def phone_behavior_analysis(request):
user_id = request.GET.get("user_id")
start_date = request.GET.get("start_date")
end_date = request.GET.get("end_date")
behavior_df = spark.read.jdbc(url=mysql_url, table="phone_behavior", properties=mysql_props)
if user_id:
behavior_df = behavior_df.filter(F.col("user_id") == user_id)
if start_date and end_date:
behavior_df = behavior_df.filter((F.col("use_date") >= start_date) & (F.col("use_date") <= end_date))
behavior_df = behavior_df.filter(F.col("use_duration").isNotNull())
behavior_df = behavior_df.withColumn("night_flag", F.when((F.hour("use_time") >= 22) | (F.hour("use_time") < 2), 1).otherwise(0))
night_df = behavior_df.filter(F.col("night_flag") == 1)
agg_df = night_df.groupBy("user_id").agg(F.count("*").alias("night_use_times"), F.round(F.sum("use_duration"), 2).alias("night_total_minutes"), F.round(F.avg("use_duration"), 2).alias("night_avg_minutes"), F.countDistinct("app_type").alias("app_type_count"))
category_df = night_df.groupBy("user_id", "app_type").agg(F.round(F.sum("use_duration"), 2).alias("type_minutes"))
top_df = category_df.orderBy(F.col("user_id"), F.col("type_minutes").desc())
top_rows = top_df.limit(50).collect()
top_app_df = top_df.groupBy("user_id").agg(F.first("app_type").alias("top_app_type"))
result_df = agg_df.join(top_app_df, on="user_id", how="left")
rows = result_df.collect()
data = [row.asDict() for row in rows]
top_data = [row.asDict() for row in top_rows]
return JsonResponse({"code": 200, "data": data, "top_apps": top_data}, json_dumps_params={"ensure_ascii": False})
def sleep_quality_analysis(request):
user_id = request.GET.get("user_id")
start_date = request.GET.get("start_date")
end_date = request.GET.get("end_date")
sleep_df = spark.read.jdbc(url=mysql_url, table="sleep_record", properties=mysql_props)
sleep_df = sleep_df.filter(F.col("sleep_minutes").isNotNull())
sleep_df = sleep_df.filter(F.col("sleep_minutes") > 0)
if user_id:
sleep_df = sleep_df.filter(F.col("user_id") == user_id)
if start_date and end_date:
sleep_df = sleep_df.filter((F.col("sleep_date") >= start_date) & (F.col("sleep_date") <= end_date))
sleep_df = sleep_df.withColumn("sleep_hours", F.round(F.col("sleep_minutes") / 60.0, 2))
sleep_df = sleep_df.withColumn("sleep_score", F.round(F.when(F.col("sleep_hours") >= 7, 90).when(F.col("sleep_hours") >= 6, 80).when(F.col("sleep_hours") >= 5, 70).otherwise(60) - F.col("wake_count") * 2, 2))
agg_df = sleep_df.groupBy("user_id").agg(F.round(F.avg("sleep_hours"), 2).alias("avg_sleep_hours"), F.round(F.avg("wake_count"), 2).alias("avg_wake_count"), F.round(F.avg("sleep_score"), 2).alias("avg_sleep_score"), F.max("sleep_hours").alias("max_sleep_hours"), F.min("sleep_hours").alias("min_sleep_hours"))
dist_df = sleep_df.withColumn("quality_level", F.when(F.col("sleep_score") >= 85, "良好").when(F.col("sleep_score") >= 70, "一般").otherwise("偏弱")).groupBy("user_id", "quality_level").count()
main_df = dist_df.orderBy(F.col("user_id"), F.col("count").desc()).groupBy("user_id").agg(F.first("quality_level").alias("main_quality_level"))
result_df = agg_df.join(main_df, on="user_id", how="left")
latest_df = sleep_df.orderBy(F.col("sleep_date").desc()).limit(100)
rows = result_df.collect()
data = [row.asDict() for row in rows]
latest_rows = [row.asDict() for row in latest_df.collect()]
return JsonResponse({"code": 200, "data": data, "latest": latest_rows}, json_dumps_params={"ensure_ascii": False})
def association_insight_analysis(request):
user_id = request.GET.get("user_id")
start_date = request.GET.get("start_date")
end_date = request.GET.get("end_date")
behavior_df = spark.read.jdbc(url=mysql_url, table="phone_behavior", properties=mysql_props)
sleep_df = spark.read.jdbc(url=mysql_url, table="sleep_record", properties=mysql_props)
if user_id:
behavior_df = behavior_df.filter(F.col("user_id") == user_id)
sleep_df = sleep_df.filter(F.col("user_id") == user_id)
if start_date and end_date:
behavior_df = behavior_df.filter((F.col("use_date") >= start_date) & (F.col("use_date") <= end_date))
sleep_df = sleep_df.filter((F.col("sleep_date") >= start_date) & (F.col("sleep_date") <= end_date))
behavior_df = behavior_df.filter(F.col("use_duration").isNotNull())
sleep_df = sleep_df.filter(F.col("sleep_minutes").isNotNull())
behavior_df = behavior_df.withColumn("night_flag", F.when((F.hour("use_time") >= 22) | (F.hour("use_time") < 2), 1).otherwise(0))
night_df = behavior_df.filter(F.col("night_flag") == 1)
behavior_daily = night_df.groupBy("user_id", "use_date").agg(F.round(F.sum("use_duration"), 2).alias("night_total_minutes"), F.count("*").alias("night_use_times"))
sleep_daily = sleep_df.withColumn("sleep_hours", F.round(F.col("sleep_minutes") / 60.0, 2)).select("user_id", "sleep_date", "sleep_hours", "wake_count")
join_df = behavior_daily.join(sleep_daily, (behavior_daily.user_id == sleep_daily.user_id) & (behavior_daily.use_date == sleep_daily.sleep_date), "inner")
corr_sleep = join_df.stat.corr("night_total_minutes", "sleep_hours")
corr_times = join_df.stat.corr("night_use_times", "sleep_hours")
corr_wake = join_df.stat.corr("night_total_minutes", "wake_count")
level_df = join_df.withColumn("use_level", F.when(F.col("night_total_minutes") >= 120, "高").when(F.col("night_total_minutes") >= 60, "中").otherwise("低")).withColumn("sleep_level", F.when(F.col("sleep_hours") >= 7, "充足").when(F.col("sleep_hours") >= 6, "一般").otherwise("偏少"))
cross_df = level_df.groupBy("use_level", "sleep_level").count()
detail_df = join_df.orderBy(F.col("night_total_minutes").desc()).limit(100)
cross_rows = cross_df.collect()
detail_rows = detail_df.collect()
cross_data = [row.asDict() for row in cross_rows]
detail_data = [row.asDict() for row in detail_rows]
return JsonResponse({"code": 200, "corr_sleep_hours": round(corr_sleep, 4) if corr_sleep is not None else None, "corr_use_times": round(corr_times, 4) if corr_times is not None else None, "corr_wake_count": round(corr_wake, 4) if corr_wake is not None else None, "cross": cross_data, "detail": detail_data}, json_dumps_params={"ensure_ascii": False})
睡前手机使用行为与睡眠关联性可视化分析系统文档展示

💖💖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
9024



被折叠的 条评论
为什么被折叠?



