🍊作者：计算机毕设匠心工作室
🍊简介：毕业后就一直专业从事计算机软件程序开发，至今也有8年工作经验。擅长Java、Python、微信小程序、安卓、大数据、PHP、.NET|C#、Golang等。
擅长：按照需求定制化开发项目、 源码、对代码进行完整讲解、文档撰写、ppt制作。
🍊心愿：点赞 👍 收藏 ⭐评论 📝
👇🏻 精彩专栏推荐订阅 👇🏻 不然下次找不到哟~
🍅 ↓↓文末获取源码联系↓↓🍅
基于大数据的烟酒成瘾个体数据分析与可视化系统-功能介绍
基于大数据的烟酒成瘾个体数据分析与可视化系统是一个集数据采集、存储、分析与可视化展示于一体的综合性平台，采用Hadoop分布式存储架构和Spark大数据处理引擎，结合Python数据科学库进行深度数据挖掘分析。系统通过Django后端框架构建RESTful API接口，前端采用Vue+ElementUI+Echarts技术栈实现交互式数据可视化界面，能够对烟酒成瘾个体的多维度数据进行智能分析处理。平台核心功能涵盖人口统计学特征与成瘾行为关联分析、成瘾历程与戒瘾尝试效果评估、健康生活方式影响因素挖掘以及多因素综合风险评估等四大模块，通过Spark SQL进行大规模数据查询优化，利用Pandas和NumPy进行统计分析计算，实现对年龄、性别、教育水平、收入状况等人口学变量与吸烟饮酒行为的深度关联挖掘，构建成瘾高风险人群特征画像和健康风险预警体系，为成瘾行为干预决策提供科学的数据支撑和可视化分析结果。
基于大数据的烟酒成瘾个体数据分析与可视化系统-选题背景意义
选题背景 烟草和酒精成瘾作为全球性公共健康问题，对个体身心健康和社会经济发展造成严重影响，传统的成瘾行为研究多依赖小样本调查和简单统计分析，难以深入挖掘海量个体数据中隐藏的复杂关联模式和风险因素。随着大数据技术的快速发展和健康医疗数据的大规模积累，利用先进的数据挖掘技术对成瘾个体进行精准分析成为可能，大数据平台能够处理包含人口统计学特征、成瘾历程记录、健康状况指标、生活方式信息等多维度海量数据，通过机器学习算法识别成瘾行为的复杂影响因素和演变规律。现有的成瘾研究系统多局限于传统数据库和简单分析工具，缺乏对大规模异构数据的深度挖掘能力，无法实现实时动态分析和智能预警功能，亟需构建基于现代大数据技术架构的专业化分析平台。 选题意义 本课题通过构建基于大数据技术的烟酒成瘾个体分析系统，能够为相关研究领域提供一定的技术实践参考，在实际应用层面具有一些潜在价值。系统通过整合多维度个体数据，尝试建立相对完整的成瘾行为分析框架，可以在一定程度上帮助识别成瘾高风险人群的特征组合，为健康管理机构制定针对性干预策略提供数据参考。平台的可视化功能能够直观展示成瘾行为的分布特征和变化趋势，便于研究人员和健康工作者理解复杂的数据关联关系，在健康教育和科普宣传中发挥辅助作用。从技术角度来看，项目实践了Hadoop+Spark大数据处理架构在健康数据分析领域的应用，探索了大数据技术与传统统计分析方法的结合方式，为类似的数据挖掘项目提供了一定的开发经验积累。系统构建的多因素风险评估模型虽然相对简单，但可以作为更复杂预测模型的基础框架，在后续研究中逐步完善和优化，为推动大数据技术在公共健康领域的应用做出微薄贡献。
基于大数据的烟酒成瘾个体数据分析与可视化系统-技术选型
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
基于大数据的烟酒成瘾个体数据分析与可视化系统-视频展示
基于大数据的烟酒成瘾个体数据分析与可视化系统-图片展示
基于大数据的烟酒成瘾个体数据分析与可视化系统-代码展示
from pyspark.sql import SparkSession
from pyspark.sql.functions import col, avg, count, when, desc, asc
from pyspark.ml.feature import VectorAssembler
from pyspark.ml.clustering import KMeans
import pandas as pd
import numpy as np
spark = SparkSession.builder.appName("AddictionAnalysis").config("spark.sql.adaptive.enabled", "true").config("spark.sql.adaptive.coalescePartitions.enabled", "true").getOrCreate()
def age_group_addiction_analysis():
df = spark.read.option("header", "true").option("inferSchema", "true").csv("hdfs://addiction_data.csv")
df_with_age_group = df.withColumn("age_group", when(col("age") < 25, "18-24").when(col("age") < 35, "25-34").when(col("age") < 45, "35-44").when(col("age") < 55, "45-54").otherwise("55+"))
age_smoking_stats = df_with_age_group.groupBy("age_group").agg(avg("smokes_per_day").alias("avg_smokes"), count("*").alias("total_count"), avg("drinks_per_week").alias("avg_drinks"))
age_gender_analysis = df_with_age_group.groupBy("age_group", "gender").agg(avg("smokes_per_day").alias("avg_smokes"), avg("drinks_per_week").alias("avg_drinks"))
heavy_smokers = df_with_age_group.filter(col("smokes_per_day") > 20).groupBy("age_group").count().withColumnRenamed("count", "heavy_smoker_count")
heavy_drinkers = df_with_age_group.filter(col("drinks_per_week") > 14).groupBy("age_group").count().withColumnRenamed("count", "heavy_drinker_count")
combined_stats = age_smoking_stats.join(heavy_smokers, "age_group", "left").join(heavy_drinkers, "age_group", "left")
addiction_severity = df_with_age_group.withColumn("addiction_score", col("smokes_per_day") * 0.3 + col("drinks_per_week") * 0.7)
severity_by_age = addiction_severity.groupBy("age_group").agg(avg("addiction_score").alias("avg_addiction_score"))
health_impact = df_with_age_group.filter(col("has_health_issues") == True).groupBy("age_group").count().withColumnRenamed("count", "health_issues_count")
final_result = combined_stats.join(severity_by_age, "age_group").join(health_impact, "age_group", "left")
quit_attempts = df_with_age_group.groupBy("age_group").agg(avg("attempts_to_quit_smoking").alias("avg_quit_smoking"), avg("attempts_to_quit_drinking").alias("avg_quit_drinking"))
comprehensive_analysis = final_result.join(quit_attempts, "age_group").orderBy(desc("avg_addiction_score"))
result_pandas = comprehensive_analysis.toPandas()
result_pandas['addiction_risk_level'] = pd.cut(result_pandas['avg_addiction_score'], bins=[0, 10, 20, 30, float('inf')], labels=['Low', 'Medium', 'High', 'Critical'])
return result_pandas.to_dict('records')
def high_risk_population_clustering():
df = spark.read.option("header", "true").option("inferSchema", "true").csv("hdfs://addiction_data.csv")
feature_cols = ["age", "annual_income_usd", "smokes_per_day", "drinks_per_week", "bmi", "sleep_hours", "exercise_frequency"]
df_cleaned = df.select(*feature_cols).na.drop()
assembler = VectorAssembler(inputCols=feature_cols, outputCol="features")
df_features = assembler.transform(df_cleaned)
kmeans = KMeans(k=4, seed=42, featuresCol="features", predictionCol="cluster")
model = kmeans.fit(df_features)
clustered_df = model.transform(df_features)
cluster_stats = clustered_df.groupBy("cluster").agg(avg("smokes_per_day").alias("avg_smokes"), avg("drinks_per_week").alias("avg_drinks"), avg("age").alias("avg_age"), avg("annual_income_usd").alias("avg_income"), count("*").alias("population_count"))
high_risk_threshold = 15
high_risk_clusters = cluster_stats.filter((col("avg_smokes") > high_risk_threshold) | (col("avg_drinks") > high_risk_threshold))
cluster_characteristics = clustered_df.join(df.select("education_level", "marital_status", "country", *feature_cols), feature_cols)
education_distribution = cluster_characteristics.groupBy("cluster", "education_level").count()
marital_distribution = cluster_characteristics.groupBy("cluster", "marital_status").count()
geographic_distribution = cluster_characteristics.groupBy("cluster", "country").count()
cluster_centers = pd.DataFrame(model.clusterCenters(), columns=feature_cols)
cluster_centers['cluster_id'] = range(len(cluster_centers))
risk_scores = cluster_centers['smokes_per_day'] * 0.4 + cluster_centers['drinks_per_week'] * 0.6
cluster_centers['risk_score'] = risk_scores
cluster_centers['risk_category'] = pd.cut(risk_scores, bins=[0, 10, 20, 30, float('inf')], labels=['Low', 'Medium', 'High', 'Critical'])
return {"cluster_stats": cluster_stats.toPandas().to_dict('records'), "cluster_centers": cluster_centers.to_dict('records'), "high_risk_clusters": high_risk_clusters.toPandas().to_dict('records')}
def health_risk_warning_system():
df = spark.read.option("header", "true").option("inferSchema", "true").csv("hdfs://addiction_data.csv")
df_with_duration = df.withColumn("smoking_duration", col("age") - col("age_started_smoking")).withColumn("drinking_duration", col("age") - col("age_started_drinking"))
smoking_risk_score = (col("smokes_per_day") * 0.3 + col("smoking_duration") * 0.2 + when(col("attempts_to_quit_smoking") > 3, 0.1).otherwise(0.05))
drinking_risk_score = (col("drinks_per_week") * 0.25 + col("drinking_duration") * 0.15 + when(col("attempts_to_quit_drinking") > 3, 0.1).otherwise(0.05))
df_risk = df_with_duration.withColumn("smoking_risk", smoking_risk_score).withColumn("drinking_risk", drinking_risk_score)
combined_risk = df_risk.withColumn("total_risk_score", col("smoking_risk") + col("drinking_risk"))
health_multiplier = when(col("has_health_issues") == True, 1.5).otherwise(1.0)
age_multiplier = when(col("age") > 50, 1.3).when(col("age") > 40, 1.2).otherwise(1.0)
bmi_multiplier = when(col("bmi") > 30, 1.4).when(col("bmi") > 25, 1.2).otherwise(1.0)
df_adjusted = combined_risk.withColumn("adjusted_risk_score", col("total_risk_score") * health_multiplier * age_multiplier * bmi_multiplier)
risk_categories = df_adjusted.withColumn("risk_level", when(col("adjusted_risk_score") < 5, "Low").when(col("adjusted_risk_score") < 15, "Medium").when(col("adjusted_risk_score") < 25, "High").otherwise("Critical"))
warning_conditions = risk_categories.withColumn("immediate_warning", when((col("adjusted_risk_score") > 20) & (col("has_health_issues") == True), True).otherwise(False))
risk_factors = warning_conditions.withColumn("primary_risk_factors", when(col("smoking_risk") > col("drinking_risk"), "Smoking Dominant").when(col("drinking_risk") > col("smoking_risk"), "Drinking Dominant").otherwise("Dual Addiction"))
intervention_priority = risk_factors.withColumn("intervention_urgency", when(col("adjusted_risk_score") > 25, "Immediate").when(col("adjusted_risk_score") > 15, "High Priority").when(col("adjusted_risk_score") > 10, "Medium Priority").otherwise("Low Priority"))
lifestyle_factors = intervention_priority.withColumn("lifestyle_score", (col("exercise_frequency") * 0.3 + col("sleep_hours") * 0.2 + when(col("diet_quality") == "Good", 0.3).when(col("diet_quality") == "Average", 0.15).otherwise(0)))
comprehensive_assessment = lifestyle_factors.withColumn("final_risk_assessment", col("adjusted_risk_score") - col("lifestyle_score"))
result_summary = comprehensive_assessment.groupBy("risk_level").agg(count("*").alias("population_count"), avg("adjusted_risk_score").alias("avg_risk_score"), avg("age").alias("avg_age"))
critical_cases = comprehensive_assessment.filter(col("risk_level") == "Critical").select("age", "gender", "smokes_per_day", "drinks_per_week", "adjusted_risk_score", "primary_risk_factors")
return {"risk_distribution": result_summary.toPandas().to_dict('records'), "critical_cases": critical_cases.limit(100).toPandas().to_dict('records'), "warning_stats": comprehensive_assessment.filter(col("immediate_warning") == True).count()}
基于大数据的烟酒成瘾个体数据分析与可视化系统-结语
👇🏻 精彩专栏推荐订阅 👇🏻 不然下次找不到哟~
🍅 主页获取源码联系🍅
