✍✍计算机编程指导师 ⭐⭐个人介绍：自己非常喜欢研究技术问题！专业做Java、Python、小程序、安卓、大数据、爬虫、Golang、大屏等实战项目。 ⛽⛽实战项目：有源码或者技术上的问题欢迎在评论区一起讨论交流！ ⚡⚡ Java实战 | SpringBoot/SSM Python实战项目 | Django 微信小程序/安卓实战项目 大数据实战项目
眼癌数据分析与可视化系统-简介
基于Spark的眼癌数据分析与可视化系统是一套专门针对眼部肿瘤医疗数据进行深度挖掘和智能展示的大数据应用平台。该系统构建在Hadoop分布式存储和Spark大数据计算引擎之上，采用Python作为主要开发语言，结合Django后端框架和Vue前端技术栈，实现了对眼癌患者临床数据的全方位分析处理。系统核心功能涵盖患者基本特征与疾病分布分析、癌症诊断与临床特征深度分析、治疗方案与预后效果综合评估以及高危因素与生存质量关联性探索四大维度。通过Spark SQL进行复杂的数据查询和统计计算，利用Pandas和NumPy进行数据预处理和科学计算，最终通过Echarts图表库将分析结果以直观的可视化形式呈现。系统能够处理大规模的医疗数据集，支持多维度交叉分析，为医疗研究人员和临床医生提供了强有力的数据分析工具，同时也展现了大数据技术在医疗健康领域的实际应用价值。
眼癌数据分析与可视化系统-技术
开发语言：Python或Java 大数据框架：Hadoop+Spark（本次没用Hive，支持定制） 后端框架：Django+Spring Boot(Spring+SpringMVC+Mybatis) 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
眼癌数据分析与可视化系统-背景
随着现代医疗信息化建设的深入推进，各类医疗机构积累了海量的患者诊疗数据，这些数据蕴含着丰富的临床价值和科研潜力。眼癌作为一类相对少见但危害极大的恶性肿瘤，其发病机制复杂，治疗方案多样，预后差异显著，传统的统计分析方法已难以满足对如此复杂医疗数据的深度挖掘需求。当前医疗大数据分析面临着数据规模庞大、结构复杂、处理效率低下等挑战，而传统的关系型数据库和单机分析工具在面对TB级医疗数据时往往力不从心。与此同时，大数据技术特别是Hadoop生态系统和Spark计算引擎的成熟发展，为医疗数据的高效处理和深度分析提供了新的技术路径。医疗行业迫切需要借助先进的大数据分析技术，从海量的临床数据中提取有价值的医学洞察，为疾病诊断、治疗决策和预后评估提供科学依据。
本课题的研究意义主要体现在理论探索和实践应用两个层面。从理论角度看，该系统将大数据技术与医疗信息学相结合，探索了Spark分布式计算在医疗数据分析中的应用模式，为医疗大数据处理提供了一种可行的技术方案。通过构建多维度的眼癌数据分析模型，能够从患者特征、诊断信息、治疗方案、预后效果等多个角度深入挖掘数据间的关联关系，丰富了医疗数据挖掘的理论基础。从实践意义来看，系统能够帮助医疗研究人员更高效地处理和分析眼癌相关数据，通过可视化展示使复杂的统计结果变得直观易懂，为临床决策提供数据支撑。对于医疗机构而言，该系统可以作为辅助工具帮助医生更好地了解患者群体特征和疾病发展规律。虽然这只是一个毕业设计项目，但它展示了大数据技术在特定医疗场景下的应用可能性，为后续更深入的医疗大数据研究奠定了基础，也为计算机专业学生提供了将理论知识应用于实际问题的实践机会。
眼癌数据分析与可视化系统-视频展示
[www.bilibili.com/video/BV1up…]
眼癌数据分析与可视化系统-图片展示
眼癌数据分析与可视化系统-代码展示
from pyspark.sql.functions import *
from pyspark.sql.types import *
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("EyeCancerDataAnalysis").config("spark.sql.adaptive.enabled", "true").config("spark.sql.adaptive.coalescePartitions.enabled", "true").getOrCreate()
@csrf_exempt
def analyze_patient_characteristics(request):
df = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/eye_cancer_db").option("dbtable", "patient_data").option("user", "root").option("password", "password").option("driver", "com.mysql.cj.jdbc.Driver").load()
age_distribution = df.select("Age").withColumn("age_group", when(col("Age") < 30, "青年组").when((col("Age") >= 30) & (col("Age") < 50), "中年组").when((col("Age") >= 50) & (col("Age") < 70), "中老年组").otherwise("老年组")).groupBy("age_group").count().orderBy("count", ascending=False)
gender_cancer_stats = df.groupBy("Gender", "Cancer_Type").count().withColumn("percentage", round((col("count") * 100.0 / df.count()), 2)).orderBy("Gender", "count", ascending=False)
country_distribution = df.groupBy("Country").count().withColumn("percentage", round((col("count") * 100.0 / df.count()), 2)).orderBy("count", ascending=False).limit(20)
diagnosis_year_trend = df.withColumn("diagnosis_year", year(col("Date_of_Diagnosis"))).groupBy("diagnosis_year").count().orderBy("diagnosis_year")
cancer_type_stats = df.groupBy("Cancer_Type").count().withColumn("percentage", round((col("count") * 100.0 / df.count()), 2)).orderBy("count", ascending=False)
age_pandas = age_distribution.toPandas()
gender_pandas = gender_cancer_stats.toPandas()
country_pandas = country_distribution.toPandas()
year_pandas = diagnosis_year_trend.toPandas()
cancer_pandas = cancer_type_stats.toPandas()
correlation_matrix = df.select("Age", "Survival_Time_Months").toPandas().corr().to_dict()
survival_by_age = df.groupBy("Cancer_Type").agg(avg("Age").alias("avg_age"), avg("Survival_Time_Months").alias("avg_survival")).orderBy("avg_survival", ascending=False).toPandas()
age_survival_trend = df.select("Age", "Survival_Time_Months", "Cancer_Type").filter(col("Survival_Time_Months").isNotNull()).toPandas()
age_survival_trend['age_range'] = pd.cut(age_survival_trend['Age'], bins=[0, 30, 50, 70, 100], labels=['<30', '30-50', '50-70', '>70'])
age_range_survival = age_survival_trend.groupby(['age_range', 'Cancer_Type'])['Survival_Time_Months'].agg(['mean', 'count']).reset_index()
result_data = {"age_distribution": age_pandas.to_dict('records'), "gender_cancer_cross": gender_pandas.to_dict('records'), "country_distribution": country_pandas.to_dict('records'), "yearly_trend": year_pandas.to_dict('records'), "cancer_type_stats": cancer_pandas.to_dict('records'), "age_survival_correlation": correlation_matrix, "survival_by_type": survival_by_age.to_dict('records'), "age_range_survival": age_range_survival.to_dict('records')}
return JsonResponse(result_data, safe=False)
@csrf_exempt
def analyze_treatment_outcomes(request):
df = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/eye_cancer_db").option("dbtable", "patient_data").option("user", "root").option("password", "password").option("driver", "com.mysql.cj.jdbc.Driver").load()
treatment_cancer_analysis = df.groupBy("Cancer_Type", "Treatment_Type").count().withColumn("total_by_cancer", sum("count").over(Window.partitionBy("Cancer_Type"))).withColumn("treatment_percentage", round((col("count") * 100.0 / col("total_by_cancer")), 2)).select("Cancer_Type", "Treatment_Type", "count", "treatment_percentage").orderBy("Cancer_Type", "treatment_percentage", ascending=False)
stage_treatment_analysis = df.groupBy("Stage_at_Diagnosis", "Treatment_Type").count().withColumn("total_by_stage", sum("count").over(Window.partitionBy("Stage_at_Diagnosis"))).withColumn("stage_treatment_percentage", round((col("count") * 100.0 / col("total_by_stage")), 2)).select("Stage_at_Diagnosis", "Treatment_Type", "count", "stage_treatment_percentage").orderBy("Stage_at_Diagnosis", "stage_treatment_percentage", ascending=False)
outcome_treatment_analysis = df.groupBy("Treatment_Type", "Outcome_Status").count().withColumn("total_by_treatment", sum("count").over(Window.partitionBy("Treatment_Type"))).withColumn("outcome_percentage", round((col("count") * 100.0 / col("total_by_treatment")), 2)).select("Treatment_Type", "Outcome_Status", "count", "outcome_percentage").orderBy("Treatment_Type", "outcome_percentage", ascending=False)
combined_treatment_analysis = df.select("Surgery_Status", "Radiation_Therapy", "Chemotherapy", "Outcome_Status").withColumn("treatment_combo", concat_ws("+", when(col("Surgery_Status") == "Yes", "Surgery").otherwise(""), when(col("Radiation_Therapy") == "Yes", "Radiation").otherwise(""), when(col("Chemotherapy") == "Yes", "Chemotherapy").otherwise(""))).withColumn("treatment_combo_clean", regexp_replace(col("treatment_combo"), "^\\+|\\+$", "")).withColumn("treatment_combo_final", regexp_replace(col("treatment_combo_clean"), "\\+{2,}", "+")).filter(col("treatment_combo_final") != "").groupBy("treatment_combo_final", "Outcome_Status").count().orderBy("treatment_combo_final", "count", ascending=False)
survival_treatment_analysis = df.select("Treatment_Type", "Survival_Time_Months").filter(col("Survival_Time_Months").isNotNull()).groupBy("Treatment_Type").agg(avg("Survival_Time_Months").alias("avg_survival"), stddev("Survival_Time_Months").alias("survival_std"), count("Survival_Time_Months").alias("patient_count")).orderBy("avg_survival", ascending=False)
treatment_pandas = treatment_cancer_analysis.toPandas()
stage_pandas = stage_treatment_analysis.toPandas()
outcome_pandas = outcome_treatment_analysis.toPandas()
combo_pandas = combined_treatment_analysis.toPandas()
survival_pandas = survival_treatment_analysis.toPandas()
treatment_effectiveness_matrix = df.select("Treatment_Type", "Stage_at_Diagnosis", "Outcome_Status", "Survival_Time_Months").toPandas()
treatment_success_rate = treatment_effectiveness_matrix.groupby(['Treatment_Type', 'Stage_at_Diagnosis'])['Outcome_Status'].apply(lambda x: (x == 'Remission').sum() / len(x) * 100).reset_index()
treatment_success_rate.columns = ['Treatment_Type', 'Stage_at_Diagnosis', 'success_rate']
stage_outcome_cross = df.select("Stage_at_Diagnosis", "Treatment_Type", "Outcome_Status").groupBy("Stage_at_Diagnosis", "Treatment_Type", "Outcome_Status").count().toPandas()
result_data = {"treatment_by_cancer": treatment_pandas.to_dict('records'), "treatment_by_stage": stage_pandas.to_dict('records'), "outcome_by_treatment": outcome_pandas.to_dict('records'), "combined_treatments": combo_pandas.to_dict('records'), "survival_by_treatment": survival_pandas.to_dict('records'), "treatment_success_rates": treatment_success_rate.to_dict('records'), "stage_outcome_matrix": stage_outcome_cross.to_dict('records')}
return JsonResponse(result_data, safe=False)
@csrf_exempt
def analyze_survival_factors(request):
df = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/eye_cancer_db").option("dbtable", "patient_data").option("user", "root").option("password", "password").option("driver", "com.mysql.cj.jdbc.Driver").load()
stage_survival_analysis = df.select("Stage_at_Diagnosis", "Survival_Time_Months").filter(col("Survival_Time_Months").isNotNull()).groupBy("Stage_at_Diagnosis").agg(avg("Survival_Time_Months").alias("avg_survival"), stddev("Survival_Time_Months").alias("survival_std"), min("Survival_Time_Months").alias("min_survival"), max("Survival_Time_Months").alias("max_survival"), count("Survival_Time_Months").alias("patient_count")).orderBy("avg_survival", ascending=False)
genetic_survival_analysis = df.select("Genetic_Markers", "Survival_Time_Months").filter(col("Survival_Time_Months").isNotNull()).groupBy("Genetic_Markers").agg(avg("Survival_Time_Months").alias("avg_survival"), stddev("Survival_Time_Months").alias("survival_std"), count("Survival_Time_Months").alias("patient_count")).orderBy("avg_survival", ascending=False)
cancer_survival_analysis = df.select("Cancer_Type", "Survival_Time_Months").filter(col("Survival_Time_Months").isNotNull()).groupBy("Cancer_Type").agg(avg("Survival_Time_Months").alias("avg_survival"), stddev("Survival_Time_Months").alias("survival_std"), count("Survival_Time_Months").alias("patient_count")).orderBy("avg_survival", ascending=False)
treatment_survival_detailed = df.select("Treatment_Type", "Cancer_Type", "Stage_at_Diagnosis", "Survival_Time_Months").filter(col("Survival_Time_Months").isNotNull()).groupBy("Treatment_Type", "Cancer_Type", "Stage_at_Diagnosis").agg(avg("Survival_Time_Months").alias("avg_survival"), count("Survival_Time_Months").alias("patient_count")).filter(col("patient_count") >= 5).orderBy("avg_survival", ascending=False)
family_history_survival = df.select("Family_History", "Survival_Time_Months", "Cancer_Type").filter(col("Survival_Time_Months").isNotNull()).groupBy("Family_History", "Cancer_Type").agg(avg("Survival_Time_Months").alias("avg_survival"), count("Survival_Time_Months").alias("patient_count")).orderBy("Cancer_Type", "avg_survival", ascending=False)
age_survival_detailed = df.select("Age", "Survival_Time_Months", "Stage_at_Diagnosis").filter(col("Survival_Time_Months").isNotNull()).withColumn("age_group", when(col("Age") < 40, "年轻组").when((col("Age") >= 40) & (col("Age") < 65), "中年组").otherwise("老年组")).groupBy("age_group", "Stage_at_Diagnosis").agg(avg("Survival_Time_Months").alias("avg_survival"), avg("Age").alias("avg_age"), count("Survival_Time_Months").alias("patient_count")).orderBy("Stage_at_Diagnosis", "avg_survival", ascending=False)
stage_pandas = stage_survival_analysis.toPandas()
genetic_pandas = genetic_survival_analysis.toPandas()
cancer_pandas = cancer_survival_analysis.toPandas()
treatment_pandas = treatment_survival_detailed.toPandas()
family_pandas = family_history_survival.toPandas()
age_pandas = age_survival_detailed.toPandas()
survival_data = df.select("Age", "Stage_at_Diagnosis", "Cancer_Type", "Treatment_Type", "Genetic_Markers", "Survival_Time_Months").filter(col("Survival_Time_Months").isNotNull()).toPandas()
survival_correlation = survival_data[['Age', 'Survival_Time_Months']].corr().iloc[0, 1]
high_risk_factors = df.select("Stage_at_Diagnosis", "Genetic_Markers", "Family_History", "Cancer_Type", "Survival_Time_Months").filter(col("Survival_Time_Months") < 24).groupBy("Stage_at_Diagnosis", "Genetic_Markers", "Cancer_Type").count().orderBy("count", ascending=False).limit(10).toPandas()
survival_range_analysis = survival_data.copy()
survival_range_analysis['survival_range'] = pd.cut(survival_range_analysis['Survival_Time_Months'], bins=[0, 12, 24, 60, float('inf')], labels=['<1年', '1-2年', '2-5年', '>5年'])
range_distribution = survival_range_analysis.groupby(['survival_range', 'Stage_at_Diagnosis']).size().reset_index(name='count')
result_data = {"stage_survival": stage_pandas.to_dict('records'), "genetic_survival": genetic_pandas.to_dict('records'), "cancer_type_survival": cancer_pandas.to_dict('records'), "treatment_survival_detailed": treatment_pandas.to_dict('records'), "family_history_survival": family_pandas.to_dict('records'), "age_group_survival": age_pandas.to_dict('records'), "age_survival_correlation": survival_correlation, "high_risk_factors": high_risk_factors.to_dict('records'), "survival_range_distribution": range_distribution.to_dict('records')}
return JsonResponse(result_data, safe=False)
眼癌数据分析与可视化系统-结语
大数据毕业设计选题推荐：基于Spark的眼癌数据分析与可视化系统 毕业设计/选题推荐/深度学习/数据分析/数据挖掘/机器学习/随机森林/大屏/预测/爬虫
如果觉得内容不错，欢迎一键三连（点赞、收藏、关注）支持！也欢迎在评论区或私信留下你的想法、建议，期待与大家交流探讨！感谢支持！
⚡⚡有技术问题或者获取源代码！欢迎在评论区一起交流！ ⚡⚡大家点赞、收藏、关注、有问题都可留言评论交流！ ⚡⚡有问题可以在主页上详细资料里↑↑联系我~~
