💖💖作者：计算机毕业设计江挽 💙💙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
基于大数据的北京高档酒店数据可视化分析系统介绍
基于Hadoop+Spark的北京高档酒店数据分析系统是一个集数据采集、存储、分析与可视化展示于一体的大数据应用平台。该系统运用Hadoop分布式文件系统HDFS作为底层数据存储架构，结合Spark强大的内存计算能力，对北京地区高档酒店的海量业务数据进行深度挖掘和智能分析。系统采用Python作为主要开发语言，后端框架选用Django进行业务逻辑处理，前端采用Vue+ElementUI构建用户交互界面，通过Echarts实现数据的动态可视化展示。核心功能模块涵盖酒店基础数据管理、用户画像特征分析、酒店设施水平评估、空间分布态势分析、价格影响因素分析以及口碑评价情况分析等多个维度。系统通过Spark SQL进行复杂查询和数据聚合运算，利用Pandas和NumPy进行数据预处理和统计分析，最终将分析结果以直观的图表形式呈现在大屏看板上，为酒店经营管理者提供科学的决策支持，同时为消费者选择合适的高档酒店提供参考依据。
基于大数据的北京高档酒店数据可视化分析系统演示视频
基于大数据的北京高档酒店数据可视化分析系统演示图片
基于大数据的北京高档酒店数据可视化分析系统代码展示
from pyspark.sql import SparkSession
from pyspark.sql.functions import col, avg, count, sum, desc, when, regexp_replace
import pandas as pd
import numpy as np
from django.http import JsonResponse
from django.views.decorators.csrf import csrf_exempt
import json
def analyze_user_portrait(request):
spark = SparkSession.builder.appName("UserPortraitAnalysis").config("spark.sql.adaptive.enabled", "true").getOrCreate()
hotel_df = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/hotel_db").option("dbtable", "hotel_data").option("user", "root").option("password", "123456").load()
user_df = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/hotel_db").option("dbtable", "user_data").option("user", "root").option("password", "123456").load()
joined_df = hotel_df.join(user_df, hotel_df.user_id == user_df.id, "inner")
age_analysis = joined_df.groupBy("age_group").agg(count("*").alias("user_count"), avg("hotel_price").alias("avg_spending")).orderBy(desc("user_count"))
gender_analysis = joined_df.groupBy("gender").agg(count("*").alias("booking_count"), avg("stay_duration").alias("avg_stay_days"))
region_analysis = joined_df.groupBy("user_region").agg(count("*").alias("region_count"), avg("hotel_rating").alias("avg_preferred_rating"))
consumption_analysis = joined_df.withColumn("spending_level", when(col("hotel_price") < 500, "经济型").when(col("hotel_price") < 1000, "舒适型").otherwise("豪华型")).groupBy("spending_level").agg(count("*").alias("level_count"))
preference_analysis = joined_df.groupBy("hotel_facilities").agg(count("*").alias("facility_preference")).orderBy(desc("facility_preference"))
age_result = age_analysis.toPandas().to_dict('records')
gender_result = gender_analysis.toPandas().to_dict('records')
region_result = region_analysis.toPandas().to_dict('records')
consumption_result = consumption_analysis.toPandas().to_dict('records')
preference_result = preference_analysis.toPandas().to_dict('records')
spark.stop()
return JsonResponse({"age_distribution": age_result, "gender_preference": gender_result, "region_analysis": region_result, "spending_behavior": consumption_result, "facility_preference": preference_result})
def analyze_hotel_facilities(request):
spark = SparkSession.builder.appName("HotelFacilitiesAnalysis").config("spark.sql.adaptive.enabled", "true").config("spark.sql.adaptive.coalescePartitions.enabled", "true").getOrCreate()
facilities_df = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/hotel_db").option("dbtable", "hotel_data").option("user", "root").option("password", "123456").load()
rating_df = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/hotel_db").option("dbtable", "hotel_rating").option("user", "root").option("password", "123456").load()
merged_df = facilities_df.join(rating_df, facilities_df.hotel_id == rating_df.hotel_id, "inner")
facilities_rating = merged_df.groupBy("facilities_type").agg(avg("overall_rating").alias("avg_rating"), count("*").alias("hotel_count"), avg("service_score").alias("avg_service"))
facilities_price_correlation = merged_df.groupBy("facilities_level").agg(avg("hotel_price").alias("avg_price"), avg("overall_rating").alias("avg_rating"))
luxury_facilities = merged_df.filter(col("facilities_level") == "豪华").groupBy("specific_facilities").agg(count("*").alias("facility_count"), avg("customer_satisfaction").alias("satisfaction_score"))
facilities_impact = merged_df.withColumn("has_pool", when(col("facilities_description").contains("游泳池"), 1).otherwise(0)).withColumn("has_gym", when(col("facilities_description").contains("健身房"), 1).otherwise(0)).withColumn("has_spa", when(col("facilities_description").contains("SPA"), 1).otherwise(0))
impact_analysis = facilities_impact.groupBy("has_pool", "has_gym", "has_spa").agg(avg("overall_rating").alias("avg_rating"), avg("hotel_price").alias("avg_price"))
maintenance_analysis = merged_df.groupBy("facilities_condition").agg(count("*").alias("condition_count"), avg("maintenance_score").alias("avg_maintenance"))
facilities_trend = merged_df.groupBy("year", "facilities_type").agg(count("*").alias("yearly_count"), avg("investment_amount").alias("avg_investment"))
rating_result = facilities_rating.toPandas().to_dict('records')
price_result = facilities_price_correlation.toPandas().to_dict('records')
luxury_result = luxury_facilities.toPandas().to_dict('records')
impact_result = impact_analysis.toPandas().to_dict('records')
maintenance_result = maintenance_analysis.toPandas().to_dict('records')
trend_result = facilities_trend.toPandas().to_dict('records')
spark.stop()
return JsonResponse({"facilities_rating": rating_result, "price_correlation": price_result, "luxury_analysis": luxury_result, "impact_analysis": impact_result, "maintenance_status": maintenance_result, "development_trend": trend_result})
def analyze_price_factors(request):
spark = SparkSession.builder.appName("PriceFactorsAnalysis").config("spark.sql.adaptive.enabled", "true").config("spark.serializer", "org.apache.spark.serializer.KryoSerializer").getOrCreate()
price_df = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/hotel_db").option("dbtable", "hotel_data").option("user", "root").option("password", "123456").load()
location_df = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/hotel_db").option("dbtable", "hotel_location").option("user", "root").option("password", "123456").load()
combined_df = price_df.join(location_df, price_df.hotel_id == location_df.hotel_id, "inner")
location_price = combined_df.groupBy("district").agg(avg("hotel_price").alias("avg_district_price"), count("*").alias("hotel_count"), avg("distance_to_center").alias("avg_distance"))
seasonal_price = combined_df.groupBy("season", "hotel_star_level").agg(avg("hotel_price").alias("seasonal_avg_price"), avg("occupancy_rate").alias("avg_occupancy"))
star_level_analysis = combined_df.groupBy("hotel_star_level").agg(avg("hotel_price").alias("avg_star_price"), avg("room_size").alias("avg_room_size"), avg("service_rating").alias("avg_service"))
facilities_price_impact = combined_df.withColumn("price_range", when(col("hotel_price") < 800, "经济档").when(col("hotel_price") < 1500, "中档").otherwise("高档")).groupBy("price_range", "main_facilities").agg(count("*").alias("range_count"))
competition_analysis = combined_df.groupBy("district").agg(count("*").alias("competitor_count"), avg("hotel_price").alias("district_avg_price"), avg("market_share").alias("avg_market_share"))
demand_supply_ratio = combined_df.groupBy("month").agg(avg("booking_demand").alias("avg_demand"), avg("room_supply").alias("avg_supply"), avg("hotel_price").alias("monthly_avg_price"))
special_events_impact = combined_df.filter(col("has_special_events") == 1).groupBy("event_type").agg(avg("hotel_price").alias("event_avg_price"), avg("price_increase_rate").alias("avg_increase_rate"))
room_type_pricing = combined_df.groupBy("room_type", "hotel_star_level").agg(avg("hotel_price").alias("room_type_price"), avg("booking_frequency").alias("booking_freq"))
location_result = location_price.toPandas().to_dict('records')
seasonal_result = seasonal_price.toPandas().to_dict('records')
star_result = star_level_analysis.toPandas().to_dict('records')
facilities_result = facilities_price_impact.toPandas().to_dict('records')
competition_result = competition_analysis.toPandas().to_dict('records')
demand_result = demand_supply_ratio.toPandas().to_dict('records')
events_result = special_events_impact.toPandas().to_dict('records')
room_result = room_type_pricing.toPandas().to_dict('records')
spark.stop()
return JsonResponse({"location_pricing": location_result, "seasonal_trends": seasonal_result, "star_level_impact": star_result, "facilities_impact": facilities_result, "competition_effect": competition_result, "supply_demand": demand_result, "events_impact": events_result, "room_type_analysis": room_result})
基于大数据的北京高档酒店数据可视化分析系统文档展示
💖💖作者：计算机毕业设计江挽 💙💙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
