import pandas as pd
import pyecharts.options as opts
from pyecharts.charts import Pie
import re


with open('data/房源信息.txt','rb') as file:
    house_list = []
    while True:
        line = file.readline()
        if not line:
            break
        line = eval(line.decode('utf-8'))
        line['面积'] = int(re.findall('\d+',line['面积'])[0])
        line['价格'] = int(re.findall('\d+',line['价格'])[0])
        house_list.append(line)
house_list_DF = pd.DataFrame(house_list)
xingzhengqu = [item for item in set(house_list_DF.get(key='行政区')) if item]

# 租房面积统计
bins = [-1,30,60,90,120,200,300,400,10000]
attr = ['0-30平方米','30-60平方米','60-90平方米','90-120平方米','120-200平方米','200-300平方米','300-400平方米','400+平方米']
tmpDF = house_list_DF.groupby(pd.cut(house_list_DF['面积'],bins = bins,labels=attr)).size().reset_index(name = 'count')
value = list(map(int,tmpDF['count'].values))
pie = Pie(init_opts=opts.InitOpts(width='800px',height='800px'))
pie.add('',zip(attr,value)).set_global_opts(title_opts=opts.TitleOpts(title='租房面积统计'))
pie.render('images/house/广州租房面积统计.html')

# 求每个区的每平方米的租房单价
from pyecharts.charts import TreeMap
def getAvgPrice(xingzhengqu):
    totalPrice = 0
    totalArea = 0
    for item in house_list:
        if item['行政区'] == xingzhengqu:
            totalArea = totalArea + item['面积']
            totalPrice = totalPrice + item['价格']
    return totalPrice / totalArea if totalArea >0 else 1
# 获取每个区 单月每平方米的价格
def getTotalAvgPrice():
    totalAvgPriceList = []
    totalAvgPriceDirList = []
    for index, item in enumerate(xingzhengqu):
        avg_price = getAvgPrice(item)
        totalAvgPriceList.append(round(avg_price,3))
        totalAvgPriceDirList.append({'value':round(avg_price,3),'name':item + " ￥" + str(round(avg_price,3))})
    return totalAvgPriceDirList
# 获取每月每平方米的价格
data = getTotalAvgPrice()
treemap = TreeMap(init_opts=opts.InitOpts(width='900px',height='800px'))
treemap.add('广州各区房租单价:平方米/月',data,label_opts=opts.LabelOpts(is_show=True, position='inside',font_size=13))
treemap.render('images/house/广州各区房租单价.html')

# 获取每个区 单日每平方米的价格
from pyecharts.charts import Bar
totalAvgPriceList = []
for index,item in enumerate(xingzhengqu):
    avg_price = getAvgPrice(item)
    totalAvgPriceList.append(round(avg_price/30,3))
attr, value = (xingzhengqu,totalAvgPriceList)
bar = Bar(init_opts=opts.InitOpts(width='900px',height='800px'))
bar.add_xaxis(attr)
bar.add_yaxis("广州",value)
bar.set_global_opts(title_opts=opts.TitleOpts(title='广州各区房租单价:平方米/日'))
bar.render('images/house/广州每日每平方米的价格.html')

# 获取户型数据
from pyecharts.charts import WordCloud
def getRooms():
    results = house_list_DF.groupby('房间').size().reset_index(name='count')
    room_list = list(results.房间.values)
    weight_list = list(map(int,results['count'].values))
    return (room_list, weight_list)
attr, value = getRooms()
wordcloud = WordCloud(init_opts=opts.InitOpts(width='900px',height='400px'))
wordcloud.add('',zip(attr,value),word_size_range=[2,100])
wordcloud.render('images/house/广州户型数据.html')

# 获取各个区的房源比重
from pyecharts.charts import Pie
def getAreaWeight():
    result = house_list_DF.groupby('行政区').size().reset_index(name='count')
    areaName = list(result.行政区.values)
    areaWeight = list(map(int,result['count'].values))
    areaName_tmp = []
    for index,item in enumerate(areaName):
        areaName_tmp.append(item + str(round(areaWeight[index]/sum(areaWeight)*100,2))+'%')
    return zip(areaName_tmp,areaWeight)
pie = Pie(init_opts=opts.InitOpts(width='600px',height='400px'))
pie.add('',getAreaWeight()).set_global_opts(title_opts=opts.TitleOpts(title='广州房源分布'))
pie.render('images/house/广州房源分布.html')