1_info.py
# encoding: utf-8
import pandas as pd
# 租房 基本資訊
# 讀取檔案 df=dataframe
df = pd.read_json("zufang.json")
# print(df)
# print(df.columns)
# 使用pandas的describe方法，列印基本資訊
print(df.describe())
# 按照區，分别統計個數
print(df["district"].value_counts())
# print('**************************')
# # 二手房 基本資訊
df = pd.read_json("ershoufang.json")
print(df.describe())
# 分别統計個數
print(df["district"].value_counts()) 複制
2_pie_chart.py
# coding:utf-8
import numpy as np
import pandas as pd
import json
import matplotlib as mpl
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
from pylab import *
mpl.rcParams['font.sans-serif'] = ['SimHei']
myfont = FontProperties(
fname='/Users/seancheney/.matplotlib/mpl-data/fonts/ttf/SimHei.ttf')
labels = '朝陽', '海澱', '昌平', '東城', '大興', '西城', '豐台', '石景山', '通州', '順義'
df_zf = pd.read_json("ershoufang.json")
chaoyang_count = df_zf['district'].value_counts()['朝陽']
haidian_count = df_zf['district'].value_counts()['海澱']
changping_count = df_zf['district'].value_counts()['昌平']
dongcheng_count = df_zf['district'].value_counts()['東城']
daxing_count = df_zf['district'].value_counts()['大興']
xicheng_count = df_zf['district'].value_counts()['西城']
fengtai_count = df_zf['district'].value_counts()['豐台']
shijingshan_count = df_zf['district'].value_counts()['石景山']
tongzhou_count = df_zf['district'].value_counts()['通州']
shunyi_count = df_zf['district'].value_counts()['順義']
sizes = [
chaoyang_count,
haidian_count,
changping_count,
dongcheng_count,
daxing_count,
xicheng_count,
fengtai_count,
shijingshan_count,
tongzhou_count,
shunyi_count]
explode = (0.1, 0, 0, 0, 0, 0, 0, 0, 0, 0)
plt.subplot(121)
plt.pie(
sizes,
explode=explode,
labels=labels,
autopct='%1.1f%%',
shadow=True,
startangle=-90)
plt.axis('equal')
plt.title("房屋出售分布", fontproperties=myfont)
labels = '朝陽', '海澱', '昌平', '東城', '大興', '西城', '豐台', '石景山', '通州', '順義'
df_zf = pd.read_json("zufang.json")
chaoyang_count = df_zf['district'].value_counts()['朝陽']
haidian_count = df_zf['district'].value_counts()['海澱']
changping_count = df_zf['district'].value_counts()['昌平']
dongcheng_count = df_zf['district'].value_counts()['東城']
daxing_count = df_zf['district'].value_counts()['大興']
xicheng_count = df_zf['district'].value_counts()['西城']
fengtai_count = df_zf['district'].value_counts()['豐台']
shijingshan_count = df_zf['district'].value_counts()['石景山']
tongzhou_count = df_zf['district'].value_counts()['通州']
labels = '朝陽', '海澱', '昌平', '東城', '大興', '西城', '豐台', '石景山', '通州'
sizes = [
chaoyang_count,
haidian_count,
changping_count,
dongcheng_count,
daxing_count,
xicheng_count,
fengtai_count,
shijingshan_count,
tongzhou_count]
explode = (0.1, 0, 0, 0, 0, 0, 0, 0, 0)
plt.subplot(122)
plt.pie(
sizes,
explode=explode,
labels=labels,
autopct='%1.1f%%',
shadow=True,
startangle=-90)
plt.axis('equal')
plt.title("房屋出租分布", fontproperties=myfont)
plt.rc('font', family=['SimHei'])
plt.show() 複制
3_hist.py
import numpy as np
import pandas as pd
import json
import matplotlib.pyplot as plt
from pylab import *
mpl.rcParams['font.sans-serif'] = ['SimHei']
df = pd.read_json("ershoufang.json")
print(df.columns)
unitprice_values = df.unitprice
plt.hist(unitprice_values,bins=25)
plt.xlim(0, 200000)
plt.title(u"房屋出售每平米價格分布")
plt.xlabel(u'價格(機關:萬/平方米)')
plt.ylabel(u'套數')
plt.show() 複制
4_ratio.py
# 售租比
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from pylab import *
mpl.rcParams['font.sans-serif'] = ['SimHei']
district = ('西城', '石景山', '東城', '海澱', '豐台', '昌平', '大興', '朝陽', '通州')
# 讀取租房資料
df_zf = pd.read_json("zufang.json")
unitprice_zf = df_zf['price'] / df_zf['area']
df_zf['unitprice'] = unitprice_zf
# print(df_zf)
month_price = df_zf.groupby(by=['district']).sum(
)['unitprice'] / df_zf["district"].value_counts()
# print(month_price)
# # 讀取二手房資料
df_esf = pd.read_json("ershoufang.json")
sell_price = df_esf.groupby(by=['district']).sum(
)['unitprice'] / df_esf["district"].value_counts()
# print(sell_price)
xicheng_ratio = sell_price['西城'] / month_price['西城']
shijingshan_ratio = sell_price['石景山'] / month_price['石景山']
dongcheng_ratio = sell_price['東城'] / month_price['東城']
haidian_ratio = sell_price['海澱'] / month_price['海澱']
fengtai_ratio = sell_price['豐台'] / month_price['豐台']
changping_ratio = sell_price['昌平'] / month_price['昌平']
daxing_ratio = sell_price['大興'] / month_price['大興']
chaoyang_ratio = sell_price['朝陽'] / month_price['朝陽']
tongzhou_ratio = sell_price['通州'] / month_price['通州']
#
#
ratio = (
xicheng_ratio,
shijingshan_ratio,
dongcheng_ratio,
haidian_ratio,
fengtai_ratio,
changping_ratio,
daxing_ratio,
chaoyang_ratio,
tongzhou_ratio
)
fig, ax = plt.subplots()
y_pos = np.arange(len(district))
# performance = ratio
ax.barh(y_pos, ratio, align='center', color='green', ecolor='black')
ax.set_yticks(y_pos)
ax.set_yticklabels(district)
# ax.invert_yaxis()
ax.set_xlabel('售租比（機關:月）')
ax.set_title('各區房屋售租比')
plt.show() 複制