부동산 거래량 과 거래 금액 추이

부동산 거래량

In [102]:

#-*- encoding: utf8 -*-
import os
import glob
import pandas as pd
import matplotlib.pyplot as plt
import unicodedata

In [103]:

import matplotlib

In [104]:

matplotlib.rc('font', family='AppleGothic')

In [193]:

def load_data(path):
    filenames = glob.glob(os.path.join(path, '*.csv'))
    ret = {}

    for fname in filenames:
        dft = pd.read_csv(fname)
        dft.columns = dft.columns.str.normalize('NFC')
        dft['거래금액(만원)'] = dft['거래금액(만원)'].str.replace(',', '')# extract('(\d+),(\d+)')
        dft['거래금액(만원)'] =  pd.to_numeric(dft['거래금액(만원)'])
        
        dname = fname.split('_')[0].split('/')[-1]
        ret[unicodedata.normalize('NFC', dname)] = dft
    return ret

In [194]:

df_dict = load_data('./trade/')

In [195]:

df_dict['서울'].head(3)

Out[195]:

	시군구	번지	본번	부번	단지명	전용면적(㎡)	계약년월	계약일	거래금액(만원)	층	건축년도	도로명
0	서울특별시 강남구 개포동	658-1	658	1	개포6차우성아파트1동~8동	79.97	201803	11~20	139500	2	1987	언주로
1	서울특별시 강남구 개포동	658-1	658	1	개포6차우성아파트1동~8동	54.98	201804	1~10	107500	5	1987	언주로
2	서울특별시 강남구 개포동	658-1	658	1	개포6차우성아파트1동~8동	79.97	201806	21~30	145000	3	1987	언주로

In [117]:

def cal_volume(data_dict):
    data = {}

    for key, dft in data_dict.items():
        data[key] = dft.groupby('계약년월').count()['시군구']
    df_count = pd.DataFrame(data)
    df_count.index = pd.to_datetime(df_count.index, format='%Y%m')
    
    return df_count

In [181]:

def cal_mean(data_dict):
    data = {}

    for key, dft in data_dict.items():
#         print(key)
        data[key] = dft[['계약년월', '거래금액(만원)']].groupby('계약년월').mean()['거래금액(만원)']
#     print(data)
    df_mean = pd.DataFrame(data)
    df_mean.index = pd.to_datetime(df_count.index, format='%Y%m')
    
    return df_mean

In [182]:

dfm = cal_mean(df_dict)

In [183]:

dfm

Out[183]:

	경기도	광주	대구	대전	서울	세종	제주
계약년월
2018-03-01	36157.297062	21204.754641	29619.066841	22587.752541	58728.301032	32115.321503	26638.266094
2018-04-01	34924.966615	21097.412190	28412.400000	22638.452815	59856.125975	31344.019011	23813.879808
2018-05-01	34452.957298	21713.175413	28147.343570	22624.980960	58969.572067	31319.115502	23434.927203
2018-06-01	35404.030386	22061.336989	24812.815326	22865.259669	60210.091309	31707.827004	25095.180412
2018-07-01	37705.976067	21510.797667	28311.549089	23717.254561	69906.172453	31106.840909	26684.820988
2018-08-01	43247.272887	23409.422186	30673.880118	27009.363918	71688.794253	31176.224880	29121.371429
2018-09-01	36653.899023	22592.559847	31996.980649	26715.617507	70335.151242	32985.492537	28613.664596
2018-10-01	34506.451154	20914.076187	29582.405161	26299.346375	65617.934763	31874.184314	26417.256917
2018-11-01	33816.169203	20567.570674	26999.507293	25586.329739	64199.914607	32410.860656	27265.452991
2018-12-01	33667.329350	20395.169421	27599.829969	22437.410328	61598.975578	29167.441860	26439.788462
2019-01-01	33166.544470	19968.007777	25912.953277	23271.179468	61272.517178	30323.490909	25148.101695
2019-02-01	31301.967317	18640.096558	23383.787152	21913.495413	54783.578801	27449.398773	22897.721519

In [191]:

dfm2 = dfm / dfm.iloc[0]
dfm2.plot(figsize=(15,8), title='평균 거래 금액')

Out[191]:

<matplotlib.axes._subplots.AxesSubplot at 0x1113437f0>

In [188]:

df_count = cal_volume(df_dict)

In [192]:

df_count_nor = df_count / df_count.iloc[0]
df_count_nor.plot(figsize=(15,8), title='거래량')

Out[192]:

<matplotlib.axes._subplots.AxesSubplot at 0x113e39b00>