민원 데이터 연령별

In [1]:

import numpy as np
import pandas as pd

# 시각화
import matplotlib.pyplot as plt
import seaborn as sns
import matplotlib as mpl

from IPython.core.display import display, HTML
display(HTML("<style>.container {width:90% !important;}</style>"))

In [2]:

M_10 = pd.read_csv('../csv2/M_10_YEARLY.csv', encoding='cp949')
M_20 = pd.read_csv('../csv2/M_20_YEARLY.csv', encoding='cp949')
M_30 = pd.read_csv('../csv2/M_30_YEARLY.csv', encoding='cp949')
M_40 = pd.read_csv('../csv2/M_40_YEARLY.csv', encoding='cp949')
M_50 = pd.read_csv('../csv2/M_50_YEARLY.csv', encoding='cp949')

In [3]:

W_10 = pd.read_csv('../csv2/W_10_YEARLY.csv', encoding='cp949')
W_20 = pd.read_csv('../csv2/W_20_YEARLY.csv', encoding='cp949')
W_30 = pd.read_csv('../csv2/W_30_YEARLY.csv', encoding='cp949')
W_40 = pd.read_csv('../csv2/W_40_YEARLY.csv', encoding='cp949')
W_50 = pd.read_csv('../csv2/W_50_YEARLY.csv', encoding='cp949')

In [4]:

# M_10= pd.DataFrame(...)
M_10['age']=10
M_10=M_10.pivot(index='age', columns='label', values='hits')
M_10

Out[4]:

label	20180101	20190101	20200101
age
10	15687	21103	6015

In [5]:

M_20['age']=20
M_20=M_20.pivot(index='age', columns='label', values='hits')
M_20

Out[5]:

label	20180101	20190101	20200101
age
20	209308	266658	125934

In [6]:

M_30['age']= 30
M_30=M_30.pivot(index='age', columns='label', values='hits')  #데이터 재구조화 

M_40['age']= 40
M_40=M_40.pivot(index='age', columns='label', values='hits')

M_50['age']= 50
M_50=M_50.pivot(index='age', columns='label', values='hits')

In [7]:

dataM = pd.concat([M_10, M_20, M_30, M_40, M_50], axis=0)
dataM.columns=['2018','2019','2020']
dataM  # 남자 

Out[7]:

	2018	2019	2020
age
10	15687	21103	6015
20	209308	266658	125934
30	570136	1152732	702670
40	562894	889950	505705
50	310630	423603	278065

In [8]:

W_10['age']=10
W_10=W_10.pivot(index='age', columns='label', values='hits')  

W_20['age']=20
W_20=W_20.pivot(index='age', columns='label', values='hits')

W_30['age']= 30
W_30=W_30.pivot(index='age', columns='label', values='hits') 

W_40['age']= 40
W_40=W_40.pivot(index='age', columns='label', values='hits')

W_50['age']= 50
W_50=W_50.pivot(index='age', columns='label', values='hits')

dataW = pd.concat([W_10, W_20, W_30, W_40, W_50], axis=0)
dataW.columns=['2018','2019','2020']
dataW  # 여자 

Out[8]:

	2018	2019	2020
age
10	19129	12704	2102
20	172311	178709	54883
30	510445	981757	437177
40	342044	713889	382116
50	194242	290498	271743

In [9]:

dataM.plot.bar()
plt.title('Man')
# y축은 값이 100000 이상 넘어가서 저렇게 표기됨 

Out[9]:

Text(0.5, 1.0, 'Man')

In [10]:

dataW.plot.bar()
plt.title('Woman')

# dataW.plot.bar().x

Out[10]:

Text(0.5, 1.0, 'Woman')

In [11]:

# 2019년도 30대 월별 결과
M_30_2019 = pd.read_csv('../csv2/M_30_MONTHLY.csv', encoding='cp949')
W_30_2019 = pd.read_csv('../csv2/W_30_MONTHLY.csv', encoding='cp949')

In [12]:

M_30_2019

Out[12]:

	hits	label
0	67998	20190101
1	65284	20190201
2	65492	20190301
3	83462	20190401
4	133628	20190501
5	173849	20190601
6	110914	20190701
7	76746	20190801
8	90342	20190901
9	88465	20191001
10	95025	20191101
11	97156	20191201

In [13]:

M_30_2019['sex']= 'M'
M_30_2019=M_30_2019.pivot(index='label', columns='sex', values='hits')
M_30_2019

Out[13]:

sex	M
label
20190101	67998
20190201	65284
20190301	65492
20190401	83462
20190501	133628
20190601	173849
20190701	110914
20190801	76746
20190901	90342
20191001	88465
20191101	95025
20191201	97156

In [14]:

W_30_2019['sex']= 'W'
W_30_2019=W_30_2019.pivot(index='label', columns='sex', values='hits')  
W_30_2019

Out[14]:

sex	W
label
20190101	86632
20190201	51532
20190301	56352
20190401	60964
20190501	125612
20190601	143827
20190701	80557
20190801	66555
20190901	74154
20191001	70279
20191101	83229
20191201	77972

In [15]:

data2019 = pd.concat([M_30_2019, W_30_2019], axis=1)
data2019.index= ['01','02','03','24','05','06','07','08','09','10','11','12']
data2019

Out[15]:

sex	M	W
01	67998	86632
02	65284	51532
03	65492	56352
24	83462	60964
05	133628	125612
06	173849	143827
07	110914	80557
08	76746	66555
09	90342	74154
10	88465	70279
11	95025	83229
12	97156	77972

In [16]:

data2019.plot.bar()
plt.title('2019_30_MONTHLY')

Out[16]:

Text(0.5, 1.0, '2019_30_MONTHLY')

In [17]:

# 2020년 남자 총 민원 건수 
sumM=sum(dataM['2020'])
sumM

Out[17]:

1618389

In [18]:

# 2020년 여자 총 민원 건수 
sumW=sum(dataW['2020'])
sumW

Out[18]:

1148021

In [19]:

# 2018~2020 남자 총 민원 건수 
sumM3 = sum(dataM['2020'])+sum(dataM['2019'])+sum(dataM['2018'])
sumM3

Out[19]:

6041090

In [20]:

# 2018~2020 여자 총 민원 건수 
sumW3 = sum(dataW['2020'])+sum(dataW['2019'])+sum(dataW['2018'])
sumW3

Out[20]:

4563749

In [ ]: