nia저소득층자료분석용코드.py

import pandas as pd 

code_df = pd.read_csv('2021licode.csv')
stat_df = pd.read_csv('2021listat.csv')

code_df = code_df.drop(code_df.columns[[3,4,5]], axis=1)
code_df = code_df.iloc[3:-1]

def counted_tag(tag):
    l = [x for x in stat_df[tag].tolist() if str(x) != 'nan']
    return dict((x,l.count(x)) for x in set(l))

print("Q8A1 computer search")
print(counted_tag("Q8A1"))
print("Q8B1 phone search")
print(counted_tag("Q8B1"))

print("Q8A4 computer edu search")
print(counted_tag("Q8A4"))
print("Q8B4 phone edu search")
print(counted_tag("Q8B4"))

def compare_wt1():
    #Q1A1 ~ Q8B4
    wt1_df = stat_df[stat_df['WT'] == 1.00]
    print(wt1_df.iloc[:,2:34].sum(axis=1).sum(axis=0)) #521
    wtl1_df = stat_df[stat_df['WT'] < 1.00]
    print(wtl1_df.iloc[:,2:34].sum(axis=1).sum(axis=0)) #1013
    wto1_df = stat_df[stat_df['WT'] > 1.00]
    print(wto1_df.iloc[:,2:34].sum(axis=1).sum(axis=0)) #666

compare_wt1()