从Dataframe的列创建元组

data=data[data['Name']!='India'] #removing the India's row data=data[data['TRU']=='Total'] #Only keeping total and excluding the rural and urban rows states_group=data[data['Level']=='State'] states_group

literacy_rate=[] total_state_pop=0 total_literate_pop=0 for key,group in states_group.iterrows(): total_state_pop+=states_group['TOT_P'] total_literate_pop+=states_group['P_LIT'] total_literate_pop+=states_group['F_LIT'] rate=(total_literate_pop/total_state_pop)*100 literacy_rate.append((states_group['Name'],rate)) print(literacy_rate)

(3 JAMMU & KASHMIR 72 HIMACHAL PRADESH 111 PUNJAB 174 CHANDIGARH 180 UTTARAKHAND 222 HARYANA 288 NCT OF DELHI 318 RAJASTHAN 420 UTTAR PRADESH 636 BIHAR 753 SIKKIM 768 MANIPUR 798 MIZORAM 825 TRIPURA 840 MEGHALAYA 864 ASSAM 948 WEST BENGAL 1008 JHARKHAND 1083 ODISHA 1176 CHHATTISGARH 1233 MADHYA PRADESH 1386 GUJARAT 1467 DAMAN & DIU 1476 DADRA & NAGAR HAVELI 1482 MAHARASHTRA 1590 ANDHRA PRADESH 1662 KARNATAKA 1755 GOA 1764 KERALA 1809 TAMIL NADU 1908 PUDUCHERRY Name: Name, dtype: object, 3 85.484832 72 99.946393 111 80.810862 174 93.793637 180 89.689123 222 79.608418 288 97.531743 318 67.745833 420 69.971651 636 52.937273 753 98.691424 768 96.236438 798 109.113300 825 116.065370 840 84.108326 864 96.451609 948 87.437511 1008 63.211190 1083 85.260257 1176 85.104889 1233 78.055310 1386 99.236215 1467 121.848465 1476 112.301972 1482 100.968386 1590 79.671587 1662 81.400129 1755 110.110417 1764 120.140132 1809 94.529868 1908 101.165414 dtype: float64), (3 JAMMU & KASHMIR 72 HIMACHAL PRADESH 111 PUNJAB 174 CHANDIGARH 180 UTTARAKHAND 222 HARYANA 288 NCT OF DELHI 318 RAJASTHAN 420 UTTAR PRADESH 636 BIHAR 753 SIKKIM 768 MANIPUR 798 MIZORAM 825 TRIPURA 840 MEGHALAYA 864 ASSAM 948 WEST BENGAL 1008 JHARKHAND 1083 ODISHA 1176 CHHATTISGARH 1233 MADHYA PRADESH 1386 GUJARAT 1467 DAMAN & DIU 1476 DADRA & NAGAR HAVELI 1482 MAHARASHTRA 1590 ANDHRA PRADESH 1662 KARNATAKA 1755 GOA 1764 KERALA 1809 TAMIL NADU 1908 PUDUCHERRY Name: Name, dtype: object, 3 85.484832 72 99.946393 111 80.810862 174 93.793637 180 89.689123 222 79.608418 288 97.531743 318 67.745833 420 69.971651 636 52.937273 753 98.691424 768 96.236438 798 109.113300 825 116.065370 840 84.108326 864 96.451609 948 87.437511 1008 63.211190 1083 85.260257 1176 85.104889 1233 78.055310 1386 99.236215 1467 121.848465 1476 112.301972 1482 100.968386 1590 79.671587 1662 81.400129 1755 110.110417 1764 120.140132 1809 94.529868 1908 101.165414 dtype: float64), (3 JAMMU & KASHMIR 72 HIMACHAL PRADESH 111 PUNJAB 174 CHANDIGARH 180 UTTARAKHAND 222 HARYANA 288 NCT OF DELHI 318 RAJASTHAN 420 UTTAR PRADESH 636 BIHAR 753 SIKKIM 768 MANIPUR 798 MIZORAM 825 TRIPURA 840 MEGHALAYA 864 ASSAM 948 WEST BENGAL 1008 JHARKHAND 1083 ODISHA 1176 CHHATTISGARH 1233 MADHYA PRADESH 1386 GUJARAT 1467 DAMAN & DIU 1476 DADRA & NAGAR HAVELI 1482 MAHARASHTRA 1590 ANDHRA PRADESH 1662 KARNATAKA 1755 GOA 1764 KERALA 1809 TAMIL NADU 1908 PUDUCHERRY Name: Name, dtype: object, 3 85.484832 72 99.946393 111 80.810862 174 93.793637 180 89.689123 222 79.608418 288 97.531743 318 67.745833 420 69.971651 636 52.937273 753 98.691424 768 96.236438 798 109.113300 825 116.065370 840 84.108326 864 96.451609 948 87.437511 1008 63.211190 1083 85.260257 1176 85.104889 1233 78.055310 1386 99.236215 1467 121.848465 1476 112.301972

2条回答

网友

1楼 · 编辑于 2024-05-23 14:36:00

在for循环中，如何将每个states_group更改为group 或者，使用.iterrows()进行for循环没有任何意义

literacy_rate=[]
total_state_pop=0
total_literate_pop=0
for key,group in states_group.iterrows():
    total_state_pop+=group['TOT_P']
    
    total_literate_pop+=group['P_LIT']
    total_literate_pop+=group['F_LIT']
    rate=(total_literate_pop/total_state_pop)*100
    literacy_rate.append((group['Name'],rate))

网友

2楼 · 编辑于 2024-05-23 14:36:00

尽可能避免迭代，因为这是熊猫的反模式good read

import pandas as pd
data = pd.read_excel('state_dist_sc.xls')
data=data[data['Name']!='India']
data=data[data['TRU']=='Total']
states_group=data[data['Level']=='State']

#create a copy of data on which we will be calculating literacy rate.
states_group = states_group.copy()

#Calculate litracy rate using vector formula which is faster and more.
states_group['literacy_rate'] = 100*(states_group['P_LIT'] + states_group['F_LIT'])/states_group['TOT_P']

# use to_records to get list of tuples
ans = states_group[['Name','literacy_rate']].to_records(index=False)
ans

输出：

rec.array([('JAMMU & KASHMIR',  85.48483174),
           ('HIMACHAL PRADESH',  99.94639301), ('PUNJAB',  80.81086172),
           ('CHANDIGARH',  93.79363692), ('UTTARAKHAND',  89.68912284),
           ('HARYANA',  79.60841792), ('NCT OF DELHI',  97.53174349),
           ('RAJASTHAN',  67.74583313), ('UTTAR PRADESH',  69.97165068),
           ('BIHAR',  52.93727261), ('SIKKIM',  98.69142352),
           ('MANIPUR',  96.23643761), ('MIZORAM', 109.11330049),
           ('TRIPURA', 116.06537002), ('MEGHALAYA',  84.10832613),
           ('ASSAM',  96.45160871), ('WEST BENGAL',  87.43751069),
           ('JHARKHAND',  63.21118996), ('ODISHA',  85.26025661),
           ('CHHATTISGARH',  85.10488906),
           ('MADHYA PRADESH',  78.05530967), ('GUJARAT',  99.23621537),
           ('DAMAN & DIU', 121.84846506),
           ('DADRA & NAGAR HAVELI', 112.3019722 ),
           ('MAHARASHTRA', 100.96838647),
           ('ANDHRA PRADESH',  79.67158709), ('KARNATAKA',  81.40012899),
           ('GOA', 110.11041691), ('KERALA', 120.14013153),
           ('TAMIL NADU',  94.529868  ), ('PUDUCHERRY', 101.16541449)],
          dtype=[('Name', 'O'), ('literacy_rate', '<f8')])

相关问题更多 >

编程相关推荐

热门问题

热门文章