Python에서 테이블 조작 (기존 R 코드 변환)

Question

Python 또는 arcpy에서 테이블 조작에 대한 몇 가지 팁을 찾고 있습니다. 하나의 열에는 스트림 세그먼트에 대한 ID 값과 해당 ID가 속한 그룹의 두 번째 값이 있습니다. 세그먼트가 둘 이상의 그룹에 속한 경우 "추가"그룹의 모든 항목을 단일 그룹 값으로 대체하려고합니다. R에서이 작업을 수행하는 방법을 알고 있으며 코드를 첨부했지만 Python에서이 작업을 수행 할 수 있기를 원합니다. 어떤 도움이라도 대단히 감사합니다.

#-----In Python get the vectors I'm interested in... 
ORIDs=[]  #empty vector to record stream segment IDs 
GRPs=[]  #empty vector to record segment groups 
SC = arcpy.SearchCursor("feature.lyr")  #Search cursor to get FIDS 
for row in SC: 
    ORIDs.append(row.getValue("ORIG_FID")) 
    GRPs.append(row.getValue("FEAT_SEQ")) 
del row 
del SC 

#-----At this point I'm lost but can do what I want in R (R code as follows) 
ORIDs<-c(2, 7, 8, 9, 9, 10, 11, 11, 12, 13, 14, 15, 16, 18, 19, 21, 23, 
    23, 25, 26, 27, 28, 29, 30, 32, 33, 34, 34, 35, 35, 36, 37, 38, 
     39, 40, 40, 41, 41, 42, 42, 43, 43, 44, 45, 45, 46, 46, 47, 47, 
    48, 49, 50, 51, 52, 52, 53, 53, 54, 55, 57, 58, 59, 60, 61, 63, 
    64, 65, 66, 66, 67, 67, 68, 68, 69, 69, 70, 71, 73, 74, 74, 75, 
    76, 76, 77, 78, 79, 80) 

GRPs<-c(1, 2, 1, 3, 1, 4, 4, 5, 3, 5, 6, 4, 5, 7, 8, 3, 8, 7, 9, 8, 
    10, 10, 9, 10, 11, 11, 11, 12, 7, 13, 9, 13, 14, 14, 14, 15, 
    12, 2, 15, 12, 13, 16, 17, 2, 6, 16, 17, 17, 18, 15, 6, 19, 
    20, 18, 20, 20, 21, 22, 21, 23, 18, 21, 23, 22, 16, 22, 24, 
    24, 25, 19, 26, 19, 26, 26, 27, 24, 27, 23, 25, 27, 28, 29, 
    25, 29, 28, 28, 29) 

dat<-data.frame(ORID=ORIDs,GRP=GRPs) 

uniq.orid<-unique(dat$ORID) 

for(i in uniq.orid){ 
    tgrp<-unique(dat[dat$ORID==i,"GRP"]) 
    if(length(tgrp)>1){ 
     dat[dat$GRP %in% tgrp,"GRP"]=tgrp[1] 
    } 
} 

write.table(dat,"D:/StreamConn/smallnetwork/simple.groups.csv",row.names=F,sep=",") 

Answer 1

팬더 스 베로의 제안에 감사드립니다. 나는 그 패키지로해야 할 일을 생각했다. 아래 파이썬 코드 :

import pandas as pd 

ORIDs=[2, 7, 8, 9, 9, 10, 11, 11, 12, 13, 14, 15, 16, 18, 19, 21, 23, 
    23, 25, 26, 27, 28, 29, 30, 32, 33, 34, 34, 35, 35, 36, 37, 38, 
     39, 40, 40, 41, 41, 42, 42, 43, 43, 44, 45, 45, 46, 46, 47, 47, 
    48, 49, 50, 51, 52, 52, 53, 53, 54, 55, 57, 58, 59, 60, 61, 63, 
    64, 65, 66, 66, 67, 67, 68, 68, 69, 69, 70, 71, 73, 74, 74, 75, 
    76, 76, 77, 78, 79, 80] 

GRPs=[1, 2, 1, 3, 1, 4, 4, 5, 3, 5, 6, 4, 5, 7, 8, 3, 8, 7, 9, 8, 
    10, 10, 9, 10, 11, 11, 11, 12, 7, 13, 9, 13, 14, 14, 14, 15, 
    12, 2, 15, 12, 13, 16, 17, 2, 6, 16, 17, 17, 18, 15, 6, 19, 
    20, 18, 20, 20, 21, 22, 21, 23, 18, 21, 23, 22, 16, 22, 24, 
    24, 25, 19, 26, 19, 26, 26, 27, 24, 27, 23, 25, 27, 28, 29, 
    25, 29, 28, 28, 29] 

uniq_orid = list(set(ORIDs)) 

tab=pd.DataFrame({'ORID':ORIDs,'GRP':GRPs}) 

for i in uniq_orid: 
    tgrp = list(tab[(tab['ORID']==i)]['GRP']) 
    if(len(tgrp)>1): 
     tab['GRP'][tab['GRP'].isin(tgrp)]=tgrp[0]