このプログラムを動作させることができません。
'''
Tasks are as follows:
1. The code to clean up the raw data and to use this information in the graphics package (R Project)
2. A graph of the month of birth and the number of the Omphaloceles and the number of children with Gastroschisis. (The counts in the file may be given as separate values. Use the sum of these two conditions in your graph.)
3. A graph of the Educational level of the mother versus the birth weight of the infant
4. A graph of the age of the mother and the trimester (not the month) of the start of prenatal care
'''
import re
nat=open('D:\Documents\Project\Nat2010us\VS2010NATL.DETAILUS.PUB', mode='rt')
#lists
Revision=[]
MonthofBirth=[]
MaternalAge=[]
MaternalEducation=[]
MonthofStartofPrenatalCare=[]
BirthWeight=[]
CongenitalAnomalies=[]
OmphaloceleGastroschisis=[]
#encoded lists
enrevision=[]
enmonthofbirth=[]
enmaternalage=[]
enmaternaleducation=[]
enmonthofstartofprenatalcare=[]
enbirthweight=[]
encongenitalanomalies=[]
enomphalocelegastroschisis=[]
#selecting data, S is Unrevised data and A Revised. For Month of Start of Prenatal Care I chose the two columns (246 and 258) that were both found in Unrevised and Revised sets.
for x in nat:
Revision.append(x[6])
MonthofBirth.append(x[18:20])
MaternalAge.append(x[88:90])
if x[6]=="S": MonthofStartofPrenatalCare.append(x[246])
if x[6]=="A": MonthofStartofPrenatalCare.append(x[258])
BirthWeight.append(x[470:472])
CongenitalAnomalies.append(x[512])
OmphaloceleGastroschisis.append(x[760])
if x[6]=="S": MaternalEducation.append(x[155:157])
if x[6]=="A": MaternalEducation.append(x[154])
nat.close()
#encoding the data, using 'en' as noting encoded lists
for x in Revision:
if x=="S": enrevision.append("U")
if x=="A": enrevision.append("R")
for x in MonthofBirth:
if x=="01": enmonthofbirth.append("January")
if x=="02": enmonthofbirth.append("February")
if x=="03": enmonthofbirth.append("March")
if x=="04": enmonthofbirth.append("April")
if x=="05": enmonthofbirth.append("May")
if x=="06": enmonthofbirth.append("June")
if x=="07": enmonthofbirth.append("July")
if x=="08": enmonthofbirth.append("August")
if x=="09": enmonthofbirth.append("September")
if x=="10": enmonthofbirth.append("October")
if x=="11": enmonthofbirth.append("November")
if x=="12": enmonthofbirth.append("December")
for x in MaternalAge:
if x=="12": enmaternalage.append("10-12")
if x=="13": enmaternalage.append("13")
if x=="14": enmaternalage.append("14")
if x=="15": enmaternalage.append("15")
if x=="16": enmaternalage.append("16")
if x=="17": enmaternalage.append("17")
if x=="18": enmaternalage.append("18")
if x=="19": enmaternalage.append("19")
if x=="20": enmaternalage.append("20")
if x=="21": enmaternalage.append("21")
if x=="22": enmaternalage.append("22")
if x=="23": enmaternalage.append("23")
if x=="24": enmaternalage.append("24")
if x=="25": enmaternalage.append("25")
if x=="26": enmaternalage.append("26")
if x=="27": enmaternalage.append("27")
if x=="28": enmaternalage.append("28")
if x=="29": enmaternalage.append("29")
if x=="30": enmaternalage.append("30")
if x=="31": enmaternalage.append("31")
if x=="32": enmaternalage.append("32")
if x=="33": enmaternalage.append("33")
if x=="34": enmaternalage.append("34")
if x=="35": enmaternalage.append("35")
if x=="36": enmaternalage.append("36")
if x=="37": enmaternalage.append("37")
if x=="38": enmaternalage.append("38")
if x=="39": enmaternalage.append("39")
if x=="40": enmaternalage.append("40")
if x=="41": enmaternalage.append("41")
if x=="42": enmaternalage.append("42")
if x=="43": enmaternalage.append("43")
if x=="44": enmaternalage.append("44")
if x=="45": enmaternalage.append("45")
if x=="46": enmaternalage.append("46")
if x=="47": enmaternalage.append("47")
if x=="48": enmaternalage.append("48")
if x=="49": enmaternalage.append("49")
if x=="50": enmaternalage.append("50-54")
for x in MonthofStartofPrenatalCare:
if x=="1": enmonthofstartofprenatalcare.append("1st Trimester")
if x=="2": enmonthofstartofprenatalcare.append("2nd Trimester")
if x=="3": enmonthofstartofprenatalcare.append("3rd Trimester")
if x=="4": enmonthofstartofprenatalcare.append("No Prenatal Care")
if x=="5": enmonthofstartofprenatalcare.append("unknown or not stated")
if x==" ": enmonthofstartofprenatalcare.append("not on certificate")
for x in BirthWeight:
if x=="01": enbirthweight.append("499 or less")
if x=="02": enbirthweight.append("500-999")
if x=="03": enbirthweight.append("1000-1499")
if x=="04": enbirthweight.append("1500-1999")
if x=="05": enbirthweight.append("2000-2499")
if x=="06": enbirthweight.append("2500-2999")
if x=="07": enbirthweight.append("3000-3499")
if x=="08": enbirthweight.append("3500-3999")
if x=="09": enbirthweight.append("4000-4499")
if x=="10": enbirthweight.append("4500-4999")
if x=="11": enbirthweight.append("5000-8165")
if x=="12": enbirthweight.append("not stated")
for x in CongenitalAnomalies:
if x=="1": encongenitalanomalies.append("anomaly reported")
if x=="2": encongenitalanomalies.append("anomaly not reported")
if x=="9": encongenitalanomalies.append("anomaly not classified")
if x==" ": encongenitalanomalies.append("not on certificate")
for x in OmphaloceleGastroschisis:
if x=="0": enomphalocelegastroschisis.append("not reporting")
if x=="1": enomphalocelegastroschisis.append("reporting")
#encoding the two different education codes to be coded the same
for x in range(0, len (MaternalEducation)):
if Revision[x]=="A":
if MaternalEducation[x]=="1": enmaternaleducation.append("8th grade or less")
if MaternalEducation[x]=="2": enmaternaleducation.append("9th through 12th grade no diploma")
if MaternalEducation[x]=="3": enmaternaleducation.append("High school graduate or GED completed")
if MaternalEducation[x]=="4": enmaternaleducation.append("Some college credit but no degree")
if MaternalEducation[x]=="5" or MaternalEducation[x]=="6": enmaternaleducation.append("Associate and/or Bachelor")
if MaternalEducation[x]=="7" or MaternalEducation[x]=="8": enmaternaleducation.append("Master's or Doctorate")
if MaternalEducation[x]=="9": enmaternaleducation.append("not stated")
if MaternalEducation[x]==" ": enmaternaleducation.append("blank")
if Revision[x]=="S":
if MaternalEducation[x]=="00" or MaternalEducation[x]=="01-08": enmaternaleducation.append("8th grade or less")
if MaternalEducation[x]=="09" or MaternalEducation[x]=="10" or MaternalEducation[x]=="11": enmaternaleducation.append("9th through 12th grade no diploma")
if MaternalEducation[x]=="12": enmaternaleducation.append("High school graduate or GED completed")
if MaternalEducation[x]=="13": enmaternaleducation.append("Some college credit but no degree")
if MaternalEducation[x]=="14" or MaternalEducation[x]=="15" or MaternalEducation[x]=="16": enmaternaleducation.append("Associate and/or Bachelor")
if MaternalEducation[x]=="17": enmaternaleducation.append("Master's or Doctorate")
if MaternalEducation[x]=="99": enmaternaleducation.append("not stated")
if MaternalEducation[x]==" ": enmaternaleducation.append("blank")
#open new file for output of data
'''
enmonthofbirth=[]
enmaternalage=[]
enmaternaleducation=[]
enmonthofstartofprenatalcare=[]
enbirthweight=[]
encongenitalanomalies=[]
enomphalocelegastroschisis=[]
'''
#write header and then, for each line, replace values in the Natality file with the encoded values from encoded lists (line by line) in the outputforR file. Matching up values based on commonality they all share - length.
#\n to end line to break to new line
f=open('D:\Documents\Project\outputforR.csv', mode='w')
f.write('month of birth'+','+'maternal age'+','+'maternal education'+','+'month of start of prenatal care'+','+'birth weight'+','+'congenital anomalies'+','+'omphalocele/gastroschisis')
for x in range(0,len(enmonthofbirth)):
f.write(enmonthofbirth[x]+','+enmaternalage[x]+','+enmaternaleducation[x]+','+enmonthofstartofprenatalcare[x]+','+enbirthweight[x]+','+encongenitalanomalies[x]+','+enomphalocelegastroschisis[x]) \n
f.close()
170 行目を修正できないようです。さまざまな方法で \n をいじって、このファイルを書き込もうとして、データを R に書き込む作業に移ることができます。結構ですが、Python で各リストの適切なヘッダーの下に値を書き込むことができません。次の行に移動するには \n が必要だと言われましたが、\ だけでは許可されず、機能しません。\n を削除しても機能しません。\そして、このリンクにあるものを正確に私に残すものは何もありません。下。
以下は、一度書いたExcelファイルの画像へのリンクです。
