In [1]:
import pandas as pd
import numpy as np
df = pd.read_excel("Data/use_all.xlsx")
df.head()
Out[1]:
In [7]:
#df.loc[0].T
In [13]:
#df[df.MSN=="HYTCP"]
In [2]:
df[(df.MSN=="HYTCP")&(df.State=="AK")]
Out[2]:
In [3]:
alist=["HYTCP","WYTCP","SOEGP","NUETP"]
dftemp=df[df['MSN'].isin(alist)&(df.State=="AK")]
del dftemp['Data_Status']
#del dftemp['State']
del dftemp['MSN']
dftemp=dftemp.T
#print(dftemp)
In [35]:
#df.drop(0)
#statelist[0]=pd.DataFrame(index=range(0,4),columns=["HYTCP","WYTCP","SOEGP","NUETP"])
#print(statelist[0])
#datlist=[range(0,51)]
#datlist[0]==1
#datlist
In [4]:
statelist=["AK","AL","AR","AZ","CA","CO","CT","DC","DE","FL","GA","HI","IA","ID","IL","IN","KS","KY","LA","MA","MD","ME","MI","MN","MO","MS","MT","NC","ND","NE","NH","NJ","NM","NV","NY","OH","OK","OR","PA","RI","SC","SD","TN","TX","US","UT","VA","VT","WA","WI","WV","WY"]
len(statelist)
statelist[51]
Out[4]:
In [5]:
alist=["HYTCP","WYTCP","SOEGP","NUETP"]
dftemp1=df[df['MSN'].isin(alist)&(df.State==statelist[0])]
del dftemp1['Data_Status']
del dftemp1['State']
del dftemp1['MSN']
dftemp1=dftemp1.T
print(dftemp1)
In [7]:
import numpy as np
datalist=[]
for i in range(0,52):
alist=["Year","HYTCP","WYTCP","SOEGP","NUETP"]
dftemp=df[df['MSN'].isin(alist)&(df.State==statelist[i])]
del dftemp['Data_Status']
del dftemp['State']
del dftemp['MSN']
dftemp=dftemp.T
#print(dftemp)
dftemp.columns=['HYTCP','WYTCP', 'SOEGP', 'NUETP']
#print(dftemp)
datalist.append(dftemp)
#datalist.append(pd.DataFrame(dftemp,index=range(1960,2015),columns=["HYTCP","WYTCP","SOEGP","NUETP"]))
datalist[i].to_csv('Data/Data_States/%s.csv'% (statelist[i]), encoding='utf-8', index=True)
#print(datalist)
In [38]:
#dataframe可以使用to_csv方法方便地导出到csv文件中，如果数据中含有中文，一般encoding指定为”utf-8″,否则导出时程序会因为不能识别相应的字符串而抛出异常，index指定为False表示不用导出dataframe的index数据。
#datalist[0].to_csv('%s.csv'% (statelist[0]), encoding='utf-8', index=True)
In [ ]: