Python:循环作用于多个文件并编写新文件

Question

我有以下代码获取文件“University2.csv”，并写入新的 csv 文件“Hours.csv”-“Hours -Stacked.csv”和“Days.csv”。

现在我希望代码能够循环并在多个文件(University3.csv、University4.csv 等)上运行，并为每个文件生成“Hours3.csv”、“Hours - Stacked3.csv”、“Days3” .csv", "Hours4.csv"等

代码如下:

    import pandas as pd
    import numpy as np
    import matplotlib.pyplot as plt


#Importing the csv file into df
df = pd.read_csv('university2.csv', sep=";", skiprows=1)

#Changing datetime
df['YYYY-MO-DD HH-MI-SS_SSS'] = pd.to_datetime(df['YYYY-MO-DD HH-MI-SS_SSS'], 
                                               format='%Y-%m-%d %H:%M:%S:%f')

#Set index from column
df = df.set_index('YYYY-MO-DD HH-MI-SS_SSS')

#Add Magnetic Magnitude Column
df['magnetic_mag'] = np.sqrt(df['MAGNETIC FIELD X (μT)']**2 + df['MAGNETIC FIELD Y (μT)']**2 + df['MAGNETIC FIELD Z (μT)']**2)

#Copy interesting values
df2 = df[[ 'ATMOSPHERIC PRESSURE (hPa)',
          'TEMPERATURE (C)', 'magnetic_mag']].copy()

#Hourly Average and Standard Deviation for interesting values 
df3 = df2.resample('H').agg(['mean','std'])
df3.columns = [' '.join(col) for col in df3.columns]   

#Daily Average and Standard Deviation for interesting values 
df4 = df2.resample('D').agg(['mean','std'])
df4.columns = [' '.join(col) for col in df4.columns] 

#Write to new csv
df3.to_csv('Hours.csv', index=True)  
df4.to_csv('Days.csv', index=True)    

#New csv with stacked hour averages
df5 = pd.read_csv('Hours.csv')
df5['YYYY-MO-DD HH-MI-SS_SSS'] = pd.to_datetime(df5['YYYY-MO-DD HH-MI-SS_SSS'])  
hour = pd.to_timedelta(df5['YYYY-MO-DD HH-MI-SS_SSS'].dt.hour, unit='H')
df6 = df5.groupby(hour).mean()
df6.to_csv('Hours - stacked.csv', index=True)

有人能帮忙吗？

谢谢!

Answer 1

我认为您可以对列表 files 使用循环。我从文件名中提取数字到 i，然后将它们添加到输出名称。

此外，您可以通过reset_index 从df3 获取df5 , 不再需要 read_csv。

import pandas as pd

files = ['university1.csv','university2.csv','university3.csv']

for f in files:
    i = f[-5]
    print i

    #Importing the csv file into df
    df = pd.read_csv(f, sep=";", skiprows=1)

    #Changing datetime
    df['YYYY-MO-DD HH-MI-SS_SSS'] = pd.to_datetime(df['YYYY-MO-DD HH-MI-SS_SSS'], 
                                                   format='%Y-%m-%d %H:%M:%S:%f')

    #Set index from column
    df = df.set_index('YYYY-MO-DD HH-MI-SS_SSS')

    #Add Magnetic Magnitude Column
    df['magnetic_mag'] = np.sqrt(df['MAGNETIC FIELD X (μT)']**2 + df['MAGNETIC FIELD Y (μT)']**2 + df['MAGNETIC FIELD Z (μT)']**2)

    #Copy interesting values
    df2 = df[[ 'ATMOSPHERIC PRESSURE (hPa)',
              'TEMPERATURE (C)', 'magnetic_mag']].copy()

    #Hourly Average and Standard Deviation for interesting values 
    df3 = df2.resample('H').agg(['mean','std'])
    df3.columns = [' '.join(col) for col in df3.columns]   

    #Daily Average and Standard Deviation for interesting values 
    df4 = df2.resample('D').agg(['mean','std'])
    df4.columns = [' '.join(col) for col in df4.columns] 

    #Write to new csv
    df3.to_csv('Hours'+ i + '.csv')  
    df4.to_csv('Day'+ i + 's.csv')    

    #New csv with stacked hour averages
    #df5 = pd.read_csv('Hours.csv')
    #df5['YYYY-MO-DD HH-MI-SS_SSS'] = pd.to_datetime(df5['YYYY-MO-DD HH-MI-SS_SSS'])  
    df5 = df3.reset_index()
    hour = pd.to_timedelta(df5['YYYY-MO-DD HH-MI-SS_SSS'].dt.hour, unit='H')
    df6 = df5.groupby(hour).mean()
    df6.to_csv('Hours - stacked'+ i + '.csv')

编辑:

更一般的是Yaron solution ，我使用它并仅将 2,3,4 更改为 range() :

import pandas as pd

#files = ['university1.csv','university2.csv','university3.csv']
for i in range(1,4):
    print i
    print 'university'+ str(i) + '.csv'

    #Importing the csv file into df
    df = pd.read_csv('university'+ str(i) + '.csv', sep=";", skiprows=1)

    #Changing datetime
    df['YYYY-MO-DD HH-MI-SS_SSS'] = pd.to_datetime(df['YYYY-MO-DD HH-MI-SS_SSS'], 
                                                   format='%Y-%m-%d %H:%M:%S:%f')

    #Set index from column
    df = df.set_index('YYYY-MO-DD HH-MI-SS_SSS')

    #Add Magnetic Magnitude Column
    df['magnetic_mag'] = np.sqrt(df['MAGNETIC FIELD X (μT)']**2 + df['MAGNETIC FIELD Y (μT)']**2 + df['MAGNETIC FIELD Z (μT)']**2)

    #Copy interesting values
    df2 = df[[ 'ATMOSPHERIC PRESSURE (hPa)',
              'TEMPERATURE (C)', 'magnetic_mag']].copy()

    #Hourly Average and Standard Deviation for interesting values 
    df3 = df2.resample('H').agg(['mean','std'])
    df3.columns = [' '.join(col) for col in df3.columns]   

    #Daily Average and Standard Deviation for interesting values 
    df4 = df2.resample('D').agg(['mean','std'])
    df4.columns = [' '.join(col) for col in df4.columns] 

    #Write to new csv
    df3.to_csv('Hours'+ str(i) + '.csv')  
    df4.to_csv('Day'+ str(i) + 's.csv')    

    #New df3 with stacked hour averages
    df5 = df3.reset_index()
    hour = pd.to_timedelta(df5['YYYY-MO-DD HH-MI-SS_SSS'].dt.hour, unit='H')
    df6 = df5.groupby(hour).mean()
    df6.to_csv('Hours - stacked'+ str(i) + '.csv')