Question

Python, I need help with glob. I have a lot of data text files and want to order them. However glob makes it in the wrong order.

Have:

data00120.txt

data00022.txt

data00045.txt

etc

Want:

data00000.txt

data00001.txt

data00002.txt

etc

Code piece:

def last_9chars(x):

    return(x[-9:])

files = sorted(glob.glob('data*.txt'),key = last_9chars)

whole code:

import numpy as np

import matplotlib.pyplot as plt

import glob

import sys

import re

from prettytable import PrettyTable

def last_9chars(x):

    return(x[-9:])

files = sorted(glob.glob('data*.txt'),key = last_9chars)

x = PrettyTable()

x.field_names = ['DataNum', 'Mean', 'Standard Deviation']

filecount = 0

n = 0

maxfilecount = int(sys.argv[1]) if len(sys.argv) > 1 else len(files)

for f in files:

    filecount +=1

    my_data = np.loadtxt(f, delimiter='\t')

    mean = np.mean(my_data[1])

    std = np.std(my_data[1])

    

    print(f"Here {n}")

    x.add_row([f"{f}", mean, std])

    n +=1

    if filecount >= maxfilecount:

        break

print(x)

data = x.get_string()

with open('Data.csv', 'w') as f:

    f.write(data)

Answer 1

i am using python 3.7 and code for the above is : -

 import numpy as np import matplotlib.pyplot as plt import glob import sys import re from prettytable import PrettyTable # function to extract last 9 characters of the filename def last_9chars(x): return(x[-9:]) # files stores the filenames grabbed by glob module matching to data* in sorted order # glob returns a list of names of files files = sorted(glob.glob('data*.txt'),key = last_9chars) # pretty tables is used for generating tables in python x = PrettyTable() x.field_names = ['DataNum', 'Mean', 'Standard Deviation'] filecount = 0 n = 0 maxfilecount = int(sys.argv[1]) if len(sys.argv) > 1 else len(files) # iterating over list of file names for f in files: filecount +=1 # m_data stores the contents of the text files my_data = np.loadtxt(f, delimiter='\t') # numpy method to find the mean of the data mean = np.mean(my_data[1]) # numpy method to find the standard deviation of data std = np.std(my_data[1]) # add new low in table x.add_row([f"{f}", mean, std]) n +=1 if filecount >= maxfilecount: break print(x) data = x.get_string() # create a new file named Data.csv and write into that with open('Data.csv', 'w') as f: f.write(data)

input files :-

output is :-

if my answer helped then please upvote and comment for any queries

thankyou !