how to ingrate my code to read txt file in dirctory(folder)and subdirectory? PLZ help

[alivip]

how to ingrate my code to read text in in parent folder contain sub folders and files for example folder name is cars and sub file is Toyota,Honda and BMW and Toyota contain file name Camry and file name corolla, file name Honda contain folder accord and BMW contain file name X5

Is there way to enter name of parent folder(cars) and search in all sub folder(Toyota,H onda and BMW) and files ?

please help ASAP

code is find most frequent word in one text file and print them in decrease order
and I wont it to find most frequant word in all text files (together) under specific folder

# count words in a text and show the first ten items
# by decreasing frequency
 
# sample text for testing

import sys
import string
import re
file = open ("arb.txt", "r")
text = file.read ( )
file.close ( )
 
word_freq = {}
 
word_list = text.split()
 
for word in word_list:
    # word all lower case
    word = word.lower()
    # strip any trailing period or comma
    word = word.rstrip('.,/"-_;\[]()')
    # build the dictionary
    count = word_freq.get(word, 0)
    word_freq[word] = count + 1
 
# create a list of (freq, word) tuples
freq_list = [(freq, word) for word, freq in word_freq.items()]
 
# sort the list by the first element in each tuple (default)
freq_list.sort(reverse=True)
 
for n, tup in enumerate(freq_list):
    # print the first ten items
    if n < 10:
        freq, word = tup
        print freq, word

[jlm699]

Is there way to enter name of parent folder(cars) and search in all sub folder(Toyota,H onda and BMW) and files ?

I'm sorry, but it's very difficult to understand what it is that you are asking. I can provide you with some direction however...

Perhaps something you're looking for is os.walk. Here is a sample:
[code=python]
>>> for root, dirs, files in os.walk(os.getc wd()):
... print 'Looking into %s' % root.split('\\' )[-1]
... print 'Found %d dirs and %d files' % (len(dirs), len(files))
... for idx, dir in enumerate(dirs) :
... print 'Directory #%d: %s' % (idx + 1, dir)
... for idx, file in enumerate(files ):
... print 'File #%d: %s' % (idx + 1, file)
...
Looking into pythtests
Found 2 dirs and 16 files
Directory #1: graphics
Directory #2: Question
File #1: bckmch.py
File #2: cmdtest.py
File #3: cobyla.py
File #4: elseerr.py
File #5: fileio.py
File #6: ldict.py
File #7: lid
File #8: mainbody
File #9: matrixprint.py
File #10: matrx_print.py
File #11: test.py
File #12: test2.py
File #13: topload
File #14: totalbottle
File #15: trivgame.py
File #16: wxtemplate.py
Looking into graphics
Found 0 dirs and 8 files
File #1: Buttons.py
File #2: dice_class.py
File #3: ghostchars.py
File #4: graphics.py
File #5: graphics.pyc
File #6: graphics22.py
File #7: graphics22.pyc
File #8: hw6-template.py
Looking into Question
Found 0 dirs and 0 files
>>> [/code]
Hope that helps a little bit

[alivip]

I mean example of parent dirctory (folder) is cars and example of subdirectory (folder) is (BMW,Honda,Toyo ta) so I wont to trace directory and all subdirctory
to find most frequant word in all text files (together) under specific folder


and I did not understand what your code mean

[alivip]

thanx M.r jlm699 your reply was helpfull

but it does not match what I wont exactly

modifyig code is

# count words in a text and show the first ten items
# by decreasing frequency
 
# sample text for testing

import sys
import string
import re
import os.path
for root, dirs, files in os.walk(os.getcwd()):
  print 'Looking into %s' % root.split('\\')[-1]
  print 'Found %d dirs and %d files' % (len(dirs), len(files))
  for idx, dir in enumerate(dirs):
    print 'Directory #%d: %s' % (idx + 1, dir)
    for idx, file in enumerate(files):
      print 'File #%d: %s' % (idx + 1, file)
      ff = open (file, "r")
      text = ff.read ( )
      ff.close ( )
     
      word_freq = {}
     
      word_list = text.split()
     
      for word in word_list:
        # word all lower case
         word = word.lower()
        # strip any trailing period or comma
         word = word.rstrip('.,/"-_;\[]()')
        # build the dictionary
         count = word_freq.get(word, 0)
         word_freq[word] = count + 1
     
    # create a list of (freq, word) tuples
      freq_list = [(freq, word) for word, freq in word_freq.items()]
     
    # sort the list by the first element in each tuple (default)
      freq_list.sort(reverse=True)
     
      for n, tup in enumerate(freq_list):
        # print the first ten items
         if n < 10:
            freq, word = tup
            print freq, word

the output like

File #12: listtoDict.py
14 with
6 python
6 for
File #13: parseAddresses
3 python
1 with
1 will

and I need to find frequacy of word in all text file not seperat for examle the previos output shud be like

15 with
9 python
6 for
1 will

so add frequancy of word in (File #12: listtoDict.py) with (File #13: parseAddresses) and print thim in one list

[jlm699]

and I need to find frequacy of word in all text file

Just move your word_freq dictionary declaration to before you begin the for loop, and then move the sorting/printing of that structure to after the for loop. And you'll achieve this.

[jlm699]

Here's the modifications that I suggest above and the resulting output.[CODE=python]
import sys, os

word_freq = {}

for root, dirs, files in os.walk(os.getc wd()):
print 'Looking into %s' % root.split('\\' )[-1]
print 'Found %d dirs and %d files' % (len(dirs), len(files))

for idx, file in enumerate(files ):
ff = open (os.path.join(r oot, file), "r")
text = ff.read ( )
ff.close ( )

word_list = text.strip().sp lit()

for word in word_list:
word = word.lower().rs trip('.,/"-_;\\[]()')
if word.isalpha():
# build the dictionary
count = word_freq.get(w ord, 0)
word_freq[word] = count + 1

# create a list of (freq, word) tuples
freq_list = [(freq, word) for word, freq in word_freq.items ()]

# sort the list by the first element in each tuple (default)
freq_list.sort( reverse=True)

for n, tup in enumerate(freq_ list):
# print the first ten items
if n < 10:
freq, word = tup
print freq, word[/CODE]
Output:
[CODE=output]
Microsoft Windows XP [Version 5.1.2600]
(C) Copyright 1985-2001 Microsoft Corp.

C:\Documents and Settings\Admini strator>cd Desktop\pythtes ts

C:\Documents and Settings\Admini strator\Desktop \pythtests>pyth on walkncount.py
Looking into pythtests
Found 2 dirs and 17 files
Looking into graphics
Found 0 dirs and 8 files
Looking into Question
Found 0 dirs and 0 files
46 the
17 and
14 of
14 a
12 is
10 to
10 in
8 you
8 this
8 that

C:\Documents and Settings\Admini strator\Desktop \pythtests>[/CODE]

[alivip]

thanx alot
but it is actualy read all file but print frequancy of only one of them
not print frequancy of word in all file which I wont

[jlm699]

read all file but print frequancy of only one of them

Ok... I'm not sure exactly what you mean by that but I think that you're trying to say you only want to display the frequency of words in the file with the highest frequencies?

[CODE=python]
import sys, os

highest_freq = [(0,'Blank')]
high_file_name = ''

for root, dirs, files in os.walk(os.getc wd()):
# print 'Looking into %s' % root.split('\\' )[-1]
# print 'Found %d dirs and %d files' % (len(dirs), len(files))

for idx, file in enumerate(files ):
# print 'File #%d: %s' % (idx + 1, file)
ff = open (os.path.join(r oot, file), "r")
text = ff.read ( )
ff.close ( )

word_freq = {}
word_list = text.strip().sp lit()

for word in word_list:
word = word.lower().rs trip('.,/"-_;\\[]()')
if word.isalpha():
# build the dictionary
word_freq[word] = word_freq.get(w ord, 0) + 1

# create a list of (freq, word) tuples
freq_list = [(freq, word) for word, freq in word_freq.items ()]

# sort the list by the first element in each tuple (default)
freq_list.sort( reverse=True)
if freq_list:
if freq_list[0][0] > highest_freq[0][0]:
highest_freq = freq_list
high_file_name = file

print 'Highest frequency file: %s' % high_file_name
for n, tup in enumerate(highe st_freq):
if n < 10:
freq, word = tup
print freq, word
raw_input('\nHi t enter to exit')
[/code]
Output:

Highest frequency file: graphics.py
93 def
44 return
36 the
31 in
29 of
26 for
25 if
23 to
19 class
19 a

Hit enter to exit

This is a crude example so I apologize; however I don't understand what you're trying to do or why. So working with what you've given this is the most I can make of your question.

[alivip]

realy I aprechat your trying to help
but unfortionatly that is no wat I ment

I meat is read all files in directory compin all words in all files and put them in new file then find freqancy of each word in taht new file

[jlm699]

realy I aprechat your trying to help
but unfortionatly that is no wat I ment

I meat is read all files in directory compin all words in all files and put them in new file then find freqancy of each word in taht new file

So basically, you're saying you want to combine the contents of all the files into a new file, and then find the frequency of the words in that file?

Well to do that w/o creating a new file would be a very slight change from a previous post:
[code=python]
import sys, os

word_freq = {}

for root, dirs, files in os.walk(os.getc wd()):
print 'Looking into %s' % root.split('\\' )[-1]
print 'Found %d dirs and %d files' % (len(dirs), len(files))

for idx, file in enumerate(files ):
ff = open (os.path.join(r oot, file), "r")
text = ff.read ( )
ff.close ( )

word_list = text.strip().sp lit()

for word in word_list:
word = word.lower().rs trip('.,/"-_;\\[]()')
if word.isalpha():
# build the dictionary
count = word_freq.get(w ord, 0)
word_freq[word] = count + 1

# create a list of (freq, word) tuples
freq_list = [(freq, word) for word, freq in word_freq.items ()]

# sort the list by the first element in each tuple (default)
freq_list.sort( reverse=True)

for n, tup in enumerate(freq_ list):
# print the first ten items
if n < 10:
print "%s times: %s" % tup
raw_input('\nHi t enter to exit')
[/code]

[alivip]

thank you very much M.r jlm699 it is work fine now

I integrat program to be GUI using Tkinter and insted search in curent direction I try to be from browser
as you can see

# a look at the Tkinter Text widget

# use ctrl+c to copy, ctrl+x to cut selected text,

# ctrl+v to paste, and ctrl+/ to select all
  # count words in a text and show the first ten items
 # by decreasing frequency

import Tkinter as tk
import os, glob
import sys
import string
import re
import tkFileDialog      
def most_frequant_word():    
 a= tkFileDialog.askdirectory()
 browser= os.listdir(a)


 for root, dirs, files in os.walk(browser):
    print 'Looking into %s' % root.split('\\')[-1]
    print 'Found %d dirs and %d files' % (len(dirs), len(files))
 
    for idx, file in enumerate(files):
     ff = open (os.path.join(root, file), "r")
     text = ff.read ( )
     ff.close ( )
     
     word_list = text.strip().split()
     
     for word in word_list:
      word = word.lower().rstrip('.,/"-_;\\[]()')

      if word.isalpha():
                # build the dictionary
       count = word_freq.get(word, 0)
       word_freq[word] = count + 1
 
       # create a list of (freq, word) tuples
       freq_list = [(freq, word) for word, freq in word_freq.items()]
     
       # sort the list by the first element in each tuple (default)
       freq_list.sort(reverse=True)
    
     for n, tup in enumerate(freq_list):
    # print the first ten items
      if n < 15:
        print "%s times: %s" % tup
        text1.insert(tk.INSERT, freq)
        text1.insert(tk.INSERT, word)
        text1.insert(tk.INSERT, "\n")
        
 raw_input('\nHit enter to exit')
 
root = tk.Tk(className = " most_frequant_word")
# text entry field, width=width chars, height=lines text
v1 = tk.StringVar()
text1 = tk.Text(root, width=50, height=20, bg='green')
text1.pack()
# function listed in command will be executed on button click
button1 = tk.Button(root, text='result', command=most_frequant_word)
button1.pack(pady=5)
text1.focus()
root.mainloop()

but give me this error

Exception in Tkinter callback
Traceback (most recent call last):
File "C:\Python25\li b\lib-tk\Tkinter.py", line 1403, in __call__
return self.func(*args )
File "C:\Documen ts and Settings\Admini strator\Desktop \ICS482\hw3\pro gramAli.py", line 21, in most_frequant_w ord
for root, dirs, files in os.walk(browser ):
File "C:\Python25\li b\os.py", line 285, in walk
names = listdir(top)
TypeError: coercing to Unicode: need string or buffer, list found

could you please help me to solve this problem

[alivip]

I fix the error now
but
it will not insert to the textbox
it just print then hanging

# a look at the Tkinter Text widget

# use ctrl+c to copy, ctrl+x to cut selected text,

# ctrl+v to paste, and ctrl+/ to select all
  # count words in a text and show the first ten items
 # by decreasing frequency

import Tkinter as tk
import os, glob
import sys
import string
import re
import tkFileDialog      
def most_frequant_word():    
 browser= tkFileDialog.askdirectory()
 #browser= os.listdir(a)


 for root, dirs, files in os.walk(browser):
    print 'Looking into %s' % root.split('\\')[-1]
    print 'Found %d dirs and %d files' % (len(dirs), len(files))
    #text1.insert(tk.INSERT,'Looking into %s' % root.split('\\')[-1])
    #text1.insert(tk.INSERT, 'Found %d dirs and %d files' % (len(dirs), len(files)))
    for idx, file in enumerate(files):
     print 'File #%d: %s' % (idx + 1, file)
      #text1.insert(tk.INSERT, 'File #%d: %s' % (idx + 1, file))
     ff = open (os.path.join(root, file), "r")
     text = ff.read ( )
     ff.close ( )
     word_freq = {}
     
     word_list = text.strip().split()
     
     for word in word_list:
      word = word.lower().rstrip('.,/"-_;\\[]()')

      if word.isalpha():
                # build the dictionary
       count = word_freq.get(word, 0)
       word_freq[word] = count + 1
 
       # create a list of (freq, word) tuples
       freq_list = [(freq, word) for word, freq in word_freq.items()]
     
       # sort the list by the first element in each tuple (default)
       freq_list.sort(reverse=True)
    
     for n, tup in enumerate(freq_list):
    # print the first ten items
      if n < 50:
        print "%s times: %s" % tup
        text1.insert(tk.INSERT, freq)
        text1.insert(tk.INSERT, word)
        text1.insert(tk.INSERT, "\n")
        
 raw_input('\nHit enter to exit')
 
root = tk.Tk(className = " most_frequant_word")
# text entry field, width=width chars, height=lines text
v1 = tk.StringVar()
text1 = tk.Text(root, width=50, height=20, bg='green')
text1.pack()
# function listed in command will be executed on button click
button1 = tk.Button(root, text='Brows', command=most_frequant_word)
button1.pack(pady=5)
text1.focus()
root.mainloop()

code try to insert

 print "%s times: %s" % tup
        text1.insert(tk.INSERT, freq)
        text1.insert(tk.INSERT, word)
        text1.insert(tk.INSERT, "\n")

when I wont to insert fil name and directory to the textbox it will hang also
code is comment

print 'Looking into %s' % root.split('\\')[-1]
    print 'Found %d dirs and %d files' % (len(dirs), len(files))
    #text1.insert(tk.INSERT,'Looking into %s' % root.split('\\')[-1])
    #text1.insert(tk.INSERT, 'Found %d dirs and %d files' % (len(dirs), len(files)))
    for idx, file in enumerate(files):
     print 'File #%d: %s' % (idx + 1, file)
      #text1.insert(tk.INSERT, 'File #%d: %s' % (idx + 1, file))