Develop Reference

Count of Specific words in Multiple text files

I have a multiple text files and I need to find and cound specific words in those files and write them in a csv file. Column A contains the txt file names and in the header the words and for each file name its count. With this code I am getting all the words and need to filter out exact words
for example the output should be like the image file I uploaded
header = ['Abuse', 'Accommodating', 'Accommodation', 'Accountability']
import csv
folderpaths = 'C:/Users/haris/Downloads/PDF/'
counter = Counter()
filepaths = glob(os.path.join(folderpaths,'*.txt'))
for file in filepaths:
with open(file) as f:
words = re.findall(r'\w+', f.read().lower())
counter = counter + Counter(words)
print(counter)
f = open('C:/Users/haris/Downloads/PDF/firstcsv.csv', 'w')
writer = csv.writer(f)
for row in counter.items():
writer.writerow(row)
Files uploaded to google drive

Edit: As per your new request, I have added the "total_words" column. The code has been updated.
Below is a code that works. Just change the "folderpath" variable to the path of the folder with the text files, and change the "target_file" variable to where you want the output csv file to be created.
Sample csv output:
Code:
from collections import Counter
import glob
import os
import re
header = ['annual', 'investment', 'statement', 'range' , 'deposit' , 'supercalifragilisticexpialidocious']
folderpath = r'C:\Users\USERname4\Desktop\myfolder'
target_file = r'C:\Users\USERname4\Desktop\mycsv.csv'
queueWAP = []
def writeAndPrint(fileObject,toBeWAP,opCode=0):
global queueWAP
if (opCode == 0):
fileObject.write(toBeWAP)
print(toBeWAP)
if (opCode == 1):
queueWAP.append(toBeWAP)
if (opCode == 2):
for temp4 in range(len(queueWAP)):
fileObject.write(queueWAP[temp4])
print(queueWAP[temp4])
queueWAP = []
mycsvfile = open(target_file, 'w')
writeAndPrint(mycsvfile,"file_name,total_words")
for temp1 in header:
writeAndPrint(mycsvfile,","+temp1)
writeAndPrint(mycsvfile,"\n")
filepaths = glob.glob(folderpath + r"\*.txt")
for file in filepaths:
with open(file) as f:
writeAndPrint(mycsvfile,file.split("\\")[-1])
counter = Counter()
words = re.findall(r'\w+', f.read().lower())
counter = counter + Counter(words)
for temp2 in header:
temp3 = False
temp5 = 0
for myword in counter.items():
temp5 = temp5 + 1
if myword[0] == temp2:
writeAndPrint(mycsvfile,","+str(myword[1]),1)
temp3 = True
if temp3 == False:
writeAndPrint(mycsvfile,","+"0",1)
writeAndPrint(mycsvfile,","+str(temp5))
writeAndPrint(mycsvfile,"",2)
writeAndPrint(mycsvfile,"\n")
mycsvfile.close()

Using 'Counter' seems to be the right choice here, but I think you are using it wrong.
Here is a possible solution that may work for you:
words = ['Abuse', 'Accommodating', 'Accommodation', 'Accountability']
rows = []
for file in filepaths:
with open(file, 'r') as f:
words_in_file = [word for line in f for word in line.split()]
# this will count all the words in the file (not optimal)
wordcounts = Counter(words_in_file)
# interested only in specific words
counts = list(map(lambda x: wordcounts[x], words))
# insert first column (filenam)
counts.insert(0, file)
# append it to the rest of the rows
rows.append(counts)
f = open('C:/Users/haris/Downloads/PDF/firstcsv.csv', 'w')
writer = csv.writer(f)
for row in rows:
writer.writerow(row)

How to save words that occur no more than 3 times in a text? Reading and writing files

I am working on a text file right now that is called "dracula.txt", and I have to do the following in python:
Save words that occur no more than 3 times in descending order in a file called less_common_words.txt. Each word with its count should be saved on a separate line.
I would appreciate any help! I've been working on this for too long.
I have already tokenized my file and counted the words. This is my code so far:
file = open("C:/Users/17733/Downloads/dracula.txt", 'r', encoding = 'utf-8-sig')
data = file.read()
data
data_list = data.split('\n')
data_list
new_list = []
for i in data_list:
if i !='':
ans_here = i.split(' ')
new_list.extend(ans_here)
new_list
import string
import re
puncs = list(string.punctuation)
puncs.append('"')
puncs.append('[')
puncs.append('.')
puncs.append('-')
puncs.append('_')
#append each seperately
new_2 = []
for i in new_list:
for p in puncs:
if p in i:
i_new = i.replace(p, ' ')
new_2.append(i_new)
new_2
new_2 = [i.replace(' ', ' ').strip().lower() for i in new_2]
new_2

from pathlib import Path
from collections import Counter
import string
filepath = Path('test.txt')
output_filepath = Path('outfile.txt')
# print(filepath.exists())
with open(filepath) as f:
content = f.readlines()
word_list = sum((
(s.lower().strip('\n').translate(str.maketrans('', '', string.punctuation))).split(' ')
for s in content
), [])
less_common_words = sorted([
key for key, value in Counter(word_list).items() if value <= 3
],reverse=True)
with open(output_filepath, mode='wt', encoding='utf-8') as myfile:
myfile.write('\n'.join(less_common_words))

This should exactly be what you need- I fixed my previous error by flattening the entire txt into a 2d list:
book_open = open('frankenstein.txt', 'r').readlines()
beauty_book = [i.split() for i in book_open]
flatten = []
for sublist in beauty_book:
for val in sublist:
flatten.append(val)
foo = 0
for i in flatten:
list_open = open('less_common_words.txt', 'r').readlines()
beauty_list = [i.replace('\n', '') for i in list_open]
count = flatten.count(flatten[foo])
compile = str((flatten[foo], count))
if count <= 3:
if compile not in beauty_list:
file = open('less_common_words.txt', 'a+')
file.write('\n'+compile)
file.close()
foo += 1

How to delete specific words from a sentence in text file?

I have two text files. The 1st file contains English sentences and 2nd file contains a number of English words (vocabulary). I want to remove those words from the sentences in the 1st file which are not present in the vocabulary and then to save the processed text back into the 1st file.
I wrote the code from which I am able to get those sentences which contains the words that are not available in our 2nd file (vocabulary).
Here is my code:
s = open('eng.txt').readlines()
for i in s:
print(i)
for word in i.split(' '):
print(word)
if word in open("vocab30000.txt").read():
print("Word exist in vocab")
else:
#print("I:", i)
print("Word does not exist")
#search_in_file_func(i)
print("I:", i)
file1 = open("MyFile.txt","a+")
if i in file1:
print("Sentence already exist")
else:
file1.write(i)
However, I am not able to remove those words.

This should work:
with open('vocab30000.txt') as f:
vocabulary = set(word.strip() for word in f.readlines())
with open('eng.txt', 'r+') as f:
data = [line.strip().split(' ') for line in f.readlines()]
removed = [[word for word in line if word in vocabulary] for line in data]
result = '\n'.join(' '.join(word for word in line) for line in removed)
f.seek(0)
f.write(result)
f.truncate()

#Read the two files
with open('vocab30000.txt') as f:
vocabulary = f.readlines()
with open('eng.txt', 'r+') as f:
eng = f.readlines()
vocab_sentences = [i.split(" ") for i in vocabulary]
eng = [i.split(" ") for i in eng]
cleaned_sentences = []
# loop over the sentences and exclude words in eng
for sent in vocab_sentences:
cleaned_sentences.append(" ".join([i for i in sent if i not in eng]))
#write the file
with open('vocab30000.txt', 'w') as f:
f.writelines(cleaned_sentences)

You can try this code. I tried not to use any loops to save your runtime if you have larger files.
import re
with open('eng.txt', 'r') as f:
s = f.read()
s_copy = s
punctuation = [".","\"",",","-","(",")","[","]"]
pattern = re.compile("\\b("+"|".join(punctuation)+")\\W", re.I)
s_copy = pattern.sub(" ", s_copy)
s_copy = s_copy.replace("\"","")
s_words = s_copy.split(" ")
with open('vocab30000.txt', 'r') as f:
check_words = f.read()
remove_words = list(set(s_words) - set(check_words))
pattern = re.compile("\\b("+"|".join(remove_words[1:])+")\\W", re.I)
pattern.sub("", s)

Trying to write function that recursively counts the number of times word appears in a text file in Python

Trying to write function that recursively counts the number of times word appears in a text file in Python.
def word_count(filename, word):
with open('C:/Users/Ibrahim/Desktop/file.txt', 'r') as f:
result_list = [x.split(',') for x in f.readlines()]
for i in result_list:
if i == word:
return word_count(filename,word)
is what I currently have.

I Think it may helpful for you:
import sys, re
def word_count(filename, niddle, splitter=","):
regex_pattern = '|'.join(map(re.escape, splitter))
with open(filename, 'r') as f:
words = [ word for line in f.read().splitlines() for word in re.split(regex_pattern, line)]
words = filter(None, words)
print "Total Words :", len(words)
print "Searching %s in list" % niddle
print "Total Occurance : %d" % words.count(niddle)
def main(argv):
splitter = ","
if len(argv)==3:
filename, word, splitter = argv
elif len(argv)==2:
filename, word = argv
splitter = splitter
else:
print "Usage : word_count.py <file> <word> <splitter>"
sys.exit()
word_count(filename, word, splitter)
if __name__ == "__main__":
main(sys.argv[1:])

Counter is your friend here, i.e.:
from collections import Counter
f = open('yourfile.txt', 'r')
counts = Counter(f.read().split())
print counts
To check if a specific word exists:
if "myword" in counts:
print "exists"
To get a specific word count value, use:
print counts.get('myword')
# or simply
print counts['myword']
Note:
A Counter is simply a dict subclass and supports all the dict operators and methods.

trying to create a dictionary from a text file but

so, I have text file (a paragraph) and I need to read the file and create a dictionary containing each different word from the file as a key and the corresponding value for each key will be an integer showing the frequency of the word in the text file.
an example of what the dictionary should look like:
{'and':2, 'all':1, 'be':1, 'is':3} etc.
so far I have this,
def create_word_frequency_dictionary () :
filename = 'dictionary.txt'
infile = open(filename, 'r')
line = infile.readline()
my_dictionary = {}
frequency = 0
while line != '' :
row = line.lower()
word_list = row.split()
print(word_list)
print (word_list[0])
words = word_list[0]
my_dictionary[words] = frequency+1
line = infile.readline()
infile.close()
print (my_dictionary)
create_word_frequency_dictionary()
any help would be appreciated thanks.

Documentation defines collections module as "High-performance container datatypes". Consider using collections.Counter instead of re-inventing the wheel.
from collections import Counter
filename = 'dictionary.txt'
infile = open(filename, 'r')
text = str(infile.read())
print(Counter(text.split()))
Update:
Okay, I fixed your code and now it works, but Counter is still a better option:
def create_word_frequency_dictionary () :
filename = 'dictionary.txt'
infile = open(filename, 'r')
lines = infile.readlines()
my_dictionary = {}
for line in lines:
row = str(line.lower())
for word in row.split():
if word in my_dictionary:
my_dictionary[word] = my_dictionary[word] + 1
else:
my_dictionary[word] = 1
infile.close()
print (my_dictionary)
create_word_frequency_dictionary()

If you are not using version of python which has Counter:
>>> import collections
>>> words = ["a", "b", "a", "c"]
>>> word_frequency = collections.defaultdict(int)
>>> for w in words:
... word_frequency[w] += 1
...
>>> print word_frequency
defaultdict(<type 'int'>, {'a': 2, 'c': 1, 'b': 1})

Just replace my_dictionary[words] = frequency+1 with my_dictionary[words] = my_dictionary[words]+1.