How to Find the Most Repeated Word in a Text File in Python

import string
from collections import Counter

def find_most_common_word(file_path):
    """
    Find the most frequently occurring word in a text file.
    
    Args:
        file_path: Path to the text file
        
    Returns:
        Tuple of (word, count) or (None, 0) if file is empty
    """
    try:
        with open(file_path, 'r', encoding='utf-8') as file:
            content = file.read().lower()
            
            translator = str.maketrans('', '', string.punctuation)
            clean_content = content.translate(translator)
            
            words = clean_content.split()
            word_counts = Counter(words)
            
            if word_counts:
                return word_counts.most_common(1)[0]
            return None, 0
            
    except FileNotFoundError:
        print(f"Error: File '{file_path}' not found")
        return None, 0


word, count = find_most_common_word("document.txt")
print(f"Most common word: '{word}' (appears {count} times)")

from collections import Counter
import string

def get_top_words(file_path, n=10):
    """Return the n most common words in a file."""
    with open(file_path, 'r', encoding='utf-8') as file:
        content = file.read().lower()
        clean = content.translate(str.maketrans('', '', string.punctuation))
        words = clean.split()
        
        return Counter(words).most_common(n)


top_words = get_top_words("article.txt", n=5)
for word, count in top_words:
    print(f"{word}: {count}")

from collections import Counter
import string

STOP_WORDS = {
    'the', 'a', 'an', 'and', 'or', 'but', 'in', 'on', 'at', 'to', 'for',
    'of', 'with', 'by', 'from', 'is', 'are', 'was', 'were', 'be', 'been',
    'being', 'have', 'has', 'had', 'do', 'does', 'did', 'will', 'would',
    'could', 'should', 'may', 'might', 'must', 'it', 'its', 'this', 'that',
    'these', 'those', 'i', 'you', 'he', 'she', 'we', 'they', 'what', 'which',
    'who', 'whom', 'as', 'if', 'then', 'than', 'so', 'not', 'no', 'yes'
}

def get_meaningful_words(file_path, n=10, min_length=3):
    """
    Find most common words excluding stop words.
    
    Args:
        file_path: Path to text file
        n: Number of top words to return
        min_length: Minimum word length to include
    """
    with open(file_path, 'r', encoding='utf-8') as file:
        content = file.read().lower()
        clean = content.translate(str.maketrans('', '', string.punctuation))
        
        words = [
            word for word in clean.split()
            if word not in STOP_WORDS and len(word) >= min_length
        ]
        
        return Counter(words).most_common(n)


keywords = get_meaningful_words("research_paper.txt", n=10)
print("Key terms:")
for word, count in keywords:
    print(f"  {word}: {count}")

from collections import Counter
import string

def count_words_streaming(file_path, chunk_size=8192):
    """
    Memory-efficient word counting for large files.
    
    Processes file in chunks to minimize memory usage.
    """
    translator = str.maketrans('', '', string.punctuation)
    word_counts = Counter()
    
    with open(file_path, 'r', encoding='utf-8') as file:
        for line in file:
            clean_line = line.lower().translate(translator)
            word_counts.update(clean_line.split())
    
    return word_counts


counts = count_words_streaming("server_logs.txt")
print(f"Total unique words: {len(counts)}")
print(f"Most common: {counts.most_common(5)}")

from collections import Counter
from pathlib import Path
import string
import re

def analyze_text_file(
    file_path,
    top_n=10,
    exclude_stop_words=True,
    min_word_length=2,
    pattern=r'[a-zA-Z]+' 
):
    """
    Perform comprehensive word frequency analysis.
    
    Args:
        file_path: Path to the text file
        top_n: Number of top words to return
        exclude_stop_words: Whether to filter common words
        min_word_length: Minimum characters for a word
        pattern: Regex pattern for word extraction
        
    Returns:
        Dictionary with analysis results
    """
    stop_words = {
        'the', 'a', 'an', 'and', 'or', 'but', 'in', 'on', 'at', 'to',
        'for', 'of', 'with', 'is', 'are', 'was', 'were', 'be', 'been',
        'have', 'has', 'had', 'it', 'this', 'that', 'as', 'by', 'from'
    } if exclude_stop_words else set()
    
    path = Path(file_path)
    if not path.exists():
        raise FileNotFoundError(f"File not found: {file_path}")
    
    word_counts = Counter()
    total_words = 0
    
    with open(file_path, 'r', encoding='utf-8') as file:
        for line in file:
            words = re.findall(pattern, line.lower())
            
            filtered = [
                w for w in words
                if len(w) >= min_word_length and w not in stop_words
            ]
            
            total_words += len(words)
            word_counts.update(filtered)
    
    return {
        "file": path.name,
        "total_words": total_words,
        "unique_words": len(word_counts),
        "top_words": word_counts.most_common(top_n),
        "most_common": word_counts.most_common(1)[0] if word_counts else None
    }


results = analyze_text_file("novel.txt", top_n=15, exclude_stop_words=True)

print(f"File: {results['file']}")
print(f"Total words: {results['total_words']:,}")
print(f"Unique words: {results['unique_words']:,}")
print(f"\nTop 15 words:")
for word, count in results['top_words']:
    print(f"  {word}: {count}")