from collections import Counter


def count_word_frequency(file_path, top_n):

    try:

        words = open(file_path, encoding='utf-8').read().lower().split()

        words = [''.join(c for c in word if c.isalnum()) for word in words]

        print(Counter(words).most_common(top_n))

    except Exception as e:

        print(f"Error: {e}")


# Usage

count_word_frequency("example.txt", 10)


Comments

Post a Comment

Popular posts from this blog

 import heapq def dijkstra(graph, start, end):     # Priority queue: (cost, current_node)     queue = [(0, start)]     distances = {node: float('inf') for node in graph}     distances[start] = 0     predecessors = {node: None for node in graph}     while queue:         current_cost, current_node = heapq.heappop(queue)         if current_node == end:             break         for neighbor, cost in graph[current_node].items():             new_cost = current_cost + cost             if new_cost < distances[neighbor]:                 distances[neighbor] = new_cost                 predecessors[neighbor] = current_node                 heapq.heappush(queue, (new_...
Read more
 clc; clear; close all; dataLength = 16;             % Length of the signal snr = 10;                    % Signal-to-noise ratio in dB signal = randn(1, dataLength);  % Random signal (e.g., Gaussian) signalPower = mean(signal.^2); snrLinear = 10^(snr / 10); noise = sqrt(signalPower / snrLinear) * randn(size(signal)); noisySignal = signal + noise; figure; subplot(2, 1, 1); plot(signal); title('Original Signal'); xlabel('Samples'); ylabel('Amplitude'); subplot(2, 1, 2); plot(noisySignal); title('Signal with Noise'); xlabel('Samples'); ylabel('Amplitude');
Read more

Pos using Seq to seq

 # Imports import numpy as np from tensorflow.keras.models import Model from tensorflow.keras.layers import Input, Embedding, LSTM, Dense from tensorflow.keras.preprocessing.text import Tokenizer from tensorflow.keras.preprocessing.sequence import pad_sequences from sklearn.model_selection import train_test_split # Example Data (Replace with your dataset) sentences = ["I love programming", "You are learning", "We enjoy coding"] tags = [["PRON", "VERB", "NOUN"], ["PRON", "VERB", "VERB"], ["PRON", "VERB", "NOUN"]] # Preprocessing tokenizer = Tokenizer() tokenizer.fit_on_texts(sentences) word_index = tokenizer.word_index input_sequences = tokenizer.texts_to_sequences(sentences) tag_tokenizer = Tokenizer() tag_tokenizer.fit_on_texts(tags) tag_index = tag_tokenizer.word_index output_sequences = tag_tokenizer.texts_to_sequences(tags) # Padding max_seq_length = max(len(seq) ...
Read more