import nltk
from gensim.models import Word2Vec
from nltk.tokenize import word_tokenize, sent_tokenize
from collections import Counter
nltk.download('stopwords')
nltk.download('punkt')
with open('txt_file_route', 'r', encoding='utf-8') as file:
text1 = file.read()
sentences = sent_tokenize(text1.lower())
print(sentences)
tokenized_sentences = [word_tokenize(sentence) for sentence in sentences]
Count the frequency of each word in each sentence
word_freq_per_sentence = [Counter(sentence) for sentence in tokenized_sentences]
Sort the words based on frequency in each sentence
sorted_words_per_sentence = [sorted(freq.items(), key=lambda x: x[1], reverse=True) for freq in word_freq_per_sentence]
Print the sorted words and their frequencies for each sentence
for i, sentence_words in enumerate(sorted_words_per_sentence):
print(f"Sentence {i + 1}:")
for word, freq in sentence_words:
print(f"{word}: {freq}")
print()
model = Word2Vec(tokenized_sentences, vector_size=100, min_count=1)
print(model)
text tokenize
text = input("what would u search:")
word_by_word = (word_tokenize(text.lower()))
print(word_by_word)
vector = model.wv[word_by_word]
print(vector)
import nltk from gensim.models import Word2Vec from nltk.tokenize import word_tokenize, sent_tokenize from collections import Counter
nltk.download('stopwords') nltk.download('punkt')
with open('txt_file_route', 'r', encoding='utf-8') as file: text1 = file.read() sentences = sent_tokenize(text1.lower())
print(sentences)
tokenized_sentences = [word_tokenize(sentence) for sentence in sentences]
Count the frequency of each word in each sentence
word_freq_per_sentence = [Counter(sentence) for sentence in tokenized_sentences]
Sort the words based on frequency in each sentence
sorted_words_per_sentence = [sorted(freq.items(), key=lambda x: x[1], reverse=True) for freq in word_freq_per_sentence]
Print the sorted words and their frequencies for each sentence
for i, sentence_words in enumerate(sorted_words_per_sentence): print(f"Sentence {i + 1}:") for word, freq in sentence_words: print(f"{word}: {freq}") print()
model = Word2Vec(tokenized_sentences, vector_size=100, min_count=1) print(model)
text tokenize
text = input("what would u search:") word_by_word = (word_tokenize(text.lower())) print(word_by_word) vector = model.wv[word_by_word] print(vector)