vocab = sorted(set(word for sentence in texts for word in sentence.split()))

def one_hot_encode(word):
    vec = np.zeros(len(vocab))
    if word in word_to_index:
        vec[word_to_index[word]] = 1
    return vec

from sklearn.preprocessing import OneHotEncoder
encoder = OneHotEncoder(sparse_output=False, handle_unknown='ignore')
encoder.fit(vocab_np)

def binary_transform(text):
    output = np.zeros(len(vocab))
    words = set(text.split())
    for i, v in enumerate(vocab):
        output[i] = v in words
    return output

from sklearn.feature_extraction.text import CountVectorizer
vec = CountVectorizer(binary=True)
vec.fit(texts)

from sklearn.feature_extraction.text import CountVectorizer
vec = CountVectorizer()
vec.fit(texts)

from sklearn.feature_extraction.text import TfidfVectorizer
vec = TfidfVectorizer()
vec.fit(texts)

import gensim
word2vec_model = gensim.models.KeyedVectors.load_word2vec_format(
    "GoogleNews-vectors-negative300.bin", binary=True)
word2vec_model["king"][:10]

glove_embeddings = {}
with open("glove.6B.100d.txt", encoding="utf-8") as f:
    for line in f:
        values = line.split()
        glove_embeddings[values[0]] = np.asarray(values[1:], dtype="float32")