An example of how to create X and Y for word embedding training

X_Y_creation_word_embeding

from scipy import sparse
import numpy as np

# Defining the number of features (unique words)
n_words = len(unique_word_dict)

# Getting all the unique words 
words = list(unique_word_dict.keys())

# Creating the X and Y matrices using one hot encoding
X = []
Y = []

for i, word_list in tqdm(enumerate(word_lists)):
    # Getting the indices
    main_word_index = unique_word_dict.get(word_list[0])
    context_word_index = unique_word_dict.get(word_list[1])

    # Creating the placeholders   
    X_row = np.zeros(n_words)
    Y_row = np.zeros(n_words)

    # One hot encoding the main word
    X_row[main_word_index] = 1

    # One hot encoding the Y matrix words 
    Y_row[context_word_index] = 1

    # Appending to the main matrices
    X.append(X_row)
    Y.append(Y_row)

# Converting the matrices into an array
X = np.asarray(X)
Y = np.asarray(Y)