model.py

import numpy as np
from emo_utils import *
import emoji
import matplotlib.pyplot as plt
X_train, Y_train = read_csv('data/train_emoji.csv')
X_test, Y_test = read_csv('data/tesss.csv')
maxLen = len(max(X_train, key=len).split())

Y_oh_train = convert_to_one_hot(Y_train, C = 5)
Y_oh_test = convert_to_one_hot(Y_test, C = 5)	

idx = 50
word_to_index, index_to_word, word_to_vec_map = read_glove_vecs('data/glove.6B.50d.txt')


def sentence_to_avg(sentence, word_to_vec_map):
    """
    Converts a sentence (string) into a list of words (strings). Extracts the GloVe representation of each word
    """

    words = [w.lower() for w in sentence.split()]

    avg = np.zeros((50,))
    
    total = 0
    for w in words:
        total += word_to_vec_map[w]
    avg = total/(len(words))
        
    return avg


def model(X, Y, word_to_vec_map, learning_rate = 0.01, num_iterations = 400):
    """
    Model to train word vector representations in numpy.
    
    Arguments:
    X -- input data, numpy array of sentences as strings, of shape (m, 1)
    Y -- labels, numpy array of integers between 0 and 7, numpy-array of shape (m, 1)
    word_to_vec_map -- dictionary mapping every word in a vocabulary into its 50-dimensional vector representation
    learning_rate -- learning_rate for the stochastic gradient descent algorithm
    num_iterations -- number of iterations

    """
    
    np.random.seed(1)

    # Define number of training examples
    m = Y.shape[0]                          # number of training examples
    n_y = 5                                 # number of classes  
    n_h = 50                                # dimensions of the GloVe vectors 
    
    # Initialize parameters using Xavier initialization
    W = np.random.randn(n_y, n_h) / np.sqrt(n_h)
    b = np.zeros((n_y,))
    
    # Convert Y to Y_onehot with n_y classes
    Y_oh = convert_to_one_hot(Y, C = n_y) 
    
    # Optimization loop
    for t in range(num_iterations): # Loop over the number of iterations
        for i in range(m):          # Loop over the training examples
            

            avg = sentence_to_avg(X[i], word_to_vec_map)

            z = np.dot(W,avg) + b
            a = softmax(z)

            cost = -np.sum(np.multiply(Y_oh[i], np.log(a)))
            
            # Compute gradients 
            dz = a - Y_oh[i]
            dW = np.dot(dz.reshape(n_y,1), avg.reshape(1, n_h))
            db = dz

            W = W - learning_rate * dW
            b = b - learning_rate * db
        
        if t % 100 == 0:
            print("Epoch: " + str(t) + " --- cost = " + str(cost))
            pred = predict(X, Y, W, b, word_to_vec_map) #predict is defined in emo_utils.py

    return pred, W, b

pred, W, b = model(X_train, Y_train, word_to_vec_map)
print(pred)

print("Training set:")
pred_train = predict(X_train, Y_train, W, b, word_to_vec_map)
print('Test set:')
pred_test = predict(X_test, Y_test, W, b, word_to_vec_map)

X_my_sentences = np.array(["i adore you", "i love you", "funny lol", "lets play with a ball", "food is ready", "not feeling happy"])
Y_my_labels = np.array([[0], [0], [2], [1], [4],[3]])

pred = predict(X_my_sentences, Y_my_labels , W, b, word_to_vec_map)
print_predictions(X_my_sentences, pred)