model.py

import numpy as np
import matplotlib.pyplot as plt
from utils import *
X_train,Y_train = read_csv('train_emoji.csv')
X_test, Y_test = read_csv('tesss.csv')
word_to_index, index_to_word, word_to_vec_map = read_glove_vecs('glove.6B.50d.txt')
from keras.models import Model
from keras.layers import Dense, Input, Dropout, LSTM, Activation
from keras.layers.embeddings import Embedding
from keras.preprocessing import sequence
from keras.initializers import glorot_uniform
np.random.seed(1)
def sentences_to_indices(X, word_to_index, max_len):
    m = X.shape[0]                                  
    X_indices = np.zeros((m,max_len))
    for i in range(m):               
        sentence_words = [w.lower() for w in X[i].split()]
        j = 0
        for w in sentence_words:
            X_indices[i, j] = word_to_index[w]
            j = j+1    
    return X_indices
def pretrained_embedding_layer(word_to_vec_map, word_to_index):
    vocab_len = len(word_to_index) + 1                  
    emb_dim = word_to_vec_map["cucumber"].shape[0]      
    emb_matrix = np.zeros((vocab_len, emb_dim))
    for word, idx in word_to_index.items():
        emb_matrix[idx, :] = word_to_vec_map[word]
    embedding_layer = Embedding(vocab_len, emb_dim, trainable=False)
    embedding_layer.build((None,)) # Do not modify the "None".  This line of code is complete as-is.
    embedding_layer.set_weights([emb_matrix])
    
    return embedding_layer
def predict_your_feel(input_shape, word_to_vec_map, word_to_index):
    sentence_indices = Input(input_shape, dtype='int32')
    embedding_layer = pretrained_embedding_layer(word_to_vec_map, word_to_index)
    embeddings = embedding_layer(sentence_indices)    
    X = LSTM(128, return_sequences=True)(embeddings)
    X = Dropout(0.5)(X)
    X = LSTM(128, return_sequences=False)(X)
    X = Dropout(0.5)(X)
    X = Dense(5)(X)
    X = Activation('softmax')(X)
    model = Model(inputs=sentence_indices, outputs=X)
    return model

maxLen = len(max(X_train, key=len).split())
model = predict_your_feel((maxLen,), word_to_vec_map, word_to_index)
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
X_train_indices = sentences_to_indices(X_train, word_to_index, maxLen)
Y_train_oh = convert_to_one_hot(Y_train, C = 5)
model.fit(X_train_indices, Y_train_oh, epochs = 50, batch_size = 32, shuffle=True)
X_test_indices = sentences_to_indices(X_test, word_to_index, max_len = maxLen)
Y_test_oh = convert_to_one_hot(Y_test, C = 5)
loss, acc = model.evaluate(X_test_indices, Y_test_oh)
print()
print("Test accuracy = ", acc)
# enter your sentences here
x_test = np.array(['please love me :)'])
X_test_indices = sentences_to_indices(x_test, word_to_index, maxLen)
print(x_test[0] +' '+  label_to_emoji(np.argmax(model.predict(X_test_indices))))