def get_data():
X_train, Y_train = read_csv('data/train_emoji.csv')
X_test, Y_test = read_csv('data/tesss.csv')
Y_oh_train = convert_to_one_hot(Y_train, C=5)
Y_oh_test = convert_to_one_hot(Y_test, C=5)
maxLen = len(max(X_train, key=len).split())
word_to_index, index_to_word, word_to_vec_map = \
read_glove_vecs('../word_vectors/data/glove.6B.50d.txt')
return word_to_index, index_to_word, word_to_vec_map, X_train, Y_train
def main():
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())
word_to_index, index_to_word, word_to_vec_map = read_glove_vecs('../data/glove.6B.50d.txt')
# X1 = np.array(["funny lol", "lets play baseball", "food is ready for you"])
# X1_indices = sentences_to_indices(X1, word_to_index, max_len=5)
# print("X1 =", X1)
# print("X1_indices =", X1_indices)
#
# embedding_layer = pretrained_embedding_layer(word_to_vec_map, word_to_index)
# print("weights[0][1][3] =", embedding_layer.get_weights()[0][1][3])
model = Emojify_V2((maxLen,), word_to_vec_map, word_to_index)
model.summary()
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)
# This code allows you to see the mislabelled examples
C = 5
y_test_oh = np.eye(C)[Y_test.reshape(-1)]
X_test_indices = sentences_to_indices(X_test, word_to_index, maxLen)
pred = model.predict(X_test_indices)
for i in range(len(X_test)):
x = X_test_indices
num = np.argmax(pred[i])
if (num != Y_test[i]):
print('Expected emoji:' + label_to_emoji(Y_test[i]) + ' prediction: ' + X_test[i] + label_to_emoji(
num).strip())
# Change the sentence below to see your prediction. Make sure all the words are in the Glove embeddings.
x_test = np.array(['not feeling happy'])
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))))
def main():
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())
for index in range(10):
print(X_train[index], label_to_emoji(Y_train[index]))
Y_oh_train = convert_to_one_hot(Y_train, C=5)
Y_oh_test = convert_to_one_hot(Y_test, C=5)
word_to_index, index_to_word, word_to_vec_map = read_glove_vecs('../data/glove.6B.50d.txt')
word = "cucumber"
index = 289846
print("")
print("the index of", word, "in the vocabulary is", word_to_index[word])
print("the", str(index) + "th word in the vocabulary is", index_to_word[index])
pred, W, b = model(X_train, Y_train, word_to_vec_map)
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]])
print('--------- PRINT PREDICTIONS ----------')
pred = predict(X_my_sentences, Y_my_labels, W, b, word_to_vec_map)
print_predictions(X_my_sentences, pred)
print(Y_test.shape)
print(' ' + label_to_emoji(0) + ' ' + label_to_emoji(1) + ' ' + label_to_emoji(
2) + ' ' + label_to_emoji(3) + ' ' + label_to_emoji(4))
print(pd.crosstab(Y_test, pred_test.reshape(56, ), rownames=['Actual'], colnames=['Predicted'], margins=True))
plot_confusion_matrix(Y_test, pred_test)
plt.show()
if __name__ == '__main__':
os.chdir(
r"E:\深度学习\【中英】【吴恩达课后编程作业】Course 5 - 序列模型 - 第二周作业 - 词向量的运算与Emoji生成器")
word_to_index, index_to_word, word_to_vec_map = emo_utils.read_glove_vecs(
'data/glove.6B.50d.txt')
embedding_layer = pretrained_embedding_layer(word_to_vec_map,
word_to_index)
print("weights[0][1][3] =", embedding_layer.get_weights()[0][1][3])
max_Len = 10
model = Emojify_V2((max_Len, ), word_to_vec_map, word_to_index)
model.summary()
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
X_train, Y_train = emo_utils.read_csv('data/train_emoji.csv')
X_test, Y_test = emo_utils.read_csv('data/test.csv')
X_train_indices = sentences_to_indices(X_train, word_to_index, max_Len)
Y_train_oh = emo_utils.convert_to_one_hot(Y_train, C=5)
model.fit(X_train_indices,
Y_train_oh,
epochs=200,
batch_size=32,
shuffle=True)
C = 5
X_test_indices = sentences_to_indices(X_test,
word_to_index,
max_len=max_Len)
Y_test_oh = emo_utils.convert_to_one_hot(Y_test, C=5)
