| import csv
|
| import numpy as np
|
| import pandas as pd
|
| import matplotlib.pyplot as plt
|
|
|
| def read_glove_vecs(glove_file):
|
| with open(glove_file, 'r',encoding='utf-8') as f:
|
| words = set()
|
| word_to_vec_map = {}
|
| for line in f:
|
| line = line.strip().split()
|
| curr_word = line[0]
|
| words.add(curr_word)
|
| word_to_vec_map[curr_word] = np.array(line[1:], dtype=np.float64)
|
|
|
| i = 4
|
| words_to_index = {}
|
| index_to_words = {}
|
| for w in sorted(words):
|
| words_to_index[w] = i
|
| index_to_words[i] = w
|
| i = i + 1
|
| return words_to_index, index_to_words, word_to_vec_map
|
|
|
| def softmax(x):
|
| """Compute softmax values for each sets of scores in x."""
|
| e_x = np.exp(x - np.max(x))
|
| return e_x / e_x.sum()
|
|
|
|
|
|
|
|
|
| def convert_to_one_hot(Y, C):
|
| Y = np.eye(C)[Y.reshape(-1)]
|
| return Y
|
|
|
|
|
|
|
|
|
|
|
| def predict(X, Y, W, b, word_to_vec_map):
|
| """
|
| Given X (sentences) and Y (emoji indices), predict emojis and compute the accuracy of your model over the given set.
|
|
|
| Arguments:
|
| X -- input data containing sentences, numpy array of shape (m, None)
|
| Y -- labels, containing index of the label emoji, numpy array of shape (m, 1)
|
|
|
| Returns:
|
| pred -- numpy array of shape (m, 1) with your predictions
|
| """
|
| m = X.shape[0]
|
| pred = np.zeros((m, 1))
|
|
|
| for j in range(m):
|
|
|
|
|
| words = X[j].lower().split()
|
|
|
|
|
| avg = np.zeros((50,))
|
| for w in words:
|
| avg += word_to_vec_map[w]
|
| avg = avg/len(words)
|
|
|
|
|
| Z = np.dot(W, avg) + b
|
| A = softmax(Z)
|
| pred[j] = np.argmax(A)
|
|
|
| print("Accuracy: " + str(np.mean((pred[:] == Y.reshape(Y.shape[0],1)[:]))))
|
|
|
| return pred
|
|
|
|
|
