# emo\_utils.py

```python
import csv
import numpy as np
import emoji
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix

def read_glove_vecs(glove_file):
    with open(glove_file, 'r') 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 = 1
        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 read_csv(filename = 'data/emojify_data.csv'):
    phrase = []
    emoji = []

    with open (filename) as csvDataFile:
        csvReader = csv.reader(csvDataFile)

        for row in csvReader:
            phrase.append(row[0])
            emoji.append(row[1])

    X = np.asarray(phrase)
    Y = np.asarray(emoji, dtype=int)

    return X, Y

def convert_to_one_hot(Y, C):
    Y = np.eye(C)[Y.reshape(-1)]
    return Y


emoji_dictionary = {"0": "\u2764\uFE0F",    # :heart: prints a black instead of red heart depending on the font
                    "1": ":baseball:",
                    "2": ":smile:",
                    "3": ":disappointed:",
                    "4": ":fork_and_knife:"}

def label_to_emoji(label):
    """
    Converts a label (int or string) into the corresponding emoji code (string) ready to be printed
    """
    return emoji.emojize(emoji_dictionary[str(label)], use_aliases=True)


def print_predictions(X, pred):
    print()
    for i in range(X.shape[0]):
        print(X[i], label_to_emoji(int(pred[i])))


def plot_confusion_matrix(y_actu, y_pred, title='Confusion matrix', cmap=plt.cm.gray_r):

    df_confusion = pd.crosstab(y_actu, y_pred.reshape(y_pred.shape[0],), rownames=['Actual'], colnames=['Predicted'], margins=True)

    df_conf_norm = df_confusion / df_confusion.sum(axis=1)

    plt.matshow(df_confusion, cmap=cmap) # imshow
    #plt.title(title)
    plt.colorbar()
    tick_marks = np.arange(len(df_confusion.columns))
    plt.xticks(tick_marks, df_confusion.columns, rotation=45)
    plt.yticks(tick_marks, df_confusion.index)
    #plt.tight_layout()
    plt.ylabel(df_confusion.index.name)
    plt.xlabel(df_confusion.columns.name)


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):                       # Loop over training examples

        # Split jth test example (sentence) into list of lower case words
        words = X[j].lower().split()

        # Average words' vectors
        avg = np.zeros((50,))
        for w in words:
            avg += word_to_vec_map[w]
        avg = avg/len(words)

        # Forward propagation
        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
```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-wu-men-ke-xu-lie-mo-xing-sequence-models/di-wu-men-kexulie-mo-578b28-sequence-models/natural-language-processing-and-word-embeddings/emoutils-py.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.