بتل کد Battle Codeدارد باز می‌شود…

جواب «Step 2: Words to Numbers» چالش 2 از جلسه‌ی 58

سؤال

قدم دوم: STOP، tokenize و واژه‌نامه‌ی VOCAB (همه‌ی کلمه‌های متن درس‌ها، مرتب) آماده‌اند. در vectorize به جای pass یک خط بنویس که در جای این کلمه در VOCAB یکی اضافه کند (اگر کلمه دو بار آمد، عددش ۲ شود). خروجی چهار خط: 73، ['words', 'look', 'other', 'words']، 4 2 و ['look', 'other', 'words'].

راهنما

VOCAB.index(w) جای کلمه است: v[VOCAB.index(w)] += 1. با = 1 کلمه‌ی تکراری فقط یک بار شمرده می‌شود.

یک جواب درست

import numpy as np

LESSONS = [
    {"title": "overfitting", "source": "session 48",
     "text": "overfitting is when a model memorises the training data and does badly on new test data",
     "answer": "Overfitting means the model memorised its training examples and fails on new ones."},
    {"title": "validation", "source": "session 49",
     "text": "a validation set is data the model never trains on so we can check it fairly",
     "answer": "A validation set is kept apart from training so you can measure the model fairly."},
    {"title": "relu", "source": "session 43",
     "text": "relu is an activation that keeps positive numbers and turns negative numbers into zero",
     "answer": "ReLU keeps a positive number and turns a negative one into 0, like max(0, x)."},
    {"title": "softmax", "source": "session 44",
     "text": "softmax turns a list of scores into probabilities that are positive and add up to one",
     "answer": "Softmax turns scores into probabilities that add up to 1."},
    {"title": "mini-batch", "source": "session 45",
     "text": "a mini batch is a small group of training examples used for one step of gradient descent",
     "answer": "A mini-batch is a small group of examples used for one gradient descent step."},
    {"title": "decision tree", "source": "sessions 50-51",
     "text": "a decision tree asks yes or no questions about the features and splits the data at every node",
     "answer": "A decision tree asks one yes/no question per node and splits the data until a leaf answers."},
    {"title": "convolution", "source": "session 53",
     "text": "convolution slides a small filter over the image and adds up each patch times the filter to find edges",
     "answer": "Convolution slides a small filter across the picture and adds up patch * filter at every spot."},
    {"title": "embedding", "source": "session 55",
     "text": "a word embedding is a vector of numbers for a word so that similar words get close vectors",
     "answer": "A word embedding is a vector for a word; similar words point in similar directions."},
    {"title": "attention", "source": "session 57",
     "text": "attention lets every word look at the other words of the sentence with a query a key and a value",
     "answer": "In attention every word scores the others (query times key), softmax gives weights, and it mixes their values."},
]


def show_lessons():
    print(len(LESSONS), "lessons")
    for lesson in LESSONS:
        print(f"{lesson['title']} ({lesson['source']})")


STOP = {"a", "an", "the", "is", "are", "what", "how", "does", "do", "of", "to", "and", "in", "on",
        "it", "that", "for", "with", "at", "so", "by", "i", "my", "we", "can", "you", "why", "which",
        "into", "its", "be", "this", "about", "or", "when", "me", "every", "each"}


def tokenize(text):
    clean = "".join(ch if ch.isalpha() else " " for ch in text.lower())
    return [w for w in clean.split() if w not in STOP]


VOCAB = sorted(set(w for lesson in LESSONS for w in tokenize(lesson["text"])))


def vectorize(text):
    v = np.zeros(len(VOCAB))
    for w in tokenize(text):
        if w in VOCAB:
            v[VOCAB.index(w)] += 1
    return v


print(len(VOCAB))
print(tokenize("How do words look at other words?"))
v = vectorize("How do words look at other words?")
print(int(v.sum()), int(v[VOCAB.index("words")]))
print([VOCAB[i] for i in range(len(VOCAB)) if v[i] > 0])

اول خودت امتحان کن؛ جواب‌های دیگر هم قبول است. برگرد و خودت حلش کن