mbednarski

import click

from random_forest import RandomForestModel
import sys

sys.path.append('src')
from data.preprocess import read_processed_data


@click.command()

mbednarski

corpus = [
    'he is a king',
    'she is a queen',
    'he is a man',
    'she is a woman',
    'warsaw is poland capital',
    'berlin is germany capital',
    'paris is france capital',
]

mbednarski

def tokenize_corpus(corpus):
    tokens = [x.split() for x in corpus]
    return tokens

mbednarski

def tokenize_corpus(corpus):
    tokens = [x.split() for x in corpus]
    return tokens

tokenized_corpus = tokenize_corpus(corpus)

mbednarski

vocabulary = []
for sentence in tokenized_corpus:
    for token in sentence:
        if token not in vocabulary:
            vocabulary.append(token)

word2idx = {w: idx for (idx, w) in enumerate(vocabulary)}
idx2word = {idx: w for (idx, w) in enumerate(vocabulary)}

vocabulary_size = len(vocabulary)

mbednarski

window_size = 2
idx_pairs = []
# for each sentence
for sentence in tokenized_corpus:
    indices = [word2idx[word] for word in sentence]
    # for each word, threated as center word
    for center_word_pos in range(len(indices)):
        # for each window position
        for w in range(-window_size, window_size + 1):
            context_word_pos = center_word_pos + w

mbednarski

def get_input_layer(word_idx):
    x = torch.zeros(vocabulary_size).float()
    x[word_idx] = 1.0
    return x

mbednarski

embedding_dims = 5
W1 = Variable(torch.randn(embedding_dims, vocabulary_size).float(), requires_grad=True)
z1 = torch.matmul(W1, x)

mbednarski

W2 = Variable(torch.randn(vocabulary_size, embedding_dims).float(), requires_grad=True)
z2 = torch.matmul(W2, z1)

mbednarski

embedding_dims = 5
W1 = Variable(torch.randn(embedding_dims, vocabulary_size).float(), requires_grad=True)
W2 = Variable(torch.randn(vocabulary_size, embedding_dims).float(), requires_grad=True)
num_epochs = 100
learning_rate = 0.001

for epo in range(num_epochs):
    loss_val = 0
    for data, target in idx_pairs:
        x = Variable(get_input_layer(data)).float()