eustin

sentences = [
    "snoopy dog",
    "milo dog",
    "dumbo elephant",
    "portugal country", 
    "brazil country",
]

eustin

tokeniser = tf.keras.preprocessing.text.Tokenizer()
tokeniser.fit_on_texts(sentences)

print(tokeniser.word_index)

eustin

sequences = tokeniser.texts_to_sequences(sentences)
for x in sequences:
    print(x)

eustin

VOCAB_SIZE = max(tokeniser.index_word) + 1
print(f"VOCAB_SIZE: {VOCAB_SIZE}")

eustin

def make_skipgrams():
    train_x, all_labels = [], []
    for sequence in sequences:
        pairs, labels = tf.keras.preprocessing.sequence.skipgrams(
            sequence, VOCAB_SIZE, negative_samples=1.0, window_size=1, shuffle=True
        )
        train_x.extend(pairs)
        all_labels.extend(labels)

    train_x = np.array(train_x)

eustin

# inputs
content_input = tf.keras.layers.Input(shape=(1, ), dtype=tf.int32, name='content_word')
context_input = tf.keras.layers.Input(shape=(1, ), dtype=tf.int32, name='context_word')

# layers
embeddings = tf.keras.layers.Embedding(input_dim=VOCAB_SIZE, output_dim=2, name='embeddings')
dot_prod = tf.keras.layers.Dot(axes=2, normalize=True, name='dot_product')
# graph
content_embedding = embeddings(content_input)
context_embedding = embeddings(context_input)

eustin

loss_hist = []

for i in range(20):
    
    if i > 0:
        
        content_words, context_words, labels = make_skipgrams()
        
        hist = model.fit([content_words, context_words], labels, epochs=1, verbose=0)
        print(f"loss: {hist.history['loss'][-1]:.4f}")

eustin

import random
random.seed(1)

import numpy as np
np.random.seed(1)

import itertools
import matplotlib.pyplot as plt
plt.style.use('ggplot')

eustin

objects_to_rank = {'dress', 'shirt', 'pants'}

eustin

all_permutations = list(itertools.permutations(objects_to_rank))

for x in sorted(all_permutations):
    print(x)