eustin

sum(true_prob_dist * np.log(true_prob_dist / predicted_prob_dist))

eustin

sum(true_prob_dist * np.log(true_prob_dist / true_prob_dist))

eustin

query_1 = "dog"

bing_search_results = [
    "Dog - Wikipedia",
    "Adopting a dog or puppy | RSPCA Australia",
    "dog | History, Domestication, Physical Traits, & Breeds",
    "New South Wales | Dogs & Puppies | Gumtree Australia Free",
    "dog - Wiktionary"
]

eustin

relevance_grades = tf.constant([
    [3.0, 2.0, 2.0, 2.0, 1.0],
    [3.0, 3.0, 1.0, 1.0, 0.0]
])

eustin

combined_texts = [query_1, *bing_search_results, query_2, *google_search_results]

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

# we add one here to account for the padding word
vocab_size = max(tokeniser.index_word) + 1
print(vocab_size)

eustin

for idx, word in tokeniser.index_word.items():
    print(f"index {idx} - {word}")

eustin

EMBEDDING_DIMS = 2

embeddings = np.random.randn(vocab_size, EMBEDDING_DIMS).astype(np.float32)

print(embeddings)

eustin

query_1_embedding_index = tokeniser.texts_to_sequences([query_1])
query_1_embeddings = np.array([embeddings[x] for x in query_1_embedding_index])

print(query_1_embeddings)

eustin

query_2_embedding_indices = tokeniser.texts_to_sequences([query_2])
query_2_embeddings = np.array([embeddings[x] for x in query_2_embedding_indices])

print(query_2_embeddings)

eustin

query_2_embeddings_avg = tf.reduce_mean(query_2_embeddings, axis=1, keepdims=True).numpy()

print(query_2_embeddings_avg)