eustin

import numpy as np

np.random.seed(123)

eustin

def draw_pairs(num_trials):
    
    trial_results = {}
    
    for trial_num in range(num_trials):
        if trial_num % 10000 == 0:
            print(f"running trial number: {trial_num}")
        trial_results[trial_num+1] = np.random.choice(all_socks, 2, replace=False).tolist()
    
    return trial_results

eustin

def calc_prop_matching_pairs(trial_results):
    num_matching_pairs = sum([1 for x in results.values() if x[0] == x[1]])
    num_total_pairs = len(results.values())

    # of all the pairs we have drawn, what proportion were matching pairs of socks?
    prop_matching_pairs = num_matching_pairs / num_total_pairs
    
    print(f"\nprop valid pairs over {NUM_TRIALS:,} trials: {prop_matching_pairs:.2f}")

eustin

import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf

sentence = "Snoopy is a beagle"

tokens = sentence.split(" ")

print(tokens)

eustin

index_word = {i: x for i, x in enumerate(tokens)}

print(index_word)

eustin

num_classes = len(index_word)

index_one_hot = {i: tf.one_hot(x, depth=num_classes) \
                 for i, x in enumerate(index_word.keys())}

for k, v in index_one_hot.items():
    word = index_word[k]
    one_hot_vector = v.numpy()
    print(f"{word:<6}: {one_hot_vector}")

eustin

embeddings = tf.random.uniform((4, 2), minval=-0.05, maxval=0.05).numpy()

print(embeddings)

eustin

snoopy_vec = index_one_hot[0]
beagle_vec = index_one_hot[3]

snoopy_vs_beagle = tf.sqrt(tf.reduce_sum(tf.square(snoopy_vec - beagle_vec)))

print(snoopy_vs_beagle.numpy())

eustin

is_vec = index_one_hot[1]

snoopy_vs_is = tf.sqrt(tf.reduce_sum(tf.square(snoopy_vec - is_vec)))

print(snoopy_vs_is.numpy())

eustin

snoopy_vs_beagle = tf.sqrt(tf.reduce_sum(tf.square(embeddings[0] - embeddings[3])))
snoopy_vs_is = tf.sqrt(tf.reduce_sum(tf.square(embeddings[0] - embeddings[1])))

print(snoopy_vs_beagle.numpy())
print(snoopy_vs_is.numpy())