概率和分布

Coin flip:
  S = {H, T}
  P(H) = 0.5,  P(T) = 0.5

Single die roll:
  S = {1, 2, 3, 4, 5, 6}
  P(even) = P({2, 4, 6}) = 3/6 = 0.5

P(A|B) = P(A and B) / P(B)

Example: deck of cards
  P(King | Face card) = P(King and Face card) / P(Face card)
                      = (4/52) / (12/52)
                      = 4/12 = 1/3

PMF: P(X = k)

Fair die:
  P(X = 1) = 1/6
  P(X = 2) = 1/6
  ...
  P(X = 6) = 1/6

  Sum of all probabilities = 1

PDF: f(x)

P(a <= X <= b) = integral of f(x) from a to b

f(x) can be greater than 1 (density, not probability)
integral from -inf to +inf of f(x) dx = 1

f(x) = (1 / sqrt(2*pi*sigma^2)) * exp(-(x - mu)^2 / (2*sigma^2))

Standard normal: mu = 0, sigma = 1
  68% of data within 1 sigma
  95% within 2 sigma
  99.7% within 3 sigma

Roll 1 die:  uniform distribution (flat)
Average of 2 dice:  triangular (peaked)
Average of 30 dice: nearly perfect bell curve

This works for ANY starting distribution with finite variance.

softmax(z_i) = exp(z_i) / sum(exp(z_j) for all j)

Properties:
  - All outputs are in (0, 1)
  - All outputs sum to 1
  - Preserves relative ordering of inputs
  - exp() amplifies differences between logits

z = [100, 101, 102]
exp(102) = overflow

z_shifted = z - max(z) = [-2, -1, 0]
exp(0) = 1  (safe)

Same result, no overflow.

import math
import random

def factorial(n):
    result = 1
    for i in range(2, n + 1):
        result *= i
    return result

def combinations(n, k):
    return factorial(n) // (factorial(k) * factorial(n - k))

def conditional_probability(p_a_and_b, p_b):
    return p_a_and_b / p_b

p_king_given_face = conditional_probability(4/52, 12/52)
print(f"P(King | Face card) = {p_king_given_face:.4f}")

def bernoulli_pmf(k, p):
    return p if k == 1 else (1 - p)

def categorical_pmf(k, probs):
    return probs[k]

def poisson_pmf(k, lam):
    return (lam ** k) * math.exp(-lam) / factorial(k)

def uniform_pdf(x, a, b):
    if a <= x <= b:
        return 1.0 / (b - a)
    return 0.0

def normal_pdf(x, mu, sigma):
    coeff = 1.0 / (sigma * math.sqrt(2 * math.pi))
    exponent = -0.5 * ((x - mu) / sigma) ** 2
    return coeff * math.exp(exponent)

def expected_value(values, probabilities):
    return sum(v * p for v, p in zip(values, probabilities))

def variance(values, probabilities):
    mu = expected_value(values, probabilities)
    return sum(p * (v - mu) ** 2 for v, p in zip(values, probabilities))

die_values = [1, 2, 3, 4, 5, 6]
die_probs = [1/6] * 6
mu = expected_value(die_values, die_probs)
var = variance(die_values, die_probs)
print(f"Die: E[X] = {mu:.4f}, Var(X) = {var:.4f}, SD = {var**0.5:.4f}")

def sample_bernoulli(p, n=1):
    return [1 if random.random() < p else 0 for _ in range(n)]

def sample_categorical(probs, n=1):
    cumulative = []
    total = 0
    for p in probs:
        total += p
        cumulative.append(total)
    samples = []
    for _ in range(n):
        r = random.random()
        for i, c in enumerate(cumulative):
            if r <= c:
                samples.append(i)
                break
    return samples

def sample_normal_box_muller(mu, sigma, n=1):
    samples = []
    for _ in range(n):
        u1 = random.random()
        u2 = random.random()
        z = math.sqrt(-2 * math.log(u1)) * math.cos(2 * math.pi * u2)
        samples.append(mu + sigma * z)
    return samples

def softmax(logits):
    max_logit = max(logits)
    shifted = [z - max_logit for z in logits]
    exps = [math.exp(z) for z in shifted]
    total = sum(exps)
    return [e / total for e in exps]

def log_softmax(logits):
    max_logit = max(logits)
    shifted = [z - max_logit for z in logits]
    log_sum_exp = max_logit + math.log(sum(math.exp(z) for z in shifted))
    return [z - log_sum_exp for z in logits]

def cross_entropy_loss(logits, target_index):
    log_probs = log_softmax(logits)
    return -log_probs[target_index]

def demonstrate_clt(dist_fn, n_samples, n_averages):
    averages = []
    for _ in range(n_averages):
        samples = [dist_fn() for _ in range(n_samples)]
        averages.append(sum(samples) / len(samples))
    return averages

import matplotlib.pyplot as plt

xs = [mu + sigma * (i - 500) / 100 for i in range(1001)]
ys = [normal_pdf(x, mu, sigma) for x, mu, sigma in ...]
plt.plot(xs, ys)

import numpy as np
from scipy import stats

normal = stats.norm(loc=0, scale=1)
samples = normal.rvs(size=10000)
print(f"Mean: {np.mean(samples):.4f}, Std: {np.std(samples):.4f}")
print(f"P(X < 1.96) = {normal.cdf(1.96):.4f}")

logits = np.array([2.0, 1.0, 0.1])
from scipy.special import softmax, log_softmax
probs = softmax(logits)
log_probs = log_softmax(logits)
print(f"Softmax: {probs}")
print(f"Log-softmax: {log_probs}")