एक साफ़-सुथरा एक्सपेरिमेंट डिज़ाइन करना

import math
import random
import statistics


def make_data(rng, n=400, noise=1.2):
    """Two overlapping clouds of points. Label 1 sits up and right."""
    rows = []
    for _ in range(n):
        y = rng.randint(0, 1)
        c = 1.0 if y == 1 else -1.0
        rows.append(((rng.gauss(c, noise), rng.gauss(0.5 * c, noise)), y))
    return rows


def split(rows, rng):
    rows = rows[:]
    rng.shuffle(rows)
    a, b = int(0.6 * len(rows)), int(0.8 * len(rows))
    return rows[:a], rows[a:b], rows[b:]   # train, validation, test


def train_logreg(train, rng, lr, epochs=20):
    w1, w2, bias = rng.gauss(0, 0.1), rng.gauss(0, 0.1), 0.0
    train = train[:]
    for _ in range(epochs):
        rng.shuffle(train)
        for (x1, x2), y in train:
            z = max(-30.0, min(30.0, w1 * x1 + w2 * x2 + bias))
            g = 1 / (1 + math.exp(-z)) - y
            w1, w2, bias = w1 - lr * g * x1, w2 - lr * g * x2, bias - lr * g
    return lambda x: 1 if w1 * x[0] + w2 * x[1] + bias > 0 else 0


def majority_baseline(train):
    guess = 1 if 2 * sum(y for _, y in train) >= len(train) else 0
    return lambda x: guess


def accuracy(model, rows):
    return sum(model(x) == y for x, y in rows) / len(rows)


def run_once(seed):
    rng = random.Random(seed)
    train, val, test = split(make_data(rng), rng)
    # Choose the learning rate on VALIDATION data only.
    best_lr = max([0.001, 0.01, 0.1],
                  key=lambda lr: accuracy(train_logreg(train, random.Random(seed), lr), val))
    model = train_logreg(train, random.Random(seed), best_lr)
    # Touch the TEST set once, at the very end.
    return accuracy(majority_baseline(train), test), accuracy(model, test), best_lr


SEEDS = [0, 1, 2, 3, 4]
base, ours = [], []
for s in SEEDS:
    b, m, lr = run_once(s)
    base.append(b)
    ours.append(m)
    print(f"seed {s}: baseline {b:.3f}  model {m:.3f}  (lr chosen on val: {lr})")

print(f"baseline: {statistics.mean(base):.3f} +/- {statistics.stdev(base):.3f}")
print(f"model:    {statistics.mean(ours):.3f} +/- {statistics.stdev(ours):.3f}")
print(f"runs per setting: {len(SEEDS)} (std is the sample standard deviation)")