iris classification with ZERO SCIKIT_LEARN

wisepine·2021년 4월 4일
0

AI

목록 보기
3/3
post-thumbnail

hands-on 서적을 참고한 글입니다.

목표

  • 사이킷런 (scikit-learn) 을 사용하지 않고
  • softmax로 붓꽃 분류를 해보자.
    (데이터셋 임포트를 위한 sklearn 사용은 제외)

github 바로가기
colab 바로가기


1. import

import numpy as np
from sklearn import datasets

iris = datasets.load_iris()
list(iris.keys())

X = iris["data"][:, (2,3)] # length, width
y = iris["target"]
X_with_bias = np.c_[np.ones([len(X),1]), X]
  • 편향 특성을 추가한다. (1로 초기화)
np.random.seed(2042)

2. train & test split

  • sklearn의 train_test_split 기능을 구현한다.
test_ratio = 0.2
validation_ratio = 0.2
total_size = len(X_with_bias)

test_size = int(total_size * test_ratio)
validation_size = int(total_size * validation_ratio)
train_size = total_size - test_size - validation_size

rnd_indices = np.random.permutation(total_size)

X_train = X_with_bias[rnd_indices[:train_size]]
y_train = y[rnd_indices[:train_size]]
X_valid = X_with_bias[rnd_indices[train_size:-test_size]]
y_valid = y[rnd_indices[train_size:-test_size]]
X_test = X_with_bias[rnd_indices[-test_size:]]
y_test = y[rnd_indices[-test_size:]]

3. one hot encoding

  • sklearn의 OneHotEncoder 기능을 구현한다.
def to_one_hot(y):
  n_classes = y.max() + 1
  m = len(y)
  Y_one_hot = np.zeros((m, n_classes))
  Y_one_hot[np.arange(m), y] = 1
  return Y_one_hot
y_train[:10]

to_one_hot(y_train[:10])

Y_train_one_hot = to_one_hot(y_train)
Y_valid_one_hot = to_one_hot(y_valid)
Y_test_one_hot = to_one_hot(y_test)

4. softmax

def softmax(logits):
  exps = np.exp(logits)
  exp_sums = np.sum(exps, axis=1, keepdims=True)
  return exps / exp_sums
n_inputs = X_train.shape[1] # 2 features and bias ( == 3 )
n_outputs = len(np.unique(y_train)) # 3 iris classes ( == 3)

Cost function

J(Θ)=1mi=1mk=1Kyk(i)log(p^k(i))J(\boldsymbol{\Theta}) = - \dfrac{1}{m}\sum\limits_{i=1}^{m}\sum\limits_{k=1}^{K}{y_k^{(i)}\log\left(\hat{p}_k^{(i)}\right)}

Gradient function

θ(k)J(Θ)=1mi=1m(p^k(i)yk(i))x(i)\nabla_{\boldsymbol{\theta}^{(k)}} \, J(\boldsymbol{\Theta}) = \dfrac{1}{m} \sum\limits_{i=1}^{m}{ \left ( \hat{p}^{(i)}_k - y_k^{(i)} \right ) \mathbf{x}^{(i)}}

eta = 0.01
n_iterations = 5001
m = len(X_train)
epsilon = 1e-7 # avoid nan (ex. log(0))

theta = np.random.randn(n_inputs, n_outputs)

for iteration in range(n_iterations):
  logits = X_train.dot(theta) # softmax score
  Y_proba = softmax(logits)
  if iteration % 500 == 0:
    loss = -np.mean(np.sum(Y_train_one_hot * np.log(Y_proba + epsilon), axis=1))
    print(iteration, loss)
  error = Y_proba - Y_train_one_hot
  gradients = 1/m * X_train.T.dot(error)
  theta = theta - eta * gradients

theta

logits = X_valid.dot(theta)
y_proba = softmax(logits)
y_predict = np.argmax(y_proba, axis=1)

accuracy_score = np.mean(y_predict == y_valid)
accuracy_score

5. early stopping

eta = 0.1
n_iterations = 5001
m = len(X_train)
epsilon = 1e-7
alpha = 0.1
best_loss = np.infty

theta = np.random.randn(n_inputs, n_outputs)

for iteration in range(n_iterations):
  logits = X_train.dot(theta)
  Y_proba = softmax(logits)
  error = Y_proba - Y_train_one_hot
  gradients = 1/m * X_train.T.dot(error) + np.r_[np.zeros([1, n_outputs]), alpha * theta[1:]]
  theta = theta - eta * gradients

  # caculate loss using validation set
  logits = X_valid.dot(theta)
  Y_proba = softmax(logits)
  xentropy_loss = -np.mean(np.sum(Y_valid_one_hot * np.log(Y_proba + epsilon), axis=1))
  l2_loss = 1/2 * np.sum(np.square(theta[1:]))  # Ridge regularization
  loss = xentropy_loss + alpha * l2_loss

  if iteration % 500 == 0:
    print(iteration, loss)
  if loss < best_loss:
    best_loss = loss
  else:
    print(iteration - 1, best_loss)
    print(iteration, loss, "early stopped")
    break

logits = X_valid.dot(theta)
Y_proba = softmax(logits)
y_predict = np.argmax(Y_proba, axis=1)

accuracy_score = np.mean(y_predict == y_valid)
accuracy_score

x0, x1 = np.meshgrid(
    np.linspace(0, 8, 500).reshape(-1, 1),
    np.linspace(0, 3.5, 200).reshape(-1, 1)
)
X_new = np.c_[x0.ravel(), x1.ravel()]
X_new_with_bias = np.c_[np.ones([len(X_new), 1]), X_new]

logits = X_new_with_bias.dot(theta)
Y_proba = softmax(logits)
y_predict = np.argmax(Y_proba, axis=1)

zz1 = Y_proba[:, 1].reshape(x0.shape)
zz = y_predict.reshape(x0.shape)

import matplotlib.pyplot as plt

plt.figure(figsize=(10, 4))
plt.plot(X[y==2, 0], X[y==2, 1], "g^", label="Iris virginica")
plt.plot(X[y==1, 0], X[y==1, 1], "bs", label="Iris versicolor")
plt.plot(X[y==0, 0], X[y==0, 1], "yo", label="Iris setosa")

from matplotlib.colors import ListedColormap
custom_cmap = ListedColormap(['#fafab0','#9898ff','#a0faa0'])

plt.contourf(x0, x1, zz, cmap=custom_cmap)
contour = plt.contour(x0, x1, zz1, cmap=plt.cm.brg)
plt.clabel(contour, inline=1, fontsize=12)
plt.xlabel("Petal length", fontsize=14)
plt.ylabel("Petal width", fontsize=14)
plt.legend(loc="upper left", fontsize=14)
plt.axis([0, 7, 0, 3.5])
plt.show()

logits = X_test.dot(theta)
Y_proba = softmax(logits)
y_predict = np.argmax(Y_proba, axis=1)

accuracy_score = np.mean(y_predict == y_test)
accuracy_score

profile
배운거 아카이빙하는 곳

0개의 댓글