[PyTorch] Logistic Regression[미완성]

Logistic Regression

sklearn libaray의 dataset을 기준으로 코드를 작성하고 연습을 진행하였다.

Linear Regression이 예측 모델이라면,

Logistic Regression은 분류 모델이다.

큰 흐름을 말하자면,

1. Dataset and Data Preprocessing

2. Model Declaration and Initialization.

3. Cost function Declaration and Gradient(Optimizer) Declaration

4. Training

5. Visualization

아직 다듬을게 많다.

import torch
import torch.nn as nn
import numpy as np
from sklearn import datasets
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split

import matplotlib.pyplot as plt

# Prepare data
bc = datasets.load_breast_cancer()
x, y = bc.data, bc.target

dir(bc)

['DESCR',
 'data',
 'data_module',
 'feature_names',
 'filename',
 'frame',
 'target',
 'target_names']

bc.data.shape

(569, 30)

bc.feature_names

array(['mean radius', 'mean texture', 'mean perimeter', 'mean area',
       'mean smoothness', 'mean compactness', 'mean concavity',
       'mean concave points', 'mean symmetry', 'mean fractal dimension',
       'radius error', 'texture error', 'perimeter error', 'area error',
       'smoothness error', 'compactness error', 'concavity error',
       'concave points error', 'symmetry error',
       'fractal dimension error', 'worst radius', 'worst texture',
       'worst perimeter', 'worst area', 'worst smoothness',
       'worst compactness', 'worst concavity', 'worst concave points',
       'worst symmetry', 'worst fractal dimension'], dtype='<U23')

bc.target_names

array(['malignant', 'benign'], dtype='<U9')

bc.target

array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,
       0, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0,
       1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0,
       1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 1,
       1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 0,
       0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 1, 1,
       1, 0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0,
       0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0,
       1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1,
       1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0,
       0, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0,
       0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0,
       1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1,
       1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 1,
       1, 0, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0,
       1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1,
       1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 1, 1,
       1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1])

n_samples, n_features = x.shape

n_samples, n_features

(569, 30)

x_train, x_test, y_train, y_test = train_test_split(x,y,test_size=0.2, random_state=42)

x_train

array([[9.029e+00, 1.733e+01, 5.879e+01, ..., 1.750e-01, 4.228e-01,
        1.175e-01],
       [2.109e+01, 2.657e+01, 1.427e+02, ..., 2.903e-01, 4.098e-01,
        1.284e-01],
       [9.173e+00, 1.386e+01, 5.920e+01, ..., 5.087e-02, 3.282e-01,
        8.490e-02],
       ...,
       [1.429e+01, 1.682e+01, 9.030e+01, ..., 3.333e-02, 2.458e-01,
        6.120e-02],
       [1.398e+01, 1.962e+01, 9.112e+01, ..., 1.827e-01, 3.179e-01,
        1.055e-01],
       [1.218e+01, 2.052e+01, 7.722e+01, ..., 7.431e-02, 2.694e-01,
        6.878e-02]])

# scale
sc = StandardScaler()
x_train = sc.fit_transform(x_train)
x_test = sc.transform(x_test)

x_train = torch.from_numpy(x_train.astype(np.float32))
x_test = torch.from_numpy(x_test.astype(np.float32))
y_train = torch.from_numpy(y_train.astype(np.float32))
y_test = torch.from_numpy(y_test.astype(np.float32))

y_train = y_train.view(y_train.shape[0], 1)
y_test = y_test.view(y_test.shape[0], 1)

# model
# f = wx * b, sigmoid at the end

class LogisticRegression(nn.Module):
  def __init__(self, input_features):
    super(LogisticRegression, self).__init__()
    self.linear = nn.Linear(input_features, 1)

  def forward(self, x):
    y_pred = torch.sigmoid(self.linear(x))
    return y_pred
  
model = LogisticRegression(n_features)

criterion = nn.BCELoss()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# training loop

epochs = 100
for epoch in range(epochs):
  # forward pass and loss
  y_pred = model(x_train)
  loss = criterion(y_pred, y_train)

  # backward pass
  loss.backward()

  # update
  optimizer.step()

  optimizer.zero_grad()

  if (epoch + 1) % 10 == 0:
    print(f"epoch = {epoch+1} loss = {loss.item():.4f} ")

epoch = 10 loss = 0.5061 
epoch = 20 loss = 0.4237 
epoch = 30 loss = 0.3709 
epoch = 40 loss = 0.3341 
epoch = 50 loss = 0.3070 
epoch = 60 loss = 0.2862 
epoch = 70 loss = 0.2695 
epoch = 80 loss = 0.2559 
epoch = 90 loss = 0.2445 
epoch = 100 loss = 0.2348 

with torch.no_grad():
  y_pred = model(x_test)
  y_pred_cls = y_pred.round()
  acc = y_pred_cls.eq(y_test).sum() / float(y_test.shape[0])
  print(f"accuracy = {acc:.4f}")

accuracy = 0.9561

y_test.shape, y_pred_cls.shape, y_pred.shape

(torch.Size([114, 1]), torch.Size([114, 1]), torch.Size([114, 1]))

# plt.plot(y_pred_cls, y_test)
plt.plot(x_test, y_pred_cls, 'ro', alpha=0.3)
# plt.scatter(x_test, y_pred_cls, color='green', marker='o', markersize=10, alpha=0.5)
plt.plot(x_test, y_test, 'bo', alpha=0.1)

# plt.scatter(x=y_test, y=y_pred_cls, c='blueviolet', alpha=0.5)
# plt.plot(x_train, y_train, 'ro')
# plt.plot(x_train, y_train, 'bo')

# plt.plot(y_pred_cls, x_test, 'ro')
# plt.plot(y_test, x_test, 'bo')


plt.show()