[딥러닝] Pytorch binary_Classification 이진분류 예측모델 템플릿

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

from sklearn.preprocessing import StandardScaler

df = pd.read_csv("경로/경로/파일명.csv")
df

target = df[['']].copy()
data = df.copy()

del data['']

 

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

data = torch.from_numpy(df.values).float()

data.shape

데이터와 target의 분류

x = data[:,:-]
y = data[:,:]

print(x.shape, y.shape)

 

Train / Valid / Test ratio 분리 비율 결정

ratios = [.6, .2, .2]

train_cnt = int(data.size(0) * ratios[0])
valid_cnt = int(data.size(0) * ratios[1])
test_cnt = data.size(0) - train_cnt - valid_cnt
cnts = [train_cnt, valid_cnt, test_cnt]

print("Train %d / Valid %d / Test %d samples." % (train_cnt, valid_cnt, test_cnt))

indices = torch.randperm(data.size(0))

x = torch.index_select(x, dim=0, index=indices)
y = torch.index_select(y, dim=0, index=indices)

x = x.split(cnts, dim=0)
y = y.split(cnts, dim=0)

for x_i, y_i in zip(x, y):
    print(x_i.size(), y_i.size())

scaler = StandardScaler()
scaler.fit(x[0].numpy())

x = [torch.from_numpy(scaler.transform(x[0].numpy())).float(),
     torch.from_numpy(scaler.transform(x[1].numpy())).float(),
     torch.from_numpy(scaler.transform(x[2].numpy())).float()]

df = pd.DataFrame(x[0].numpy(), columns=cancer.feature_names)
df.tail()

모델 설정

model = nn.Sequential(
    nn.Linear(x[0].size(-1), 25),
    nn.LeakyReLU(),
    nn.Linear(25, 20),
    nn.LeakyReLU(),
    nn.Linear(20, 15),
    nn.LeakyReLU(),
    nn.Linear(15, 10),
    nn.LeakyReLU(),
    nn.Linear(10, 5),
    nn.LeakyReLU(),
    nn.Linear(5, y[0].size(-1)),
    nn.Sigmoid(),
)

model

optimizer = optim.Adam(model.parameters())

n_epochs = 10000
batch_size = 32
print_interval = 100
early_stop = 1000

from copy import deepcopy

lowest_loss = np.inf
best_model = None

lowest_epoch = np.inf

train_history, valid_history = [], []

for i in range(n_epochs):
    indices = torch.randperm(x[0].size(0))
    x_ = torch.index_select(x[0], dim=0, index=indices)
    y_ = torch.index_select(y[0], dim=0, index=indices)
    
    x_ = x_.split(batch_size, dim=0)
    y_ = y_.split(batch_size, dim=0)
    
    train_loss, valid_loss = 0, 0
    y_hat = []
    
    for x_i, y_i in zip(x_, y_):
        y_hat_i = model(x_i)
        loss = F.binary_cross_entropy(y_hat_i, y_i)

        optimizer.zero_grad()
        loss.backward()

        optimizer.step()        
        train_loss += float(loss) # This is very important to prevent memory leak.

    train_loss = train_loss / len(x_)
        
    with torch.no_grad():
        x_ = x[1].split(batch_size, dim=0)
        y_ = y[1].split(batch_size, dim=0)
        
        valid_loss = 0
        
        for x_i, y_i in zip(x_, y_):
            y_hat_i = model(x_i)
            loss = F.binary_cross_entropy(y_hat_i, y_i)
            
            valid_loss += float(loss)
            
            y_hat += [y_hat_i]
            
    valid_loss = valid_loss / len(x_)
    
    train_history += [train_loss]
    valid_history += [valid_loss]
        
    if (i + 1) % print_interval == 0:
        print('Epoch %d: train loss=%.4e  valid_loss=%.4e  lowest_loss=%.4e' % (
            i + 1,
            train_loss,
            valid_loss,
            lowest_loss,
        ))
        
    if valid_loss <= lowest_loss:
        lowest_loss = valid_loss
        lowest_epoch = i
        
        best_model = deepcopy(model.state_dict())
    else:
        if early_stop > 0 and lowest_epoch + early_stop < i + 1:
            print("There is no improvement during last %d epochs." % early_stop)
            break

print("The best validation loss from epoch %d: %.4e" % (lowest_epoch + 1, lowest_loss))
model.load_state_dict(best_model)

시각화

plot_from = 2

plt.figure(figsize=(20, 10))
plt.grid(True)
plt.title("Train / Valid Loss History")
plt.plot(
    range(plot_from, len(train_history)), train_history[plot_from:],
    range(plot_from, len(valid_history)), valid_history[plot_from:],
)
plt.yscale('log')
plt.show()

결과보기

test_loss = 0
y_hat = []

with torch.no_grad():
    x_ = x[2].split(batch_size, dim=0)
    y_ = y[2].split(batch_size, dim=0)

    for x_i, y_i in zip(x_, y_):
        y_hat_i = model(x_i)
        loss = F.binary_cross_entropy(y_hat_i, y_i)

        test_loss += loss # Gradient is already detached.

        y_hat += [y_hat_i]

test_loss = test_loss / len(x_)
y_hat = torch.cat(y_hat, dim=0)

print("Test loss: %.4e" % test_loss)

correct_cnt = (y[2] == (y_hat > .5)).sum()
total_cnt = float(y[2].size(0))

print('Test Accuracy: %.4f' % (correct_cnt / total_cnt))

df = pd.DataFrame(torch.cat([y[2], y_hat], dim=1).detach().numpy(),
                  columns=["y", "y_hat"])

sns.histplot(df, x='y_hat', hue='y', bins=50, stat='probability')
plt.show()

from sklearn.metrics import roc_auc_score

roc_auc_score(df.values[:, 0], df.values[:, 1])