import numpy as np
import matplotlib.pyplot as plt

import torch
from torch import nn # 'n'eural 'n'etworks <- PyTorch's building blocks for neural networks

torch.__version__

1. Preparing the dataset

torch.arange(0, 1, 0.02) # array of range 

tensor([0.0000, 0.0200, 0.0400, 0.0600, 0.0800, 0.1000, 0.1200, 0.1400, 0.1600, 0.1800, 0.2000, 0.2200, 0.2400, 0.2600, 0.2800, 0.3000, 0.3200, 0.3400, 0.3600, 0.3800, 0.4000, 0.4200, 0.4400, 0.4600, 0.4800, 0.5000, 0.5200, 0.5400, 0.5600, 0.5800, 0.6000, 0.6200, 0.6400, 0.6600, 0.6800, 0.7000, 0.7200, 0.7400, 0.7600, 0.7800, 0.8000, 0.8200, 0.8400, 0.8600, 0.8800, 0.9000, 0.9200, 0.9400, 0.9600, 0.9800])

torch.arange(0, 1, 0.02).reshape(-1, 1) #.shape # 모양을 다시 바꾸다 (like numpy)

torch.arange(0, 1, 0.02).unsqueeze(dim=1) #.shape # index 번호 기준 1번 위치의 차원(2번째 차원)으로 1개 차원을 추가

torch.Size([50, 1])

X = torch.arange(0, 1, 0.02).reshape(-1, 1)

weight = 0.7 # <- 모델이 Gradient descent로 찾아낼 parameter 
bias = 0.3   # <- 모델이 Gradient descent로 찾아낼 parameter 

y = weight * X + bias

print(X[:5])
print(y[:5])

tensor([[0.0000], [0.0200], [0.0400], [0.0600], [0.0800]]) tensor([[0.3000], [0.3140], [0.3280], [0.3420], [0.3560]])

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, 
                                                    y, 
                                                    test_size=0.3, 
                                                    random_state=42) 

def scatter_predictions(X_train=X_train, y_train=y_train, 
                        X_test=X_test, y_test=y_test, 
                        y_predicted=None):
    
    plt.figure(figsize=(10, 7), dpi=100) # figure size & dot per inch

    # train data
    plt.scatter(X_train, y_train, c="black", s=3, label="Train data") # 산점도 (Scatter plots)

    # test data
    plt.scatter(X_test, y_test, c="blue", s=10, label="Test data")

    if y_predicted is not None:
        plt.scatter(X_test, y_predicted, c="red", s=20, label="Predictions")

    plt.legend(prop={"size": 14})

scatter_predictions(X_train, y_train, X_test, y_test)

2. Build the model (Linear Regression)