#!/usr/bin/env python
# coding: utf-8

# In[1]:


import torch
import numpy as np
import matplotlib.pyplot as plt


# In[2]:


torch.__version__


# In[3]:


get_ipython().run_line_magic('matplotlib', 'inline')


# In[4]:


study = [1,2,3]
grade = [2,4,6]


# In[5]:


study = torch.tensor(study, dtype=torch.float)
grade = torch.tensor(grade, dtype = torch.float)


# In[6]:


w = torch.tensor([np.random.rand()], requires_grad=True, dtype=torch.float)
w


# In[7]:


def forward(x):
    return x *w


# In[8]:


def loss(x,y):
    y_pred = forward(x)
    return (y_pred - y)**2


# In[9]:


forward(2)


# In[10]:


epoch_list = []
loss_list = []


# In[11]:


epoch = 30
lr = 0.01
for i in range(epoch):
    l = 0
    for x,y in zip(study,grade):
        y_pred = forward(x)
        loss_val = loss(x,y)
        loss_val.backward()
        with torch.no_grad():
            w -= lr * w.grad
            w.grad.zero_()
        l += loss_val.item()
    epoch_list.append(i)
    loss_list.append(l/3)


# In[12]:


plt.plot(epoch_list, loss_list)