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

# In[6]:


# !pip install yfinance # uncomment these to install missing packages if they are not already installed
# !pip install pandas 

import yfinance as yf
import pandas as pd

def get_price(tick,start='2022-10-01',end=None):
    return yf.Ticker(tick).history(start=start,end=end)['Close']

def get_prices(tickers,start='2022-10-01',end=None):
    df=pd.DataFrame()
    for s in tickers:
        df[s]=get_price(s,start,end)
    return df


# # Prepare training and testing data sets

# In[2]:


feature_stocks=['tsla','meta','twtr','amzn','nflx','gbtc','gdx','intc','dal','c']
predict_stock='msft'

# training set
start_date_train='2022-10-01'
end_date_train='2022-12-31'

X_train=get_prices(feature_stocks,start=start_date_train,end=end_date_train)
y_train=get_prices([predict_stock],start=start_date_train,end=end_date_train)

# testing set
start_date_test='2023-01-01' # end date omit, default is doday
X_test=get_prices(feature_stocks,start=start_date_test)
y_test=get_prices([predict_stock],start=start_date_test)


# In[4]:


X_train


# In[5]:


y_train


# # Convert training and testing data into numpy array

# In[ ]:


import numpy as np

X_train=np.array(X_train)
y_train=np.array(y_train)
X_test=np.array(X_test)
y_test=np.array(y_test)


# # Use linear regression to predict msft stock price from the other stocks' prices 

# ## 1. Append a dummy feature to both X_train and X_test

# In[ ]:


# Your solution here


# ## 2. Find the best linear regression model based on your training data ($w=(X X')^{-1} X y$)
# ### Note that you may need to transpose the matrices to make things work
# 
# 

# In[ ]:


# Your solution here


# ## 3. Report your training and testing error
# ### How far your prediction from the actual price. Compute the mean square error for both training and testing

# In[ ]:


# Your solution here


# In[ ]:





# In[ ]: