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

# <a href="https://colab.research.google.com/github/cyrus723/my-first-binder/blob/main/CAPM_Capital_Asset_Pricing_Model1.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>

# # CAPM - Capital Asset Pricing Model 

# In[1]:


pip install yfinance


# In[2]:


import yfinance as yf
import pandas as pd
import numpy as np
import statsmodels.api as sm   
import datetime as dt

import urllib.request       # handle online files
import zipfile            
import os                

import statsmodels.formula.api as smf
import statsmodels.api as sm
from scipy import stats
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression

import matplotlib.pyplot as plt
from pylab import mpl, plt

plt.style.use('seaborn')
mpl.rcParams['font.family'] = 'DejaVu Sans'
mpl.rcParams["savefig.dpi"] = 500
np.set_printoptions(precision=5, suppress=True, formatter={"float": lambda x: f"{x:6.3f}"})

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


# In[ ]:


#help(stats.linregress)


# In[3]:


def get_prices(tickers, freq_p, st_day, end_day):
    mystock = pd.DataFrame()
    for t in tickers:
        mystock[t] = yf.download(t, start=st_day, end=end_day, interval=freq_p)['Adj Close']
    return mystock


# In[4]:


tic=['TSLA', 'SPY']
prices= get_prices(tic, freq_p='1wk', st_day="2011-01-01", end_day="2022-05-31")  # id , 1wk, 1mo
print(prices)

prices.rename(columns={"TSLA": "Your_Stock", "SPY":"INDEX"}, inplace=True)

prices.info()
prices.tail(20)


# In[5]:


print(prices.isnull().sum())
prices.dropna(how='any', inplace=True)
print(prices.isnull().sum())
prices.info()
print(prices)


# In[6]:


prices.plot(figsize=(10,6))
plt.legend()


# In[7]:


(prices / prices.iloc[0] * 1).plot(figsize=(10, 6), subplots=False)  #cumulative returns
plt.title('Cumulative Return')
plt.tight_layout()


# In[8]:


prices.pct_change(1).dropna()
plt.scatter(prices['Your_Stock'], prices['INDEX'], color = 'red', alpha=0.2)


# In[9]:


returns = prices.pct_change(1).dropna()

plt.hist(returns['INDEX'], label='INDEX', bins=100) 
plt.hist(returns['Your_Stock'], label='Stock', bins=100)
  
plt.legend(loc='upper right')
plt.title('Overlapping')
plt.show()


# In[10]:


returns


# #using scipy

# In[11]:


beta,alpha,r_value,p_value,std_err = stats.linregress(returns['INDEX'],returns["Your_Stock"])


# In[12]:


print(beta.round(4))
print(alpha.round(4))
print(r_value.round(2))
print(p_value.round(4))


# #using statsmodels

# In[13]:


formula = 'Your_Stock ~ INDEX'
results = smf.ols(formula, returns).fit()
print(results.summary())


# #using scikit-learn
# You need to take a look at the shape of the data you are feeding into .fit().
# 
# Here x.shape = (10,) but we need it to be (10, 1), see sklearn. Same goes for y. So we reshape:

# In[14]:


X = returns.loc[:, ['INDEX']].values


# In[15]:


y = returns.loc[:, ['Your_Stock']].values


# In[16]:


X.shape


# In[17]:


type(X)


# In[18]:


X.dtype


# In[19]:


y.shape


# In[20]:


reg = LinearRegression(fit_intercept=True).fit(X,y)


# In[21]:


reg.predict(X[0].reshape(-1,1))


# In[22]:


reg.predict(X[0:10])


# In[23]:


score = reg.score(X, y)
print(score)


# In[24]:


reg.coef_


# In[25]:


reg.intercept_


# In[26]:


m = reg.coef_[0,0]
b = reg.intercept_[0]


# In[27]:


m


# In[28]:


b


# In[29]:


# following slope intercept form 
print("formula: y = {:.4f}X + {:.4f}".format(m, b) )


# In[30]:


from numpy.ma.core import flatten_structured_array
fig, ax = plt.subplots(nrows = 1, ncols = 1, figsize = (10,7));

ax.scatter(X, y, color='blue', s=10);
ax.plot(X, reg.predict(X), color='red',linewidth=2);
ax.grid(True,
        axis = 'both',
        zorder = 0,
        linestyle = ':',
        color = 'y')
ax.tick_params(labelsize = 20)
ax.set_xlabel('INDEX', fontsize = 24)
ax.set_ylabel('Your_Stock', fontsize = 24)
ax.set_title("Linear Regression Line with Intercept y = {:.4f} + {:.4f}x (R2 = {:.2f})".format(b, m, score), fontsize = 16 )
fig.tight_layout()
#fig.savefig('images/linearregression', dpi = 300)