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

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

# In[4]:


get_ipython().system('pip install yfinance')


# In[5]:


# Importing the modules
import yfinance as yf
import pandas as pd
import numpy as np 
import math
import matplotlib.pyplot as plt


# In[8]:


dataset = yf.download("TSLA", start="2017-01-01", end="2022-05-19")
dataset


# In[9]:


dataset.info()


# In[11]:


(dataset['Adj Close'] / dataset['Adj Close'].iloc[0] * 100).plot(figsize = (15, 6));
plt.show()


# #Let's do the multiple stocks.

# In[17]:


tickers = ['SBUX', 'WMT', 'AMZN', 'HD']
mydata = pd.DataFrame()
for t in tickers:
    mydata[t] = yf.download(t, start="2000-01-01", end="2022-05-31")['Adj Close']


# In[18]:


mydata.head()


# In[ ]:





# In[19]:


mydata.plot(figsize=(10, 12), subplots=True);  


# In[20]:


mydata.describe().round(2)  


# In[27]:


mydata.pct_change().describe().round(4) 


# In[28]:


mydata.pct_change().mean().plot(kind='bar', figsize=(10, 6));  


# In[29]:


mydata.pct_change().std().plot(kind='bar', figsize=(10, 6));  


# In[33]:


ret = np.log(mydata / mydata.shift(1))  
ret.describe()


# In[34]:


ret.mean().plot(kind='bar', figsize=(10, 6));  


# In[35]:


ret.std().plot(kind='bar', figsize=(10, 6));  


# In[36]:


ret.cumsum().apply(np.exp).plot(figsize=(10, 6));  


# In[37]:


ret.dropna(inplace=True)


# In[39]:


ret.plot(subplots=True, figsize=(10, 12));


# In[41]:


ret.plot(subplots=False, figsize=(15, 10));


# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# In[ ]:





# ### Oops! AMZN was not a public firm in 1995. Let's choose another one instead.

# In[42]:


tickers = ['SBUX', 'WMT', 'ORCL', 'HD']
mydata = pd.DataFrame()
for t in tickers:
    mydata[t] = yf.download(t, start="1995-01-01", end="2020-12-31")['Adj Close']


# In[43]:


mydata


# ### What if we invest $1 in 1995?

# In[44]:


(mydata / mydata.iloc[0] * 1)


# ### What if we invest $100?

# In[45]:


(mydata / mydata.iloc[0] * 100).plot(figsize = (15, 6));
plt.show()


# In[ ]:





# In[ ]:





# In[46]:


tickers = ['SBUX', 'WMT', 'ORCL', 'HD']
mydata = pd.DataFrame()
for t in tickers:
    mydata[t] = yf.download(t, start="2000-01-01", end="2020-12-31", interval="1wk")['Adj Close']


# In[47]:


mydata["HD"].pct_change().plot.hist(alpha=0.9, bins=50)


# In[ ]:





# In[48]:


tickers = ['SBUX', 'WMT', 'ORCL', 'HD']
mydata = pd.DataFrame()
for t in tickers:
    mydata[t] = yf.download(t, start="2000-01-01", end="2020-12-31", interval="1d")['Adj Close']


# In[49]:


mydata


# ### resmaple of Pandas ###
# https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases

# In[50]:


mydata_m=mydata.resample('BM').last()
mydata_m


# In[51]:


returns=mydata_m.pct_change()


# In[52]:


returns


# In[53]:


returns2=returns.dropna()


# In[54]:


returns2


# In[55]:


sbux_stock = returns2["SBUX"]


# In[56]:


sbux_stock


# In[57]:


plt.hist(sbux_stock,bins=25)


# In[58]:


p=np.percentile(sbux_stock, 50)
p


# In[59]:


sbux_stock.median()


# In[60]:


p=np.percentile(sbux_stock, 95)
p


# In[ ]: