In [1]:
import pandas as pd
from pandas import Series,DataFrame
import numpy as np
In [2]:
import matplotlib.pyplot as plt
import seaborn as sns
sns.set_style('whitegrid')
%matplotlib inline
In [3]:
from pandas_datareader import data as wb
In [4]:
from datetime import datetime
In [5]:
from __future__ import division
In [6]:
tech_list=['AAPL','GOOG','MSFT','AMZN']
In [7]:
end=datetime.now()
start=datetime(end.year-1,end.month,end.day)
for stock in tech_list:
globals()[stock]=wb.DataReader(stock,'google',start,end)
In [8]:
AAPL.describe()
Out[8]:
In [9]:
AAPL.info()
In [10]:
AAPL['Close'].plot(legend=True,figsize=(10,4))
Out[10]:
In [11]:
AAPL['Volume'].plot(legend=True,figsize=(10,4))
Out[11]:
In [ ]:
In [ ]:
In [ ]:
In [50]:
ma_day=[10,20,50]
for ma in ma_day:
column_name="MA for %s days" %(str(ma))
AAPL[column_name]=Series.rolling(AAPL['Close'],ma).mean()
In [51]:
AAPL[['Close','MA for 10 days','MA for 20 days','MA for 50 days']].plot(subplots=False,figsize=(10,4))
Out[51]:
In [52]:
AAPL['Daily Return']=AAPL['Close'].pct_change()
AAPL['Daily Return'].plot(figsize=(10,4),legend=True,linestyle='--',marker='o')
Out[52]:
In [53]:
sns.distplot(AAPL['Daily Return'].dropna(),bins=100,color='purple')
Out[53]:
In [54]:
AAPL['Daily Return'].hist(bins=100)
Out[54]:
In [55]:
closing_df=wb.DataReader(tech_list,'google',start,end)['Close']
In [56]:
closing_df.head()
Out[56]:
In [57]:
tech_rets=closing_df.pct_change()
In [58]:
tech_rets.head()
Out[58]:
In [59]:
sns.jointplot('GOOG','GOOG',tech_rets,kind='scatter',color='seagreen')
Out[59]:
In [60]:
sns.jointplot('GOOG','MSFT',tech_rets,kind='scatter')
Out[60]:
In [ ]:
In [ ]:
In [ ]:
In [61]:
tech_rets.head()
Out[61]:
In [62]:
sns.pairplot(tech_rets.dropna())
Out[62]:
In [63]:
returns_fig=sns.PairGrid(tech_rets.dropna())
returns_fig.map_upper(plt.scatter,color='purple')
returns_fig.map_lower(sns.kdeplot,cmap='cool_d')
returns_fig.map_diag(plt.hist,bins=30)
Out[63]:
In [64]:
returns_fig=sns.PairGrid(closing_df)
returns_fig.map_upper(plt.scatter,color='purple')
returns_fig.map_lower(sns.kdeplot,cmap='cool_d')
returns_fig.map_diag(plt.hist,bins=30)
Out[64]:
In [65]:
sns.heatmap(tech_rets.dropna().corr(),annot=True)
Out[65]:
In [66]:
sns.heatmap(closing_df.dropna().corr(),annot=True)
Out[66]:
In [ ]:
In [ ]:
In [ ]:
Risk Analysis
In [67]:
rets=tech_rets.dropna()
In [73]:
area=np.pi*20
plt.scatter(rets.mean(),rets.std(),s=area)
plt.xlabel('Expected Return')
plt.ylabel('Risk')
for label,x,y in zip(rets.columns,rets.mean(),rets.std()):
plt.annotate(
label,
xy=(x,y),xytext=(50,50),
textcoords='offset points',ha='right',va='bottom',
arrowprops=dict(arrowstyle='-',connectionstyle='arc3,rad=-0.3'))
In [ ]:
In [ ]:
In [ ]:
Value at Risk
In [74]:
sns.distplot(AAPL['Daily Return'].dropna(),bins=100,color='purple')
Out[74]:
In [75]:
rets.head()
Out[75]:
In [76]:
rets['AAPL'].quantile(0.05)
Out[76]:
Monte Carlo Simulation
In [78]:
days=365
dt=1/days
mu=rets.mean()['GOOG']
sigma=rets.std()['GOOG']
In [82]:
def stock_monte_carlo(start_price,days,mu,sigma):
price=np.zeros(days)
price[0]=start_price
shock=np.zeros(days)
drift=np.zeros(days)
for x in xrange(1,days):
shock[x]=np.random.normal(loc=mu*dt,scale=sigma*np.sqrt(dt))
drift[x]=mu*dt
price[x]=price[x-1]+(price[x-1]*(drift[x]+shock[x]))
return price
In [83]:
GOOG.head()
Out[83]:
In [86]:
start_price=540.74
for run in xrange(100):
plt.plot(stock_monte_carlo(start_price,days,mu,sigma))
plt.xlabel('Days')
plt.ylabel('Price')
plt.title('Monte Carlo Analysis for Google')
Out[86]:
In [88]:
runs=10000
simulations=np.zeros(runs)
for run in xrange(runs):
simulations[run]=stock_monte_carlo(start_price,days,mu,sigma)[days-1]
In [89]:
q=np.percentile(simulations,1)
plt.hist(simulations,bins=200)
plt.figtext(0.6,0.8,s="Start price: $%.2f" %start_price)
plt.figtext(0.6,0.7,"Mean final price: $%.2f" % simulations.mean())
plt.figtext(0.6,0.6,"VaR(0.99): $%.2f" % (start_price-q,))
plt.figtext(0.15,0.6,"q(0.99): $%.2f" % q)
plt.axvline(x=q,linewidth=4,color='r')
plt.title(u"Final price distribution for Google Stock after %s days" % days, weight='bold');
In [ ]: