!conda env list
%matplotlib inline

#Importing The Data


from pandas_datareader import data
import pandas as pd

# Define the instruments to download. We would like to see Apple, Microsoft and the S&P500 index.
# tickers = ['W', 'HD', 'AMZN','LOW','LL']
tickers = ['ROIC', 'SKT', 'TCO' ,'SPG' ,'MAC']
# Define which online source one should use
data_source = 'yahoo'

# We would like all available data from 01/01/2000 until 12/31/2016.
start_date = '2016-12-01'
end_date = '2017-12-31'

# User pandas_reader.data.DataReader to load the desired data. As simple as that.
panel_data = data.DataReader(tickers, data_source, start_date, end_date)

panel_data.head()

df = panel_data['Adj Close']

# Basic Description of the Data

df.describe()

first = df.head()
last = df.tail()
print(first)
print(last)

df.sample(6)

# A Closer Look At Your Data: Queries

df.query('MAC == ROIC')

#cleaning
print(df.columns[df.isnull().any()])

# Getting all weekdays between 01/01/2000 and 12/31/2016
all_weekdays = pd.date_range(start=start_date, end=end_date, freq='B')

# How do we align the existing prices in adj_close with our new set of dates?
# All we need to do is reindex adj_close using all_weekdays as the new index
df = df.reindex(all_weekdays)

# Reindexing will insert missing values (NaN) for the dates that were not present
# in the original set. To cope with this, we can fill the missing by replacing them
# with the latest available price for each instrument.
df = df.fillna(method='ffill')
df.isnull().head()

# Define your own bins
mybins = range(int(df.MAC.min()), int(df.MAC.max()), 2)

# Cut the data with the help of the bins
df['MAC_bucket'] = pd.cut(df.MAC, bins=mybins)

# Count the number of values per bucket
df['MAC_bucket'].value_counts()

from pandas_datareader import data
import pandas as pd
%matplotlib inline


# Define the instruments to download. We would like to see Apple, Microsoft and the S&P500 index.
# tickers = ['W', 'HD', 'AMZN','LOW','LL']
tickers = ['ROIC', 'SKT', 'TCO' ,'SPG' ,'MAC']
# Define which online source one should use
data_source = 'yahoo'

# We would like all available data from 01/01/2000 until 12/31/2016.
start_date = '2016-12-01'
end_date = '2017-12-31'

# User pandas_reader.data.DataReader to load the desired data. As simple as that.
panel_data = data.DataReader(tickers, data_source, start_date, end_date)

# Getting just the adjusted closing prices. This will return a Pandas DataFrame
# The index in this DataFrame is the major index of the panel_data.
close = panel_data.ix['Close']

# Getting all weekdays between 01/01/2000 and 12/31/2016
all_weekdays = pd.date_range(start=start_date, end=end_date, freq='B')

# How do we align the existing prices in adj_close with our new set of dates?
# All we need to do is reindex close using all_weekdays as the new index
close = close.reindex(all_weekdays)

close.head()

# Getting just the adjusted closing prices. This will return a Pandas DataFrame
# The index in this DataFrame is the major index of the panel_data.
adj_close = panel_data.ix['Adj Close']

# Getting all weekdays between 01/01/2000 and 12/31/2016
all_weekdays = pd.date_range(start=start_date, end=end_date, freq='B')

# How do we align the existing prices in adj_close with our new set of dates?
# All we need to do is reindex adj_close using all_weekdays as the new index
adj_close = adj_close.reindex(all_weekdays)

# Reindexing will insert missing values (NaN) for the dates that were not present
# in the original set. To cope with this, we can fill the missing by replacing them
# with the latest available price for each instrument.
adj_close = adj_close.fillna(method='ffill')
adj_close.describe()

# Define your own bins
mybins = range(df.MAC.min(), df.MAC.max(), 10)

# Cut the data with the help of the bins
df['MAC_bucket'] = pd.cut(df.MAC, bins=mybins)

# Count the number of values per bucket
df['MAC_bucket'].value_counts()

import pandas as pd
import pandas_datareader.data as web
import datetime
pd.set_option('display.width', 200) # Displaying more columns in one row

# Data date range, Google provides up to 4000 entries in one call
start = datetime.datetime(2017, 9, 1) 
end = datetime.datetime(2018, 2, 3)

spy = web.DataReader("AAPL", "yahoo", start, end)

print(spy.head()) # See first few rows

%matplotlib inline
import matplotlib.pyplot as plt
from matplotlib.ticker import FuncFormatter
from matplotlib import style
style.use('fivethirtyeight')

spy['Adj Close'].plot(figsize=(20,10))
ax = plt.subplot()
ax.yaxis.set_major_formatter(FuncFormatter(lambda x, pos: '${:,.0f}'.format(x))) # Y axis dollarsymbols
plt.title('AAPL Historical Price on Close')
plt.xlabel('')
plt.ylabel('Stock Price ($)');

value_price = spy['Adj Close'][-1] # The final value of our stock
initial_investment = 10000 # Our initial investment of $10k

num_stocks_bought = initial_investment / spy['Adj Close']
lumpsum = num_stocks_bought * value_price
lumpsum.name = 'Lump Sum'

lumpsum.plot(figsize=(20,10))
ax = plt.subplot()
ax.yaxis.set_major_formatter(FuncFormatter(lambda x, pos: '${:,.0f}'.format(x))) # Y axis dollarsymbols
plt.title('Lump sum - Value today of $10,000 invested on date')
plt.xlabel('')
plt.ylabel('Investment Value ($)');

def doDCA(investment, start_date):
    # Get 12 investment dates in 7 day increments starting from start date
    investment_dates_all = pd.date_range(start_date,periods=12,freq='7D')
    # Remove those dates beyond our known data range
    investment_dates = investment_dates_all[investment_dates_all < spy.index[-1]]

    # Get closest business dates with available data
    closest_investment_dates = spy.index.searchsorted(investment_dates)

    # How much to invest on each date
    portion = investment/12.0 # (Python 3.0 does implicit double conversion, Python 2.7 does not)

    # Get the total of all stocks purchased for each of those dates (on the Close)
    stocks_invested = sum(portion / spy['Adj Close'][closest_investment_dates])

    # Add uninvested amount back
    uninvested_dollars = portion * sum(investment_dates_all >= spy.index[-1])

    # value of stocks today
    total_value = value_price*stocks_invested + uninvested_dollars
    return total_value

# Generate DCA series for every possible date
dca = pd.Series(spy.index.map(lambda x: doDCA(initial_investment, x)), index=spy.index, name='Dollar Cost Averaging (DCA)')

dca.plot(figsize=(20,10))
ax = plt.subplot()
ax.yaxis.set_major_formatter(FuncFormatter(lambda x, pos: '${:,.0f}'.format(x))) # Y axis dollarsymbols
plt.title('Dollar Cost Averaging - Value today of $10,000 invested on date')
plt.xlabel('')
plt.ylabel('Investment Value ($)');

# http://nbviewer.jupyter.org/gist/theandygross/4544012
import sys
print('Python: {}'.format(sys.version))

print ('This is really exciting')

print (12)

print ('hello, notebook blog :)')