# Useful Functions
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

l = np.random.randint(1,100, size=1000)
s = pd.Series(l)

new_index = pd.date_range("2016-01-01", periods=len(s), freq="D")
s.index = new_index
print s

# Print every other element of the first 50 elements
s.iloc[:50:2];
# Values associated with the index 2017-02-20
s.loc['2017-02-20']

# Print s between 1 and 3
s.loc[(s>1) & (s<3)]

# First 5 elements
s.head(5)
# Last 5 elements
s.tail(5)

symbol = "CMG"
start = "2012-01-01"
end = "2016-01-01"
prices = get_pricing(symbol, start_date=start, end_date=end, fields="price")

# Resample daily prices to get monthly prices using median. 
monthly_prices = prices.resample('M').median()
monthly_prices.head(24)

# Data for every day, (including weekends and holidays)
calendar_dates = pd.date_range(start=start, end=end, freq='D', tz='UTC')
calendar_prices = prices.reindex(calendar_dates, method='ffill')
calendar_prices.head(15)

# Fill missing data using Backwards fill method
bfilled_prices = calendar_prices.fillna(method='bfill')
bfilled_prices.head(10)

# Drop instances of nan in the data
dropped_prices = calendar_prices.dropna()
dropped_prices.head(10)

print "Summary Statistics"
print prices.describe()

data = get_pricing('GE', fields='open_price', start_date='2016-01-01', end_date='2017-01-01')

mult_returns = data.pct_change()[1:] #Multiplicative returns 
add_returns = data.diff()[1:] #Additive returns 

# Rolling mean
rolling_mean = data.rolling(window=60).mean()
rolling_mean.name = "60-day rolling mean"

# Rolling Standard Deviation
rolling_std = data.rolling(window=60).std()
rolling_std.name = "60-day rolling volatility"

l = ['First','Second', 'Third', 'Fourth', 'Fifth']
dict_data = {'a' : [1, 2, 3, 4, 5], 
             'b' : ['L', 'K', 'J', 'M', 'Z'],
             'c' : np.random.normal(0, 1, 5)
            }

# Adding l as an index to dict_data
frame_data = pd.DataFrame(dict_data, index=l)
print frame_data

s1 = pd.Series([2, 3, 5, 7, 11, 13], name='prime')
s2 = pd.Series([1, 4, 6, 8, 9, 10], name='other')

numbers = pd.concat([s1, s2], axis=1) # Concatenate the two series
numbers.columns = ['Useful Numbers', 'Not Useful Numbers'] # Rename the two columns
numbers.index = pd.date_range("2016-01-01", periods=len(numbers)) # Index change
print numbers

symbol = ["XOM", "BP", "COP", "TOT"]
start = "2012-01-01"
end = "2016-01-01"
prices = get_pricing(symbol, start_date=start, end_date=end, fields="price")
if isinstance(symbol, list):
    prices.columns = map(lambda x: x.symbol, prices.columns)
else:
    prices.name = symbol

# Check Type of Data for these two.    
prices.XOM.head()
prices.loc[:, 'XOM'].head()

# Print data type
print type(prices.XOM)
print type(prices.loc[:, 'XOM'])

# Print values associated with time range
prices.loc['2013-01-01':'2013-01-10']

# Filter data 
# BP > 30
print prices.loc[prices.BP > 30].head()
# XOM < 100
print prices.loc[prices.XOM < 100].head()
# BP > 30 AND XOM < 100
print prices.loc[(prices.BP > 30) & (prices.XOM < 100)].head()
# The union of (BP > 30 AND XOM < 100) with TOT being non-nan
print prices.loc[((prices.BP > 30) & (prices.XOM < 100)) | (~ prices.TOT.isnull())].head()

# Adding TSLA 
s_1 = get_pricing('TSLA', start_date=start, end_date=end, fields='price')
prices.loc[:, 'TSLA'] = s_1

# Dropping XOM
prices = prices.drop('XOM', axis=1)
prices.head(5)

df_1 = get_pricing(['SPY', 'VXX'], start_date=start, end_date=end, fields='price')
df_2 = get_pricing(['MSFT', 'AAPL', 'GOOG'], start_date=start, end_date=end, fields='price')
# Concatenate the dataframes
df_3 = pd.concat([df_1, df_2], axis=1)
df_3.head()

# Fill GOOG missing data with nan
filled0_df_3 = df_3.fillna(0)
filled0_df_3.head(5)

# Summary
prices.describe()

# Natural Log of the returns and print out the first 10 values
np.log(prices).head(10)

# Multiplicative returns
mult_returns = prices.pct_change()[1:]
mult_returns.head()

# Normalizing the returns and plotting one year of data
norm_returns = (mult_returns - mult_returns.mean(axis=0))/mult_returns.std(axis=0)
norm_returns.loc['2014-01-01':'2015-01-01'].plot();

# Rolling mean
rolling_mean = prices.rolling(window=60).mean()
rolling_mean.columns = prices.columns

# Rolling standard deviation
rolling_std = prices.rolling(window=60).std()
rolling_mean.columns = prices.columns

# Plotting 
mean = rolling_mean.plot();
plt.title("Rolling Mean of Prices")
plt.xlabel("Date")
plt.ylabel("Price")
plt.legend();

std = rolling_std.plot();
plt.title("Rolling standard deviation of Prices")
plt.xlabel("Date")
plt.ylabel("Price")
plt.legend();