QuantSoftwareToolkit/Examples/Basic/tutorial1.py at 6b7e15fa3c0ba483a30674ff5acf30c77b91b877 · QuantSoftware/QuantSoftwareToolkit · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
'''
(c) 2011, 2012 Georgia Tech Research Corporation
This source code is released under the New BSD license.  Please see
http://wiki.quantsoftware.org/index.php?title=QSTK_License
for license details.

Created on January, 24, 2013

@author: Sourabh Bajaj
@contact: sourabhbajaj@gatech.edu
@summary: Example tutorial code.
'''

# QSTK Imports
import QSTK.qstkutil.qsdateutil as du
import QSTK.qstkutil.tsutil as tsu
import QSTK.qstkutil.DataAccess as da

# Third Party Imports
import datetime as dt
import matplotlib.pyplot as plt
import pandas as pd

print("Pandas Version", pd.__version__)


def main():
    ''' Main Function'''

    # List of symbols
    ls_symbols = ["AAPL", "GLD", "GOOG", "$SPX", "XOM"]

    # Start and End date of the charts
    dt_start = dt.datetime(2006, 1, 1)
    dt_end = dt.datetime(2010, 12, 31)

    # We need closing prices so the timestamp should be hours=16.
    dt_timeofday = dt.timedelta(hours=16)

    # Get a list of trading days between the start and the end.
    ldt_timestamps = du.getNYSEdays(dt_start, dt_end, dt_timeofday)

    # Creating an object of the dataaccess class with Yahoo as the source.
    c_dataobj = da.DataAccess('Yahoo')

    # Keys to be read from the data, it is good to read everything in one go.
    ls_keys = ['open', 'high', 'low', 'close', 'volume', 'actual_close']

    # Reading the data, now d_data is a dictionary with the keys above.
    # Timestamps and symbols are the ones that were specified before.
    ldf_data = c_dataobj.get_data(ldt_timestamps, ls_symbols, ls_keys)
    d_data = dict(list(zip(ls_keys, ldf_data)))

    # Filling the data for NAN
    for s_key in ls_keys:
        d_data[s_key] = d_data[s_key].fillna(method='ffill')
        d_data[s_key] = d_data[s_key].fillna(method='bfill')
        d_data[s_key] = d_data[s_key].fillna(1.0)

    # Getting the numpy ndarray of close prices.
    na_price = d_data['close'].values

    # Plotting the prices with x-axis=timestamps
    plt.clf()
    plt.plot(ldt_timestamps, na_price)
    plt.legend(ls_symbols)
    plt.ylabel('Adjusted Close')
    plt.xlabel('Date')
    plt.savefig('adjustedclose.pdf', format='pdf')

    # Normalizing the prices to start at 1 and see relative returns
    na_normalized_price = na_price / na_price[0, :]

    # Plotting the prices with x-axis=timestamps
    plt.clf()
    plt.plot(ldt_timestamps, na_normalized_price)
    plt.legend(ls_symbols)
    plt.ylabel('Normalized Close')
    plt.xlabel('Date')
    plt.savefig('normalized.pdf', format='pdf')

    # Copy the normalized prices to a new ndarry to find returns.
    na_rets = na_normalized_price.copy()

    # Calculate the daily returns of the prices. (Inplace calculation)
    # returnize0 works on ndarray and not dataframes.
    tsu.returnize0(na_rets)

    # Plotting the plot of daily returns
    plt.clf()
    plt.plot(ldt_timestamps[0:50], na_rets[0:50, 3])  # $SPX 50 days
    plt.plot(ldt_timestamps[0:50], na_rets[0:50, 4])  # XOM 50 days
    plt.axhline(y=0, color='r')
    plt.legend(['$SPX', 'XOM'])
    plt.ylabel('Daily Returns')
    plt.xlabel('Date')
    plt.savefig('rets.pdf', format='pdf')

    # Plotting the scatter plot of daily returns between XOM VS $SPX
    plt.clf()
    plt.scatter(na_rets[:, 3], na_rets[:, 4], c='blue')
    plt.ylabel('XOM')
    plt.xlabel('$SPX')
    plt.savefig('scatterSPXvXOM.pdf', format='pdf')

    # Plotting the scatter plot of daily returns between $SPX VS GLD
    plt.clf()
    plt.scatter(na_rets[:, 3], na_rets[:, 1], c='blue')  # $SPX v GLD
    plt.ylabel('GLD')
    plt.xlabel('$SPX')
    plt.savefig('scatterSPXvGLD.pdf', format='pdf')

if __name__ == '__main__':
    main()