ci/homework6.py at master · tux2009/ci · 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
import numpy as np
import copy
import QSTK.qstkutil.qsdateutil as du
import QSTK.qstkutil.tsutil as tsu
import QSTK.qstkutil.DataAccess as da
import datetime as dt
import matplotlib.pyplot as plt
import QSTK.qstkstudy.EventProfiler as ep
import pandas


def find_bollinger_values(adjcloses, periods):
    means = pandas.rolling_mean(adjcloses, periods, min_periods=periods)
    stds = pandas.rolling_std(adjcloses, periods, min_periods=periods)
    bands = (adjcloses - means) / stds
    return bands

def find_events(ls_symbols, d_data):
    ''' Finding the event dataframe '''
    df_close = d_data['close']
    ts_market = df_close['SPY']
    market_bands = find_bollinger_values(ts_market, 20)
    print "-----------------SPY"
    print market_bands
    print "Finding Events"

    # Creating an empty dataframe
    df_events = copy.deepcopy(df_close)
    df_events = df_events * np.NAN

    # Time stamps for the event range
    ldt_timestamps = df_close.index

    for s_sym in ls_symbols:
        if s_sym == "SPY":
            continue
        sym_bands = find_bollinger_values(df_close[s_sym], 20)
        print "-----------------" + s_sym
        print sym_bands
        for i in range(1, len(ldt_timestamps)):
            # Calculating the returns for this timestamp
            f_symband_today = sym_bands.ix[ldt_timestamps[i]]
            f_symband_yest = sym_bands.ix[ldt_timestamps[i - 1]]
            f_marketband_today = market_bands.ix[ldt_timestamps[i]]

            # Event is found if the symbol is down more then 3% while the
            # market is up more then 2%
            #if f_symreturn_today <= -0.03 and f_marketreturn_today >= 0.02:
            if f_symband_today < -2.0 and f_symband_yest >= -2.0 and f_marketband_today >= 1.4:
                df_events[s_sym].ix[ldt_timestamps[i]] = 1

    return df_events


#
# Prepare to read the data
#
if __name__ == '__main__':
    symbols = ["AAPL", "GOOG", "IBM", "MSFT"]
    dt_start = dt.datetime(2008, 1, 1)
    dt_end = dt.datetime(2009, 12, 31)
    ldt_timestamps = du.getNYSEdays(dt_start, dt_end, dt.timedelta(hours=16))

    dataobj = da.DataAccess('Yahoo')
    ls_symbols = dataobj.get_symbols_from_list('sp5002012')
    ls_symbols.append('SPY')
    ls_keys = ['open', 'high', 'low', 'close', 'volume', 'actual_close']
    ldf_data = dataobj.get_data(ldt_timestamps, ls_symbols, ls_keys)
    d_data = dict(zip(ls_keys, ldf_data))
    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)
    df_events = find_events(ls_symbols, d_data)
    print "Creating Study"
    ep.eventprofiler(df_events, d_data, i_lookback=20, i_lookforward=20,
                s_filename='MyEventStudy6.pdf', b_market_neutral=True, b_errorbars=True,
                s_market_sym='SPY')
    # Plot the prices