Code-for-quant-/cadf.py at main · Zijia-Cheng/Code-for-quant- · 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
import datetime
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
import pandas as pd
import pandas.io.data as web
import pprint
import statsmodels.tsa.stattools as ts

from pandas.stats.api import ols


def plot_price_series(df, ts1, ts2):
    months = mdates.MonthLocator()  # every month
    fig, ax = plt.subplots()
    ax.plot(df.index, df[ts1], label=ts1)
    ax.plot(df.index, df[ts2], label=ts2)
    ax.xaxis.set_major_locator(months)
    ax.xaxis.set_major_formatter(mdates.DateFormatter('%b %Y'))
    ax.set_xlim(datetime.datetime(2012, 1, 1), datetime.datetime(2013, 1, 1))
    ax.grid(True)
    fig.autofmt_xdate()

    plt.xlabel('Month/Year')
    plt.ylabel('Price ($)')
    plt.title('%s and %s Daily Prices' % (ts1, ts2))
    plt.legend()
    plt.show()

def plot_scatter_series(df, ts1, ts2):
    plt.xlabel('%s Price ($)' % ts1)
    plt.ylabel('%s Price ($)' % ts2)
    plt.title('%s and %s Price Scatterplot' % (ts1, ts2))
    plt.scatter(df[ts1], df[ts2])
    plt.show()

def plot_residuals(df):
    months = mdates.MonthLocator()  # every month
    fig, ax = plt.subplots()
    ax.plot(df.index, df["res"], label="Residuals")
    ax.xaxis.set_major_locator(months)
    ax.xaxis.set_major_formatter(mdates.DateFormatter('%b %Y'))
    ax.set_xlim(datetime.datetime(2012, 1, 1), datetime.datetime(2013, 1, 1))
    ax.grid(True)
    fig.autofmt_xdate()

    plt.xlabel('Month/Year')
    plt.ylabel('Price ($)')
    plt.title('Residual Plot')
    plt.legend()

    plt.plot(df["res"])
    plt.show()

if __name__ == "__main__":
    start = datetime.datetime(2012, 1, 1)
    end = datetime.datetime(2013, 1, 1)

    arex = web.DataReader("AREX", "yahoo", start, end)
    wll = web.DataReader("WLL", "yahoo", start, end)

    df = pd.DataFrame(index=arex.index)
    df["AREX"] = arex["Adj Close"]
    df["WLL"] = wll["Adj Close"]

    # Plot the two time series
    plot_price_series(df, "AREX", "WLL")

    # Display a scatter plot of the two time series
    plot_scatter_series(df, "AREX", "WLL")

    # Calculate optimal hedge ratio "beta"
    res = ols(y=df['WLL'], x=df["AREX"])
    beta_hr = res.beta.x

    # Calculate the residuals of the linear combination
    df["res"] = df["WLL"] - beta_hr*df["AREX"]

    # Plot the residuals
    plot_residuals(df)

    # Calculate and output the CADF test on the residuals
    cadf = ts.adfuller(df["res"])
    pprint.pprint(cadf)