Skip to content

Instantly share code, notes, and snippets.

@biank88

biank88/QSTK-Tutorial-9-notebook.ipynb

Last active May 26, 2017 03:07
Show Gist options
  • Save biank88/3919e51dab351eb2c2ee441eeb114840 to your computer and use it in GitHub Desktop.
Save biank88/3919e51dab351eb2c2ee441eeb114840 to your computer and use it in GitHub Desktop.
Download ZIP
QSTK-tutoria-9-notebook
Display the source blob
Display the rendered blob
Raw
QSTK-Tutorial-9-notebook.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import math\n",
"import copy\n",
"import QSTK.qstkutil.qsdateutil as du\n",
"import datetime as dt\n",
"import QSTK.qstkutil.DataAccess as da\n",
"import QSTK.qstkutil.tsutil as tsu\n",
"import QSTK.qstkstudy.EventProfiler as ep ## This function has been reimplemented in this notebook"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### find_events() function definition"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def find_events(ls_symbols, d_data):\n",
" ''' Finding the event dataframe '''\n",
" df_close = d_data['close']\n",
" ts_market = df_close['SPY']\n",
"\n",
" # Creating an empty dataframe\n",
" df_events = copy.deepcopy(df_close)\n",
" df_events = df_events * np.NAN\n",
"\n",
" # Time stamps for the event range\n",
" ldt_timestamps = df_close.index\n",
"\n",
" for s_sym in ls_symbols:\n",
" for i in range(1, len(ldt_timestamps)):\n",
" # Calculating the returns for this timestamp\n",
" f_symprice_today = df_close[s_sym].ix[ldt_timestamps[i]]\n",
" f_symprice_yest = df_close[s_sym].ix[ldt_timestamps[i - 1]]\n",
" f_marketprice_today = ts_market.ix[ldt_timestamps[i]]\n",
" f_marketprice_yest = ts_market.ix[ldt_timestamps[i - 1]]\n",
" f_symreturn_today = (f_symprice_today / f_symprice_yest) - 1\n",
" f_marketreturn_today = (f_marketprice_today / f_marketprice_yest) - 1\n",
"\n",
" # Event is found if the symbol is down more then 3% while the\n",
" # market is up more then 2%\n",
" if f_symreturn_today <= -0.03 and f_marketreturn_today >= 0.02:\n",
" df_events[s_sym].ix[ldt_timestamps[i]] = 1\n",
"\n",
" return df_events"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### eventprofiler2() function def"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"\n",
"import QSTK.qstkutil.DataAccess as da\n",
"import QSTK.qstkutil.tsutil as tsu\n",
"import QSTK.qstkutil.qsdateutil as du\n",
"\n",
"def eventprofiler2(df_events_arg, d_data, i_lookback=20, i_lookforward=20,\n",
" s_filename='study', b_market_neutral=True, b_errorbars=True,\n",
" s_market_sym='SPY', show = False):\n",
" '''\n",
" Event Profiler for an event matrix\n",
" '''\n",
" df_close = d_data['close'].copy()\n",
" df_rets = df_close.copy()\n",
"\n",
" # Do not modify the original event dataframe.\n",
" df_events = df_events_arg.copy()\n",
" \n",
" # Calculate the daily returns of the prices. (Inplace calculation)\n",
" # returnize0 works on ndarray and not dataframes.\n",
" tsu.returnize0(df_rets.values)\n",
"\n",
" # (optional) remove market component from daily returns (suppose beta==1 )\n",
" if b_market_neutral == True:\n",
" \n",
" ## the following line caused an error, so it has been modified\n",
" # df_rets = df_rets - df_rets[s_market_sym]\n",
" \n",
" df_rets = df_rets.sub(df_rets[s_market_sym].values, axis=0)\n",
" \n",
" del df_rets[s_market_sym]\n",
" del df_events[s_market_sym]\n",
"\n",
" df_close = df_close.reindex(columns=df_events.columns)\n",
"\n",
" # Remove the starting and the end events\n",
" df_events.values[0:i_lookback, :] = np.NaN\n",
" df_events.values[-i_lookforward:, :] = np.NaN\n",
"\n",
" # Get the number of events in the matrix \n",
" i_no_events = int(np.logical_not(np.isnan(df_events.values)).sum())\n",
" assert i_no_events > 0, \"Zero events in the event matrix\"\n",
" na_event_rets = \"False\"\n",
"\n",
" # Look for the events and push them to a matrix\n",
" for i, s_sym in enumerate(df_events.columns):\n",
" for j, dt_date in enumerate(df_events.index):\n",
" if df_events[s_sym][dt_date] == 1:\n",
" na_ret = df_rets[s_sym][j - i_lookback:j + 1 + i_lookforward]\n",
" if type(na_event_rets) == type(\"\"):\n",
" na_event_rets = na_ret\n",
" else:\n",
" na_event_rets = np.vstack((na_event_rets, na_ret))\n",
"\n",
" if len(na_event_rets.shape) == 1:\n",
" na_event_rets = np.expand_dims(na_event_rets, axis=0)\n",
"\n",
" # Compute daily returns\n",
" na_event_rets = np.cumprod(na_event_rets + 1, axis=1)\n",
" na_event_rets = (na_event_rets.T / na_event_rets[:, i_lookback]).T\n",
"\n",
" # Study Params\n",
" na_mean = np.mean(na_event_rets, axis=0)\n",
" na_std = np.std(na_event_rets, axis=0)\n",
" li_time = range(-i_lookback, i_lookforward + 1)\n",
"\n",
" # Plot the chart\n",
" plt.clf()\n",
" plt.axhline(y=1.0, xmin=-i_lookback, xmax=i_lookforward, color='k')\n",
" \n",
" if b_errorbars == True:\n",
" plt.errorbar(li_time[i_lookback:], na_mean[i_lookback:],\n",
" yerr=na_std[i_lookback:], ecolor='#AAAAFF',\n",
" alpha=0.5) #Changed alpha from 0.1 to 0.5\n",
" \n",
" plt.plot(li_time, na_mean, linewidth=3, label='mean', color='b')\n",
" plt.xlim(-i_lookback - 1, i_lookforward + 1)\n",
" \n",
" if b_market_neutral == True:\n",
" plt.title('Market Relative mean return of ' + str(i_no_events) + ' events')\n",
" else:\n",
" plt.title('Mean return of ' + str(i_no_events) + ' events')\n",
" \n",
" plt.xlabel('Days')\n",
" plt.ylabel('Cumulative Returns')\n",
" plt.savefig(s_filename, format='pdf')\n",
" \n",
" if show == True:\n",
" plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Define a time interval"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"dt_start = dt.datetime(2008, 1, 1)\n",
"dt_end = dt.datetime(2009, 12, 31)\n",
"ldt_timestamps = du.getNYSEdays(dt_start, dt_end, dt.timedelta(hours=16))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Define the desired list of symbols\n",
"Note that the list should contain the list of equities from SP500 (as it was in 2012) plus a market index (i.e. _SPY_)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"dataobj = da.DataAccess('Yahoo')\n",
"ls_symbols = dataobj.get_symbols_from_list('sp5002012')\n",
"ls_symbols.append('SPY')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Define and create pandas dataframe objects"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"ls_keys = ['open', 'high', 'low', 'close', 'volume', 'actual_close']\n",
"ldf_data = dataobj.get_data(ldt_timestamps, ls_symbols, ls_keys)\n",
"d_data = dict(zip(ls_keys, ldf_data))"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"for s_key in ls_keys:\n",
" d_data[s_key] = d_data[s_key].fillna(method='ffill')\n",
" d_data[s_key] = d_data[s_key].fillna(method='bfill')\n",
" d_data[s_key] = d_data[s_key].fillna(1.0)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Creating an Event Matrix\n",
"\n",
"An Event Matrix is a Pandas DataFrame. For each equity for each date, we indicate whether an event occurred or not. A NaN indicates no event for that equity/date. A 1 indicates that an event occurred. Here's an example:\n",
"\n",
"|Date|IBM |GOOG|XOM |MSFT|GS |JP |\n",
"|----|----|----|----|----|----|----|\n",
"|(d1)|nan |nan | 1 |nan |nan | 1 |\n",
"|(d2)|nan | 1 |nan |nan |nan |nan |\n",
"|(d3)| 1 |nan | 1 |nan | 1 |nan |\n",
"|(d4)|nan | 1 |nan | 1 |nan |nan |\n"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"df_events = find_events(ls_symbols, d_data)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The following line shows the first 5 lines in df_events."
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>A</th>\n",
" <th>AA</th>\n",
" <th>AAPL</th>\n",
" <th>ABC</th>\n",
" <th>ABT</th>\n",
" <th>ACE</th>\n",
" <th>ACN</th>\n",
" <th>ADBE</th>\n",
" <th>ADI</th>\n",
" <th>ADM</th>\n",
" <th>...</th>\n",
" <th>XLNX</th>\n",
" <th>XOM</th>\n",
" <th>XRAY</th>\n",
" <th>XRX</th>\n",
" <th>XYL</th>\n",
" <th>YHOO</th>\n",
" <th>YUM</th>\n",
" <th>ZION</th>\n",
" <th>ZMH</th>\n",
" <th>SPY</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2008-01-02 16:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2008-01-03 16:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2008-01-04 16:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2008-01-07 16:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2008-01-08 16:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 502 columns</p>\n",
"</div>"
],
"text/plain": [
" A AA AAPL ABC ABT ACE ACN ADBE ADI ADM ... \\\n",
"2008-01-02 16:00:00 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... \n",
"2008-01-03 16:00:00 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... \n",
"2008-01-04 16:00:00 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... \n",
"2008-01-07 16:00:00 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... \n",
"2008-01-08 16:00:00 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... \n",
"\n",
" XLNX XOM XRAY XRX XYL YHOO YUM ZION ZMH SPY \n",
"2008-01-02 16:00:00 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN \n",
"2008-01-03 16:00:00 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN \n",
"2008-01-04 16:00:00 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN \n",
"2008-01-07 16:00:00 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN \n",
"2008-01-08 16:00:00 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN \n",
"\n",
"[5 rows x 502 columns]"
]
},
"execution_count": 31,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_events.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Plotting the event study\n",
"\n",
"The code below shows how to call the\n",
"event profiler once you have created\n",
"the event matrix using the findEvents\n",
"function. This code plots the event\n",
"profiler output in the file\n",
"MyEventStudy.pdf."
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/fra/anaconda2/envs/QSTK/lib/python2.7/site-packages/pandas/indexes/base.py:2683: RuntimeWarning: Cannot compare type 'Timestamp' with type 'str', sort order is undefined for incomparable objects\n",
" return this.join(other, how=how, return_indexers=return_indexers)\n"
]
}
],
"source": [
"ep.eventprofiler(df_events, d_data, i_lookback=20, i_lookforward=20,\n",
" s_filename='MyEventStudy.pdf', b_market_neutral=True, b_errorbars=True,\n",
" s_market_sym='SPY')"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAYUAAAEWCAYAAACJ0YulAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nSIKSgoiIJCgpiIhIgpKCiIgk/D+8RIhS3sDAWwAAAABJRU5ErkJggg==\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7fa258064350>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"eventprofiler2(df_events, d_data, i_lookback=20, i_lookforward=20,\n",
" s_filename='MyEventStudy.pdf', b_market_neutral=True, b_errorbars=True,\n",
" s_market_sym='SPY', show=True)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.13"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Raw
requirements_conda_env.txt
backports-abc==0.5
backports.shutil-get-terminal-size==1.0.0
backports.ssl-match-hostname==3.4.0.2
configparser==3.5.0
cycler==0.10.0
decorator==4.0.11
enum34==1.1.6
functools32==3.2.3.post2
ipykernel==4.5.2
ipython==5.1.0
ipython-genutils==0.1.0
ipywidgets==5.2.2
Jinja2==2.9.4
jsonschema==2.5.1
jupyter==1.0.0
jupyter-client==4.4.0
jupyter-console==5.0.0
jupyter-core==4.2.1
MarkupSafe==0.23
matplotlib==2.0.0
mistune==0.7.3
nbconvert==4.2.0
nbformat==4.2.0
notebook==4.3.1
numpy==1.11.3
pandas==0.19.2
pathlib2==2.2.0
pexpect==4.2.1
pickleshare==0.7.4
prompt-toolkit==1.0.9
ptyprocess==0.5.1
pycairo==1.10.0
Pygments==2.1.3
pyparsing==2.1.4
python-dateutil==1.5
pytz==2016.10
pyzmq==16.0.2
QSTK==0.2.8
qtconsole==4.2.1
scandir==1.4
scikit-learn==0.18.1
scipy==0.18.1
simplegeneric==0.8.1
singledispatch==3.4.0.3
six==1.10.0
subprocess32==3.2.7
terminado==0.6
tornado==4.4.2
traitlets==4.3.1
wcwidth==0.1.7
widgetsnbextension==1.2.6
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment