diff options
Diffstat (limited to 'python/notebooks/Single Names Monitoring.ipynb')
| -rw-r--r-- | python/notebooks/Single Names Monitoring.ipynb | 241 |
1 files changed, 195 insertions, 46 deletions
diff --git a/python/notebooks/Single Names Monitoring.ipynb b/python/notebooks/Single Names Monitoring.ipynb index 1f5643e4..8b734db9 100644 --- a/python/notebooks/Single Names Monitoring.ipynb +++ b/python/notebooks/Single Names Monitoring.ipynb @@ -8,37 +8,16 @@ "source": [ "import pandas as pd\n", "import numpy as np\n", + "import datetime\n", + "\n", "from analytics.basket_index import MarkitBasketIndex\n", + "from analytics import on_the_run\n", "import matplotlib.pyplot as plt\n", "\n", "from utils.db import dbengine\n", - "from ipywidgets import widgets\n", - "engine = dbengine('serenitasdb')" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "w = widgets.Dropdown(\n", - " options=['IG', 'HY', 'EU', 'XO'],\n", - " value='IG',\n", - " description='Index:',\n", - " disabled=False,\n", - ")\n", - "w" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "w_1 = widgets.IntSlider(value=32, min=22, max=32, description = 'Series')\n", - "w_1" + "serenitas_engine = dbengine('serenitasdb')\n", + "\n", + "%matplotlib inline" ] }, { @@ -47,9 +26,9 @@ "metadata": {}, "outputs": [], "source": [ - "value_date = (pd.datetime.today() - pd.offsets.BDay(2)).date()\n", - "index_type = w.value\n", - "series = w_1.value" + "value_date = (pd.datetime.today() - pd.offsets.BDay(1)).date()\n", + "index_type = 'HY'\n", + "series = 32" ] }, { @@ -59,8 +38,20 @@ "outputs": [], "source": [ "sql_string = \"select * from index_members(%s, %s)\"\n", - "df = pd.read_sql_query(sql_string, engine, params=(index_type + str(series), value_date), index_col=['markit_ticker'])\n", - "df1 = pd.read_sql_query(sql_string, engine, params=(index_type + str(series-2), value_date), index_col=['markit_ticker'])" + "\n", + "df = pd.read_sql_query(sql_string, serenitas_engine, params=(index_type + str(series), value_date), index_col=['markit_ticker'])\n", + "df1 = pd.read_sql_query(sql_string, serenitas_engine, params=(index_type + str(series-2), value_date), index_col=['markit_ticker'])\n", + "\n", + "default_prob = {}\n", + "for s in [series, series-2]:\n", + " index = MarkitBasketIndex(index_type, s, ['5yr'])\n", + " surv_prob, tickers = index.survival_matrix()\n", + " default_prob[s] = pd.Series(1 - np.ravel(surv_prob), index=tickers)\n", + "default_prob = pd.concat(default_prob, names=['series', 'markit_ticker'])\n", + "default_prob.name = 'default_prob'\n", + "\n", + "df = df.merge(default_prob.loc[series], left_index=True, right_index = True)\n", + "df1 = df1.merge(default_prob.loc[series-2], left_index=True, right_index = True)" ] }, { @@ -89,7 +80,7 @@ "metadata": {}, "outputs": [], "source": [ - "date_range = pd.bdate_range(value_date - 52 * pd.offsets.Week(), value_date, freq='5B')\n", + "date_range = pd.bdate_range(value_date - 52 * .5 * pd.offsets.Week(), value_date, freq='5B')\n", "index = MarkitBasketIndex(index_type, series, ['5yr'])\n", "default_prob = {}\n", "for d in date_range:\n", @@ -118,24 +109,182 @@ { "cell_type": "code", "execution_count": null, - "metadata": { - "jupyter": { - "source_hidden": true - } - }, + "metadata": {}, "outputs": [], - "source": [] + "source": [ + "tenors = ['3yr', '5yr', '7yr', '10yr']\n", + "#index_type = 'IG'\n", + "#series = 26\n", + "indices = MarkitBasketIndex(index_type, series, tenors)\n", + "indices.value_date = datetime.date.today()\n", + "today_surv_prob, tickers = indices.survival_matrix()\n", + "today_default_prob = pd.DataFrame(1 - today_surv_prob, index=tickers, columns=tenors)" + ] }, { "cell_type": "code", "execution_count": null, - "metadata": { - "jupyter": { - "source_hidden": true - } - }, + "metadata": {}, + "outputs": [], + "source": [ + "#Dispersion: std_dev of default_prob/average default_prob\n", + "date_range = pd.bdate_range(value_date - 52 * 4 * pd.offsets.Week(), value_date, freq='5B')\n", + "default_prob = {}\n", + "ontr = on_the_run(index_type, date_range[0])\n", + "index = MarkitBasketIndex(index_type, ontr, ['5yr'])\n", + "for d in date_range:\n", + " if ontr != on_the_run(index_type, d):\n", + " ontr = on_the_run(index_type, d)\n", + " index = MarkitBasketIndex(index_type, ontr, ['5yr'])\n", + " try:\n", + " index.value_date = d\n", + " surv_prob, tickers = index.survival_matrix()\n", + " default_prob[d] = pd.Series(1 - np.ravel(surv_prob), index=tickers)\n", + " except:\n", + " continue\n", + "default_prob = pd.concat(default_prob)\n", + "dispersion = default_prob.unstack(level=0)\n", + "dispersion = dispersion.std()/dispersion.mean()\n", + "dispersion.plot()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "def gini(array):\n", + " \"\"\"Calculate the Gini coefficient of a numpy array.\"\"\"\n", + " array = array.values\n", + " # based on bottom eq: http://www.statsdirect.com/help/content/image/stat0206_wmf.gif\n", + " # from: http://www.statsdirect.com/help/default.htm#nonparametric_methods/gini.htm\n", + " if np.amin(array) < 0:\n", + " array -= np.amin(array) #values cannot be negative\n", + " array += 0.0000001 #values cannot be 0\n", + " array = np.sort(array) #values must be sorted\n", + " index = np.arange(1,array.shape[0]+1) #index per array element\n", + " n = array.shape[0]#number of array elements\n", + " return ((np.sum((2 * index - n - 1) * array)) / (n * np.sum(array))) #Gini coefficient" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, "outputs": [], - "source": [] + "source": [ + "#Instead of std dev of spread get Gini Factor default prob\n", + "sql_string = \"select * from index_version where index = %s\"\n", + "idx_ver = pd.read_sql_query(sql_string, serenitas_engine, params=[index_type,], parse_dates=['lastdate'])\n", + "idx_ver['date'] = pd.to_datetime([d.strftime('%Y-%m-%d') if not pd.isnull(d) else datetime.date(2050,1,1) for d in idx_ver['lastdate']])\n", + "sql_string = \"select * from risk_numbers where index = %s\"\n", + "risk = pd.read_sql_query(sql_string, serenitas_engine, parse_dates={'date': {'utc':True}}, params=[index_type])\n", + "risk.date = risk.date.dt.normalize().dt.tz_convert(None)\n", + "risk = risk.groupby(['date','index','series','tenor','attach']).mean()\n", + "risk.reset_index(inplace=True)\n", + "idx_ver.sort_values(by=['date'], inplace=True, ascending=True)\n", + "risk = pd.merge_asof(risk, idx_ver[['date','series','cumulativeloss','indexfactor']], left_on=['date'], right_on=['date'], by='series', direction='forward')\n", + "risk.set_index('date', inplace=True) \n", + "risk['moneyness'] = risk.apply(lambda df: (df.detach-df.cumulativeloss)/df.indexfactor/df.index_expected_loss, axis=1)\n", + "\n", + "single_day_risk = {}\n", + "date_range = pd.bdate_range(value_date - 52 * 5 * pd.offsets.Week(), value_date, freq='5B')\n", + "for d in date_range:\n", + " default_prob={}\n", + " try:\n", + " df = risk.loc[d]\n", + " except:\n", + " continue\n", + " for s in df.series.unique():\n", + " tenors = list(df[df.series==s]['tenor'].sort_values().unique())\n", + " indices = MarkitBasketIndex(index_type, s, tenors)\n", + " try:\n", + " indices.value_date = d\n", + " surv_prob, tickers = indices.survival_matrix()\n", + " default_prob[s] = pd.DataFrame(1 - surv_prob, index=tickers, columns=tenors)\n", + " except:\n", + " continue\n", + " if default_prob:\n", + " default_prob = pd.concat(default_prob, names=['series', 'name'], sort=True)\n", + " default_prob.columns.name = 'tenor'\n", + " gini_coeff = default_prob.stack().groupby(['series', 'tenor']).apply(gini)\n", + " single_day_risk[d] = df.merge(gini_coeff.rename('gini_coeff').reset_index(), on=['series', 'tenor'])\n", + "tranche_risk = pd.concat(single_day_risk, names=['date', 'idx'], sort=True)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "to_plot_gini = tranche_risk[(tranche_risk.tenor == '5yr') & (tranche_risk.attach ==0)].groupby(['date', 'series']).nth(-1)\n", + "to_plot_gini['gini_coeff'].unstack().plot()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "import statsmodels.formula.api as smf\n", + "equity = tranche_risk[tranche_risk.attach==0]\n", + "#use a subset for modeling purposes?\n", + "equity = equity[(equity.tenor=='5yr') & (equity.series >= 27)]\n", + "gini_model = smf.gls(\"corr_at_detach ~ gini_coeff + duration + moneyness\", data=equity).fit()\n", + "gini_model.summary()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "predict_today = equity.reset_index()[['gini_coeff', 'duration', 'moneyness']].iloc[-1]\n", + "spread_gls_model.predict(predict_today)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "#Let's use a GAM model instead?\n", + "from pygam import LinearGAM, s, f\n", + "X = np.array(equity[['gini_coeff', 'duration', 'moneyness']])\n", + "y = np.array(equity['corr_at_detach'])\n", + "\n", + "gam_model = LinearGAM(s(0) + s(1) + s(2))\n", + "lam = np.logspace(-3, 5, 5, base=3)\n", + "lams = [lam] * 3\n", + "\n", + "gam_model.gridsearch(X, y, lam=lams)\n", + "gam_model.summary()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "## plotting\n", + "plt.figure();\n", + "fig, axs = plt.subplots(1,3);\n", + "\n", + "titles = ['gini_coeff', 'duration', 'moneyness']\n", + "for i, ax in enumerate(axs):\n", + " XX = gam_model.generate_X_grid(term=i)\n", + " ax.plot(XX[:, i], gam_model.partial_dependence(term=i, X=XX))\n", + " ax.plot(XX[:, i], gam_model.partial_dependence(term=i, X=XX, width=.95)[1], c='r', ls='--')\n", + " if i == 0:\n", + " ax.set_ylim(-30,30)\n", + " ax.set_title(titles[i]);" + ] } ], "metadata": { @@ -154,7 +303,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.3" + "version": "3.7.4" } }, "nbformat": 4, |