diff options
Diffstat (limited to 'python/notebooks')
| -rw-r--r-- | python/notebooks/dispersion_tranche_model.ipynb | 127 |
1 files changed, 74 insertions, 53 deletions
diff --git a/python/notebooks/dispersion_tranche_model.ipynb b/python/notebooks/dispersion_tranche_model.ipynb index a2bb5a67..cd59fb3f 100644 --- a/python/notebooks/dispersion_tranche_model.ipynb +++ b/python/notebooks/dispersion_tranche_model.ipynb @@ -53,21 +53,22 @@ "outputs": [], "source": [ "#Section 1----------------------------------------------------\n", + "#index basis doesn't work with HY (opposite reaction to what I think)\n", "#RFE\n", "drop_variable_list = ['tranche_loss_per', 'tranche_id', 'index_price', 'detach', 'corr_at_detach', \n", " 'corr01', 'exp_percentage', 'indexfactor', 'duration', 'index_expected_loss',\n", " 'index_theta', 'delta', 'expected_loss', 'attach_adj', 'detach_adj',\n", - " 'theta', 'cumulativeloss', \n", + " 'cumulativeloss', \n", " 'forward_delta', \n", " #Comment out to include\n", - " 'index_duration',\n", - " # 'thickness',\n", - " # 'moneyness',\n", + " # 'index_duration',\n", + " 'thickness',\n", + " 'moneyness',\n", " # 'index_basis',\n", - " 'att_moneyness', \n", - " 'det_moneyness',\n", + " # 'att_moneyness', \n", + " # 'det_moneyness',\n", " 'dispersion',\n", - " # 'gini', \n", + " # 'gini', \n", " 'gamma',\n", " 'theta',\n", " 'index_theta'\n", @@ -77,7 +78,9 @@ { "cell_type": "code", "execution_count": null, - "metadata": {}, + "metadata": { + "tags": [] + }, "outputs": [], "source": [ "def run_rfe(index_type):\n", @@ -93,6 +96,7 @@ " X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)\n", " \n", " pipe_rfe = make_pipeline (PowerTransformer(),\n", + " #PolynomialFeatures(degree=2),\n", " PolynomialFeatures(interaction_only=True),\n", " RFECV(estimator=LinearRegression(), \n", " cv=10,\n", @@ -118,9 +122,9 @@ " # 'learning_rate': 0.01,\n", " # 'loss': 'huber',\n", " # 'verbose':1}\n", - " #gb = GradientBoostingRegressor(**params).fit(X_p, y)\n", + " #gb = GradientBoostingRegressor(**params).fit(X_train, y_train)\n", " \n", - " #model = VotingRegressor([('rf', model), ('lr', randomforest)]).fit(X_train, y_train)\n", + " #model = VotingRegressor([('rf', model), ('gb', gb)]).fit(X_train, y_train)\n", " #model = VotingRegressor([('lr', pipe_rfe)]).fit(X, logit(y))\n", "\n", " df = pd.merge(risk, \n", @@ -167,43 +171,46 @@ "source": [ "#examine the effect of any paricular variable\n", "steps = 100\n", - "index_type = 'HY'\n", - "plots = {}\n", - "tranche_attach = []\n", + "for index_type in ['HY', 'IG', 'EU', 'XO']:\n", + " plots = {}\n", + " tranche_attach = []\n", + "\n", + " for i, X in gini_X[index_type].groupby('attach'):\n", + " tranche_attach.append(X.index[0][5])\n", + " for var in X.columns:\n", + " bins = np.linspace(X[var].min(), X[var].max(),num=steps)\n", + " testing_df = pd.DataFrame(bins, columns=[var])\n", + " for var_1 in X.drop(var, axis=1).columns:\n", + " testing_df = pd.concat([testing_df, pd.Series(np.repeat(X.iloc[-1][var_1], steps),name=var_1)], axis=1)\n", + " plots[i, var] = pd.Series(expit(gini_model[index_type].predict(testing_df[X.columns])), index=testing_df[var])\n", "\n", - "for i, X in gini_X[index_type].groupby('attach'):\n", - " tranche_attach.append(X.index[0][5])\n", - " for var in X.columns:\n", - " bins = np.linspace(X[var].min(), X[var].max(),num=steps)\n", - " testing_df = pd.DataFrame(bins, columns=[var])\n", - " for var_1 in X.drop(var, axis=1).columns:\n", - " testing_df = pd.concat([testing_df, pd.Series(np.repeat(X.iloc[-1][var_1], steps),name=var_1)], axis=1)\n", - " plots[i, var] = pd.Series(expit(gini_model[index_type].predict(testing_df[X.columns])), index=testing_df[var])\n", + " sensitivies = pd.concat(plots, names=['attach', 'shock', 'value'])\n", + " sensitivies.to_csv('/home/serenitas/edwin/DispersionModel/' + index_type + '_sensitivies.csv')\n", "\n", - "fig, axes = plt.subplots(nrows=3, ncols=len(X.columns), figsize = (20,10))\n", - "for i, p in enumerate(plots):\n", - " x_loc = int(i/len(X.columns))\n", - " y_loc = i % len(X.columns)\n", - " if x_loc == 0:\n", - " axes[x_loc, y_loc].set_title(p[1]) \n", - " plots[p].plot(ax=axes[x_loc, y_loc], label=i, xlabel=\"\")\n", - "for i in [0,1,2]:\n", - " fig.axes[i*len(X.columns)].text(-0.2, 0.5, \"tranche attach: \" + str(tranche_attach[i]),\n", - " transform=fig.axes[i*len(X.columns)].transAxes,\n", - " verticalalignment='center',\n", - " rotation=90)\n", - "fig.savefig(\"/home/serenitas/edwin/PythonGraphs/dispersion_model.png\", bbox_inches='tight')\n", + " fig, axes = plt.subplots(nrows=3, ncols=len(X.columns), figsize = (20,10))\n", + " for i, p in enumerate(plots):\n", + " x_loc = int(i/len(X.columns))\n", + " y_loc = i % len(X.columns)\n", + " if x_loc == 0:\n", + " axes[x_loc, y_loc].set_title(p[1]) \n", + " plots[p].plot(ax=axes[x_loc, y_loc], label=i, xlabel=\"\")\n", + " for i in [0,1,2]:\n", + " fig.axes[i*len(X.columns)].text(-0.2, 0.5, \"tranche attach: \" + str(tranche_attach[i]),\n", + " transform=fig.axes[i*len(X.columns)].transAxes,\n", + " verticalalignment='center',\n", + " rotation=90)\n", + " fig.savefig(\"/home/serenitas/edwin/PythonGraphs/dispersion_model.png\", bbox_inches='tight')\n", "\n", - "fig_1, axes_1 = plt.subplots(nrows=3, ncols=1, figsize = (15,8))\n", - "for i, p in enumerate(plots):\n", - " x_loc = int(i/len(X.columns))\n", - " plots[p].plot(ax=axes_1[x_loc], label=p[1], xlabel=\"\", legend=True)\n", - "for i in [0,1,2]:\n", - " fig_1.axes[i].text(-0.05, 0.5, \"tranche attach: \" + str(tranche_attach[i]),\n", - " transform=fig_1.axes[i].transAxes,\n", - " verticalalignment='center',\n", - " rotation=90)\n", - "fig_1.savefig(\"/home/serenitas/edwin/PythonGraphs/dispersion_model_consolidated.png\", bbox_inches='tight')" + " fig_1, axes_1 = plt.subplots(nrows=3, ncols=1, figsize = (15,8))\n", + " for i, p in enumerate(plots):\n", + " x_loc = int(i/len(X.columns))\n", + " plots[p].plot(ax=axes_1[x_loc], label=p[1], xlabel=\"\", legend=True)\n", + " for i in [0,1,2]:\n", + " fig_1.axes[i].text(-0.05, 0.5, \"tranche attach: \" + str(tranche_attach[i]),\n", + " transform=fig_1.axes[i].transAxes,\n", + " verticalalignment='center',\n", + " rotation=90)\n", + " fig_1.savefig(\"/home/serenitas/edwin/PythonGraphs/dispersion_model_consolidated.png\", bbox_inches='tight')" ] }, { @@ -213,6 +220,19 @@ "outputs": [], "source": [ "#Section 2----------------------------------------------------\n", + "#plot the gini coefficients\n", + "for index_type in ['HY', 'IG', 'EU', 'XO']:\n", + " ginis = gini_results[index_type].xs([0, '5yr', index_type],level=['attach','tenor', 'index']).groupby(['date', 'series']).nth(-1).gini.unstack(level='series')\n", + " ginis.to_csv('/home/serenitas/edwin/DispersionModel/' + index_type + '_gini.csv')" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "#Section 3----------------------------------------------------\n", "#Fixed Model\n", "value_date = (datetime.datetime.today() - pd.offsets.BDay(1)).date()\n", "start = (datetime.datetime.today() - pd.offsets.BDay(1) * 365 *4).date()\n", @@ -236,6 +256,13 @@ "execution_count": null, "metadata": {}, "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "#plot the residuals\n", "fitted = gini_model['HY'].fit()\n", @@ -256,13 +283,7 @@ "execution_count": null, "metadata": {}, "outputs": [], - "source": [ - "#Section 3----------------------------------------------------\n", - "#plot the gini coefficients\n", - "index_type='EU'\n", - "ginis = gini_results[index_type].xs([0, '5yr', index_type],level=['attach','tenor', 'index']).groupby(['date', 'series']).nth(-1).gini.unstack(level='series')\n", - "ginis.sort_index(ascending=False).to_clipboard()" - ] + "source": [] }, { "cell_type": "code", @@ -274,9 +295,9 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "Python 3.9.1 64-bit", "language": "python", - "name": "python3" + "name": "python39164bit6ddd573894c04d6a858a9a58880cc9d4" }, "language_info": { "codemirror_mode": { |