{ "cells": [ { "cell_type": "markdown", "id": "81d12e20", "metadata": {}, "source": [ "# Assignment 5" ] }, { "cell_type": "markdown", "id": "d7e98fab", "metadata": {}, "source": [ "## Martha Brinkmann - 6504930105" ] }, { "cell_type": "markdown", "id": "44c694df", "metadata": {}, "source": [ "### 1.1" ] }, { "cell_type": "code", "execution_count": 8, "id": "a0028196", "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
FoodBeerSmokeGamesBooksHshldClthsHlthChemsTxtls...TelcmServsBusEqPaperTransWhlslRtailMealsFinOther
1926070.56-5.191.292.9310.97-0.488.081.778.140.39...0.839.222.067.701.91-23.790.071.87-0.025.20
1926082.5927.036.500.5510.01-3.58-2.514.255.507.97...2.172.024.39-2.384.855.39-0.75-0.134.476.76
1926091.164.021.266.58-0.990.73-0.510.695.332.30...2.412.250.19-5.540.07-7.870.25-0.56-1.61-3.86
192610-3.06-3.311.06-4.769.47-4.680.12-0.57-4.761.00...-0.11-2.00-1.09-5.08-2.61-15.38-2.20-4.11-5.51-8.49
1926116.357.294.551.66-5.80-0.541.875.425.203.10...1.633.773.643.841.614.676.524.332.344.00
..................................................................
2022043.013.036.37-25.22-10.762.04-7.00-6.80-2.286.63...-10.70-12.59-12.26-0.74-10.93-2.14-11.41-5.47-7.99-7.65
202205-1.68-1.602.67-2.93-7.40-5.12-6.450.994.522.38...8.54-3.35-0.75-0.66-4.591.03-5.64-3.292.80-1.19
202206-1.64-0.02-11.63-11.33-12.53-2.56-12.00-2.05-15.65-11.17...-6.72-6.79-10.19-8.51-7.14-6.43-8.50-9.02-9.05-11.78
2022073.675.490.5614.6212.100.7611.862.757.666.86...-0.408.6015.687.229.339.0816.3311.897.389.19
202208-1.61-1.87-0.12-2.95-4.97-2.16-6.01-5.07-1.39-12.20...-3.00-4.72-5.89-7.66-1.46-1.60-3.46-1.47-2.24-3.65
\n", "

1154 rows × 30 columns

\n", "
" ], "text/plain": [ " Food Beer Smoke Games Books Hshld Clths Hlth Chems Txtls \\\n", "192607 0.56 -5.19 1.29 2.93 10.97 -0.48 8.08 1.77 8.14 0.39 \n", "192608 2.59 27.03 6.50 0.55 10.01 -3.58 -2.51 4.25 5.50 7.97 \n", "192609 1.16 4.02 1.26 6.58 -0.99 0.73 -0.51 0.69 5.33 2.30 \n", "192610 -3.06 -3.31 1.06 -4.76 9.47 -4.68 0.12 -0.57 -4.76 1.00 \n", "192611 6.35 7.29 4.55 1.66 -5.80 -0.54 1.87 5.42 5.20 3.10 \n", "... ... ... ... ... ... ... ... ... ... ... \n", "202204 3.01 3.03 6.37 -25.22 -10.76 2.04 -7.00 -6.80 -2.28 6.63 \n", "202205 -1.68 -1.60 2.67 -2.93 -7.40 -5.12 -6.45 0.99 4.52 2.38 \n", "202206 -1.64 -0.02 -11.63 -11.33 -12.53 -2.56 -12.00 -2.05 -15.65 -11.17 \n", "202207 3.67 5.49 0.56 14.62 12.10 0.76 11.86 2.75 7.66 6.86 \n", "202208 -1.61 -1.87 -0.12 -2.95 -4.97 -2.16 -6.01 -5.07 -1.39 -12.20 \n", "\n", " ... Telcm Servs BusEq Paper Trans Whlsl Rtail Meals Fin \\\n", "192607 ... 0.83 9.22 2.06 7.70 1.91 -23.79 0.07 1.87 -0.02 \n", "192608 ... 2.17 2.02 4.39 -2.38 4.85 5.39 -0.75 -0.13 4.47 \n", "192609 ... 2.41 2.25 0.19 -5.54 0.07 -7.87 0.25 -0.56 -1.61 \n", "192610 ... -0.11 -2.00 -1.09 -5.08 -2.61 -15.38 -2.20 -4.11 -5.51 \n", "192611 ... 1.63 3.77 3.64 3.84 1.61 4.67 6.52 4.33 2.34 \n", "... ... ... ... ... ... ... ... ... ... ... \n", "202204 ... -10.70 -12.59 -12.26 -0.74 -10.93 -2.14 -11.41 -5.47 -7.99 \n", "202205 ... 8.54 -3.35 -0.75 -0.66 -4.59 1.03 -5.64 -3.29 2.80 \n", "202206 ... -6.72 -6.79 -10.19 -8.51 -7.14 -6.43 -8.50 -9.02 -9.05 \n", "202207 ... -0.40 8.60 15.68 7.22 9.33 9.08 16.33 11.89 7.38 \n", "202208 ... -3.00 -4.72 -5.89 -7.66 -1.46 -1.60 -3.46 -1.47 -2.24 \n", "\n", " Other \n", "192607 5.20 \n", "192608 6.76 \n", "192609 -3.86 \n", "192610 -8.49 \n", "192611 4.00 \n", "... ... \n", "202204 -7.65 \n", "202205 -1.19 \n", "202206 -11.78 \n", "202207 9.19 \n", "202208 -3.65 \n", "\n", "[1154 rows x 30 columns]" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "\n", "%matplotlib inline\n", "# activate plot theme\n", "import qeds\n", "\n", "qeds.themes.mpl_style();\n", "plotly_template = qeds.themes.plotly_template()\n", "colors = qeds.themes.COLOR_CYCLE\n", "\n", "\n", "from sklearn import (linear_model, metrics, model_selection)\n", "\n", "df = pd.read_csv('30_Industry_Portfolios.csv', index_col=0)\n", "df.astype(float)\n" ] }, { "cell_type": "code", "execution_count": 11, "id": "7a24a76b", "metadata": {}, "outputs": [], "source": [ "beta = {}\n", "alpha = {}" ] }, { "cell_type": "code", "execution_count": null, "id": "f4d7e9d4", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "id": "f9e38d5c", "metadata": {}, "source": [ "1.2" ] }, { "cell_type": "code", "execution_count": null, "id": "5a0dd9e8", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "id": "f32bbcfc", "metadata": {}, "source": [ "1.3" ] }, { "cell_type": "code", "execution_count": 12, "id": "394b2f6f", "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import KFold\n", "kf = KFold(n_splits=10,shuffle=True)" ] }, { "cell_type": "code", "execution_count": null, "id": "81a04d4e", "metadata": {}, "outputs": [], "source": [ "err_train = 0\n", "err_test =0\n", "for train,test in kf.split(X):\n", " lr=linear_model.LinearRegression()\n", " reg=lr.fit(X[train],y[train])\n", " y_pred_train =reg.predict(X[train])\n", " y_pred_test =reg.predict(X[test])\n", " e_train= y[train]-y_pred_train\n", " e_test = y[test]-y_pred_test\n", " err_train += np.sqrt(np.mean(e_train*e_train)) \n", " err_test += np.sqrt(np.mean(e_test*e_test)) \n", "rmse_train_10cv_model1 = err_train/10 #average the rmse\n", "rmse_test_10cv_model1 = err_test/10 #average the rmse\n", "print('RMSE on 10-fold CV on the train data: {}'.format(rmse_train_10cv_model1))\n", "print('RMSE on 10-fold CV on the test data: {}'.format(rmse_test_10cv_model1))" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.12" } }, "nbformat": 4, "nbformat_minor": 5 }