Solution - Pandas, Numpy, Statsmodels, Plotting.ipynb 4.37 KB
 christian.foerster committed Nov 21, 2019 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 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 ``````{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Pandas, (Numpy), Statsmodels and Plotting\n", "\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "#####################################################\n", "## YOUR DATA\n", "from sklearn import datasets\n", "iris=datasets.load_iris()\n", "\n", "iris_data=iris.data\n", "iris_header=iris.feature_names\n", "iris_group=iris.target\n", "iris_target_names=iris.target_names\n", "####################################################" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**1. Convert data to a Pandas dataframe!**\n", "\n", "These columns must be in the dataframe:\n", "\n", "sepal_length | sepal_width | petal_length | petal_width | species\n", "\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "\n", "\n", "df = pd.DataFrame(iris_data, columns=iris_header)\n", "df.columns = [\"sepal_length\", \"sepal_width\", \"petal_length\", \"petal_width\"]\n", "df[\"species\"] = iris_group\n", "for i in range(3):\n", " df.loc[df.species == i, \"species\"] = iris_target_names[i]\n", " \n", "df.head(5)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**2. Plot the data to get a better feel for it. (Scattermatrix would be a good idea)**" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "%matplotlib inline\n", "from pandas.plotting import scatter_matrix\n", "\n", "# to get a nice plot we're gonna use some colors\n", "species_to_color = { 'setosa': '#377eb8',\n", " 'versicolor': '#4eae4b',\n", " 'virginica': '#e41a1c'}\n", "\n", "colors = [species_to_color[s] for s in df.species]\n", "\n", "scatter_matrix(df,c=colors, figsize=(16,16))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**3. Now plot the data _grouped_ by target_name.**" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "df.groupby(\"species\").plot()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**4. Create a multidimensional linear model that tries to guess the petal width depending on petal_length, sepal_width, sepal_length and check how well it fits!**" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import statsmodels.formula.api as smf\n", "\n", "linear = smf.ols(formula='petal_width ~ petal_length + sepal_width + sepal_length', data=df)\n", "result_linear = linear.fit()\n", "print(result_linear.summary())\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**5. Create Numpy array from the setosa sepal and petal values only!**" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "array=df.loc[df.species == \"setosa\", df.columns[:-1]].values\n", "array" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "df.species.unique()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "@webio": { "lastCommId": null, "lastKernelId": null }, "kernelspec": { "display_name": "Python 3", "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": "3.6.8" } }, "nbformat": 4, "nbformat_minor": 2 }``````