{ "cells": [ { "cell_type": "markdown", "id": "9b690938", "metadata": {}, "source": [ "# Class 29: Choosing a Model\n", "\n", "1. log onto prismia\n", "1. share your favorite restaraunt on/near campus in the zoom chat" ] }, { "cell_type": "markdown", "id": "dd6303b2", "metadata": {}, "source": [ "## Portfolio PR" ] }, { "cell_type": "code", "execution_count": 1, "id": "06ee681e", "metadata": {}, "outputs": [], "source": [ "# %load http://drsmb.co/310\n", "import matplotlib.pyplot as plt\n", "import numpy as np\n", "import seaborn as sns\n", "import pandas as pd\n", "from sklearn import datasets\n", "from sklearn import cluster\n", "from sklearn import svm\n", "from sklearn import tree\n", "from sklearn import model_selection" ] }, { "cell_type": "code", "execution_count": 2, "id": "d1f44a3b", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "GridSearchCV(estimator=DecisionTreeClassifier(),\n", " param_grid={'criterion': ['gini', 'entropy'],\n", " 'max_depth': [2, 3, 4],\n", " 'min_samples_leaf': [2, 4, 6, 8, 10, 12, 14, 16, 18]})" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "iris_X, iris_y = datasets.load_iris(return_X_y= True)\n", "iris_X_train, iris_X_test, iris_y_train, iris_y_test = model_selection.train_test_split(iris_X,iris_y)\n", "dt = tree.DecisionTreeClassifier()\n", "params_dt = {'criterion':['gini','entropy'],'max_depth':[2,3,4],\n", " 'min_samples_leaf':list(range(2,20,2))}\n", "dt_opt = model_selection.GridSearchCV(dt,params_dt)\n", "dt_opt.fit(iris_X_train,iris_y_train)" ] }, { "cell_type": "code", "execution_count": 3, "id": "7e99589b", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([1, 0, 0, 1, 2, 2, 0, 2, 0, 2, 0, 0, 2, 1, 2, 0, 2, 2, 2, 2, 0, 2,\n", " 2, 0, 2, 1, 0, 1, 1, 0, 0, 2, 1, 2, 2, 1, 2, 2])" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dt_opt.predict(iris_X_test)" ] }, { "cell_type": "code", "execution_count": 4, "id": "a006dd92", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([1, 0, 0, 1, 2, 2, 0, 2, 0, 2, 0, 0, 2, 1, 2, 0, 2, 2, 2, 2, 0, 2,\n", " 2, 0, 2, 1, 0, 1, 1, 0, 0, 2, 1, 2, 2, 1, 2, 2])" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dt_opt.best_estimator_.predict(iris_X_test)" ] }, { "cell_type": "code", "execution_count": 5, "id": "b5195fe1", "metadata": {}, "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
mean_fit_timestd_fit_timemean_score_timestd_score_timeparam_criterionparam_max_depthparam_min_samples_leafparamssplit0_test_scoresplit1_test_scoresplit2_test_scoresplit3_test_scoresplit4_test_scoremean_test_scorestd_test_scorerank_test_score
00.0005610.0001380.0002760.000041gini22{'criterion': 'gini', 'max_depth': 2, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
10.0004430.0000230.0002380.000013gini24{'criterion': 'gini', 'max_depth': 2, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
20.0004840.0000220.0002660.000011gini26{'criterion': 'gini', 'max_depth': 2, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
30.0004470.0000270.0002390.000015gini28{'criterion': 'gini', 'max_depth': 2, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
40.0004890.0000220.0002550.000008gini210{'criterion': 'gini', 'max_depth': 2, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
50.0004730.0000310.0002440.000019gini212{'criterion': 'gini', 'max_depth': 2, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
60.0004600.0000310.0002500.000013gini214{'criterion': 'gini', 'max_depth': 2, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
70.0004470.0000310.0002490.000019gini216{'criterion': 'gini', 'max_depth': 2, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
80.0004770.0000210.0002660.000032gini218{'criterion': 'gini', 'max_depth': 2, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
90.0004750.0000380.0002480.000021gini32{'criterion': 'gini', 'max_depth': 3, 'min_sam...0.8695650.9130431.0000001.0000000.9545450.9474310.0506421
100.0005020.0000140.0002610.000023gini34{'criterion': 'gini', 'max_depth': 3, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
110.0004700.0000400.0002430.000024gini36{'criterion': 'gini', 'max_depth': 3, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
120.0004380.0000260.0002340.000016gini38{'criterion': 'gini', 'max_depth': 3, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
130.0004740.0000460.0002520.000026gini310{'criterion': 'gini', 'max_depth': 3, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
140.0004990.0000180.0002630.000010gini312{'criterion': 'gini', 'max_depth': 3, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
150.0005000.0000200.0002580.000008gini314{'criterion': 'gini', 'max_depth': 3, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
160.0004950.0000230.0002590.000009gini316{'criterion': 'gini', 'max_depth': 3, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
170.0004810.0000220.0002490.000015gini318{'criterion': 'gini', 'max_depth': 3, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
180.0004860.0000250.0002460.000021gini42{'criterion': 'gini', 'max_depth': 4, 'min_sam...0.8695650.9130431.0000001.0000000.9545450.9474310.0506421
190.0004990.0000190.0002570.000008gini44{'criterion': 'gini', 'max_depth': 4, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
200.0004810.0000330.0002500.000025gini46{'criterion': 'gini', 'max_depth': 4, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
210.0004760.0000290.0002510.000017gini48{'criterion': 'gini', 'max_depth': 4, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
220.0004800.0000430.0002480.000020gini410{'criterion': 'gini', 'max_depth': 4, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
230.0004730.0000360.0002470.000023gini412{'criterion': 'gini', 'max_depth': 4, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
240.0004970.0000200.0002550.000016gini414{'criterion': 'gini', 'max_depth': 4, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
250.0004250.0000490.0002340.000027gini416{'criterion': 'gini', 'max_depth': 4, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
260.0004330.0000340.0002250.000008gini418{'criterion': 'gini', 'max_depth': 4, 'min_sam...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
270.0004720.0000490.0002470.000022entropy22{'criterion': 'entropy', 'max_depth': 2, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
280.0004650.0000390.0002480.000017entropy24{'criterion': 'entropy', 'max_depth': 2, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
290.0004510.0000570.0002290.000030entropy26{'criterion': 'entropy', 'max_depth': 2, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
300.0004380.0000370.0002260.000025entropy28{'criterion': 'entropy', 'max_depth': 2, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
310.0004120.0000600.0002240.000040entropy210{'criterion': 'entropy', 'max_depth': 2, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
320.0004800.0000340.0002400.000025entropy212{'criterion': 'entropy', 'max_depth': 2, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
330.0004650.0000350.0002460.000023entropy214{'criterion': 'entropy', 'max_depth': 2, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
340.0004700.0000320.0002360.000024entropy216{'criterion': 'entropy', 'max_depth': 2, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
350.0004430.0000620.0002240.000025entropy218{'criterion': 'entropy', 'max_depth': 2, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
360.0004500.0000540.0002370.000034entropy32{'criterion': 'entropy', 'max_depth': 3, 'min_...0.8695650.9130430.9090911.0000000.9545450.9292490.0444454
370.0004660.0000490.0002230.000029entropy34{'criterion': 'entropy', 'max_depth': 3, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
380.0004190.0000300.0002110.000014entropy36{'criterion': 'entropy', 'max_depth': 3, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
390.0004780.0000570.0002370.000036entropy38{'criterion': 'entropy', 'max_depth': 3, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
400.0004630.0000320.0002370.000017entropy310{'criterion': 'entropy', 'max_depth': 3, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
410.0004270.0000490.0002250.000033entropy312{'criterion': 'entropy', 'max_depth': 3, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
420.0004530.0000410.0002230.000026entropy314{'criterion': 'entropy', 'max_depth': 3, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
430.0004220.0000490.0002240.000032entropy316{'criterion': 'entropy', 'max_depth': 3, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
440.0003930.0000390.0002030.000021entropy318{'criterion': 'entropy', 'max_depth': 3, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
450.0004590.0000690.0002250.000041entropy42{'criterion': 'entropy', 'max_depth': 4, 'min_...0.8695650.9565220.9545451.0000000.9545450.9470360.0424493
460.0004070.0000350.0002000.000014entropy44{'criterion': 'entropy', 'max_depth': 4, 'min_...0.8695650.9565220.9545450.9090910.9545450.9288540.0346165
470.0004890.0000540.0002560.000019entropy46{'criterion': 'entropy', 'max_depth': 4, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
480.0004380.0000530.0002260.000027entropy48{'criterion': 'entropy', 'max_depth': 4, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
490.0004130.0000720.0002090.000032entropy410{'criterion': 'entropy', 'max_depth': 4, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
500.0004000.0000350.0002180.000026entropy412{'criterion': 'entropy', 'max_depth': 4, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
510.0004450.0000600.0002410.000029entropy414{'criterion': 'entropy', 'max_depth': 4, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
520.0004400.0000310.0002300.000024entropy416{'criterion': 'entropy', 'max_depth': 4, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
530.0004700.0000390.0002550.000019entropy418{'criterion': 'entropy', 'max_depth': 4, 'min_...0.8695650.9130430.9090910.9090910.9545450.9110670.0269246
\n", "
" ], "text/plain": [ " mean_fit_time std_fit_time mean_score_time std_score_time \\\n", "0 0.000561 0.000138 0.000276 0.000041 \n", "1 0.000443 0.000023 0.000238 0.000013 \n", "2 0.000484 0.000022 0.000266 0.000011 \n", "3 0.000447 0.000027 0.000239 0.000015 \n", "4 0.000489 0.000022 0.000255 0.000008 \n", "5 0.000473 0.000031 0.000244 0.000019 \n", "6 0.000460 0.000031 0.000250 0.000013 \n", "7 0.000447 0.000031 0.000249 0.000019 \n", "8 0.000477 0.000021 0.000266 0.000032 \n", "9 0.000475 0.000038 0.000248 0.000021 \n", "10 0.000502 0.000014 0.000261 0.000023 \n", "11 0.000470 0.000040 0.000243 0.000024 \n", "12 0.000438 0.000026 0.000234 0.000016 \n", "13 0.000474 0.000046 0.000252 0.000026 \n", "14 0.000499 0.000018 0.000263 0.000010 \n", "15 0.000500 0.000020 0.000258 0.000008 \n", "16 0.000495 0.000023 0.000259 0.000009 \n", "17 0.000481 0.000022 0.000249 0.000015 \n", "18 0.000486 0.000025 0.000246 0.000021 \n", "19 0.000499 0.000019 0.000257 0.000008 \n", "20 0.000481 0.000033 0.000250 0.000025 \n", "21 0.000476 0.000029 0.000251 0.000017 \n", "22 0.000480 0.000043 0.000248 0.000020 \n", "23 0.000473 0.000036 0.000247 0.000023 \n", "24 0.000497 0.000020 0.000255 0.000016 \n", "25 0.000425 0.000049 0.000234 0.000027 \n", "26 0.000433 0.000034 0.000225 0.000008 \n", "27 0.000472 0.000049 0.000247 0.000022 \n", "28 0.000465 0.000039 0.000248 0.000017 \n", "29 0.000451 0.000057 0.000229 0.000030 \n", "30 0.000438 0.000037 0.000226 0.000025 \n", "31 0.000412 0.000060 0.000224 0.000040 \n", "32 0.000480 0.000034 0.000240 0.000025 \n", "33 0.000465 0.000035 0.000246 0.000023 \n", "34 0.000470 0.000032 0.000236 0.000024 \n", "35 0.000443 0.000062 0.000224 0.000025 \n", "36 0.000450 0.000054 0.000237 0.000034 \n", "37 0.000466 0.000049 0.000223 0.000029 \n", "38 0.000419 0.000030 0.000211 0.000014 \n", "39 0.000478 0.000057 0.000237 0.000036 \n", "40 0.000463 0.000032 0.000237 0.000017 \n", "41 0.000427 0.000049 0.000225 0.000033 \n", "42 0.000453 0.000041 0.000223 0.000026 \n", "43 0.000422 0.000049 0.000224 0.000032 \n", "44 0.000393 0.000039 0.000203 0.000021 \n", "45 0.000459 0.000069 0.000225 0.000041 \n", "46 0.000407 0.000035 0.000200 0.000014 \n", "47 0.000489 0.000054 0.000256 0.000019 \n", "48 0.000438 0.000053 0.000226 0.000027 \n", "49 0.000413 0.000072 0.000209 0.000032 \n", "50 0.000400 0.000035 0.000218 0.000026 \n", "51 0.000445 0.000060 0.000241 0.000029 \n", "52 0.000440 0.000031 0.000230 0.000024 \n", "53 0.000470 0.000039 0.000255 0.000019 \n", "\n", " param_criterion param_max_depth param_min_samples_leaf \\\n", "0 gini 2 2 \n", "1 gini 2 4 \n", "2 gini 2 6 \n", "3 gini 2 8 \n", "4 gini 2 10 \n", "5 gini 2 12 \n", "6 gini 2 14 \n", "7 gini 2 16 \n", "8 gini 2 18 \n", "9 gini 3 2 \n", "10 gini 3 4 \n", "11 gini 3 6 \n", "12 gini 3 8 \n", "13 gini 3 10 \n", "14 gini 3 12 \n", "15 gini 3 14 \n", "16 gini 3 16 \n", "17 gini 3 18 \n", "18 gini 4 2 \n", "19 gini 4 4 \n", "20 gini 4 6 \n", "21 gini 4 8 \n", "22 gini 4 10 \n", "23 gini 4 12 \n", "24 gini 4 14 \n", "25 gini 4 16 \n", "26 gini 4 18 \n", "27 entropy 2 2 \n", "28 entropy 2 4 \n", "29 entropy 2 6 \n", "30 entropy 2 8 \n", "31 entropy 2 10 \n", "32 entropy 2 12 \n", "33 entropy 2 14 \n", "34 entropy 2 16 \n", "35 entropy 2 18 \n", "36 entropy 3 2 \n", "37 entropy 3 4 \n", "38 entropy 3 6 \n", "39 entropy 3 8 \n", "40 entropy 3 10 \n", "41 entropy 3 12 \n", "42 entropy 3 14 \n", "43 entropy 3 16 \n", "44 entropy 3 18 \n", "45 entropy 4 2 \n", "46 entropy 4 4 \n", "47 entropy 4 6 \n", "48 entropy 4 8 \n", "49 entropy 4 10 \n", "50 entropy 4 12 \n", "51 entropy 4 14 \n", "52 entropy 4 16 \n", "53 entropy 4 18 \n", "\n", " params split0_test_score \\\n", "0 {'criterion': 'gini', 'max_depth': 2, 'min_sam... 0.869565 \n", "1 {'criterion': 'gini', 'max_depth': 2, 'min_sam... 0.869565 \n", "2 {'criterion': 'gini', 'max_depth': 2, 'min_sam... 0.869565 \n", "3 {'criterion': 'gini', 'max_depth': 2, 'min_sam... 0.869565 \n", "4 {'criterion': 'gini', 'max_depth': 2, 'min_sam... 0.869565 \n", "5 {'criterion': 'gini', 'max_depth': 2, 'min_sam... 0.869565 \n", "6 {'criterion': 'gini', 'max_depth': 2, 'min_sam... 0.869565 \n", "7 {'criterion': 'gini', 'max_depth': 2, 'min_sam... 0.869565 \n", "8 {'criterion': 'gini', 'max_depth': 2, 'min_sam... 0.869565 \n", "9 {'criterion': 'gini', 'max_depth': 3, 'min_sam... 0.869565 \n", "10 {'criterion': 'gini', 'max_depth': 3, 'min_sam... 0.869565 \n", "11 {'criterion': 'gini', 'max_depth': 3, 'min_sam... 0.869565 \n", "12 {'criterion': 'gini', 'max_depth': 3, 'min_sam... 0.869565 \n", "13 {'criterion': 'gini', 'max_depth': 3, 'min_sam... 0.869565 \n", "14 {'criterion': 'gini', 'max_depth': 3, 'min_sam... 0.869565 \n", "15 {'criterion': 'gini', 'max_depth': 3, 'min_sam... 0.869565 \n", "16 {'criterion': 'gini', 'max_depth': 3, 'min_sam... 0.869565 \n", "17 {'criterion': 'gini', 'max_depth': 3, 'min_sam... 0.869565 \n", "18 {'criterion': 'gini', 'max_depth': 4, 'min_sam... 0.869565 \n", "19 {'criterion': 'gini', 'max_depth': 4, 'min_sam... 0.869565 \n", "20 {'criterion': 'gini', 'max_depth': 4, 'min_sam... 0.869565 \n", "21 {'criterion': 'gini', 'max_depth': 4, 'min_sam... 0.869565 \n", "22 {'criterion': 'gini', 'max_depth': 4, 'min_sam... 0.869565 \n", "23 {'criterion': 'gini', 'max_depth': 4, 'min_sam... 0.869565 \n", "24 {'criterion': 'gini', 'max_depth': 4, 'min_sam... 0.869565 \n", "25 {'criterion': 'gini', 'max_depth': 4, 'min_sam... 0.869565 \n", "26 {'criterion': 'gini', 'max_depth': 4, 'min_sam... 0.869565 \n", "27 {'criterion': 'entropy', 'max_depth': 2, 'min_... 0.869565 \n", "28 {'criterion': 'entropy', 'max_depth': 2, 'min_... 0.869565 \n", "29 {'criterion': 'entropy', 'max_depth': 2, 'min_... 0.869565 \n", "30 {'criterion': 'entropy', 'max_depth': 2, 'min_... 0.869565 \n", "31 {'criterion': 'entropy', 'max_depth': 2, 'min_... 0.869565 \n", "32 {'criterion': 'entropy', 'max_depth': 2, 'min_... 0.869565 \n", "33 {'criterion': 'entropy', 'max_depth': 2, 'min_... 0.869565 \n", "34 {'criterion': 'entropy', 'max_depth': 2, 'min_... 0.869565 \n", "35 {'criterion': 'entropy', 'max_depth': 2, 'min_... 0.869565 \n", "36 {'criterion': 'entropy', 'max_depth': 3, 'min_... 0.869565 \n", "37 {'criterion': 'entropy', 'max_depth': 3, 'min_... 0.869565 \n", "38 {'criterion': 'entropy', 'max_depth': 3, 'min_... 0.869565 \n", "39 {'criterion': 'entropy', 'max_depth': 3, 'min_... 0.869565 \n", "40 {'criterion': 'entropy', 'max_depth': 3, 'min_... 0.869565 \n", "41 {'criterion': 'entropy', 'max_depth': 3, 'min_... 0.869565 \n", "42 {'criterion': 'entropy', 'max_depth': 3, 'min_... 0.869565 \n", "43 {'criterion': 'entropy', 'max_depth': 3, 'min_... 0.869565 \n", "44 {'criterion': 'entropy', 'max_depth': 3, 'min_... 0.869565 \n", "45 {'criterion': 'entropy', 'max_depth': 4, 'min_... 0.869565 \n", "46 {'criterion': 'entropy', 'max_depth': 4, 'min_... 0.869565 \n", "47 {'criterion': 'entropy', 'max_depth': 4, 'min_... 0.869565 \n", "48 {'criterion': 'entropy', 'max_depth': 4, 'min_... 0.869565 \n", "49 {'criterion': 'entropy', 'max_depth': 4, 'min_... 0.869565 \n", "50 {'criterion': 'entropy', 'max_depth': 4, 'min_... 0.869565 \n", "51 {'criterion': 'entropy', 'max_depth': 4, 'min_... 0.869565 \n", "52 {'criterion': 'entropy', 'max_depth': 4, 'min_... 0.869565 \n", "53 {'criterion': 'entropy', 'max_depth': 4, 'min_... 0.869565 \n", "\n", " split1_test_score split2_test_score split3_test_score \\\n", "0 0.913043 0.909091 0.909091 \n", "1 0.913043 0.909091 0.909091 \n", "2 0.913043 0.909091 0.909091 \n", "3 0.913043 0.909091 0.909091 \n", "4 0.913043 0.909091 0.909091 \n", "5 0.913043 0.909091 0.909091 \n", "6 0.913043 0.909091 0.909091 \n", "7 0.913043 0.909091 0.909091 \n", "8 0.913043 0.909091 0.909091 \n", "9 0.913043 1.000000 1.000000 \n", "10 0.913043 0.909091 0.909091 \n", "11 0.913043 0.909091 0.909091 \n", "12 0.913043 0.909091 0.909091 \n", "13 0.913043 0.909091 0.909091 \n", "14 0.913043 0.909091 0.909091 \n", "15 0.913043 0.909091 0.909091 \n", "16 0.913043 0.909091 0.909091 \n", "17 0.913043 0.909091 0.909091 \n", "18 0.913043 1.000000 1.000000 \n", "19 0.913043 0.909091 0.909091 \n", "20 0.913043 0.909091 0.909091 \n", "21 0.913043 0.909091 0.909091 \n", "22 0.913043 0.909091 0.909091 \n", "23 0.913043 0.909091 0.909091 \n", "24 0.913043 0.909091 0.909091 \n", "25 0.913043 0.909091 0.909091 \n", "26 0.913043 0.909091 0.909091 \n", "27 0.913043 0.909091 0.909091 \n", "28 0.913043 0.909091 0.909091 \n", "29 0.913043 0.909091 0.909091 \n", "30 0.913043 0.909091 0.909091 \n", "31 0.913043 0.909091 0.909091 \n", "32 0.913043 0.909091 0.909091 \n", "33 0.913043 0.909091 0.909091 \n", "34 0.913043 0.909091 0.909091 \n", "35 0.913043 0.909091 0.909091 \n", "36 0.913043 0.909091 1.000000 \n", "37 0.913043 0.909091 0.909091 \n", "38 0.913043 0.909091 0.909091 \n", "39 0.913043 0.909091 0.909091 \n", "40 0.913043 0.909091 0.909091 \n", "41 0.913043 0.909091 0.909091 \n", "42 0.913043 0.909091 0.909091 \n", "43 0.913043 0.909091 0.909091 \n", "44 0.913043 0.909091 0.909091 \n", "45 0.956522 0.954545 1.000000 \n", "46 0.956522 0.954545 0.909091 \n", "47 0.913043 0.909091 0.909091 \n", "48 0.913043 0.909091 0.909091 \n", "49 0.913043 0.909091 0.909091 \n", "50 0.913043 0.909091 0.909091 \n", "51 0.913043 0.909091 0.909091 \n", "52 0.913043 0.909091 0.909091 \n", "53 0.913043 0.909091 0.909091 \n", "\n", " split4_test_score mean_test_score std_test_score rank_test_score \n", "0 0.954545 0.911067 0.026924 6 \n", "1 0.954545 0.911067 0.026924 6 \n", "2 0.954545 0.911067 0.026924 6 \n", "3 0.954545 0.911067 0.026924 6 \n", "4 0.954545 0.911067 0.026924 6 \n", "5 0.954545 0.911067 0.026924 6 \n", "6 0.954545 0.911067 0.026924 6 \n", "7 0.954545 0.911067 0.026924 6 \n", "8 0.954545 0.911067 0.026924 6 \n", "9 0.954545 0.947431 0.050642 1 \n", "10 0.954545 0.911067 0.026924 6 \n", "11 0.954545 0.911067 0.026924 6 \n", "12 0.954545 0.911067 0.026924 6 \n", "13 0.954545 0.911067 0.026924 6 \n", "14 0.954545 0.911067 0.026924 6 \n", "15 0.954545 0.911067 0.026924 6 \n", "16 0.954545 0.911067 0.026924 6 \n", "17 0.954545 0.911067 0.026924 6 \n", "18 0.954545 0.947431 0.050642 1 \n", "19 0.954545 0.911067 0.026924 6 \n", "20 0.954545 0.911067 0.026924 6 \n", "21 0.954545 0.911067 0.026924 6 \n", "22 0.954545 0.911067 0.026924 6 \n", "23 0.954545 0.911067 0.026924 6 \n", "24 0.954545 0.911067 0.026924 6 \n", "25 0.954545 0.911067 0.026924 6 \n", "26 0.954545 0.911067 0.026924 6 \n", "27 0.954545 0.911067 0.026924 6 \n", "28 0.954545 0.911067 0.026924 6 \n", "29 0.954545 0.911067 0.026924 6 \n", "30 0.954545 0.911067 0.026924 6 \n", "31 0.954545 0.911067 0.026924 6 \n", "32 0.954545 0.911067 0.026924 6 \n", "33 0.954545 0.911067 0.026924 6 \n", "34 0.954545 0.911067 0.026924 6 \n", "35 0.954545 0.911067 0.026924 6 \n", "36 0.954545 0.929249 0.044445 4 \n", "37 0.954545 0.911067 0.026924 6 \n", "38 0.954545 0.911067 0.026924 6 \n", "39 0.954545 0.911067 0.026924 6 \n", "40 0.954545 0.911067 0.026924 6 \n", "41 0.954545 0.911067 0.026924 6 \n", "42 0.954545 0.911067 0.026924 6 \n", "43 0.954545 0.911067 0.026924 6 \n", "44 0.954545 0.911067 0.026924 6 \n", "45 0.954545 0.947036 0.042449 3 \n", "46 0.954545 0.928854 0.034616 5 \n", "47 0.954545 0.911067 0.026924 6 \n", "48 0.954545 0.911067 0.026924 6 \n", "49 0.954545 0.911067 0.026924 6 \n", "50 0.954545 0.911067 0.026924 6 \n", "51 0.954545 0.911067 0.026924 6 \n", "52 0.954545 0.911067 0.026924 6 \n", "53 0.954545 0.911067 0.026924 6 " ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pd.DataFrame(dt_opt.cv_results_)" ] }, { "cell_type": "code", "execution_count": 6, "id": "0805fa57", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "filenames": { "image/png": "/home/runner/work/BrownFall20/BrownFall20/_build/jupyter_execute/notes/2020-11-16_7_1.png" }, "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "df = pd.DataFrame(dt_opt.cv_results_)\n", "df.plot('mean_score_time','mean_test_score')" ] }, { "cell_type": "code", "execution_count": 7, "id": "19e9313a", "metadata": {}, "outputs": [], "source": [ "%load http://drsmb.co" ] }, { "cell_type": "code", "execution_count": 8, "id": "5337d5a8", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "GridSearchCV(estimator=SVC(kernel='linear'),\n", " param_grid={'C': [0.5, 1, 10], 'kernel': ['linear', 'rbf']})" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "param_grid = {'kernel':['linear','rbf'], 'C':[.5, 1, 10]}\n", "svm_clf = svm.SVC(kernel='linear')\n", "svm_opt =model_selection.GridSearchCV(svm_clf,param_grid,)\n", "svm_opt.fit(iris_X_train, iris_y_train)" ] }, { "cell_type": "code", "execution_count": 9, "id": "421b7fe7", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "filenames": { "image/png": "/home/runner/work/BrownFall20/BrownFall20/_build/jupyter_execute/notes/2020-11-16_10_1.png" }, "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "df_svm = pd.DataFrame(svm_opt.cv_results_)\n", "df_svm.plot.scatter('mean_score_time','mean_test_score')" ] }, { "cell_type": "code", "execution_count": 10, "id": "42328b52", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "filenames": { "image/png": "/home/runner/work/BrownFall20/BrownFall20/_build/jupyter_execute/notes/2020-11-16_11_1.png" }, "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "df_svm.plot.scatter('mean_score_time','std_test_score')" ] }, { "cell_type": "code", "execution_count": null, "id": "88f87fe5", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "jupytext": { "text_representation": { "extension": ".md", "format_name": "myst", "format_version": 0.12, "jupytext_version": "1.6.0" } }, "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": "3.7.10" }, "source_map": [ 12, 19, 23, 36, 46, 50, 55, 59, 64, 68, 75, 80, 84 ] }, "nbformat": 4, "nbformat_minor": 5 }