diff --git "a/GA_KKPM.ipynb" "b/GA_KKPM.ipynb" --- "a/GA_KKPM.ipynb" +++ "b/GA_KKPM.ipynb" @@ -1094,10 +1094,10 @@ "text": [ "(690, 22) (230, 22) (690,) (230,)\n", "Best score in generation 1 : [0.7913043478260869]\n", - "Best score in generation 2 : [0.8173913043478261]\n", - "Best score in generation 3 : [0.7913043478260869]\n", - "Best score in generation 4 : [0.8217391304347826]\n", - "Best score in generation 5 : [0.8173913043478261]\n" + "Best score in generation 2 : [0.7913043478260869]\n", + "Best score in generation 3 : [0.8173913043478261]\n", + "Best score in generation 4 : [0.8130434782608695]\n", + "Best score in generation 5 : [0.8260869565217391]\n" ] } ], @@ -1131,7 +1131,7 @@ "outputs": [ { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -1152,13 +1152,13 @@ }, "outputs": [], "source": [ - "for index, clf in enumerate(best_models):\n", - " dump(clf, 'model-{}.joblib'.format(index))" + "# for index, clf in enumerate(best_models):\n", + "# dump(clf, 'model-{}.joblib'.format(index))" ] }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 11, "metadata": { "id": "fGbUe1WJYbxp" }, @@ -1169,7 +1169,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 12, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -1366,7 +1366,7 @@ "[230 rows x 9 columns]" ] }, - "execution_count": 13, + "execution_count": 12, "metadata": {}, "output_type": "execute_result" } @@ -1377,7 +1377,7 @@ }, { "cell_type": "code", - "execution_count": 36, + "execution_count": 13, "metadata": { "colab": { "base_uri": "https://localhost:8080/" @@ -1401,7 +1401,7 @@ }, { "cell_type": "code", - "execution_count": 34, + "execution_count": 14, "metadata": {}, "outputs": [ { @@ -1591,7 +1591,7 @@ "[230 rows x 9 columns]" ] }, - "execution_count": 34, + "execution_count": 14, "metadata": {}, "output_type": "execute_result" } @@ -1602,7 +1602,7 @@ }, { "cell_type": "code", - "execution_count": 37, + "execution_count": 15, "metadata": {}, "outputs": [ { @@ -1621,7 +1621,7 @@ " 0, 0, 1, 0, 1, 0, 1, 1, 1, 0], dtype=int64)" ] }, - "execution_count": 37, + "execution_count": 15, "metadata": {}, "output_type": "execute_result" } @@ -1630,6 +1630,1970 @@ "predictions" ] }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [ + { + "data": { + "image/svg+xml": [ + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "Tree\n", + "\n", + "\n", + "\n", + "0\n", + "\n", + "cp_4.0 <= 0.5\n", + "gini = 0.494\n", + "samples = 690\n", + "value = [308.0, 382.0]\n", + "\n", + "\n", + "\n", + "1\n", + "\n", + "sex <= 0.5\n", + "gini = 0.415\n", + "samples = 320\n", + "value = [226, 94]\n", + "\n", + "\n", + "\n", + "0->1\n", + "\n", + "\n", + "True\n", + "\n", + "\n", + "\n", + "86\n", + "\n", + "exang <= 0.5\n", + "gini = 0.345\n", + "samples = 370\n", + "value = [82, 288]\n", + "\n", + "\n", + "\n", + "0->86\n", + "\n", + "\n", + "False\n", + "\n", + "\n", + "\n", + "2\n", + "\n", + "thal_7.0 <= 0.5\n", + "gini = 0.172\n", + "samples = 95\n", + "value = [86, 9]\n", + "\n", + "\n", + "\n", + "1->2\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "29\n", + "\n", + "cp_2.0 <= 0.5\n", + "gini = 0.47\n", + "samples = 225\n", + "value = [140, 85]\n", + "\n", + "\n", + "\n", + "1->29\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "3\n", + "\n", + "cp_2.0 <= 0.5\n", + "gini = 0.126\n", + "samples = 89\n", + "value = [83, 6]\n", + "\n", + "\n", + "\n", + "2->3\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "22\n", + "\n", + "slope_1 <= 0.5\n", + "gini = 0.5\n", + "samples = 6\n", + "value = [3, 3]\n", + "\n", + "\n", + "\n", + "2->22\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "4\n", + "\n", + "slope_2 <= 0.5\n", + "gini = 0.162\n", + "samples = 45\n", + "value = [41, 4]\n", + "\n", + "\n", + "\n", + "3->4\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "15\n", + "\n", + "slope_2 <= 0.5\n", + "gini = 0.087\n", + "samples = 44\n", + "value = [42, 2]\n", + "\n", + "\n", + "\n", + "3->15\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "5\n", + "\n", + "exang <= 0.5\n", + "gini = 0.087\n", + "samples = 22\n", + "value = [21, 1]\n", + "\n", + "\n", + "\n", + "4->5\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "10\n", + "\n", + "thal_3.0 <= 0.5\n", + "gini = 0.227\n", + "samples = 23\n", + "value = [20, 3]\n", + "\n", + "\n", + "\n", + "4->10\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "6\n", + "\n", + "cp_1.0 <= 0.5\n", + "gini = 0.1\n", + "samples = 19\n", + "value = [18, 1]\n", + "\n", + "\n", + "\n", + "5->6\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "9\n", + "\n", + "gini = 0.0\n", + "samples = 3\n", + "value = [3, 0]\n", + "\n", + "\n", + "\n", + "5->9\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "7\n", + "\n", + "gini = 0.117\n", + "samples = 16\n", + "value = [15, 1]\n", + "\n", + "\n", + "\n", + "6->7\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "8\n", + "\n", + "gini = 0.0\n", + "samples = 3\n", + "value = [3, 0]\n", + "\n", + "\n", + "\n", + "6->8\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "11\n", + "\n", + "gini = 0.0\n", + "samples = 1\n", + "value = [1, 0]\n", + "\n", + "\n", + "\n", + "10->11\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "12\n", + "\n", + "cp_1.0 <= 0.5\n", + "gini = 0.236\n", + "samples = 22\n", + "value = [19, 3]\n", + "\n", + "\n", + "\n", + "10->12\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "13\n", + "\n", + "gini = 0.208\n", + "samples = 17\n", + "value = [15, 2]\n", + "\n", + "\n", + "\n", + "12->13\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "14\n", + "\n", + "gini = 0.32\n", + "samples = 5\n", + "value = [4, 1]\n", + "\n", + "\n", + "\n", + "12->14\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "16\n", + "\n", + "exang <= 0.5\n", + "gini = 0.153\n", + "samples = 12\n", + "value = [11, 1]\n", + "\n", + "\n", + "\n", + "15->16\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "19\n", + "\n", + "exang <= 0.5\n", + "gini = 0.061\n", + "samples = 32\n", + "value = [31, 1]\n", + "\n", + "\n", + "\n", + "15->19\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "17\n", + "\n", + "gini = 0.18\n", + "samples = 10\n", + "value = [9, 1]\n", + "\n", + "\n", + "\n", + "16->17\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "18\n", + "\n", + "gini = 0.0\n", + "samples = 2\n", + "value = [2, 0]\n", + "\n", + "\n", + "\n", + "16->18\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "20\n", + "\n", + "gini = 0.062\n", + "samples = 31\n", + "value = [30, 1]\n", + "\n", + "\n", + "\n", + "19->20\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "21\n", + "\n", + "gini = 0.0\n", + "samples = 1\n", + "value = [1, 0]\n", + "\n", + "\n", + "\n", + "19->21\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "23\n", + "\n", + "cp_2.0 <= 0.5\n", + "gini = 0.48\n", + "samples = 5\n", + "value = [2, 3]\n", + "\n", + "\n", + "\n", + "22->23\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "28\n", + "\n", + "gini = 0.0\n", + "samples = 1\n", + "value = [1, 0]\n", + "\n", + "\n", + "\n", + "22->28\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "24\n", + "\n", + "exang <= 0.5\n", + "gini = 0.444\n", + "samples = 3\n", + "value = [1, 2]\n", + "\n", + "\n", + "\n", + "23->24\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "27\n", + "\n", + "gini = 0.5\n", + "samples = 2\n", + "value = [1, 1]\n", + "\n", + "\n", + "\n", + "23->27\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "25\n", + "\n", + "gini = 0.5\n", + "samples = 2\n", + "value = [1, 1]\n", + "\n", + "\n", + "\n", + "24->25\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "26\n", + "\n", + "gini = 0.0\n", + "samples = 1\n", + "value = [0, 1]\n", + "\n", + "\n", + "\n", + "24->26\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "30\n", + "\n", + "slope_1 <= 0.5\n", + "gini = 0.5\n", + "samples = 137\n", + "value = [70, 67]\n", + "\n", + "\n", + "\n", + "29->30\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "69\n", + "\n", + "exang <= 0.5\n", + "gini = 0.325\n", + "samples = 88\n", + "value = [70, 18]\n", + "\n", + "\n", + "\n", + "29->69\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "31\n", + "\n", + "exang <= 0.5\n", + "gini = 0.496\n", + "samples = 105\n", + "value = [48.0, 57.0]\n", + "\n", + "\n", + "\n", + "30->31\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "58\n", + "\n", + "cp_1.0 <= 0.5\n", + "gini = 0.43\n", + "samples = 32\n", + "value = [22, 10]\n", + "\n", + "\n", + "\n", + "30->58\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "32\n", + "\n", + "cp_1.0 <= 0.5\n", + "gini = 0.5\n", + "samples = 82\n", + "value = [41, 41]\n", + "\n", + "\n", + "\n", + "31->32\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "49\n", + "\n", + "slope_2 <= 0.5\n", + "gini = 0.423\n", + "samples = 23\n", + "value = [7, 16]\n", + "\n", + "\n", + "\n", + "31->49\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "33\n", + "\n", + "thal_3.0 <= 0.5\n", + "gini = 0.498\n", + "samples = 64\n", + "value = [34, 30]\n", + "\n", + "\n", + "\n", + "32->33\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "42\n", + "\n", + "thal_3.0 <= 0.5\n", + "gini = 0.475\n", + "samples = 18\n", + "value = [7, 11]\n", + "\n", + "\n", + "\n", + "32->42\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "34\n", + "\n", + "slope_2 <= 0.5\n", + "gini = 0.444\n", + "samples = 12\n", + "value = [4, 8]\n", + "\n", + "\n", + "\n", + "33->34\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "39\n", + "\n", + "slope_2 <= 0.5\n", + "gini = 0.488\n", + "samples = 52\n", + "value = [30.0, 22.0]\n", + "\n", + "\n", + "\n", + "33->39\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "35\n", + "\n", + "gini = 0.0\n", + "samples = 1\n", + "value = [1, 0]\n", + "\n", + "\n", + "\n", + "34->35\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "36\n", + "\n", + "thal_7.0 <= 0.5\n", + "gini = 0.397\n", + "samples = 11\n", + "value = [3, 8]\n", + "\n", + "\n", + "\n", + "34->36\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "37\n", + "\n", + "gini = 0.375\n", + "samples = 4\n", + "value = [1, 3]\n", + "\n", + "\n", + "\n", + "36->37\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "38\n", + "\n", + "gini = 0.408\n", + "samples = 7\n", + "value = [2, 5]\n", + "\n", + "\n", + "\n", + "36->38\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "40\n", + "\n", + "gini = 0.5\n", + "samples = 4\n", + "value = [2, 2]\n", + "\n", + "\n", + "\n", + "39->40\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "41\n", + "\n", + "gini = 0.486\n", + "samples = 48\n", + "value = [28, 20]\n", + "\n", + "\n", + "\n", + "39->41\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "43\n", + "\n", + "slope_2 <= 0.5\n", + "gini = 0.408\n", + "samples = 7\n", + "value = [5, 2]\n", + "\n", + "\n", + "\n", + "42->43\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "46\n", + "\n", + "slope_2 <= 0.5\n", + "gini = 0.298\n", + "samples = 11\n", + "value = [2, 9]\n", + "\n", + "\n", + "\n", + "42->46\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "44\n", + "\n", + "gini = 0.0\n", + "samples = 2\n", + "value = [2, 0]\n", + "\n", + "\n", + "\n", + "43->44\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "45\n", + "\n", + "gini = 0.48\n", + "samples = 5\n", + "value = [3, 2]\n", + "\n", + "\n", + "\n", + "43->45\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "47\n", + "\n", + "gini = 0.0\n", + "samples = 1\n", + "value = [0, 1]\n", + "\n", + "\n", + "\n", + "46->47\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "48\n", + "\n", + "gini = 0.32\n", + "samples = 10\n", + "value = [2, 8]\n", + "\n", + "\n", + "\n", + "46->48\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "50\n", + "\n", + "gini = 0.0\n", + "samples = 1\n", + "value = [0, 1]\n", + "\n", + "\n", + "\n", + "49->50\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "51\n", + "\n", + "cp_1.0 <= 0.5\n", + "gini = 0.434\n", + "samples = 22\n", + "value = [7.0, 15.0]\n", + "\n", + "\n", + "\n", + "49->51\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "52\n", + "\n", + "thal_3.0 <= 0.5\n", + "gini = 0.444\n", + "samples = 21\n", + "value = [7, 14]\n", + "\n", + "\n", + "\n", + "51->52\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "57\n", + "\n", + "gini = 0.0\n", + "samples = 1\n", + "value = [0, 1]\n", + "\n", + "\n", + "\n", + "51->57\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "53\n", + "\n", + "thal_7.0 <= 0.5\n", + "gini = 0.408\n", + "samples = 7\n", + "value = [2, 5]\n", + "\n", + "\n", + "\n", + "52->53\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "56\n", + "\n", + "gini = 0.459\n", + "samples = 14\n", + "value = [5, 9]\n", + "\n", + "\n", + "\n", + "52->56\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "54\n", + "\n", + "gini = 0.0\n", + "samples = 1\n", + "value = [0, 1]\n", + "\n", + "\n", + "\n", + "53->54\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "55\n", + "\n", + "gini = 0.444\n", + "samples = 6\n", + "value = [2, 4]\n", + "\n", + "\n", + "\n", + "53->55\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "59\n", + "\n", + "exang <= 0.5\n", + "gini = 0.393\n", + "samples = 26\n", + "value = [19, 7]\n", + "\n", + "\n", + "\n", + "58->59\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "66\n", + "\n", + "thal_3.0 <= 0.5\n", + "gini = 0.5\n", + "samples = 6\n", + "value = [3, 3]\n", + "\n", + "\n", + "\n", + "58->66\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "60\n", + "\n", + "thal_7.0 <= 0.5\n", + "gini = 0.375\n", + "samples = 24\n", + "value = [18, 6]\n", + "\n", + "\n", + "\n", + "59->60\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "63\n", + "\n", + "thal_3.0 <= 0.5\n", + "gini = 0.5\n", + "samples = 2\n", + "value = [1, 1]\n", + "\n", + "\n", + "\n", + "59->63\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "61\n", + "\n", + "gini = 0.375\n", + "samples = 20\n", + "value = [15, 5]\n", + "\n", + "\n", + "\n", + "60->61\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "62\n", + "\n", + "gini = 0.375\n", + "samples = 4\n", + "value = [3, 1]\n", + "\n", + "\n", + "\n", + "60->62\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "64\n", + "\n", + "gini = 0.0\n", + "samples = 1\n", + "value = [1, 0]\n", + "\n", + "\n", + "\n", + "63->64\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "65\n", + "\n", + "gini = 0.0\n", + "samples = 1\n", + "value = [0, 1]\n", + "\n", + "\n", + "\n", + "63->65\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "67\n", + "\n", + "gini = 0.0\n", + "samples = 1\n", + "value = [1, 0]\n", + "\n", + "\n", + "\n", + "66->67\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "68\n", + "\n", + "gini = 0.48\n", + "samples = 5\n", + "value = [2, 3]\n", + "\n", + "\n", + "\n", + "66->68\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "70\n", + "\n", + "thal_7.0 <= 0.5\n", + "gini = 0.242\n", + "samples = 78\n", + "value = [67, 11]\n", + "\n", + "\n", + "\n", + "69->70\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "81\n", + "\n", + "slope_1 <= 0.5\n", + "gini = 0.42\n", + "samples = 10\n", + "value = [3, 7]\n", + "\n", + "\n", + "\n", + "69->81\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "71\n", + "\n", + "slope_1 <= 0.5\n", + "gini = 0.185\n", + "samples = 68\n", + "value = [61, 7]\n", + "\n", + "\n", + "\n", + "70->71\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "76\n", + "\n", + "slope_2 <= 0.5\n", + "gini = 0.48\n", + "samples = 10\n", + "value = [6, 4]\n", + "\n", + "\n", + "\n", + "70->76\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "72\n", + "\n", + "thal_3.0 <= 0.5\n", + "gini = 0.215\n", + "samples = 49\n", + "value = [43, 6]\n", + "\n", + "\n", + "\n", + "71->72\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "75\n", + "\n", + "gini = 0.1\n", + "samples = 19\n", + "value = [18, 1]\n", + "\n", + "\n", + "\n", + "71->75\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "73\n", + "\n", + "gini = 0.0\n", + "samples = 2\n", + "value = [2, 0]\n", + "\n", + "\n", + "\n", + "72->73\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "74\n", + "\n", + "gini = 0.223\n", + "samples = 47\n", + "value = [41.0, 6.0]\n", + "\n", + "\n", + "\n", + "72->74\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "77\n", + "\n", + "slope_1 <= 0.5\n", + "gini = 0.5\n", + "samples = 6\n", + "value = [3, 3]\n", + "\n", + "\n", + "\n", + "76->77\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "80\n", + "\n", + "gini = 0.375\n", + "samples = 4\n", + "value = [3, 1]\n", + "\n", + "\n", + "\n", + "76->80\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "78\n", + "\n", + "gini = 0.0\n", + "samples = 1\n", + "value = [0, 1]\n", + "\n", + "\n", + "\n", + "77->78\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "79\n", + "\n", + "gini = 0.48\n", + "samples = 5\n", + "value = [3, 2]\n", + "\n", + "\n", + "\n", + "77->79\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "82\n", + "\n", + "thal_3.0 <= 0.5\n", + "gini = 0.346\n", + "samples = 9\n", + "value = [2, 7]\n", + "\n", + "\n", + "\n", + "81->82\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "85\n", + "\n", + "gini = 0.0\n", + "samples = 1\n", + "value = [1, 0]\n", + "\n", + "\n", + "\n", + "81->85\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "83\n", + "\n", + "gini = 0.0\n", + "samples = 1\n", + "value = [0, 1]\n", + "\n", + "\n", + "\n", + "82->83\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "84\n", + "\n", + "gini = 0.375\n", + "samples = 8\n", + "value = [2, 6]\n", + "\n", + "\n", + "\n", + "82->84\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "87\n", + "\n", + "thal_3.0 <= 0.5\n", + "gini = 0.462\n", + "samples = 160\n", + "value = [58, 102]\n", + "\n", + "\n", + "\n", + "86->87\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "110\n", + "\n", + "sex <= 0.5\n", + "gini = 0.202\n", + "samples = 210\n", + "value = [24, 186]\n", + "\n", + "\n", + "\n", + "86->110\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "88\n", + "\n", + "slope_1 <= 0.5\n", + "gini = 0.236\n", + "samples = 44\n", + "value = [6, 38]\n", + "\n", + "\n", + "\n", + "87->88\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "99\n", + "\n", + "sex <= 0.5\n", + "gini = 0.495\n", + "samples = 116\n", + "value = [52, 64]\n", + "\n", + "\n", + "\n", + "87->99\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "89\n", + "\n", + "thal_7.0 <= 0.5\n", + "gini = 0.111\n", + "samples = 34\n", + "value = [2, 32]\n", + "\n", + "\n", + "\n", + "88->89\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "96\n", + "\n", + "thal_7.0 <= 0.5\n", + "gini = 0.48\n", + "samples = 10\n", + "value = [4, 6]\n", + "\n", + "\n", + "\n", + "88->96\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "90\n", + "\n", + "slope_2 <= 0.5\n", + "gini = 0.198\n", + "samples = 9\n", + "value = [1, 8]\n", + "\n", + "\n", + "\n", + "89->90\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "93\n", + "\n", + "sex <= 0.5\n", + "gini = 0.077\n", + "samples = 25\n", + "value = [1, 24]\n", + "\n", + "\n", + "\n", + "89->93\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "91\n", + "\n", + "gini = 0.0\n", + "samples = 1\n", + "value = [0, 1]\n", + "\n", + "\n", + "\n", + "90->91\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "92\n", + "\n", + "gini = 0.219\n", + "samples = 8\n", + "value = [1, 7]\n", + "\n", + "\n", + "\n", + "90->92\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "94\n", + "\n", + "gini = 0.0\n", + "samples = 4\n", + "value = [0, 4]\n", + "\n", + "\n", + "\n", + "93->94\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "95\n", + "\n", + "gini = 0.091\n", + "samples = 21\n", + "value = [1, 20]\n", + "\n", + "\n", + "\n", + "93->95\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "97\n", + "\n", + "gini = 0.0\n", + "samples = 1\n", + "value = [1, 0]\n", + "\n", + "\n", + "\n", + "96->97\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "98\n", + "\n", + "gini = 0.444\n", + "samples = 9\n", + "value = [3, 6]\n", + "\n", + "\n", + "\n", + "96->98\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "100\n", + "\n", + "slope_2 <= 0.5\n", + "gini = 0.397\n", + "samples = 22\n", + "value = [16, 6]\n", + "\n", + "\n", + "\n", + "99->100\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "105\n", + "\n", + "slope_1 <= 0.5\n", + "gini = 0.473\n", + "samples = 94\n", + "value = [36, 58]\n", + "\n", + "\n", + "\n", + "99->105\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "101\n", + "\n", + "slope_1 <= 0.5\n", + "gini = 0.48\n", + "samples = 10\n", + "value = [6, 4]\n", + "\n", + "\n", + "\n", + "100->101\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "104\n", + "\n", + "gini = 0.278\n", + "samples = 12\n", + "value = [10, 2]\n", + "\n", + "\n", + "\n", + "100->104\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "102\n", + "\n", + "gini = 0.0\n", + "samples = 2\n", + "value = [0, 2]\n", + "\n", + "\n", + "\n", + "101->102\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "103\n", + "\n", + "gini = 0.375\n", + "samples = 8\n", + "value = [6, 2]\n", + "\n", + "\n", + "\n", + "101->103\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "106\n", + "\n", + "slope_2 <= 0.5\n", + "gini = 0.477\n", + "samples = 74\n", + "value = [29, 45]\n", + "\n", + "\n", + "\n", + "105->106\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "109\n", + "\n", + "gini = 0.455\n", + "samples = 20\n", + "value = [7, 13]\n", + "\n", + "\n", + "\n", + "105->109\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "107\n", + "\n", + "gini = 0.5\n", + "samples = 4\n", + "value = [2, 2]\n", + "\n", + "\n", + "\n", + "106->107\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "108\n", + "\n", + "gini = 0.474\n", + "samples = 70\n", + "value = [27, 43]\n", + "\n", + "\n", + "\n", + "106->108\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "111\n", + "\n", + "thal_3.0 <= 0.5\n", + "gini = 0.384\n", + "samples = 27\n", + "value = [7, 20]\n", + "\n", + "\n", + "\n", + "110->111\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "118\n", + "\n", + "thal_3.0 <= 0.5\n", + "gini = 0.169\n", + "samples = 183\n", + "value = [17, 166]\n", + "\n", + "\n", + "\n", + "110->118\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "112\n", + "\n", + "gini = 0.0\n", + "samples = 9\n", + "value = [0, 9]\n", + "\n", + "\n", + "\n", + "111->112\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "113\n", + "\n", + "slope_1 <= 0.5\n", + "gini = 0.475\n", + "samples = 18\n", + "value = [7, 11]\n", + "\n", + "\n", + "\n", + "111->113\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "114\n", + "\n", + "slope_2 <= 0.5\n", + "gini = 0.444\n", + "samples = 15\n", + "value = [5, 10]\n", + "\n", + "\n", + "\n", + "113->114\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "117\n", + "\n", + "gini = 0.444\n", + "samples = 3\n", + "value = [2, 1]\n", + "\n", + "\n", + "\n", + "113->117\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "115\n", + "\n", + "gini = 0.0\n", + "samples = 1\n", + "value = [0, 1]\n", + "\n", + "\n", + "\n", + "114->115\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "116\n", + "\n", + "gini = 0.459\n", + "samples = 14\n", + "value = [5, 9]\n", + "\n", + "\n", + "\n", + "114->116\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "119\n", + "\n", + "slope_2 <= 0.5\n", + "gini = 0.123\n", + "samples = 76\n", + "value = [5, 71]\n", + "\n", + "\n", + "\n", + "118->119\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "128\n", + "\n", + "slope_2 <= 0.5\n", + "gini = 0.199\n", + "samples = 107\n", + "value = [12, 95]\n", + "\n", + "\n", + "\n", + "118->128\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "120\n", + "\n", + "thal_7.0 <= 0.5\n", + "gini = 0.185\n", + "samples = 29\n", + "value = [3, 26]\n", + "\n", + "\n", + "\n", + "119->120\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "125\n", + "\n", + "thal_7.0 <= 0.5\n", + "gini = 0.081\n", + "samples = 47\n", + "value = [2, 45]\n", + "\n", + "\n", + "\n", + "119->125\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "121\n", + "\n", + "gini = 0.0\n", + "samples = 2\n", + "value = [0, 2]\n", + "\n", + "\n", + "\n", + "120->121\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "122\n", + "\n", + "slope_1 <= 0.5\n", + "gini = 0.198\n", + "samples = 27\n", + "value = [3, 24]\n", + "\n", + "\n", + "\n", + "120->122\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "123\n", + "\n", + "gini = 0.198\n", + "samples = 9\n", + "value = [1, 8]\n", + "\n", + "\n", + "\n", + "122->123\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "124\n", + "\n", + "gini = 0.198\n", + "samples = 18\n", + "value = [2, 16]\n", + "\n", + "\n", + "\n", + "122->124\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "126\n", + "\n", + "gini = 0.0\n", + "samples = 9\n", + "value = [0, 9]\n", + "\n", + "\n", + "\n", + "125->126\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "127\n", + "\n", + "gini = 0.1\n", + "samples = 38\n", + "value = [2, 36]\n", + "\n", + "\n", + "\n", + "125->127\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "129\n", + "\n", + "slope_1 <= 0.5\n", + "gini = 0.142\n", + "samples = 26\n", + "value = [2, 24]\n", + "\n", + "\n", + "\n", + "128->129\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "132\n", + "\n", + "gini = 0.216\n", + "samples = 81\n", + "value = [10, 71]\n", + "\n", + "\n", + "\n", + "128->132\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "130\n", + "\n", + "gini = 0.124\n", + "samples = 15\n", + "value = [1, 14]\n", + "\n", + "\n", + "\n", + "129->130\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "131\n", + "\n", + "gini = 0.165\n", + "samples = 11\n", + "value = [1, 10]\n", + "\n", + "\n", + "\n", + "129->131\n", + "\n", + "\n", + "\n", + "\n", + "\n" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import graphviz\n", + "from sklearn import tree\n", + "\n", + "tree.export_graphviz(clf, feature_names=clf.feature_names_in_, rounded=True, out_file='decision.dot')\n", + "\n", + "graphviz.Source(open('./decision.dot').read())" + ] + }, { "cell_type": "code", "execution_count": null,