schuetoliver
/
handson-ml
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Use 'np.random' rather than 'import numpy.random as rnd', and add random_state to make notebook's output constant

main
Aurélien Geron 2017-06-06 16:32:08 +02:00
parent fb33333924
commit 1a165e2864
1 changed files with 58 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

83
07_ensemble_learning_and_random_forests.ipynb
View File

@ -55,11 +55,10 @@
"\n", "\n",
"# Common imports\n", "# Common imports\n",
"import numpy as np\n", "import numpy as np\n",
"import numpy.random as rnd\n",
"import os\n", "import os\n",
"\n", "\n",
"# to make this notebook's output stable across runs\n", "# to make this notebook's output stable across runs\n",
"rnd.seed(42)\n", "np.random.seed(42)\n",
"\n", "\n",
"# To plot pretty figures\n", "# To plot pretty figures\n",
"%matplotlib inline\n", "%matplotlib inline\n",
@ -104,7 +103,7 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"heads_proba = 0.51\n", "heads_proba = 0.51\n",
"coin_tosses = (rnd.rand(10000, 10) < heads_proba).astype(np.int32)\n", "coin_tosses = (np.random.rand(10000, 10) < heads_proba).astype(np.int32)\n",
"cumulative_heads_ratio = np.cumsum(coin_tosses, axis=0) / np.arange(1, 10001).reshape(-1, 1)" "cumulative_heads_ratio = np.cumsum(coin_tosses, axis=0) / np.arange(1, 10001).reshape(-1, 1)"
] ]
}, },
@ -134,7 +133,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 4,
"metadata": { "metadata": {
"collapsed": true "collapsed": true,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -174,7 +175,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 6,
"metadata": { "metadata": {
"collapsed": false "collapsed": false,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -190,7 +193,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 7,
"metadata": { "metadata": {
"collapsed": false "collapsed": false,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -208,7 +213,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": 8,
"metadata": { "metadata": {
"collapsed": false "collapsed": false,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -234,7 +241,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": 9,
"metadata": { "metadata": {
"collapsed": true "collapsed": true,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -358,7 +367,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 15, "execution_count": 15,
"metadata": { "metadata": {
"collapsed": false "collapsed": false,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -442,7 +453,7 @@
"\n", "\n",
"for i in range(15):\n", "for i in range(15):\n",
" tree_clf = DecisionTreeClassifier(max_leaf_nodes=16, random_state=42 + i)\n", " tree_clf = DecisionTreeClassifier(max_leaf_nodes=16, random_state=42 + i)\n",
" indices_with_replacement = rnd.randint(0, len(X_train), len(X_train))\n", " indices_with_replacement = np.random.randint(0, len(X_train), len(X_train))\n",
" tree_clf.fit(X[indices_with_replacement], y[indices_with_replacement])\n", " tree_clf.fit(X[indices_with_replacement], y[indices_with_replacement])\n",
" plot_decision_boundary(tree_clf, X, y, axes=[-1.5, 2.5, -1, 1.5], alpha=0.02, contour=False)\n", " plot_decision_boundary(tree_clf, X, y, axes=[-1.5, 2.5, -1, 1.5], alpha=0.02, contour=False)\n",
"\n", "\n",
@ -592,7 +603,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 28, "execution_count": 28,
"metadata": { "metadata": {
"collapsed": false "collapsed": false,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -608,7 +621,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 29, "execution_count": 29,
"metadata": { "metadata": {
"collapsed": false "collapsed": false,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -632,7 +647,7 @@
" sample_weights = np.ones(m)\n", " sample_weights = np.ones(m)\n",
" for i in range(5):\n", " for i in range(5):\n",
" plt.subplot(subplot)\n", " plt.subplot(subplot)\n",
" svm_clf = SVC(kernel=\"rbf\", C=0.05)\n", " svm_clf = SVC(kernel=\"rbf\", C=0.05, random_state=42)\n",
" svm_clf.fit(X_train, y_train, sample_weight=sample_weights)\n", " svm_clf.fit(X_train, y_train, sample_weight=sample_weights)\n",
" y_pred = svm_clf.predict(X_train)\n", " y_pred = svm_clf.predict(X_train)\n",
" sample_weights[y_pred != y_train] *= (1 + learning_rate)\n", " sample_weights[y_pred != y_train] *= (1 + learning_rate)\n",
@ -676,13 +691,15 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 32, "execution_count": 32,
"metadata": { "metadata": {
"collapsed": true "collapsed": true,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"rnd.seed(42)\n", "np.random.seed(42)\n",
"X = rnd.rand(100, 1) - 0.5\n", "X = np.random.rand(100, 1) - 0.5\n",
"y = 3*X[:, 0]**2 + 0.05 * rnd.randn(100)" "y = 3*X[:, 0]**2 + 0.05 * np.random.randn(100)"
] ]
}, },
{ {
@ -705,7 +722,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 34, "execution_count": 34,
"metadata": { "metadata": {
"collapsed": false "collapsed": false,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -718,7 +737,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 35, "execution_count": 35,
"metadata": { "metadata": {
"collapsed": false "collapsed": false,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -731,7 +752,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 36, "execution_count": 36,
"metadata": { "metadata": {
"collapsed": true "collapsed": true,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -742,7 +765,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 37, "execution_count": 37,
"metadata": { "metadata": {
"collapsed": false "collapsed": false,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -753,7 +778,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 38, "execution_count": 38,
"metadata": { "metadata": {
"collapsed": false "collapsed": false,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -833,7 +860,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 41, "execution_count": 41,
"metadata": { "metadata": {
"collapsed": false "collapsed": false,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -845,7 +874,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 42, "execution_count": 42,
"metadata": { "metadata": {
"collapsed": false "collapsed": false,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
@ -904,7 +935,9 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 44, "execution_count": 44,
"metadata": { "metadata": {
"collapsed": true "collapsed": true,
"deletable": true,
"editable": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [