{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"collapsed": false,
"deletable": true,
"editable": true
},
"source": [
"## Neural Networks in scikit-learn \n",
"\n",
"#### Linear models:\n",
"\n",
" ลท = w[0] \\* x[0] + w[1] \\* x[1] + ... + w[p] \\* x[p] + b "
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [
{
"data": {
"image/svg+xml": [
"\r\n",
"\r\n",
"\r\n",
"\r\n",
"\r\n"
],
"text/plain": [
""
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import mglearn\n",
"\n",
"mglearn.plots.plot_logistic_regression_graph()"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [
{
"data": {
"image/svg+xml": [
"\r\n",
"\r\n",
"\r\n",
"\r\n",
"\r\n"
],
"text/plain": [
""
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"mglearn.plots.plot_single_hidden_layer_graph()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [
{
"data": {
"image/svg+xml": [
"\r\n",
"\r\n",
"\r\n",
"\r\n",
"\r\n"
],
"text/plain": [
""
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"mglearn.plots.plot_two_hidden_layer_graph()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy on the training subset: 0.906\n",
"Accuracy on the test subset: 0.881\n"
]
}
],
"source": [
"from sklearn.neural_network import MLPClassifier\n",
"from sklearn.datasets import load_breast_cancer\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"cancer = load_breast_cancer()\n",
"\n",
"X_train, X_test, y_train, y_test = train_test_split(cancer.data, cancer.target, random_state=0)\n",
"\n",
"mlp = MLPClassifier(random_state=42)\n",
"mlp.fit(X_train, y_train)\n",
"\n",
"print('Accuracy on the training subset: {:.3f}'.format(mlp.score(X_train, y_train)))\n",
"print('Accuracy on the test subset: {:.3f}'.format(mlp.score(X_test, y_test)))"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The maximum per each feature:\n",
"[ 2.81100000e+01 3.92800000e+01 1.88500000e+02 2.50100000e+03\n",
" 1.63400000e-01 3.45400000e-01 4.26800000e-01 2.01200000e-01\n",
" 3.04000000e-01 9.74400000e-02 2.87300000e+00 4.88500000e+00\n",
" 2.19800000e+01 5.42200000e+02 3.11300000e-02 1.35400000e-01\n",
" 3.96000000e-01 5.27900000e-02 7.89500000e-02 2.98400000e-02\n",
" 3.60400000e+01 4.95400000e+01 2.51200000e+02 4.25400000e+03\n",
" 2.22600000e-01 1.05800000e+00 1.25200000e+00 2.91000000e-01\n",
" 6.63800000e-01 2.07500000e-01]\n"
]
}
],
"source": [
"print('The maximum per each feature:\\n{}'.format(cancer.data.max(axis=0)))"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy on the training subset: 0.995\n",
"Accuracy on the test subset: 0.958\n"
]
}
],
"source": [
"from sklearn.preprocessing import StandardScaler\n",
"\n",
"scaler = StandardScaler()\n",
"X_train_scaled = scaler.fit(X_train).transform(X_train)\n",
"X_test_scaled = scaler.fit(X_test).transform(X_test)\n",
"\n",
"mlp = MLPClassifier(max_iter=1000, random_state=42) \n",
"\n",
"mlp.fit(X_train_scaled, y_train)\n",
"\n",
"print('Accuracy on the training subset: {:.3f}'.format(mlp.score(X_train_scaled, y_train)))\n",
"print('Accuracy on the test subset: {:.3f}'.format(mlp.score(X_test_scaled, y_test)))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true,
"deletable": true,
"editable": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"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": "3.5.0"
}
},
"nbformat": 4,
"nbformat_minor": 2
}