262 lines
8.9 KiB
Plaintext
262 lines
8.9 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import os\n",
|
|
"import numpy as np\n",
|
|
"import sklearn\n",
|
|
"from sklearn import svm, datasets, metrics\n",
|
|
"from sklearn.neighbors import KNeighborsClassifier\n",
|
|
"import pickle"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Features: ['mean radius' 'mean texture' 'mean perimeter' 'mean area'\n",
|
|
" 'mean smoothness' 'mean compactness' 'mean concavity'\n",
|
|
" 'mean concave points' 'mean symmetry' 'mean fractal dimension'\n",
|
|
" 'radius error' 'texture error' 'perimeter error' 'area error'\n",
|
|
" 'smoothness error' 'compactness error' 'concavity error'\n",
|
|
" 'concave points error' 'symmetry error' 'fractal dimension error'\n",
|
|
" 'worst radius' 'worst texture' 'worst perimeter' 'worst area'\n",
|
|
" 'worst smoothness' 'worst compactness' 'worst concavity'\n",
|
|
" 'worst concave points' 'worst symmetry' 'worst fractal dimension']\n",
|
|
"labels: ['malignant' 'benign']\n",
|
|
"data: [[1.799e+01 1.038e+01 1.228e+02 ... 2.654e-01 4.601e-01 1.189e-01]\n",
|
|
" [2.057e+01 1.777e+01 1.329e+02 ... 1.860e-01 2.750e-01 8.902e-02]\n",
|
|
" [1.969e+01 2.125e+01 1.300e+02 ... 2.430e-01 3.613e-01 8.758e-02]\n",
|
|
" ...\n",
|
|
" [1.660e+01 2.808e+01 1.083e+02 ... 1.418e-01 2.218e-01 7.820e-02]\n",
|
|
" [2.060e+01 2.933e+01 1.401e+02 ... 2.650e-01 4.087e-01 1.240e-01]\n",
|
|
" [7.760e+00 2.454e+01 4.792e+01 ... 0.000e+00 2.871e-01 7.039e-02]]\n",
|
|
"target: [0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
|
|
" 1 0 0 0 0 0 0 0 0 1 0 1 1 1 1 1 0 0 1 0 0 1 1 1 1 0 1 0 0 1 1 1 1 0 1 0 0\n",
|
|
" 1 0 1 0 0 1 1 1 0 0 1 0 0 0 1 1 1 0 1 1 0 0 1 1 1 0 0 1 1 1 1 0 1 1 0 1 1\n",
|
|
" 1 1 1 1 1 1 0 0 0 1 0 0 1 1 1 0 0 1 0 1 0 0 1 0 0 1 1 0 1 1 0 1 1 1 1 0 1\n",
|
|
" 1 1 1 1 1 1 1 1 0 1 1 1 1 0 0 1 0 1 1 0 0 1 1 0 0 1 1 1 1 0 1 1 0 0 0 1 0\n",
|
|
" 1 0 1 1 1 0 1 1 0 0 1 0 0 0 0 1 0 0 0 1 0 1 0 1 1 0 1 0 0 0 0 1 1 0 0 1 1\n",
|
|
" 1 0 1 1 1 1 1 0 0 1 1 0 1 1 0 0 1 0 1 1 1 1 0 1 1 1 1 1 0 1 0 0 0 0 0 0 0\n",
|
|
" 0 0 0 0 0 0 0 1 1 1 1 1 1 0 1 0 1 1 0 1 1 0 1 0 0 1 1 1 1 1 1 1 1 1 1 1 1\n",
|
|
" 1 0 1 1 0 1 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 0 1 1 1 0 1 0 1 1 1 1 0 0 0 1 1\n",
|
|
" 1 1 0 1 0 1 0 1 1 1 0 1 1 1 1 1 1 1 0 0 0 1 1 1 1 1 1 1 1 1 1 1 0 0 1 0 0\n",
|
|
" 0 1 0 0 1 1 1 1 1 0 1 1 1 1 1 0 1 1 1 0 1 1 0 0 1 1 1 1 1 1 0 1 1 1 1 1 1\n",
|
|
" 1 0 1 1 1 1 1 0 1 1 0 1 1 1 1 1 1 1 1 1 1 1 1 0 1 0 0 1 0 1 1 1 1 1 0 1 1\n",
|
|
" 0 1 0 1 1 0 1 0 1 1 1 1 1 1 1 1 0 0 1 1 1 1 1 1 0 1 1 1 1 1 1 1 1 1 1 0 1\n",
|
|
" 1 1 1 1 1 1 0 1 0 1 1 0 1 1 1 1 1 0 0 1 0 1 0 1 1 1 1 1 0 1 1 0 1 0 1 0 0\n",
|
|
" 1 1 1 0 1 1 1 1 1 1 1 1 1 1 1 0 1 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1\n",
|
|
" 1 1 1 1 1 1 1 0 0 0 0 0 0 1]\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"cancer = datasets.load_breast_cancer()\n",
|
|
"print(\"Features:\", cancer.feature_names)\n",
|
|
"print(\"labels:\", cancer.target_names)\n",
|
|
"print(\"data:\", cancer.data)\n",
|
|
"print(\"target:\", cancer.target)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"[[1.160e+01 2.449e+01 7.423e+01 4.172e+02 7.474e-02 5.688e-02 1.974e-02\n",
|
|
" 1.313e-02 1.935e-01 5.878e-02 2.512e-01 1.786e+00 1.961e+00 1.821e+01\n",
|
|
" 6.122e-03 2.337e-02 1.596e-02 6.998e-03 3.194e-02 2.211e-03 1.244e+01\n",
|
|
" 3.162e+01 8.139e+01 4.765e+02 9.545e-02 1.361e-01 7.239e-02 4.815e-02\n",
|
|
" 3.244e-01 6.745e-02]\n",
|
|
" [1.288e+01 1.822e+01 8.445e+01 4.931e+02 1.218e-01 1.661e-01 4.825e-02\n",
|
|
" 5.303e-02 1.709e-01 7.253e-02 4.426e-01 1.169e+00 3.176e+00 3.437e+01\n",
|
|
" 5.273e-03 2.329e-02 1.405e-02 1.244e-02 1.816e-02 3.299e-03 1.505e+01\n",
|
|
" 2.437e+01 9.931e+01 6.747e+02 1.456e-01 2.961e-01 1.246e-01 1.096e-01\n",
|
|
" 2.582e-01 8.893e-02]\n",
|
|
" [1.086e+01 2.148e+01 6.851e+01 3.605e+02 7.431e-02 4.227e-02 0.000e+00\n",
|
|
" 0.000e+00 1.661e-01 5.948e-02 3.163e-01 1.304e+00 2.115e+00 2.067e+01\n",
|
|
" 9.579e-03 1.104e-02 0.000e+00 0.000e+00 3.004e-02 2.228e-03 1.166e+01\n",
|
|
" 2.477e+01 7.408e+01 4.123e+02 1.001e-01 7.348e-02 0.000e+00 0.000e+00\n",
|
|
" 2.458e-01 6.592e-02]\n",
|
|
" [2.020e+01 2.683e+01 1.337e+02 1.234e+03 9.905e-02 1.669e-01 1.641e-01\n",
|
|
" 1.265e-01 1.875e-01 6.020e-02 9.761e-01 1.892e+00 7.128e+00 1.036e+02\n",
|
|
" 8.439e-03 4.674e-02 5.904e-02 2.536e-02 3.710e-02 4.286e-03 2.419e+01\n",
|
|
" 3.381e+01 1.600e+02 1.671e+03 1.278e-01 3.416e-01 3.703e-01 2.152e-01\n",
|
|
" 3.271e-01 7.632e-02]\n",
|
|
" [2.047e+01 2.067e+01 1.347e+02 1.299e+03 9.156e-02 1.313e-01 1.523e-01\n",
|
|
" 1.015e-01 2.166e-01 5.419e-02 8.336e-01 1.736e+00 5.168e+00 1.004e+02\n",
|
|
" 4.938e-03 3.089e-02 4.093e-02 1.699e-02 2.816e-02 2.719e-03 2.323e+01\n",
|
|
" 2.715e+01 1.520e+02 1.645e+03 1.097e-01 2.534e-01 3.092e-01 1.613e-01\n",
|
|
" 3.220e-01 6.386e-02]]\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"x = cancer.data\n",
|
|
"y = cancer.target\n",
|
|
"\n",
|
|
"# Split into train, dev, test sets with 90 / 5 / 5 split\n",
|
|
"x_train, x_test, y_train, y_test = sklearn.model_selection.train_test_split(\n",
|
|
" x,y,test_size=0.1)\n",
|
|
"\n",
|
|
"x_test, x_dev, y_test, y_dev = sklearn.model_selection.train_test_split(\n",
|
|
" x_test, y_test, test_size=0.5)\n",
|
|
"\n",
|
|
"print(x_train[:5])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"0.9285714285714286\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"classes = cancer.target_names\n",
|
|
"clf = svm.SVC(kernel='linear', gamma='scale')\n",
|
|
"clf.fit(x_train, y_train)\n",
|
|
"\n",
|
|
"y_pred = clf.predict(x_test)\n",
|
|
"acc = metrics.accuracy_score(y_test, y_pred)\n",
|
|
"print(acc)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"0.9310344827586207\n",
|
|
"0.9655172413793104\n",
|
|
"0.9310344827586207\n",
|
|
"0.896551724137931\n",
|
|
"0.896551724137931\n",
|
|
"0.896551724137931\n",
|
|
"0.896551724137931\n",
|
|
"0.896551724137931\n",
|
|
"0.9310344827586207\n",
|
|
"0.9310344827586207\n",
|
|
"0.6896551724137931\n",
|
|
"0.896551724137931\n",
|
|
"0.9310344827586207\n",
|
|
"0.896551724137931\n",
|
|
"0.9310344827586207\n",
|
|
"0.9310344827586207\n",
|
|
"0.9310344827586207\n",
|
|
"0.9655172413793104\n",
|
|
"0.9655172413793104\n",
|
|
"0.9655172413793104\n",
|
|
"0.6896551724137931\n",
|
|
"0.6896551724137931\n",
|
|
"0.6896551724137931\n",
|
|
"0.4827586206896552\n",
|
|
"0.41379310344827586\n",
|
|
"0.41379310344827586\n",
|
|
"0.41379310344827586\n",
|
|
"0.41379310344827586\n",
|
|
"0.41379310344827586\n",
|
|
"0.41379310344827586\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# Tune parameters of kernel, C, gamma \n",
|
|
"# Note: use logarithmic scale random values\n",
|
|
"kernels = ['linear','rbf','sigmoid']\n",
|
|
"C_values = [0.001, 0.01, 0.1, 1, 5, 25, 50, 100, 500, 1000]\n",
|
|
"\n",
|
|
"\n",
|
|
"\n",
|
|
"best = 0\n",
|
|
"for kernel in kernels:\n",
|
|
" for C in C_values:\n",
|
|
" classes = cancer.target_names\n",
|
|
" clf = svm.SVC(kernel=kernel, C=C, gamma='scale')\n",
|
|
" clf.fit(x_train, y_train)\n",
|
|
" y_pred = clf.predict(x_dev)\n",
|
|
" acc = metrics.accuracy_score(y_dev, y_pred)\n",
|
|
" print(acc)\n",
|
|
" if acc > best:\n",
|
|
" best = acc\n",
|
|
" with open('cancerModel.pickle','wb') as f:\n",
|
|
" pickle.dump(clf,f)\n",
|
|
" \n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"0.9285714285714286\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"pickle_in = open('cancerModel.pickle','rb')\n",
|
|
"clf = pickle.load(pickle_in)\n",
|
|
"y_pred = clf.predict(x_test)\n",
|
|
"acc = metrics.accuracy_score(y_test, y_pred)\n",
|
|
"print(acc)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"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": "3.7.4"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|