tsb95
/
MLProjects
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Clean up code and add comments

This commit is contained in:
tsb1995 2020-06-07 11:06:45 -07:00
parent b8ba9c81e6
commit 34ea348f9c
12 changed files with 3630 additions and 238 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

160
breastCancerML/.ipynb_checkpoints/breastCancerML-checkpoint.ipynb
View File

@ -10,7 +10,6 @@
"import numpy as np\n", "import numpy as np\n",
"import sklearn\n", "import sklearn\n",
"from sklearn import svm, datasets, metrics\n", "from sklearn import svm, datasets, metrics\n",
"from sklearn.neighbors import KNeighborsClassifier\n",
"import pickle" "import pickle"
] ]
}, },
@ -18,93 +17,19 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 2,
"metadata": {}, "metadata": {},
"outputs": [ "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": [ "source": [
"cancer = datasets.load_breast_cancer()\n", "# Load in our data\n",
"print(\"Features:\", cancer.feature_names)\n", "cancer = datasets.load_breast_cancer()"
"print(\"labels:\", cancer.target_names)\n",
"print(\"data:\", cancer.data)\n",
"print(\"target:\", cancer.target)"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 3,
"metadata": {}, "metadata": {},
"outputs": [ "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": [ "source": [
"# Split our input and target features\n",
"x = cancer.data\n", "x = cancer.data\n",
"y = cancer.target\n", "y = cancer.target\n",
"\n", "\n",
@ -113,9 +38,7 @@
" x,y,test_size=0.1)\n", " x,y,test_size=0.1)\n",
"\n", "\n",
"x_test, x_dev, y_test, y_dev = sklearn.model_selection.train_test_split(\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", " x_test, y_test, test_size=0.5)"
"\n",
"print(x_train[:5])"
] ]
}, },
{ {
@ -127,15 +50,17 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"0.9285714285714286\n" "0.9642857142857143\n"
] ]
} }
], ],
"source": [ "source": [
"# Setup Support Vector Classifier\n",
"classes = cancer.target_names\n", "classes = cancer.target_names\n",
"clf = svm.SVC(kernel='linear', gamma='scale')\n", "clf = svm.SVC(kernel='linear', gamma='scale')\n",
"clf.fit(x_train, y_train)\n", "clf.fit(x_train, y_train)\n",
"\n", "\n",
"# Make predictions and measure accuracy\n",
"y_pred = clf.predict(x_test)\n", "y_pred = clf.predict(x_test)\n",
"acc = metrics.accuracy_score(y_test, y_pred)\n", "acc = metrics.accuracy_score(y_test, y_pred)\n",
"print(acc)" "print(acc)"
@ -152,45 +77,43 @@
"text": [ "text": [
"0.9310344827586207\n", "0.9310344827586207\n",
"0.9655172413793104\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", "0.9310344827586207\n",
"0.9655172413793104\n", "0.9310344827586207\n",
"0.6896551724137931\n", "0.9310344827586207\n",
"0.6896551724137931\n", "0.9310344827586207\n",
"0.6896551724137931\n", "0.9310344827586207\n",
"0.9310344827586207\n",
"0.9310344827586207\n",
"0.6206896551724138\n",
"0.7931034482758621\n",
"0.8620689655172413\n",
"0.8620689655172413\n",
"0.8275862068965517\n",
"0.8620689655172413\n",
"0.8620689655172413\n",
"0.896551724137931\n",
"0.9310344827586207\n",
"0.9310344827586207\n",
"0.6206896551724138\n",
"0.6206896551724138\n",
"0.6206896551724138\n",
"0.5862068965517241\n",
"0.5517241379310345\n",
"0.4827586206896552\n", "0.4827586206896552\n",
"0.41379310344827586\n", "0.4827586206896552\n",
"0.41379310344827586\n", "0.4827586206896552\n",
"0.41379310344827586\n", "0.4827586206896552\n",
"0.41379310344827586\n", "0.4827586206896552\n"
"0.41379310344827586\n",
"0.41379310344827586\n"
] ]
} }
], ],
"source": [ "source": [
"# Tune parameters of kernel, C, gamma \n", "# Tune parameters of kernel, C, gamma \n",
"# Note: use logarithmic scale random values\n", "# Note: use logarithmically scaled values for C\n",
"kernels = ['linear','rbf','sigmoid']\n", "kernels = ['linear','rbf','sigmoid']\n",
"C_values = [0.001, 0.01, 0.1, 1, 5, 25, 50, 100, 500, 1000]\n", "C_values = [0.001, 0.01, 0.1, 1, 5, 25, 50, 100, 500, 1000]\n",
"\n", "\n",
"\n",
"\n",
"best = 0\n", "best = 0\n",
"for kernel in kernels:\n", "for kernel in kernels:\n",
" for C in C_values:\n", " for C in C_values:\n",
@ -203,25 +126,24 @@
" if acc > best:\n", " if acc > best:\n",
" best = acc\n", " best = acc\n",
" with open('cancerModel.pickle','wb') as f:\n", " with open('cancerModel.pickle','wb') as f:\n",
" pickle.dump(clf,f)\n", " pickle.dump(clf,f)"
" \n",
"\n"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 6,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"0.9285714285714286\n" "0.9642857142857143\n"
] ]
} }
], ],
"source": [ "source": [
"# Load in our best model (according to Validation accuracy)\n",
"pickle_in = open('cancerModel.pickle','rb')\n", "pickle_in = open('cancerModel.pickle','rb')\n",
"clf = pickle.load(pickle_in)\n", "clf = pickle.load(pickle_in)\n",
"y_pred = clf.predict(x_test)\n", "y_pred = clf.predict(x_test)\n",
@ -253,7 +175,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.7.4" "version": "3.7.5"
} }
}, },
"nbformat": 4, "nbformat": 4,

160
breastCancerML/breastCancerML.ipynb
View File

@ -10,7 +10,6 @@
"import numpy as np\n", "import numpy as np\n",
"import sklearn\n", "import sklearn\n",
"from sklearn import svm, datasets, metrics\n", "from sklearn import svm, datasets, metrics\n",
"from sklearn.neighbors import KNeighborsClassifier\n",
"import pickle" "import pickle"
] ]
}, },
@ -18,93 +17,19 @@
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 2,
"metadata": {}, "metadata": {},
"outputs": [ "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": [ "source": [
"cancer = datasets.load_breast_cancer()\n", "# Load in our data\n",
"print(\"Features:\", cancer.feature_names)\n", "cancer = datasets.load_breast_cancer()"
"print(\"labels:\", cancer.target_names)\n",
"print(\"data:\", cancer.data)\n",
"print(\"target:\", cancer.target)"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 3,
"metadata": {}, "metadata": {},
"outputs": [ "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": [ "source": [
"# Split our input and target features\n",
"x = cancer.data\n", "x = cancer.data\n",
"y = cancer.target\n", "y = cancer.target\n",
"\n", "\n",
@ -113,9 +38,7 @@
" x,y,test_size=0.1)\n", " x,y,test_size=0.1)\n",
"\n", "\n",
"x_test, x_dev, y_test, y_dev = sklearn.model_selection.train_test_split(\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", " x_test, y_test, test_size=0.5)"
"\n",
"print(x_train[:5])"
] ]
}, },
{ {
@ -127,15 +50,17 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"0.9285714285714286\n" "0.9642857142857143\n"
] ]
} }
], ],
"source": [ "source": [
"# Setup Support Vector Classifier\n",
"classes = cancer.target_names\n", "classes = cancer.target_names\n",
"clf = svm.SVC(kernel='linear', gamma='scale')\n", "clf = svm.SVC(kernel='linear', gamma='scale')\n",
"clf.fit(x_train, y_train)\n", "clf.fit(x_train, y_train)\n",
"\n", "\n",
"# Make predictions and measure accuracy\n",
"y_pred = clf.predict(x_test)\n", "y_pred = clf.predict(x_test)\n",
"acc = metrics.accuracy_score(y_test, y_pred)\n", "acc = metrics.accuracy_score(y_test, y_pred)\n",
"print(acc)" "print(acc)"
@ -152,45 +77,43 @@
"text": [ "text": [
"0.9310344827586207\n", "0.9310344827586207\n",
"0.9655172413793104\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", "0.9310344827586207\n",
"0.9655172413793104\n", "0.9310344827586207\n",
"0.6896551724137931\n", "0.9310344827586207\n",
"0.6896551724137931\n", "0.9310344827586207\n",
"0.6896551724137931\n", "0.9310344827586207\n",
"0.9310344827586207\n",
"0.9310344827586207\n",
"0.6206896551724138\n",
"0.7931034482758621\n",
"0.8620689655172413\n",
"0.8620689655172413\n",
"0.8275862068965517\n",
"0.8620689655172413\n",
"0.8620689655172413\n",
"0.896551724137931\n",
"0.9310344827586207\n",
"0.9310344827586207\n",
"0.6206896551724138\n",
"0.6206896551724138\n",
"0.6206896551724138\n",
"0.5862068965517241\n",
"0.5517241379310345\n",
"0.4827586206896552\n", "0.4827586206896552\n",
"0.41379310344827586\n", "0.4827586206896552\n",
"0.41379310344827586\n", "0.4827586206896552\n",
"0.41379310344827586\n", "0.4827586206896552\n",
"0.41379310344827586\n", "0.4827586206896552\n"
"0.41379310344827586\n",
"0.41379310344827586\n"
] ]
} }
], ],
"source": [ "source": [
"# Tune parameters of kernel, C, gamma \n", "# Tune parameters of kernel, C, gamma \n",
"# Note: use logarithmic scale random values\n", "# Note: use logarithmically scaled values for C\n",
"kernels = ['linear','rbf','sigmoid']\n", "kernels = ['linear','rbf','sigmoid']\n",
"C_values = [0.001, 0.01, 0.1, 1, 5, 25, 50, 100, 500, 1000]\n", "C_values = [0.001, 0.01, 0.1, 1, 5, 25, 50, 100, 500, 1000]\n",
"\n", "\n",
"\n",
"\n",
"best = 0\n", "best = 0\n",
"for kernel in kernels:\n", "for kernel in kernels:\n",
" for C in C_values:\n", " for C in C_values:\n",
@ -203,25 +126,24 @@
" if acc > best:\n", " if acc > best:\n",
" best = acc\n", " best = acc\n",
" with open('cancerModel.pickle','wb') as f:\n", " with open('cancerModel.pickle','wb') as f:\n",
" pickle.dump(clf,f)\n", " pickle.dump(clf,f)"
" \n",
"\n"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 6,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"0.9285714285714286\n" "0.9642857142857143\n"
] ]
} }
], ],
"source": [ "source": [
"# Load in our best model (according to Validation accuracy)\n",
"pickle_in = open('cancerModel.pickle','rb')\n", "pickle_in = open('cancerModel.pickle','rb')\n",
"clf = pickle.load(pickle_in)\n", "clf = pickle.load(pickle_in)\n",
"y_pred = clf.predict(x_test)\n", "y_pred = clf.predict(x_test)\n",
@ -253,7 +175,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.7.4" "version": "3.7.5"
} }
}, },
"nbformat": 4, "nbformat": 4,

BIN
breastCancerML/cancerModel.pickle
View File

Binary file not shown.

1225
kaggle_time_series_air_passenger/.ipynb_checkpoints/model-checkpoint.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

404
kaggle_time_series_air_passenger/.ipynb_checkpoints/model2-checkpoint.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

145
kaggle_time_series_air_passenger/AirPassengers.csv Normal file
View File

@ -0,0 +1,145 @@
Month,#Passengers
1949-01,112
1949-02,118
1949-03,132
1949-04,129
1949-05,121
1949-06,135
1949-07,148
1949-08,148
1949-09,136
1949-10,119
1949-11,104
1949-12,118
1950-01,115
1950-02,126
1950-03,141
1950-04,135
1950-05,125
1950-06,149
1950-07,170
1950-08,170
1950-09,158
1950-10,133
1950-11,114
1950-12,140
1951-01,145
1951-02,150
1951-03,178
1951-04,163
1951-05,172
1951-06,178
1951-07,199
1951-08,199
1951-09,184
1951-10,162
1951-11,146
1951-12,166
1952-01,171
1952-02,180
1952-03,193
1952-04,181
1952-05,183
1952-06,218
1952-07,230
1952-08,242
1952-09,209
1952-10,191
1952-11,172
1952-12,194
1953-01,196
1953-02,196
1953-03,236
1953-04,235
1953-05,229
1953-06,243
1953-07,264
1953-08,272
1953-09,237
1953-10,211
1953-11,180
1953-12,201
1954-01,204
1954-02,188
1954-03,235
1954-04,227
1954-05,234
1954-06,264
1954-07,302
1954-08,293
1954-09,259
1954-10,229
1954-11,203
1954-12,229
1955-01,242
1955-02,233
1955-03,267
1955-04,269
1955-05,270
1955-06,315
1955-07,364
1955-08,347
1955-09,312
1955-10,274
1955-11,237
1955-12,278
1956-01,284
1956-02,277
1956-03,317
1956-04,313
1956-05,318
1956-06,374
1956-07,413
1956-08,405
1956-09,355
1956-10,306
1956-11,271
1956-12,306
1957-01,315
1957-02,301
1957-03,356
1957-04,348
1957-05,355
1957-06,422
1957-07,465
1957-08,467
1957-09,404
1957-10,347
1957-11,305
1957-12,336
1958-01,340
1958-02,318
1958-03,362
1958-04,348
1958-05,363
1958-06,435
1958-07,491
1958-08,505
1958-09,404
1958-10,359
1958-11,310
1958-12,337
1959-01,360
1959-02,342
1959-03,406
1959-04,396
1959-05,420
1959-06,472
1959-07,548
1959-08,559
1959-09,463
1959-10,407
1959-11,362
1959-12,405
1960-01,417
1960-02,391
1960-03,419
1960-04,461
1960-05,472
1960-06,535
1960-07,622
1960-08,606
1960-09,508
1960-10,461
1960-11,390
1960-12,432
1 Month #Passengers
2 1949-01 112
3 1949-02 118
4 1949-03 132
5 1949-04 129
6 1949-05 121
7 1949-06 135
8 1949-07 148
9 1949-08 148
10 1949-09 136
11 1949-10 119
12 1949-11 104
13 1949-12 118
14 1950-01 115
15 1950-02 126
16 1950-03 141
17 1950-04 135
18 1950-05 125
19 1950-06 149
20 1950-07 170
21 1950-08 170
22 1950-09 158
23 1950-10 133
24 1950-11 114
25 1950-12 140
26 1951-01 145
27 1951-02 150
28 1951-03 178
29 1951-04 163
30 1951-05 172
31 1951-06 178
32 1951-07 199
33 1951-08 199
34 1951-09 184
35 1951-10 162
36 1951-11 146
37 1951-12 166
38 1952-01 171
39 1952-02 180
40 1952-03 193
41 1952-04 181
42 1952-05 183
43 1952-06 218
44 1952-07 230
45 1952-08 242
46 1952-09 209
47 1952-10 191
48 1952-11 172
49 1952-12 194
50 1953-01 196
51 1953-02 196
52 1953-03 236
53 1953-04 235
54 1953-05 229
55 1953-06 243
56 1953-07 264
57 1953-08 272
58 1953-09 237
59 1953-10 211
60 1953-11 180
61 1953-12 201
62 1954-01 204
63 1954-02 188
64 1954-03 235
65 1954-04 227
66 1954-05 234
67 1954-06 264
68 1954-07 302
69 1954-08 293
70 1954-09 259
71 1954-10 229
72 1954-11 203
73 1954-12 229
74 1955-01 242
75 1955-02 233
76 1955-03 267
77 1955-04 269
78 1955-05 270
79 1955-06 315
80 1955-07 364
81 1955-08 347
82 1955-09 312
83 1955-10 274
84 1955-11 237
85 1955-12 278
86 1956-01 284
87 1956-02 277
88 1956-03 317
89 1956-04 313
90 1956-05 318
91 1956-06 374
92 1956-07 413
93 1956-08 405
94 1956-09 355
95 1956-10 306
96 1956-11 271
97 1956-12 306
98 1957-01 315
99 1957-02 301
100 1957-03 356
101 1957-04 348
102 1957-05 355
103 1957-06 422
104 1957-07 465
105 1957-08 467
106 1957-09 404
107 1957-10 347
108 1957-11 305
109 1957-12 336
110 1958-01 340
111 1958-02 318
112 1958-03 362
113 1958-04 348
114 1958-05 363
115 1958-06 435
116 1958-07 491
117 1958-08 505
118 1958-09 404
119 1958-10 359
120 1958-11 310
121 1958-12 337
122 1959-01 360
123 1959-02 342
124 1959-03 406
125 1959-04 396
126 1959-05 420
127 1959-06 472
128 1959-07 548
129 1959-08 559
130 1959-09 463
131 1959-10 407
132 1959-11 362
133 1959-12 405
134 1960-01 417
135 1960-02 391
136 1960-03 419
137 1960-04 461
138 1960-05 472
139 1960-06 535
140 1960-07 622
141 1960-08 606
142 1960-09 508
143 1960-10 461
144 1960-11 390
145 1960-12 432

145
kaggle_time_series_air_passenger/data/AirPassengers.csv Normal file
View File

@ -0,0 +1,145 @@
Month,#Passengers
1949-01,112
1949-02,118
1949-03,132
1949-04,129
1949-05,121
1949-06,135
1949-07,148
1949-08,148
1949-09,136
1949-10,119
1949-11,104
1949-12,118
1950-01,115
1950-02,126
1950-03,141
1950-04,135
1950-05,125
1950-06,149
1950-07,170
1950-08,170
1950-09,158
1950-10,133
1950-11,114
1950-12,140
1951-01,145
1951-02,150
1951-03,178
1951-04,163
1951-05,172
1951-06,178
1951-07,199
1951-08,199
1951-09,184
1951-10,162
1951-11,146
1951-12,166
1952-01,171
1952-02,180
1952-03,193
1952-04,181
1952-05,183
1952-06,218
1952-07,230
1952-08,242
1952-09,209
1952-10,191
1952-11,172
1952-12,194
1953-01,196
1953-02,196
1953-03,236
1953-04,235
1953-05,229
1953-06,243
1953-07,264
1953-08,272
1953-09,237
1953-10,211
1953-11,180
1953-12,201
1954-01,204
1954-02,188
1954-03,235
1954-04,227
1954-05,234
1954-06,264
1954-07,302
1954-08,293
1954-09,259
1954-10,229
1954-11,203
1954-12,229
1955-01,242
1955-02,233
1955-03,267
1955-04,269
1955-05,270
1955-06,315
1955-07,364
1955-08,347
1955-09,312
1955-10,274
1955-11,237
1955-12,278
1956-01,284
1956-02,277
1956-03,317
1956-04,313
1956-05,318
1956-06,374
1956-07,413
1956-08,405
1956-09,355
1956-10,306
1956-11,271
1956-12,306
1957-01,315
1957-02,301
1957-03,356
1957-04,348
1957-05,355
1957-06,422
1957-07,465
1957-08,467
1957-09,404
1957-10,347
1957-11,305
1957-12,336
1958-01,340
1958-02,318
1958-03,362
1958-04,348
1958-05,363
1958-06,435
1958-07,491
1958-08,505
1958-09,404
1958-10,359
1958-11,310
1958-12,337
1959-01,360
1959-02,342
1959-03,406
1959-04,396
1959-05,420
1959-06,472
1959-07,548
1959-08,559
1959-09,463
1959-10,407
1959-11,362
1959-12,405
1960-01,417
1960-02,391
1960-03,419
1960-04,461
1960-05,472
1960-06,535
1960-07,622
1960-08,606
1960-09,508
1960-10,461
1960-11,390
1960-12,432
1 Month #Passengers
2 1949-01 112
3 1949-02 118
4 1949-03 132
5 1949-04 129
6 1949-05 121
7 1949-06 135
8 1949-07 148
9 1949-08 148
10 1949-09 136
11 1949-10 119
12 1949-11 104
13 1949-12 118
14 1950-01 115
15 1950-02 126
16 1950-03 141
17 1950-04 135
18 1950-05 125
19 1950-06 149
20 1950-07 170
21 1950-08 170
22 1950-09 158
23 1950-10 133
24 1950-11 114
25 1950-12 140
26 1951-01 145
27 1951-02 150
28 1951-03 178
29 1951-04 163
30 1951-05 172
31 1951-06 178
32 1951-07 199
33 1951-08 199
34 1951-09 184
35 1951-10 162
36 1951-11 146
37 1951-12 166
38 1952-01 171
39 1952-02 180
40 1952-03 193
41 1952-04 181
42 1952-05 183
43 1952-06 218
44 1952-07 230
45 1952-08 242
46 1952-09 209
47 1952-10 191
48 1952-11 172
49 1952-12 194
50 1953-01 196
51 1953-02 196
52 1953-03 236
53 1953-04 235
54 1953-05 229
55 1953-06 243
56 1953-07 264
57 1953-08 272
58 1953-09 237
59 1953-10 211
60 1953-11 180
61 1953-12 201
62 1954-01 204
63 1954-02 188
64 1954-03 235
65 1954-04 227
66 1954-05 234
67 1954-06 264
68 1954-07 302
69 1954-08 293
70 1954-09 259
71 1954-10 229
72 1954-11 203
73 1954-12 229
74 1955-01 242
75 1955-02 233
76 1955-03 267
77 1955-04 269
78 1955-05 270
79 1955-06 315
80 1955-07 364
81 1955-08 347
82 1955-09 312
83 1955-10 274
84 1955-11 237
85 1955-12 278
86 1956-01 284
87 1956-02 277
88 1956-03 317
89 1956-04 313
90 1956-05 318
91 1956-06 374
92 1956-07 413
93 1956-08 405
94 1956-09 355
95 1956-10 306
96 1956-11 271
97 1956-12 306
98 1957-01 315
99 1957-02 301
100 1957-03 356
101 1957-04 348
102 1957-05 355
103 1957-06 422
104 1957-07 465
105 1957-08 467
106 1957-09 404
107 1957-10 347
108 1957-11 305
109 1957-12 336
110 1958-01 340
111 1958-02 318
112 1958-03 362
113 1958-04 348
114 1958-05 363
115 1958-06 435
116 1958-07 491
117 1958-08 505
118 1958-09 404
119 1958-10 359
120 1958-11 310
121 1958-12 337
122 1959-01 360
123 1959-02 342
124 1959-03 406
125 1959-04 396
126 1959-05 420
127 1959-06 472
128 1959-07 548
129 1959-08 559
130 1959-09 463
131 1959-10 407
132 1959-11 362
133 1959-12 405
134 1960-01 417
135 1960-02 391
136 1960-03 419
137 1960-04 461
138 1960-05 472
139 1960-06 535
140 1960-07 622
141 1960-08 606
142 1960-09 508
143 1960-10 461
144 1960-11 390
145 1960-12 432

1225
kaggle_time_series_air_passenger/model.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

404
kaggle_time_series_air_passenger/model2.ipynb Normal file
View File

File diff suppressed because one or more lines are too long

BIN
kaggle_time_series_air_passenger/my_checkpoint/saved_model.pb Normal file
View File

Binary file not shown.

BIN
kaggle_time_series_air_passenger/my_checkpoint/variables/variables.data-00000-of-00001 Normal file
View File

Binary file not shown.

BIN
kaggle_time_series_air_passenger/my_checkpoint/variables/variables.index Normal file
View File

Binary file not shown.