diff --git a/lab-svm.ipynb b/lab-svm.ipynb
index bbbfd6b..eccc4dd 100644
--- a/lab-svm.ipynb
+++ b/lab-svm.ipynb
@@ -44,30 +44,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "#!pip install scikit-learn==0.23.1"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "import piplite\n",
- "await piplite.install(['pandas'])\n",
- "await piplite.install(['matplotlib'])\n",
- "await piplite.install(['numpy'])\n",
- "await piplite.install(['scikit-learn'])\n",
- "await piplite.install(['scipy'])\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
+ "execution_count": 146,
"metadata": {},
"outputs": [],
"source": [
@@ -83,17 +60,17 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 147,
"metadata": {},
"outputs": [],
"source": [
- "from pyodide.http import pyfetch\n",
+ "import requests\n",
"\n",
- "async def download(url, filename):\n",
- " response = await pyfetch(url)\n",
- " if response.status == 200:\n",
+ "def download(url, filename):\n",
+ " response = requests.get(url)\n",
+ " if response.status_code == 200:\n",
" with open(filename, \"wb\") as f:\n",
- " f.write(await response.bytes())\n"
+ " f.write(response.content)\n"
]
},
{
@@ -131,7 +108,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 148,
"metadata": {
"button": false,
"new_sheet": false,
@@ -160,16 +137,16 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 149,
"metadata": {},
"outputs": [],
"source": [
- "await download(path, \"cell_samples.csv\")"
+ "download(path, \"cell_samples.csv\")"
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 150,
"metadata": {
"button": false,
"new_sheet": false,
@@ -177,7 +154,137 @@
"read_only": false
}
},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " ID \n",
+ " Clump \n",
+ " UnifSize \n",
+ " UnifShape \n",
+ " MargAdh \n",
+ " SingEpiSize \n",
+ " BareNuc \n",
+ " BlandChrom \n",
+ " NormNucl \n",
+ " Mit \n",
+ " Class \n",
+ " \n",
+ " \n",
+ " \n",
+ " \n",
+ " 0 \n",
+ " 1000025 \n",
+ " 5 \n",
+ " 1 \n",
+ " 1 \n",
+ " 1 \n",
+ " 2 \n",
+ " 1 \n",
+ " 3 \n",
+ " 1 \n",
+ " 1 \n",
+ " 2 \n",
+ " \n",
+ " \n",
+ " 1 \n",
+ " 1002945 \n",
+ " 5 \n",
+ " 4 \n",
+ " 4 \n",
+ " 5 \n",
+ " 7 \n",
+ " 10 \n",
+ " 3 \n",
+ " 2 \n",
+ " 1 \n",
+ " 2 \n",
+ " \n",
+ " \n",
+ " 2 \n",
+ " 1015425 \n",
+ " 3 \n",
+ " 1 \n",
+ " 1 \n",
+ " 1 \n",
+ " 2 \n",
+ " 2 \n",
+ " 3 \n",
+ " 1 \n",
+ " 1 \n",
+ " 2 \n",
+ " \n",
+ " \n",
+ " 3 \n",
+ " 1016277 \n",
+ " 6 \n",
+ " 8 \n",
+ " 8 \n",
+ " 1 \n",
+ " 3 \n",
+ " 4 \n",
+ " 3 \n",
+ " 7 \n",
+ " 1 \n",
+ " 2 \n",
+ " \n",
+ " \n",
+ " 4 \n",
+ " 1017023 \n",
+ " 4 \n",
+ " 1 \n",
+ " 1 \n",
+ " 3 \n",
+ " 2 \n",
+ " 1 \n",
+ " 3 \n",
+ " 1 \n",
+ " 1 \n",
+ " 2 \n",
+ " \n",
+ " \n",
+ "
\n",
+ "
"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
"source": [
"ax = cell_df[cell_df['Class'] == 4][0:50].plot(kind='scatter', x='Clump', y='UnifSize', color='DarkBlue', label='malignant');\n",
"cell_df[cell_df['Class'] == 2][0:50].plot(kind='scatter', x='Clump', y='UnifSize', color='Yellow', label='benign', ax=ax);\n",
@@ -221,9 +339,31 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 152,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "ID int64\n",
+ "Clump int64\n",
+ "UnifSize int64\n",
+ "UnifShape int64\n",
+ "MargAdh int64\n",
+ "SingEpiSize int64\n",
+ "BareNuc object\n",
+ "BlandChrom int64\n",
+ "NormNucl int64\n",
+ "Mit int64\n",
+ "Class int64\n",
+ "dtype: object"
+ ]
+ },
+ "execution_count": 152,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"cell_df.dtypes"
]
@@ -237,9 +377,31 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 153,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "ID int64\n",
+ "Clump int64\n",
+ "UnifSize int64\n",
+ "UnifShape int64\n",
+ "MargAdh int64\n",
+ "SingEpiSize int64\n",
+ "BareNuc int64\n",
+ "BlandChrom int64\n",
+ "NormNucl int64\n",
+ "Mit int64\n",
+ "Class int64\n",
+ "dtype: object"
+ ]
+ },
+ "execution_count": 153,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"cell_df = cell_df[pd.to_numeric(cell_df['BareNuc'], errors='coerce').notnull()]\n",
"cell_df['BareNuc'] = cell_df['BareNuc'].astype('int')\n",
@@ -248,9 +410,24 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 154,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([[ 5, 1, 1, 1, 2, 1, 3, 1, 1],\n",
+ " [ 5, 4, 4, 5, 7, 10, 3, 2, 1],\n",
+ " [ 3, 1, 1, 1, 2, 2, 3, 1, 1],\n",
+ " [ 6, 8, 8, 1, 3, 4, 3, 7, 1],\n",
+ " [ 4, 1, 1, 3, 2, 1, 3, 1, 1]])"
+ ]
+ },
+ "execution_count": 154,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"feature_df = cell_df[['Clump', 'UnifSize', 'UnifShape', 'MargAdh', 'SingEpiSize', 'BareNuc', 'BlandChrom', 'NormNucl', 'Mit']]\n",
"X = np.asarray(feature_df)\n",
@@ -266,9 +443,20 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 155,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([2, 2, 2, 2, 2])"
+ ]
+ },
+ "execution_count": 155,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"cell_df['Class'] = cell_df['Class'].astype('int')\n",
"y = np.asarray(cell_df['Class'])\n",
@@ -291,9 +479,18 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 156,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Train set: (546, 9) (546,)\n",
+ "Test set: (137, 9) (137,)\n"
+ ]
+ }
+ ],
"source": [
"X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.2, random_state=4)\n",
"print ('Train set:', X_train.shape, y_train.shape)\n",
@@ -325,9 +522,438 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 157,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "SVC() In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. "
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
"source": [
"# Compute confusion matrix\n",
"cnf_matrix = confusion_matrix(y_test, yhat, labels=[2,4])\n",
@@ -435,9 +1101,20 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 162,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0.9639038982104676"
+ ]
+ },
+ "execution_count": 162,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"from sklearn.metrics import f1_score\n",
"f1_score(y_test, yhat, average='weighted') "
@@ -452,9 +1129,20 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 163,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "np.float64(0.9444444444444444)"
+ ]
+ },
+ "execution_count": 163,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"from sklearn.metrics import jaccard_score\n",
"jaccard_score(y_test, yhat,pos_label=2)"
@@ -470,11 +1158,24 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 164,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Avg F1-score: 0.9639038982104676\n",
+ "Jaccard score: 0.9444444444444444\n"
+ ]
+ }
+ ],
"source": [
- "# write your code here\n"
+ "clf2 = svm.SVC(kernel='linear')\n",
+ "clf2.fit(X_train, y_train) \n",
+ "yhat2 = clf2.predict(X_test)\n",
+ "print(\"Avg F1-score: \", f1_score(y_test, yhat2, average='weighted'))\n",
+ "print(\"Jaccard score: \", jaccard_score(y_test, yhat2,pos_label=2))\n"
]
},
{
@@ -505,7 +1206,7 @@
],
"metadata": {
"kernelspec": {
- "display_name": "Python 3 (ipykernel)",
+ "display_name": "Python 3",
"language": "python",
"name": "python3"
},
@@ -519,7 +1220,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.11.8"
+ "version": "3.9.6"
}
},
"nbformat": 4,