Skip to content
Permalink
master
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?

CSE5713_DataMiningProject/Best-SVM.ipynb

Go to file
 
 
Cannot retrieve contributors at this time
532 lines (532 sloc) 16 KB
Raw Blame
Open in GitHub Desktop
{
"cells": [
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import seaborn as sn\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.decomposition import PCA\n",
"from sklearn.manifold import TSNE\n",
"from mpl_toolkits.mplot3d import Axes3D\n",
"import seaborn as sns\n",
"from sklearn.neural_network import MLPClassifier\n",
"from sklearn.model_selection import train_test_split\n"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>samplecodenumber</th>\n",
" <th>clumpthickness</th>\n",
" <th>cellsize</th>\n",
" <th>cellshape</th>\n",
" <th>marginaladhesion</th>\n",
" <th>singleepithelialcellsize</th>\n",
" <th>barenuclei</th>\n",
" <th>blandchromatin</th>\n",
" <th>normalnucleoli</th>\n",
" <th>mitoses</th>\n",
" <th>class</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <td>0</td>\n",
" <td>1000025</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <td>1</td>\n",
" <td>1002945</td>\n",
" <td>5</td>\n",
" <td>4</td>\n",
" <td>4</td>\n",
" <td>5</td>\n",
" <td>7</td>\n",
" <td>10</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <td>2</td>\n",
" <td>1015425</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <td>3</td>\n",
" <td>1016277</td>\n",
" <td>6</td>\n",
" <td>8</td>\n",
" <td>8</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>4</td>\n",
" <td>3</td>\n",
" <td>7</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <td>4</td>\n",
" <td>1017023</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" samplecodenumber clumpthickness cellsize cellshape marginaladhesion \\\n",
"0 1000025 5 1 1 1 \n",
"1 1002945 5 4 4 5 \n",
"2 1015425 3 1 1 1 \n",
"3 1016277 6 8 8 1 \n",
"4 1017023 4 1 1 3 \n",
"\n",
" singleepithelialcellsize barenuclei blandchromatin normalnucleoli \\\n",
"0 2 1 3 1 \n",
"1 7 10 3 2 \n",
"2 2 2 3 1 \n",
"3 3 4 3 7 \n",
"4 2 1 3 1 \n",
"\n",
" mitoses class \n",
"0 1 2 \n",
"1 1 2 \n",
"2 1 2 \n",
"3 1 2 \n",
"4 1 2 "
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"##Standaridzed preprocessign with rest of group\n",
"\n",
"df=pd.read_csv('breast-cancer-wisconsin.csv')\n",
"features = ['samplecodenumber', 'clumpthickness', 'cellsize', 'cellshape', 'marginaladhesion','singleepithelialcellsize','barenuclei','blandchromatin','normalnucleoli','mitoses']\n",
"\n",
"#impute missing values (all of which are in barenuclei) with mean of barenuclei\n",
"df=df.replace('?',3.54465593)\n",
"\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[-0.11623873 0.20693572 -0.69999505 ... -0.17966213 -0.61182504\n",
" -0.34391178]\n",
" [-0.1115035 0.20693572 0.28384518 ... -0.17966213 -0.28411186\n",
" -0.34391178]\n",
" [-0.09126525 -0.50386559 -0.69999505 ... -0.17966213 -0.61182504\n",
" -0.34391178]\n",
" ...\n",
" [-0.29657482 0.20693572 2.25152563 ... 1.87236122 2.33759359\n",
" 0.23956962]\n",
" [-0.28254589 -0.14846494 1.59563215 ... 2.69317056 1.02674087\n",
" -0.34391178]\n",
" [-0.28254589 -0.14846494 1.59563215 ... 2.69317056 0.37131451\n",
" -0.34391178]]\n"
]
}
],
"source": [
"# Separating out the features\n",
"\n",
"x = df.loc[:, features].values# Separating out the target\n",
"y = df.loc[:,['class']].values# Standardizing the features\n",
"x = StandardScaler().fit_transform(x)\n",
"print(x)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.model_selection import train_test_split\n",
"X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.3, random_state=1)\n"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\sruth\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py:724: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
" y = column_or_1d(y, warn=True)\n",
"C:\\Users\\sruth\\Anaconda3\\lib\\site-packages\\sklearn\\svm\\base.py:193: FutureWarning: The default value of gamma will change from 'auto' to 'scale' in version 0.22 to account better for unscaled features. Set gamma explicitly to 'auto' or 'scale' to avoid this warning.\n",
" \"avoid this warning.\", FutureWarning)\n"
]
},
{
"data": {
"text/plain": [
"SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,\n",
" decision_function_shape='ovr', degree=3, gamma='auto_deprecated',\n",
" kernel='rbf', max_iter=-1, probability=False, random_state=None,\n",
" shrinking=True, tol=0.001, verbose=False)"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#RBF Kernel had best result\n",
"from sklearn.svm import SVC\n",
"svc_model=SVC()\n",
"svc_model.fit(X_train, y_train)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
"y_predict = svc_model.predict(X_test)"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Classification Report\n",
" precision recall f1-score support\n",
"\n",
" 2 0.99 0.99 0.99 137\n",
" 4 0.97 0.97 0.97 73\n",
"\n",
" accuracy 0.98 210\n",
" macro avg 0.98 0.98 0.98 210\n",
"weighted avg 0.98 0.98 0.98 210\n",
"\n"
]
}
],
"source": [
"from sklearn.metrics import classification_report, confusion_matrix\n",
"print(\"Classification Report\")\n",
"print(classification_report(y_test, y_predict))"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {
"scrolled": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" 0 1 2 3 4 5 6 \\\n",
"0 0.236782 0.206936 -0.699995 -0.743299 1.119088 -0.097628 -0.706991 \n",
"1 0.272864 -1.214667 -0.699995 -0.743299 -0.633247 -0.549561 -0.706991 \n",
"2 -1.165331 -0.148465 -0.699995 -0.743299 -0.282780 -0.549561 -0.706991 \n",
"3 -0.387798 -0.148465 -0.372048 -0.069850 0.768621 -0.097628 1.237845 \n",
"4 0.176966 -0.503866 -0.699995 -0.743299 -0.633247 -0.097628 -0.706991 \n",
".. ... ... ... ... ... ... ... \n",
"205 -0.751713 1.983939 0.283845 -0.069850 2.520955 0.354305 1.793513 \n",
"206 -1.635161 1.628538 -0.699995 -0.406574 1.119088 0.354305 1.793513 \n",
"207 -0.610736 -1.214667 -0.699995 -0.743299 -0.633247 -0.549561 -0.706991 \n",
"208 0.156741 1.273138 -0.372048 -0.069850 -0.633247 1.258172 -0.151324 \n",
"209 0.426435 -1.214667 -0.699995 -0.743299 -0.633247 -0.549561 -0.706991 \n",
"\n",
" 7 8 9 \n",
"0 -1.000471 -0.611825 -0.343912 \n",
"1 -0.590067 -0.611825 -0.343912 \n",
"2 -1.000471 -0.611825 -0.343912 \n",
"3 1.461957 1.026741 -0.343912 \n",
"4 -0.590067 -0.611825 -0.343912 \n",
".. ... ... ... \n",
"205 2.693171 -0.611825 -0.343912 \n",
"206 1.461957 1.354454 0.239570 \n",
"207 -0.590067 -0.611825 -0.343912 \n",
"208 1.461957 -0.611825 -0.343912 \n",
"209 -1.000471 -0.611825 -0.343912 \n",
"\n",
"[210 rows x 10 columns]\n"
]
}
],
"source": [
"datafeatures = np.array(X_test)\n",
"fin_results = pd.DataFrame(data = datafeatures)\n",
"print(fin_results)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" 0\n",
"0 0.236782\n",
"1 0.272864\n",
"2 -1.165331\n",
"3 -0.387798\n",
"4 0.176966\n",
".. ...\n",
"205 -0.751713\n",
"206 -1.635161\n",
"207 -0.610736\n",
"208 0.156741\n",
"209 0.426435\n",
"\n",
"[210 rows x 1 columns]\n"
]
}
],
"source": [
"fin_results.drop(fin_results.columns[1:], axis=1, inplace=True)\n",
"print(fin_results)"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2 2 2 4 2 2 4 2 2 2 4 4 2 4 4 4 2 2 2 2 2 4 4 2 4 2 4 2 2 2 2 4 4 4 4 4 2\n",
" 4 2 2 2 2 2 2 2 4 2 2 2 2 2 2 4 2 4 4 4 2 2 4 2 2 2 2 2 2 2 4 2 2 2 2 2 2\n",
" 4 4 2 2 2 2 4 4 2 4 2 2 2 4 4 2 4 2 2 2 2 4 2 2 2 2 2 2 4 2 2 4 4 2 4 2 4\n",
" 2 2 2 2 2 2 2 2 2 2 4 4 4 2 4 2 4 2 2 2 4 4 2 4 2 2 2 4 4 2 4 2 2 2 4 2 4\n",
" 2 2 2 2 2 4 2 2 2 2 2 2 2 4 2 2 4 4 2 2 2 2 2 4 4 2 2 4 4 4 4 4 4 2 2 2 2\n",
" 4 2 2 2 2 2 2 2 4 2 4 4 4 4 2 2 2 2 2 4 4 4 2 4 2]\n"
]
}
],
"source": [
"y_test = np.array(y_test)\n",
"y_test = y_test.ravel()\n",
"np.array(y_test)\n",
"print(y_test)"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" 0 y_test\n",
"0 0.236782 2\n",
"1 0.272864 2\n",
"2 -1.165331 2\n",
"3 -0.387798 4\n",
"4 0.176966 2\n",
".. ... ...\n",
"205 -0.751713 4\n",
"206 -1.635161 4\n",
"207 -0.610736 2\n",
"208 0.156741 4\n",
"209 0.426435 2\n",
"\n",
"[210 rows x 2 columns]\n"
]
}
],
"source": [
"fin_results.insert(1, 'y_test', y_test, allow_duplicates = True) \n",
"print(fin_results)"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[2 2 2 4 2 2 4 2 2 2 4 4 2 4 4 4 2 2 2 2 2 4 4 2 4 2 4 4 2 2 2 4 4 4 4 4 2\n",
" 4 2 2 2 2 2 2 2 4 2 2 2 2 2 2 4 2 4 2 4 2 2 4 2 2 2 2 2 2 2 4 2 2 2 2 2 2\n",
" 2 4 2 2 2 2 4 4 2 4 2 2 2 4 4 2 4 2 2 2 2 4 2 2 2 2 2 2 4 2 2 4 4 2 4 2 4\n",
" 2 2 2 2 2 2 2 2 2 2 4 4 4 2 4 2 4 2 2 2 4 4 2 4 2 2 2 4 4 2 4 2 2 2 4 2 4\n",
" 2 2 2 2 2 4 2 2 2 2 2 2 2 4 2 2 4 4 2 2 2 2 2 4 4 2 2 4 4 4 4 4 4 2 2 2 2\n",
" 4 2 2 4 2 2 2 2 4 2 4 4 4 4 2 2 2 2 2 4 4 4 2 4 2]\n"
]
}
],
"source": [
"y_predict = np.array(y_predict)\n",
"y_predict = y_predict.ravel()\n",
"np.array(y_predict)\n",
"print(y_predict)"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" 0 y_predict y_test\n",
"0 0.236782 2 2\n",
"1 0.272864 2 2\n",
"2 -1.165331 2 2\n",
"3 -0.387798 4 4\n",
"4 0.176966 2 2\n",
".. ... ... ...\n",
"205 -0.751713 4 4\n",
"206 -1.635161 4 4\n",
"207 -0.610736 2 2\n",
"208 0.156741 4 4\n",
"209 0.426435 2 2\n",
"\n",
"[210 rows x 3 columns]\n"
]
}
],
"source": [
"fin_results.insert(1, 'y_predict', y_predict, allow_duplicates = True) \n",
"print(fin_results)"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [],
"source": [
"fin_results.to_csv(\"svmp_rediction\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"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
}