part - B

Untitled7.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "58e43186",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "         0            1          2            3           4            5    \\\n",
+      "0  70.399324  127673.0908 -49.572308  127648.0176 -169.578319  127723.2374   \n",
+      "\n",
+      "         6          7          8          9    ...  119  120  121  122  123  \\\n",
+      "0  65.689611  605.91099 -57.003571  626.78553  ...    0    0    0    0    0   \n",
+      "\n",
+      "   124  125  126  127  128  \n",
+      "0    0    0    0    0    0  \n",
+      "\n",
+      "[1 rows x 129 columns]\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "\n",
+    "from sklearn import datasets\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn import svm, metrics\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "from sklearn.metrics import accuracy_score\n",
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "from sklearn.model_selection import cross_val_score\n",
+    "\n",
+    "df = pd.read_csv('C:\\\\Users\\yl3r22\\Downloads\\TrainingDataMulti.csv', header= None)\n",
+    "df1 = pd.read_csv('C:\\\\Users\\yl3r22\\Downloads\\TestingDataMulti.csv', header= None)\n",
+    "\n",
+    "print(df.head(1))\n",
+    "\n",
+    "df_feature = df.iloc[:, :128]\n",
+    "df_label = df.iloc[:, 128]\n",
+    "cancer = datasets.load_breast_cancer()\n",
+    "\n",
+    "# Split dataset into training set and test set\n",
+    "X_train, X_test, y_train, y_test = train_test_split(df_feature, df_label, test_size=0.2)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "461e2292",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "TrainingAccuracy: 0.7008333333333333\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Create a svm Classifier\n",
+    "clf = svm.SVC(kernel='linear') # Linear Kernel\n",
+    "\n",
+    "#Train the model using the training sets\n",
+    "clf.fit(X_train, y_train)\n",
+    "\n",
+    "#Predict the response for test dataset\n",
+    "y_pred = clf.predict(X_test)\n",
+    "\n",
+    "print(\"TrainingAccuracy:\",metrics.accuracy_score(y_test, y_pred))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "fcda6021",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[2 0 2 0 0 0 1 1 2 2 1 1 1 1 1 1 0 2 0 0 0 1 1 1 1 1 1 0 0 0 0 0 0 1 1 1 1\n",
+      " 1 0 1 1 0 1 0 0 1 1 1 0 0 1 1 1 1 1 1 1 2 1 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
+      " 0 0 0 0 0 0 0 0 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0]\n",
+      "TrainingAccuracy: 0.9316666666666666\n"
+     ]
+    }
+   ],
+   "source": [
+    "y_result = clf.predict(df1)\n",
+    "print(y_result)\n",
+    "#Create a svm Classifier\n",
+    "clf1 = RandomForestClassifier(n_estimators=100, max_features=70)# Linear Kernel\n",
+    "\n",
+    "#Train the model using the training sets\n",
+    "clf1.fit(X_train, y_train)\n",
+    "\n",
+    "#Predict the response for test dataset\n",
+    "y_pred = clf1.predict(X_test)\n",
+    "\n",
+    "print(\"TrainingAccuracy:\",metrics.accuracy_score(y_test, y_pred))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "897bcf3d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Scores: [0.9275  0.9375  0.9475  0.94375 0.94    0.9325 ]\n",
+      "MeanScores: 0.938125\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Evaluate the classifier\n",
+    "scores0 = cross_val_score(clf1, X_train, y_train, cv = 6)\n",
+    "\n",
+    "print(\"Scores:\", scores0)\n",
+    "print(\"MeanScores:\", np.mean(scores0))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "1a48b862",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_data=pd.read_csv(\"C:\\\\Users\\yl3r22\\Downloads\\TestingDataMulti.csv\",header=None)\n",
+    "\n",
+    "# Predict testing datasets at first\n",
+    "# Use previous model - df1\n",
+    "\n",
+    "predictions = clf1.predict(test_data)\n",
+    "\n",
+    "# Convert data frame\n",
+    "prediction_df = pd.DataFrame(predictions)\n",
+    "\n",
+    "result = pd.concat([test_data,prediction_df],axis=1)\n",
+    "\n",
+    "# output the csv documentary\n",
+    "\n",
+    "result.to_csv('C:\\\\Users\\yl3r22\\Downloads\\part2.csv',index = False, header = False)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "354f7f52",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[2 2 2 2 2 2 1 1 2 2 2 1 1 1 2 2 2 2 2 2 1 1 2 2 2 2 1 0 0 0 0 0 0 1 1 1 1\n",
+      " 1 2 2 2 2 2 2 2 2 2 2 2 1 2 2 2 1 2 2 2 1 1 2 1 1 1 1 1 1 0 0 0 0 0 0 0 0\n",
+      " 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 0 0 0 0 0 0 0 0 0]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Check Predictions\n",
+    "print(predictions)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "54cd25fd",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.9.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}