Upload New File

AI_Part2.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "6064e0b1",
+   "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 scikit-learn dataset library\n",
+    "#from sklearn import datasets\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.model_selection import cross_val_score\n",
+    "from sklearn import svm, metrics\n",
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from joblib import dump\n",
+    "\n",
+    "#Read training datasets\n",
+    "df = pd.read_csv('H:\\AI classification\\TrainingDataMulti.csv', header=None)\n",
+    "\n",
+    "# Print the head of csv document to check\n",
+    "print(df.head(1))\n",
+    "\n",
+    "# The first 128 columns are features\n",
+    "df_feature = df.iloc[:, :128]\n",
+    "\n",
+    "# the 129th column is labels\n",
+    "df_label = df.iloc[:, 128]\n",
+    "\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) # 80% training and 20% test\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "cdc65331",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.9416666666666667\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Create a Randomforest Classifier \n",
+    "clf1 = RandomForestClassifier(n_estimators=100, max_features=78)\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_pred1 = clf1.predict(X_test)\n",
+    "\n",
+    "print(\"Accuracy:\",metrics.accuracy_score(y_test, y_pred1))\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "ae7d5339",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Scores [0.94166667 0.95104167 0.934375   0.934375   0.921875  ]\n",
+      "Mean Scores 0.9366666666666668\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Using Cross-validation to evaluate classifier\n",
+    "scores1 = cross_val_score(clf1, X_train, y_train, cv=5)\n",
+    "\n",
+    "#Print model's Scores\n",
+    "print(\"Scores\", scores1)\n",
+    "print(\"Mean Scores\", np.mean(scores1))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "253d7c20",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['H:/AI classification/RFC_part2.pkl']"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Dump the model\n",
+    "dump(clf1, 'H:/AI classification/RFC_part2.pkl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "943bcea4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load testing dataset\n",
+    "test_data=pd.read_csv('H:\\AI classification\\TestingDataMulti.csv', header=None)\n",
+    "\n",
+    "# Predict Testing dataset\n",
+    "predictions = clf1.predict(test_data)\n",
+    "\n",
+    "# Convert predictions into dataframe format\n",
+    "predictions_df = pd.DataFrame(predictions)\n",
+    "\n",
+    "#Write the predictions to testing dataset\n",
+    "result = pd.concat([test_data,predictions_df], axis=1)\n",
+    "\n",
+    "#Output a csv document\n",
+    "result.to_csv('H:/AI classification/test_pre2.csv', index = False, header = False)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "8a8a1e04",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[2 2 2 2 2 2 1 1 2 2 2 1 1 1 1 1 2 1 1 1 1 1 2 2 2 2 0 0 0 0 0 0 0 1 1 1 1\n",
+      " 1 2 2 1 1 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 1 0 0 0 0 0 0 0 0]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# print precdictions\n",
+    "print(predictions)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1521abed",
+   "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
+}