diff --git a/Assignment2Final.ipynb b/Assignment2Final.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..eec504b889112d3f439e0706be54d818e4009765
--- /dev/null
+++ b/Assignment2Final.ipynb
@@ -0,0 +1,200 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "a115ed80",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import matplotlib.pyplot as plt\n",
+ "from sklearn.model_selection import GridSearchCV, train_test_split\n",
+ "from sklearn.ensemble import RandomForestClassifier\n",
+ "from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay, f1_score, classification_report\n",
+ "from sklearn.preprocessing import StandardScaler, MinMaxScaler\n",
+ "from sklearn.decomposition import PCA, FastICA\n",
+ "from sklearn.manifold import LocallyLinearEmbedding\n",
+ "from sklearn.pipeline import Pipeline\n",
+ "from sklearn.linear_model import Ridge, Lasso\n",
+ "\n",
+ "#Load csv datasets into pandas dataframes\n",
+ "binTrain = pd.read_csv('TrainingDataBinary.csv', header=None)\n",
+ "binTest = pd.read_csv('TestingDataBinary.csv', header=None)\n",
+ "mulTrain = pd.read_csv('TrainingDataMulti.csv', header=None)\n",
+ "mulTest = pd.read_csv('TestingDataMulti.csv', header=None)\n",
+ "\n",
+ "#Get feature set from first 128 columns of the datasets\n",
+ "binTrainX = binTrain.iloc[:, :128]\n",
+ "mulTrainX = mulTrain.iloc[:, :128]\n",
+ "\n",
+ "#Get label set from last column (129th) of the datasets\n",
+ "binTrainY = binTrain.iloc[:, 128]\n",
+ "mulTrainY = mulTrain.iloc[:, 128]\n",
+ "\n",
+ "#Split feature and label sets into training and testing sets with 80/20 split\n",
+ "#Random state seed used to reproduce performance results for testing\n",
+ "binX_train, binX_test, binY_train, binY_test = train_test_split(binTrainX, binTrainY, test_size=0.2, random_state = 2)\n",
+ "mulX_train, mulX_test, mulY_train, mulY_test = train_test_split(mulTrainX, mulTrainY, test_size=0.2, random_state = 3)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "14ef5b96",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "F1 Score: 0.9916638647990019\n",
+ " precision recall f1-score support\n",
+ "\n",
+ " 0 1.00 0.99 0.99 614\n",
+ " 1 0.99 1.00 0.99 586\n",
+ "\n",
+ " accuracy 0.99 1200\n",
+ " macro avg 0.99 0.99 0.99 1200\n",
+ "weighted avg 0.99 0.99 0.99 1200\n",
+ "\n"
+ ]
+ },
+ {
+ "data": {
+ "image/png": "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\n",
+ "text/plain": [
+ "<Figure size 640x480 with 2 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "#Random Forest created using optimal hyperparamters from grid search\n",
+ "rf = RandomForestClassifier(random_state = 1, n_estimators = 50, criterion = 'gini', min_samples_split = 2, min_samples_leaf = 1, max_features = 'sqrt')\n",
+ "#Train model using training features and labels \n",
+ "rf.fit(binX_train, binY_train)\n",
+ "#Get predicted labels for test features\n",
+ "preds = rf.predict(binX_test)\n",
+ "\n",
+ "#Get F1 score from predicted labels against actual labels\n",
+ "print(f\"F1 Score: {f1_score(binY_test, preds, average='macro')}\")\n",
+ "#Get F1 score, accuracy, precision and recall of each class from predicted labels against actual labels\n",
+ "print(classification_report(binY_test, preds))\n",
+ "\n",
+ "#Create and display confusion matrix of results\n",
+ "cm = confusion_matrix(binY_test, preds, labels=rf.classes_)\n",
+ "disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=rf.classes_)\n",
+ "disp.plot()\n",
+ "plt.show()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "e25a4b1b",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#Get prediction labels for testing data\n",
+ "test_preds = rf.predict(binTest)\n",
+ "#Add labels to last (129th) column of testing dataset\n",
+ "binTestLabels = binTest.assign(Label=test_preds)\n",
+ "#Save testing data with labels as csv\n",
+ "binTestLabels.to_csv('TestingResultsBinary.csv', index = False, header = False)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "d0fe268b",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "F1 Score: 0.9535275147686754\n",
+ " precision recall f1-score support\n",
+ "\n",
+ " 0 0.99 0.99 0.99 589\n",
+ " 1 0.96 0.92 0.94 321\n",
+ " 2 0.92 0.94 0.93 290\n",
+ "\n",
+ " accuracy 0.96 1200\n",
+ " macro avg 0.95 0.95 0.95 1200\n",
+ "weighted avg 0.96 0.96 0.96 1200\n",
+ "\n"
+ ]
+ },
+ {
+ "data": {
+ "image/png": "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\n",
+ "text/plain": [
+ "<Figure size 640x480 with 2 Axes>