ModelTraining.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Picking Data from file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: pandas in c:\\users\\sa\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (2.2.2)\n",
      "Requirement already satisfied: numpy>=1.26.0 in c:\\users\\sa\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from pandas) (2.2.1)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in c:\\users\\sa\\appdata\\roaming\\python\\python312\\site-packages (from pandas) (2.9.0.post0)\n",
      "Requirement already satisfied: pytz>=2020.1 in c:\\users\\sa\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from pandas) (2024.1)\n",
      "Requirement already satisfied: tzdata>=2022.7 in c:\\users\\sa\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from pandas) (2024.1)\n",
      "Requirement already satisfied: six>=1.5 in c:\\users\\sa\\appdata\\roaming\\python\\python312\\site-packages (from python-dateutil>=2.8.2->pandas) (1.16.0)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "DEPRECATION: Loading egg at c:\\users\\sa\\appdata\\local\\programs\\python\\python312\\lib\\site-packages\\yapf-0.40.2-py3.12.egg is deprecated. pip 25.1 will enforce this behaviour change. A possible replacement is to use pip for package installation. Discussion can be found at https://github.com/pypa/pip/issues/12330\n"
     ]
    }
   ],
   "source": [
    "!pip install pandas\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import pandas as pd\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.model_selection import train_test_split, GridSearchCV\n",
    "from sklearn.metrics import accuracy_score, classification_report\n",
    "import joblib\n",
    "\n",
    "# Function to load and concatenate CSV files from a folder\n",
    "def load_csv_files(folder_path):\n",
    "    dataframes = []\n",
    "    for file_name in os.listdir(folder_path):\n",
    "        if file_name.endswith(\".csv\"):\n",
    "            label = file_name.split(\".\")[0]  # Use the file name (without extension) as the label\n",
    "            df = pd.read_csv(os.path.join(folder_path, file_name))\n",
    "            df['label'] = label  # Add a label column\n",
    "            dataframes.append(df)\n",
    "    return pd.concat(dataframes, ignore_index=True)\n",
    "\n",
    "# Load dataset\n",
    "data_folder = r\"data\"\n",
    "df = load_csv_files(data_folder)\n",
    "\n",
    "# columns for features and labels\n",
    "selected_columns = [\"Flex1\", \"Flex2\", \"Flex3\", \"Flex4\", \"Flex5\", \n",
    "                    \"AccelX\", \"AccelY\", \"AccelZ\", \"GyroX\", \"GyroY\", \"GyroZ\", \"label\"]\n",
    "\n",
    "# Ensure selected columns exist\n",
    "df = df[selected_columns]\n",
    "\n",
    "# Handle missing values\n",
    "df = df.dropna()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data Analysis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of instances of label 'hellow': 0\n"
     ]
    },
    {
     "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>Flex1</th>\n",
       "      <th>Flex2</th>\n",
       "      <th>Flex3</th>\n",
       "      <th>Flex4</th>\n",
       "      <th>Flex5</th>\n",
       "      <th>AccelX</th>\n",
       "      <th>AccelY</th>\n",
       "      <th>AccelZ</th>\n",
       "      <th>GyroX</th>\n",
       "      <th>GyroY</th>\n",
       "      <th>GyroZ</th>\n",
       "      <th>label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>790</td>\n",
       "      <td>792</td>\n",
       "      <td>805</td>\n",
       "      <td>778</td>\n",
       "      <td>772</td>\n",
       "      <td>-1.45</td>\n",
       "      <td>1.88</td>\n",
       "      <td>10.64</td>\n",
       "      <td>-0.57</td>\n",
       "      <td>1.21</td>\n",
       "      <td>0.41</td>\n",
       "      <td>a</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>784</td>\n",
       "      <td>784</td>\n",
       "      <td>793</td>\n",
       "      <td>774</td>\n",
       "      <td>771</td>\n",
       "      <td>-3.19</td>\n",
       "      <td>1.33</td>\n",
       "      <td>10.11</td>\n",
       "      <td>0.29</td>\n",
       "      <td>1.10</td>\n",
       "      <td>-0.05</td>\n",
       "      <td>a</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>775</td>\n",
       "      <td>777</td>\n",
       "      <td>785</td>\n",
       "      <td>767</td>\n",
       "      <td>769</td>\n",
       "      <td>-3.21</td>\n",
       "      <td>2.02</td>\n",
       "      <td>9.56</td>\n",
       "      <td>0.04</td>\n",
       "      <td>0.30</td>\n",
       "      <td>0.08</td>\n",
       "      <td>a</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>772</td>\n",
       "      <td>775</td>\n",
       "      <td>782</td>\n",
       "      <td>767</td>\n",
       "      <td>767</td>\n",
       "      <td>-3.26</td>\n",
       "      <td>1.76</td>\n",
       "      <td>9.42</td>\n",
       "      <td>-0.68</td>\n",
       "      <td>0.11</td>\n",
       "      <td>0.32</td>\n",
       "      <td>a</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>776</td>\n",
       "      <td>776</td>\n",
       "      <td>785</td>\n",
       "      <td>769</td>\n",
       "      <td>768</td>\n",
       "      <td>-3.88</td>\n",
       "      <td>1.29</td>\n",
       "      <td>9.48</td>\n",
       "      <td>-0.03</td>\n",
       "      <td>-0.19</td>\n",
       "      <td>-0.07</td>\n",
       "      <td>a</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Flex1  Flex2  Flex3  Flex4  Flex5  AccelX  AccelY  AccelZ  GyroX  GyroY  \\\n",
       "0    790    792    805    778    772   -1.45    1.88   10.64  -0.57   1.21   \n",
       "1    784    784    793    774    771   -3.19    1.33   10.11   0.29   1.10   \n",
       "2    775    777    785    767    769   -3.21    2.02    9.56   0.04   0.30   \n",
       "3    772    775    782    767    767   -3.26    1.76    9.42  -0.68   0.11   \n",
       "4    776    776    785    769    768   -3.88    1.29    9.48  -0.03  -0.19   \n",
       "\n",
       "   GyroZ label  \n",
       "0   0.41     a  \n",
       "1  -0.05     a  \n",
       "2   0.08     a  \n",
       "3   0.32     a  \n",
       "4  -0.07     a  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Analyze feature distribution for the label 'hellow'\n",
    "label_hellow_count = df[df['label'] == 'hello'].shape[0]\n",
    "print(f\"Number of instances of label 'hellow': {label_hellow_count}\")\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "label\n",
       "Yes           1286\n",
       "No             973\n",
       "I_Love_You     896\n",
       "Hello          895\n",
       "f              800\n",
       "c              797\n",
       "e              700\n",
       "Now            699\n",
       "Awkward        694\n",
       "Sorry          673\n",
       "Bathroom       672\n",
       "d              667\n",
       "Deaf           665\n",
       "Goodbye        664\n",
       "a              662\n",
       "b              653\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Display label counts\n",
    "label_counts = df[\"label\"].value_counts()\n",
    "label_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 3 folds for each of 81 candidates, totalling 243 fits\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "['rf_model.pkl']"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Split into features (X) and labels (y)\n",
    "X = df[[\"Flex1\", \"Flex2\", \"Flex3\", \"Flex4\", \"Flex5\", \"AccelX\", \"AccelY\", \"AccelZ\", \"GyroX\", \"GyroY\", \"GyroZ\"]]\n",
    "y = df[\"label\"]\n",
    "\n",
    "# Split into train and test sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
    "\n",
    "# Initialize Random Forest Classifier\n",
    "rf = RandomForestClassifier(random_state=42)\n",
    "\n",
    "# Perform hyperparameter tuning with GridSearchCV\n",
    "param_grid = {\n",
    "    \"n_estimators\": [50, 100, 150],\n",
    "    \"max_depth\": [None, 10, 20],\n",
    "    \"min_samples_split\": [2, 5, 10],\n",
    "    \"min_samples_leaf\": [1, 2, 4]\n",
    "}\n",
    "\n",
    "grid_search = GridSearchCV(rf, param_grid, cv=3, n_jobs=-1, scoring=\"accuracy\", verbose=2)\n",
    "grid_search.fit(X_train, y_train)\n",
    "\n",
    "# Best model from grid search\n",
    "best_rf = grid_search.best_estimator_\n",
    "\n",
    "# Train the model with the best parameters\n",
    "best_rf.fit(X_train, y_train)\n",
    "\n",
    "# Save the trained model\n",
    "joblib.dump(best_rf, \"rf_model.pkl\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Model Evaluation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model Accuracy: 0.9826612903225806\n",
      "\n",
      "Classification Report:\n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "     Awkward       1.00      0.96      0.98       140\n",
      "    Bathroom       1.00      1.00      1.00       149\n",
      "        Deaf       1.00      1.00      1.00       136\n",
      "     Goodbye       0.99      1.00      1.00       129\n",
      "       Hello       0.97      0.98      0.98       170\n",
      "  I_Love_You       0.95      0.96      0.95       198\n",
      "          No       0.94      0.95      0.94       202\n",
      "         Now       0.99      0.98      0.98       130\n",
      "       Sorry       1.00      1.00      1.00       132\n",
      "         Yes       0.96      0.98      0.97       231\n",
      "           a       1.00      0.96      0.98       140\n",
      "           b       1.00      1.00      1.00       132\n",
      "           c       0.99      0.99      0.99       156\n",
      "           d       1.00      1.00      1.00       132\n",
      "           e       1.00      0.99      0.99       153\n",
      "           f       0.99      1.00      1.00       150\n",
      "\n",
      "    accuracy                           0.98      2480\n",
      "   macro avg       0.99      0.98      0.99      2480\n",
      "weighted avg       0.98      0.98      0.98      2480\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Precision: 0.9829256342781658\n",
      "Recall: 0.9826612903225806\n",
      "F1 Score: 0.9827088199565449\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import confusion_matrix, precision_score, recall_score, f1_score, roc_auc_score\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "# Evaluate the model on the test set\n",
    "y_pred = best_rf.predict(X_test)\n",
    "y_pred_proba = best_rf.predict_proba(X_test)  # For ROC-AUC, if applicable\n",
    "\n",
    "# Accuracy\n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print(f\"Model Accuracy: {accuracy}\")\n",
    "\n",
    "# Classification Report\n",
    "print(\"\\nClassification Report:\\n\", classification_report(y_test, y_pred))\n",
    "\n",
    "# Confusion Matrix\n",
    "conf_matrix = confusion_matrix(y_test, y_pred)\n",
    "plt.figure(figsize=(10, 6))\n",
    "sns.heatmap(conf_matrix, annot=True, fmt=\"d\", cmap=\"Blues\", xticklabels=best_rf.classes_, yticklabels=best_rf.classes_)\n",
    "plt.title(\"Confusion Matrix\")\n",
    "plt.xlabel(\"Predicted\")\n",
    "plt.ylabel(\"Actual\")\n",
    "plt.show()\n",
    "\n",
    "# Precision, Recall, F1-Score\n",
    "precision = precision_score(y_test, y_pred, average=\"weighted\")\n",
    "recall = recall_score(y_test, y_pred, average=\"weighted\")\n",
    "f1 = f1_score(y_test, y_pred, average=\"weighted\")\n",
    "print(f\"Precision: {precision}\")\n",
    "print(f\"Recall: {recall}\")\n",
    "print(f\"F1 Score: {f1}\")\n",
    "\n",
    "# ROC-AUC (only for binary classification)\n",
    "if len(y.unique()) == 2:\n",
    "    roc_auc = roc_auc_score(y_test, y_pred_proba[:, 1])\n",
    "    print(f\"ROC-AUC Score: {roc_auc}\")\n"
   ]
  },
  {
   "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": "3.12.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}