2.2.training_KNN.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<font color='lime'>\n",
    "\n",
    "# Model training and parameter selection with Grid Search\n",
    "\n",
    "</font> "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<font color='yellow'>\n",
    "\n",
    "## K-nearest neighbors (KNN)\n",
    "\n",
    "</font> "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<font color='orange'>\n",
    "\n",
    "### Load the dataset\n",
    "\n",
    "</font> "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "file_path = 'data/spotify_songs_with_mood.csv'\n",
    "spotify_data = pd.read_csv(file_path)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<font color='orange'>\n",
    "\n",
    "### Separate to training and test subset\n",
    "\n",
    "</font> "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "# Selecting the features and the target\n",
    "features = spotify_data[['danceability', 'energy', 'valence', 'acousticness']]\n",
    "target = spotify_data['mood']\n",
    "\n",
    "# Standardizing the features\n",
    "scaler = StandardScaler()\n",
    "features_scaled = scaler.fit_transform(features)\n",
    "\n",
    "# Splitting the dataset into training (70%) and testing (30%) sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(features_scaled, target, test_size=0.3, random_state=42)\n",
    "\n",
    "# Checking the shape of the training and test sets\n",
    "X_train.shape, X_test.shape, y_train.shape, y_test.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<font color='orange'>\n",
    "\n",
    "### Run algorithm\n",
    "\n",
    "</font> "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import GridSearchCV\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "\n",
    "# Defining the KNN classifier and the grid search parameters\n",
    "knn = KNeighborsClassifier()\n",
    "param_grid = {\n",
    "    'n_neighbors': range(1, 31, 2),\n",
    "    'weights': ['uniform', 'distance'],\n",
    "    'metric': ['euclidean', 'manhattan']\n",
    "}\n",
    "\n",
    "# Setting up the grid search with cross-validation\n",
    "grid_search = GridSearchCV(knn, param_grid, cv=5, scoring='accuracy', verbose=1)\n",
    "\n",
    "# Fitting the grid search to the training data\n",
    "grid_search.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<font color='orange'>\n",
    "\n",
    "### Save model\n",
    "\n",
    "</font> "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import joblib\n",
    "\n",
    "# Save the best KNN model from grid search\n",
    "best_knn_model = grid_search.best_estimator_\n",
    "model_path = 'model/songs_mood_knn_model.joblib'\n",
    "joblib.dump(best_knn_model, model_path)\n",
    "\n",
    "# Return the path for confirmation\n",
    "model_path"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<font color='orange'>\n",
    "\n",
    "### Testing subset usage\n",
    "\n",
    "</font> "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "\n",
    "# Making predictions on the test set\n",
    "y_pred = best_knn_model.predict(X_test)\n",
    "\n",
    "# Calculating the accuracy of the model\n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "accuracy_percentage = accuracy * 100\n",
    "\n",
    "# Return the accuracy as a percentage\n",
    "accuracy_percentage"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<font color='yellow'>\n",
    "\n",
    "## Model estimation\n",
    "\n",
    "</font> "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<font color='orange'>\n",
    "\n",
    "### Visualization of predicted values\n",
    "\n",
    "</font> "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from sklearn.metrics import confusion_matrix\n",
    "\n",
    "# Create a confusion matrix\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "\n",
    "# Plotting the confusion matrix\n",
    "plt.figure(figsize=(10, 7))\n",
    "sns.heatmap(cm, annot=True, fmt='g', cmap='Blues', xticklabels=best_knn_model.classes_, yticklabels=best_knn_model.classes_)\n",
    "plt.xlabel('Predicted')\n",
    "plt.ylabel('True')\n",
    "plt.title('Confusion Matrix of the KNN Classifier')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<font color='orange'>\n",
    "\n",
    "### Prediction quality assessment (precision/recall/f1-score/ROC-AUC)\n",
    "\n",
    "</font> "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from sklearn.multiclass import OneVsRestClassifier\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import roc_auc_score, roc_curve, auc, classification_report\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.preprocessing import label_binarize\n",
    "\n",
    "# Feature scaling\n",
    "scaler = StandardScaler()\n",
    "X_train_scaled = scaler.fit_transform(X_train)\n",
    "X_test_scaled = scaler.transform(X_test)\n",
    "\n",
    "# Binarize the y_train and y_test for multi-class ROC AUC calculation\n",
    "y_train_binarized = label_binarize(y_train, classes=np.unique(target))\n",
    "y_test_binarized = label_binarize(y_test, classes=np.unique(target))\n",
    "\n",
    "# Train a OneVsRestClassifier for Logistic Regression to compute ROC AUC\n",
    "logreg_ovr = OneVsRestClassifier(LogisticRegression(max_iter=1000, random_state=42))\n",
    "logreg_ovr.fit(X_train_scaled, y_train_binarized)\n",
    "\n",
    "# Compute ROC AUC Score\n",
    "roc_auc_ovr = dict()\n",
    "fpr = dict()\n",
    "tpr = dict()\n",
    "thresholds = dict()\n",
    "\n",
    "for i in range(y_test_binarized.shape[1]):\n",
    "    fpr[i], tpr[i], thresholds[i] = roc_curve(y_test_binarized[:, i], logreg_ovr.predict_proba(X_test_scaled)[:, i])\n",
    "    roc_auc_ovr[i] = auc(fpr[i], tpr[i])\n",
    "\n",
    "# Plot ROC curve for each class\n",
    "plt.figure(figsize=(10, 8))\n",
    "\n",
    "# Colors for different classes\n",
    "colors = ['blue', 'red', 'green', 'purple']\n",
    "\n",
    "for i, color in zip(range(y_test_binarized.shape[1]), colors):\n",
    "    plt.plot(fpr[i], tpr[i], color=color, lw=2,\n",
    "             label='ROC curve of class {0} (area = {1:0.2f})'.format(np.unique(target)[i], roc_auc_ovr[i]))\n",
    "\n",
    "plt.plot([0, 1], [0, 1], 'k--', lw=2)\n",
    "plt.xlim([0.0, 1.0])\n",
    "plt.ylim([0.0, 1.05])\n",
    "plt.xlabel('False Positive Rate')\n",
    "plt.ylabel('True Positive Rate')\n",
    "plt.title('Receiver Operating Characteristic for each class')\n",
    "plt.legend(loc=\"lower right\")\n",
    "plt.show()\n",
    "\n",
    "roc_auc_ovr"
   ]
  }
 ],
 "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": "3.12.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}