{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "869e4d61",
   "metadata": {},
   "source": [
    "# Task 1: Model Training and Optimization Pipeline\n",
    "Use this notebook to perform your data preprocessing, hyperparameter tuning via Cross-Validation, and final evaluation on the test set."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "476ea18c",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import pickle\n",
    "import time\n",
    "import optuna\n",
    "import trackio\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.ensemble import RandomForestRegressor\n",
    "from sklearn.model_selection import GridSearchCV, RandomizedSearchCV, cross_val_score\n",
    "from sklearn.metrics import mean_absolute_error\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "\n",
    "# Add any other imports you need here\n",
    "import os\n",
    "from pathlib import Path\n",
    "from optuna.visualization.matplotlib import plot_contour as optuna_mpl_plot_contour\n",
    "import optuna.visualization as ov"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bf91fcbd",
   "metadata": {},
   "source": [
    "## 1. Data Loading & Preprocessing\n",
    "Load `train.csv` and `test.csv`. Convert string categorical variables to numeric.\n",
    "**Required:** Save your label encoders/mappings because your Streamlit UI will need them later to prepare user inputs for inference!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "45e68d75",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train shape: (11128, 14), Test shape: (2782, 14)\n",
      "Categorical columns encoded: ['location', 'city', 'Status', 'property_type']\n",
      "Unknown-category counts in test after safe encoding: {'location': 53, 'city': 0, 'Status': 0, 'property_type': 0}\n",
      "Saved preprocessing artifacts: label_encoders.pkl, feature_columns.pkl, feature_metadata.pkl\n"
     ]
    }
   ],
   "source": [
    "train_df = pd.read_csv('Dataset/train.csv')\n",
    "test_df = pd.read_csv('Dataset/test.csv')\n",
    "\n",
    "SEED = 42\n",
    "TARGET_COL = \"price\"\n",
    "UNKNOWN_CATEGORY_TOKEN = \"__UNK__\"\n",
    "DATA_DIR = Path(\"Dataset\")\n",
    "MODELS_DIR = Path(\"models\")\n",
    "PLOTS_DIR = Path(\"plots\")\n",
    "\n",
    "MODELS_DIR.mkdir(exist_ok=True)\n",
    "PLOTS_DIR.mkdir(exist_ok=True)\n",
    "\n",
    "# TODO: Implement your preprocessing here (use LabelEncoder or manual dictionaries)\n",
    "# Ensure you keep all necessary features that will be shown on the UI dashboard.\n",
    "\n",
    "categorical_cols = [col for col in train_df.columns if train_df[col].dtype == \"object\"]\n",
    "feature_cols = [col for col in train_df.columns if col != TARGET_COL]\n",
    "\n",
    "label_encoders = {}\n",
    "test_unknown_counts = {}\n",
    "\n",
    "for col in categorical_cols:\n",
    "    train_series = train_df[col].astype(str)\n",
    "    test_series = test_df[col].astype(str)\n",
    "\n",
    "    known_train_values = set(train_series.unique())\n",
    "    safe_test_series = test_series.where(test_series.isin(known_train_values), UNKNOWN_CATEGORY_TOKEN)\n",
    "\n",
    "    encoder = LabelEncoder()\n",
    "    encoder.fit(pd.concat([train_series, pd.Series([UNKNOWN_CATEGORY_TOKEN])], ignore_index=True))\n",
    "\n",
    "    train_df[col] = encoder.transform(train_series)\n",
    "    test_df[col] = encoder.transform(safe_test_series)\n",
    "\n",
    "    label_encoders[col] = encoder\n",
    "    test_unknown_counts[col] = int((safe_test_series == UNKNOWN_CATEGORY_TOKEN).sum())\n",
    "\n",
    "\n",
    "# TODO: Separate predictors (X) and target (y: 'price')\n",
    "\n",
    "X_train = train_df[feature_cols].copy()\n",
    "y_train = train_df[TARGET_COL].copy()\n",
    "X_test = test_df[feature_cols].copy()\n",
    "y_test = test_df[TARGET_COL].copy()\n",
    "\n",
    "feature_metadata = {}\n",
    "for col in feature_cols:\n",
    "    col_values = X_train[col]\n",
    "    feature_metadata[col] = {\n",
    "        \"dtype\": str(col_values.dtype),\n",
    "        \"min\": float(col_values.min()),\n",
    "        \"max\": float(col_values.max()),\n",
    "        \"mean\": float(col_values.mean())\n",
    "    }\n",
    "\n",
    "with open(MODELS_DIR / \"label_encoders.pkl\", \"wb\") as f:\n",
    "    pickle.dump(label_encoders, f)\n",
    "\n",
    "with open(MODELS_DIR / \"feature_columns.pkl\", \"wb\") as f:\n",
    "    pickle.dump(feature_cols, f)\n",
    "\n",
    "with open(MODELS_DIR / \"feature_metadata.pkl\", \"wb\") as f:\n",
    "    pickle.dump(feature_metadata, f)\n",
    "\n",
    "print(f\"Train shape: {X_train.shape}, Test shape: {X_test.shape}\")\n",
    "print(f\"Categorical columns encoded: {categorical_cols}\")\n",
    "print(f\"Unknown-category counts in test after safe encoding: {test_unknown_counts}\")\n",
    "print(\"Saved preprocessing artifacts: label_encoders.pkl, feature_columns.pkl, feature_metadata.pkl\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0f594594",
   "metadata": {},
   "source": [
    "## 2. Hyperparameter Tuning using Cross-Validation\n",
    "\n",
    "**Strict Search Space:**\n",
    "- `n_estimators`: 50 to 200\n",
    "- `max_depth`: 10 to 30\n",
    "- `min_samples_split`: 2 to 10\n",
    "\n",
    "Implement Grid Search, Random Search, and Bayesian Optimization (using Optuna). Evaluate each using 5-fold cross-validation on `train_df`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "4a4a1037",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "* Trackio project initialized: cs203-assignment4\n",
      "* Trackio metrics logged to: C:\\Users\\Aayush\\.cache\\huggingface\\trackio\n",
      "* View dashboard by running in your terminal:\n",
      "\u001b[1m\u001b[38;5;208mtrackio show --project \"cs203-assignment4\"\u001b[0m\n",
      "* or by running in Python: trackio.show(project=\"cs203-assignment4\")\n",
      "* Created new run: fancy-breeze-4\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\Aayush\\miniconda3\\envs\\stt-ai\\Lib\\site-packages\\trackio\\__init__.py:257: UserWarning: * Warning: resume='never' but a run 'rf-optimization-comparison' already exists in project 'cs203-assignment4'. Generating a new name and instead. If you want to resume this run, call init() with resume='must' or resume='allow'.\n",
      "  warnings.warn(\n",
      "\u001b[32m[I 2026-04-14 22:48:07,717]\u001b[0m A new study created in memory with name: rf_bayesian_optimization\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:48:12,329]\u001b[0m Trial 0 finished with value: 13976.072203573402 and parameters: {'n_estimators': 163, 'max_depth': 20, 'min_samples_split': 10}. Best is trial 0 with value: 13976.072203573402.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:48:15,133]\u001b[0m Trial 1 finished with value: 13469.757792931317 and parameters: {'n_estimators': 68, 'max_depth': 27, 'min_samples_split': 4}. Best is trial 1 with value: 13469.757792931317.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:48:21,159]\u001b[0m Trial 2 finished with value: 13889.729831128032 and parameters: {'n_estimators': 167, 'max_depth': 22, 'min_samples_split': 9}. Best is trial 1 with value: 13469.757792931317.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:48:24,103]\u001b[0m Trial 3 finished with value: 13681.118548542558 and parameters: {'n_estimators': 73, 'max_depth': 26, 'min_samples_split': 6}. Best is trial 1 with value: 13469.757792931317.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:48:28,948]\u001b[0m Trial 4 finished with value: 15204.378639267505 and parameters: {'n_estimators': 189, 'max_depth': 10, 'min_samples_split': 2}. Best is trial 1 with value: 13469.757792931317.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:48:36,529]\u001b[0m Trial 5 finished with value: 13966.555997250602 and parameters: {'n_estimators': 199, 'max_depth': 29, 'min_samples_split': 10}. Best is trial 1 with value: 13469.757792931317.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:48:41,260]\u001b[0m Trial 6 finished with value: 13499.083290142818 and parameters: {'n_estimators': 114, 'max_depth': 30, 'min_samples_split': 4}. Best is trial 1 with value: 13469.757792931317.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:48:45,030]\u001b[0m Trial 7 finished with value: 14235.023942759546 and parameters: {'n_estimators': 114, 'max_depth': 14, 'min_samples_split': 8}. Best is trial 1 with value: 13469.757792931317.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:48:50,560]\u001b[0m Trial 8 finished with value: 13881.10859592156 and parameters: {'n_estimators': 152, 'max_depth': 25, 'min_samples_split': 9}. Best is trial 1 with value: 13469.757792931317.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:48:55,631]\u001b[0m Trial 9 finished with value: 14570.161040112178 and parameters: {'n_estimators': 179, 'max_depth': 12, 'min_samples_split': 7}. Best is trial 1 with value: 13469.757792931317.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:48:57,757]\u001b[0m Trial 10 finished with value: 13592.353036008057 and parameters: {'n_estimators': 53, 'max_depth': 18, 'min_samples_split': 4}. Best is trial 1 with value: 13469.757792931317.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:49:01,306]\u001b[0m Trial 11 finished with value: 13484.703501449709 and parameters: {'n_estimators': 86, 'max_depth': 30, 'min_samples_split': 4}. Best is trial 1 with value: 13469.757792931317.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:49:04,768]\u001b[0m Trial 12 finished with value: 13485.80258884633 and parameters: {'n_estimators': 84, 'max_depth': 26, 'min_samples_split': 4}. Best is trial 1 with value: 13469.757792931317.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:49:08,620]\u001b[0m Trial 13 finished with value: 13346.412085785949 and parameters: {'n_estimators': 89, 'max_depth': 28, 'min_samples_split': 2}. Best is trial 13 with value: 13346.412085785949.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:49:10,933]\u001b[0m Trial 14 finished with value: 13355.03867101239 and parameters: {'n_estimators': 54, 'max_depth': 23, 'min_samples_split': 2}. Best is trial 13 with value: 13346.412085785949.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:49:13,126]\u001b[0m Trial 15 finished with value: 13356.090130935883 and parameters: {'n_estimators': 51, 'max_depth': 23, 'min_samples_split': 2}. Best is trial 13 with value: 13346.412085785949.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:49:16,817]\u001b[0m Trial 16 finished with value: 13602.80062434621 and parameters: {'n_estimators': 100, 'max_depth': 16, 'min_samples_split': 2}. Best is trial 13 with value: 13346.412085785949.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:49:22,324]\u001b[0m Trial 17 finished with value: 13389.36812535609 and parameters: {'n_estimators': 134, 'max_depth': 23, 'min_samples_split': 3}. Best is trial 13 with value: 13346.412085785949.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:49:25,931]\u001b[0m Trial 18 finished with value: 13610.85510434176 and parameters: {'n_estimators': 96, 'max_depth': 20, 'min_samples_split': 5}. Best is trial 13 with value: 13346.412085785949.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:49:28,815]\u001b[0m Trial 19 finished with value: 13377.476013135925 and parameters: {'n_estimators': 71, 'max_depth': 24, 'min_samples_split': 3}. Best is trial 13 with value: 13346.412085785949.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:49:34,088]\u001b[0m Trial 20 finished with value: 13663.071055653732 and parameters: {'n_estimators': 137, 'max_depth': 28, 'min_samples_split': 6}. Best is trial 13 with value: 13346.412085785949.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:49:36,219]\u001b[0m Trial 21 finished with value: 13342.650791515425 and parameters: {'n_estimators': 51, 'max_depth': 22, 'min_samples_split': 2}. Best is trial 21 with value: 13342.650791515425.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:49:38,634]\u001b[0m Trial 22 finished with value: 13441.794366822447 and parameters: {'n_estimators': 58, 'max_depth': 21, 'min_samples_split': 3}. Best is trial 21 with value: 13342.650791515425.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:49:41,331]\u001b[0m Trial 23 finished with value: 13420.488878600625 and parameters: {'n_estimators': 66, 'max_depth': 18, 'min_samples_split': 2}. Best is trial 21 with value: 13342.650791515425.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:49:44,750]\u001b[0m Trial 24 finished with value: 13488.21221279252 and parameters: {'n_estimators': 83, 'max_depth': 18, 'min_samples_split': 3}. Best is trial 21 with value: 13342.650791515425.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:49:48,714]\u001b[0m Trial 25 finished with value: 13604.486155627568 and parameters: {'n_estimators': 100, 'max_depth': 25, 'min_samples_split': 5}. Best is trial 21 with value: 13342.650791515425.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:49:51,302]\u001b[0m Trial 26 finished with value: 13326.978117091432 and parameters: {'n_estimators': 61, 'max_depth': 27, 'min_samples_split': 2}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:49:54,591]\u001b[0m Trial 27 finished with value: 13407.248842421643 and parameters: {'n_estimators': 78, 'max_depth': 28, 'min_samples_split': 3}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:49:57,035]\u001b[0m Trial 28 finished with value: 13575.737223744762 and parameters: {'n_estimators': 62, 'max_depth': 28, 'min_samples_split': 5}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:50:01,005]\u001b[0m Trial 29 finished with value: 13337.730951035997 and parameters: {'n_estimators': 94, 'max_depth': 26, 'min_samples_split': 2}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:50:05,628]\u001b[0m Trial 30 finished with value: 13446.715123486658 and parameters: {'n_estimators': 114, 'max_depth': 21, 'min_samples_split': 3}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:50:09,752]\u001b[0m Trial 31 finished with value: 13338.466149141721 and parameters: {'n_estimators': 93, 'max_depth': 26, 'min_samples_split': 2}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:50:14,198]\u001b[0m Trial 32 finished with value: 13343.732865597718 and parameters: {'n_estimators': 106, 'max_depth': 26, 'min_samples_split': 2}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:50:17,242]\u001b[0m Trial 33 finished with value: 13412.294181887348 and parameters: {'n_estimators': 74, 'max_depth': 25, 'min_samples_split': 3}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:50:20,007]\u001b[0m Trial 34 finished with value: 13331.451949921382 and parameters: {'n_estimators': 64, 'max_depth': 27, 'min_samples_split': 2}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:50:22,777]\u001b[0m Trial 35 finished with value: 13327.018899771492 and parameters: {'n_estimators': 65, 'max_depth': 27, 'min_samples_split': 2}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:50:25,491]\u001b[0m Trial 36 finished with value: 13461.328595547999 and parameters: {'n_estimators': 67, 'max_depth': 27, 'min_samples_split': 4}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:50:28,650]\u001b[0m Trial 37 finished with value: 13402.695599594434 and parameters: {'n_estimators': 76, 'max_depth': 29, 'min_samples_split': 3}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:50:31,026]\u001b[0m Trial 38 finished with value: 13766.98958384117 and parameters: {'n_estimators': 62, 'max_depth': 27, 'min_samples_split': 7}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:50:34,511]\u001b[0m Trial 39 finished with value: 13358.05506703355 and parameters: {'n_estimators': 79, 'max_depth': 30, 'min_samples_split': 2}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:50:36,994]\u001b[0m Trial 40 finished with value: 13916.72233469579 and parameters: {'n_estimators': 69, 'max_depth': 24, 'min_samples_split': 9}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:50:41,103]\u001b[0m Trial 41 finished with value: 13331.099993299576 and parameters: {'n_estimators': 92, 'max_depth': 26, 'min_samples_split': 2}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:50:47,214]\u001b[0m Trial 42 finished with value: 13359.137024258333 and parameters: {'n_estimators': 123, 'max_depth': 29, 'min_samples_split': 2}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:50:49,657]\u001b[0m Trial 43 finished with value: 13425.62774183571 and parameters: {'n_estimators': 58, 'max_depth': 27, 'min_samples_split': 3}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:50:54,062]\u001b[0m Trial 44 finished with value: 13339.925715912992 and parameters: {'n_estimators': 104, 'max_depth': 26, 'min_samples_split': 2}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:50:57,765]\u001b[0m Trial 45 finished with value: 13487.22807229446 and parameters: {'n_estimators': 90, 'max_depth': 24, 'min_samples_split': 4}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:51:01,217]\u001b[0m Trial 46 finished with value: 13397.857487229721 and parameters: {'n_estimators': 81, 'max_depth': 29, 'min_samples_split': 3}. Best is trial 26 with value: 13326.978117091432.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:51:08,079]\u001b[0m Trial 47 finished with value: 13283.993701625182 and parameters: {'n_estimators': 156, 'max_depth': 25, 'min_samples_split': 2}. Best is trial 47 with value: 13283.993701625182.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:51:14,097]\u001b[0m Trial 48 finished with value: 13448.93475916206 and parameters: {'n_estimators': 151, 'max_depth': 25, 'min_samples_split': 4}. Best is trial 47 with value: 13283.993701625182.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:51:20,793]\u001b[0m Trial 49 finished with value: 13285.03188014614 and parameters: {'n_estimators': 156, 'max_depth': 28, 'min_samples_split': 2}. Best is trial 47 with value: 13283.993701625182.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:51:27,211]\u001b[0m Trial 50 finished with value: 13728.302396484545 and parameters: {'n_estimators': 171, 'max_depth': 30, 'min_samples_split': 7}. Best is trial 47 with value: 13283.993701625182.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:51:33,681]\u001b[0m Trial 51 finished with value: 13276.910751708998 and parameters: {'n_estimators': 153, 'max_depth': 28, 'min_samples_split': 2}. Best is trial 51 with value: 13276.910751708998.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:51:40,415]\u001b[0m Trial 52 finished with value: 13285.86141176207 and parameters: {'n_estimators': 157, 'max_depth': 28, 'min_samples_split': 2}. Best is trial 51 with value: 13276.910751708998.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:51:47,034]\u001b[0m Trial 53 finished with value: 13314.883807071374 and parameters: {'n_estimators': 157, 'max_depth': 29, 'min_samples_split': 2}. Best is trial 51 with value: 13276.910751708998.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:51:53,479]\u001b[0m Trial 54 finished with value: 13380.551166800811 and parameters: {'n_estimators': 156, 'max_depth': 29, 'min_samples_split': 3}. Best is trial 51 with value: 13276.910751708998.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:51:59,634]\u001b[0m Trial 55 finished with value: 13287.166464758939 and parameters: {'n_estimators': 143, 'max_depth': 28, 'min_samples_split': 2}. Best is trial 51 with value: 13276.910751708998.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:52:05,702]\u001b[0m Trial 56 finished with value: 13371.728796860372 and parameters: {'n_estimators': 146, 'max_depth': 28, 'min_samples_split': 3}. Best is trial 51 with value: 13276.910751708998.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:52:11,603]\u001b[0m Trial 57 finished with value: 13970.934772875393 and parameters: {'n_estimators': 164, 'max_depth': 30, 'min_samples_split': 10}. Best is trial 51 with value: 13276.910751708998.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:52:20,086]\u001b[0m Trial 58 finished with value: 13284.08513797446 and parameters: {'n_estimators': 179, 'max_depth': 28, 'min_samples_split': 2}. Best is trial 51 with value: 13276.910751708998.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:52:25,179]\u001b[0m Trial 59 finished with value: 14703.121005374769 and parameters: {'n_estimators': 185, 'max_depth': 11, 'min_samples_split': 3}. Best is trial 51 with value: 13276.910751708998.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:52:32,585]\u001b[0m Trial 60 finished with value: 13285.749118937925 and parameters: {'n_estimators': 171, 'max_depth': 28, 'min_samples_split': 2}. Best is trial 51 with value: 13276.910751708998.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:52:39,938]\u001b[0m Trial 61 finished with value: 13286.574606787748 and parameters: {'n_estimators': 172, 'max_depth': 28, 'min_samples_split': 2}. Best is trial 51 with value: 13276.910751708998.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:52:49,698]\u001b[0m Trial 62 finished with value: 13286.229214688672 and parameters: {'n_estimators': 173, 'max_depth': 28, 'min_samples_split': 2}. Best is trial 51 with value: 13276.910751708998.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:53:00,165]\u001b[0m Trial 63 finished with value: 13289.279013650399 and parameters: {'n_estimators': 193, 'max_depth': 30, 'min_samples_split': 2}. Best is trial 51 with value: 13276.910751708998.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:53:07,622]\u001b[0m Trial 64 finished with value: 13372.348390093208 and parameters: {'n_estimators': 180, 'max_depth': 29, 'min_samples_split': 3}. Best is trial 51 with value: 13276.910751708998.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:53:15,019]\u001b[0m Trial 65 finished with value: 13283.779276254132 and parameters: {'n_estimators': 170, 'max_depth': 28, 'min_samples_split': 2}. Best is trial 51 with value: 13276.910751708998.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:53:20,420]\u001b[0m Trial 66 finished with value: 13702.561274688831 and parameters: {'n_estimators': 159, 'max_depth': 15, 'min_samples_split': 3}. Best is trial 51 with value: 13276.910751708998.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:53:28,263]\u001b[0m Trial 67 finished with value: 13275.172780672356 and parameters: {'n_estimators': 181, 'max_depth': 25, 'min_samples_split': 2}. Best is trial 67 with value: 13275.172780672356.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:53:35,370]\u001b[0m Trial 68 finished with value: 13352.063705022438 and parameters: {'n_estimators': 178, 'max_depth': 19, 'min_samples_split': 2}. Best is trial 67 with value: 13275.172780672356.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:53:42,330]\u001b[0m Trial 69 finished with value: 13812.842103075911 and parameters: {'n_estimators': 197, 'max_depth': 22, 'min_samples_split': 8}. Best is trial 67 with value: 13275.172780672356.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:53:49,124]\u001b[0m Trial 70 finished with value: 13376.797524000363 and parameters: {'n_estimators': 166, 'max_depth': 25, 'min_samples_split': 3}. Best is trial 67 with value: 13275.172780672356.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:53:56,883]\u001b[0m Trial 71 finished with value: 13277.923594876134 and parameters: {'n_estimators': 183, 'max_depth': 27, 'min_samples_split': 2}. Best is trial 67 with value: 13275.172780672356.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:54:05,344]\u001b[0m Trial 72 finished with value: 13280.728081723952 and parameters: {'n_estimators': 190, 'max_depth': 27, 'min_samples_split': 2}. Best is trial 67 with value: 13275.172780672356.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:54:13,878]\u001b[0m Trial 73 finished with value: 13275.051100141742 and parameters: {'n_estimators': 187, 'max_depth': 25, 'min_samples_split': 2}. Best is trial 73 with value: 13275.051100141742.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:54:22,020]\u001b[0m Trial 74 finished with value: 13286.611634904402 and parameters: {'n_estimators': 184, 'max_depth': 23, 'min_samples_split': 2}. Best is trial 73 with value: 13275.051100141742.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:54:30,219]\u001b[0m Trial 75 finished with value: 13273.812119955666 and parameters: {'n_estimators': 192, 'max_depth': 25, 'min_samples_split': 2}. Best is trial 75 with value: 13273.812119955666.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:54:38,100]\u001b[0m Trial 76 finished with value: 13347.37604844108 and parameters: {'n_estimators': 192, 'max_depth': 24, 'min_samples_split': 3}. Best is trial 75 with value: 13273.812119955666.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:54:45,087]\u001b[0m Trial 77 finished with value: 13649.500586567738 and parameters: {'n_estimators': 186, 'max_depth': 26, 'min_samples_split': 6}. Best is trial 75 with value: 13273.812119955666.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:54:53,637]\u001b[0m Trial 78 finished with value: 13269.572428086225 and parameters: {'n_estimators': 199, 'max_depth': 25, 'min_samples_split': 2}. Best is trial 78 with value: 13269.572428086225.\u001b[0m\n",
      "\u001b[32m[I 2026-04-14 22:55:01,732]\u001b[0m Trial 79 finished with value: 13275.152624580176 and parameters: {'n_estimators': 191, 'max_depth': 24, 'min_samples_split': 2}. Best is trial 78 with value: 13269.572428086225.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Optimization completed with updated search spaces.\n",
      "Grid Search: best CV MAE=13268.9343, duration=181.76s, params={'max_depth': 25, 'min_samples_split': 2, 'n_estimators': 200}\n",
      "Random Search: best CV MAE=13280.8876, duration=270.14s, params={'n_estimators': 176, 'min_samples_split': 2, 'max_depth': 26}\n",
      "Bayesian Optimization: best CV MAE=13269.5724, duration=414.02s, params={'n_estimators': 199, 'max_depth': 25, 'min_samples_split': 2}\n"
     ]
    }
   ],
   "source": [
    "rf = RandomForestRegressor(random_state=42)\n",
    "\n",
    "grid_param_grid = {\n",
    "    \"n_estimators\": [50, 100, 150, 200],\n",
    "    \"max_depth\": [10, 15, 20, 25, 30],\n",
    "    \"min_samples_split\": [2, 5, 8]\n",
    "}\n",
    "\n",
    "random_param_distributions = {\n",
    "    \"n_estimators\": np.arange(50, 201),\n",
    "    \"max_depth\": np.arange(10, 31),\n",
    "    \"min_samples_split\": np.arange(2, 11)\n",
    "}\n",
    "\n",
    "RANDOM_SEARCH_ITERATIONS = 80\n",
    "OPTUNA_TRIALS = 80\n",
    "\n",
    "# TODO: Initialize trackio project/experiment here\n",
    "\n",
    "trackio.init(\n",
    "    project=\"cs203-assignment4\",\n",
    "    name=\"rf-optimization-comparison\",\n",
    "    config={\n",
    "        \"cv_folds\": 5,\n",
    "        \"scoring\": \"neg_mean_absolute_error\",\n",
    "        \"random_seed\": SEED,\n",
    "        \"grid_space\": grid_param_grid,\n",
    "        \"random_search_iterations\": RANDOM_SEARCH_ITERATIONS,\n",
    "        \"optuna_trials\": OPTUNA_TRIALS\n",
    "    },\n",
    "    embed=False\n",
    ")\n",
    "\n",
    "# TODO: 1. Grid Search Implementation\n",
    "# Use trackio to log the method name, time taken, number of iterations, and best cross-validation score\n",
    "grid_start = time.time()\n",
    "grid_search = GridSearchCV(\n",
    "    estimator=rf,\n",
    "    param_grid=grid_param_grid,\n",
    "    scoring=\"neg_mean_absolute_error\",\n",
    "    cv=5,\n",
    "    n_jobs=-1,\n",
    "    verbose=0,\n",
    "    return_train_score=False\n",
    ")\n",
    "grid_search.fit(X_train, y_train)\n",
    "grid_duration = time.time() - grid_start\n",
    "\n",
    "grid_trial_mae = -grid_search.cv_results_[\"mean_test_score\"]\n",
    "grid_best_curve = np.minimum.accumulate(grid_trial_mae)\n",
    "for idx, best_mae in enumerate(grid_best_curve, start=1):\n",
    "    trackio.log({\"grid_best_cv_mae_so_far\": float(best_mae)}, step=idx)\n",
    "\n",
    "grid_best_mae = float(-grid_search.best_score_)\n",
    "trackio.log({\n",
    "    \"grid_total_iterations\": int(len(grid_trial_mae)),\n",
    "    \"grid_duration_seconds\": float(grid_duration),\n",
    "    \"grid_best_cv_mae\": grid_best_mae,\n",
    "    \"grid_best_n_estimators\": int(grid_search.best_params_[\"n_estimators\"]),\n",
    "    \"grid_best_max_depth\": int(grid_search.best_params_[\"max_depth\"]),\n",
    "    \"grid_best_min_samples_split\": int(grid_search.best_params_[\"min_samples_split\"])\n",
    "})\n",
    "\n",
    "# TODO: 2. Random Search Implementation\n",
    "# Use trackio to log the method name, time taken, number of iterations, and best cross-validation score\n",
    "\n",
    "random_start = time.time()\n",
    "random_search = RandomizedSearchCV(\n",
    "    estimator=rf,\n",
    "    param_distributions=random_param_distributions,\n",
    "    n_iter=RANDOM_SEARCH_ITERATIONS,\n",
    "    scoring=\"neg_mean_absolute_error\",\n",
    "    cv=5,\n",
    "    random_state=SEED,\n",
    "    n_jobs=-1,\n",
    "    verbose=0,\n",
    "    return_train_score=False\n",
    ")\n",
    "random_search.fit(X_train, y_train)\n",
    "random_duration = time.time() - random_start\n",
    "\n",
    "random_trial_mae = -random_search.cv_results_[\"mean_test_score\"]\n",
    "random_best_curve = np.minimum.accumulate(random_trial_mae)\n",
    "for idx, best_mae in enumerate(random_best_curve, start=1):\n",
    "    trackio.log({\"random_best_cv_mae_so_far\": float(best_mae)}, step=1000 + idx)\n",
    "\n",
    "random_best_mae = float(-random_search.best_score_)\n",
    "trackio.log({\n",
    "    \"random_total_iterations\": int(len(random_trial_mae)),\n",
    "    \"random_duration_seconds\": float(random_duration),\n",
    "    \"random_best_cv_mae\": random_best_mae,\n",
    "    \"random_best_n_estimators\": int(random_search.best_params_[\"n_estimators\"]),\n",
    "    \"random_best_max_depth\": int(random_search.best_params_[\"max_depth\"]),\n",
    "    \"random_best_min_samples_split\": int(random_search.best_params_[\"min_samples_split\"])\n",
    "})\n",
    "\n",
    "# TODO: 3. Bayesian Optimization (Optuna) Implementation\n",
    "# Use trackio to log the method name, time taken, number of iterations, and best cross-validation score\n",
    "\n",
    "bayes_trial_mae = []\n",
    "\n",
    "def objective(trial):\n",
    "    params = {\n",
    "        \"n_estimators\": trial.suggest_int(\"n_estimators\", 50, 200),\n",
    "        \"max_depth\": trial.suggest_int(\"max_depth\", 10, 30),\n",
    "        \"min_samples_split\": trial.suggest_int(\"min_samples_split\", 2, 10),\n",
    "        \"random_state\": SEED,\n",
    "        \"n_jobs\": 1\n",
    "    }\n",
    "\n",
    "    model = RandomForestRegressor(**params)\n",
    "    scores = cross_val_score(\n",
    "        model,\n",
    "        X_train,\n",
    "        y_train,\n",
    "        cv=5,\n",
    "        scoring=\"neg_mean_absolute_error\",\n",
    "        n_jobs=-1\n",
    "    )\n",
    "    mae = float(-scores.mean())\n",
    "    bayes_trial_mae.append(mae)\n",
    "\n",
    "    trackio.log({\n",
    "        \"bayes_trial_cv_mae\": mae,\n",
    "        \"bayes_trial_n_estimators\": int(params[\"n_estimators\"]),\n",
    "        \"bayes_trial_max_depth\": int(params[\"max_depth\"]),\n",
    "        \"bayes_trial_min_samples_split\": int(params[\"min_samples_split\"])\n",
    "    }, step=2000 + trial.number + 1)\n",
    "\n",
    "    return mae\n",
    "\n",
    "bayes_start = time.time()\n",
    "study = optuna.create_study(direction=\"minimize\", study_name=\"rf_bayesian_optimization\")\n",
    "study.optimize(objective, n_trials=OPTUNA_TRIALS, show_progress_bar=False)\n",
    "bayes_duration = time.time() - bayes_start\n",
    "\n",
    "bayes_best_curve = np.minimum.accumulate(np.array(bayes_trial_mae))\n",
    "bayes_best_mae = float(study.best_value)\n",
    "trackio.log({\n",
    "    \"bayes_total_iterations\": int(len(bayes_trial_mae)),\n",
    "    \"bayes_duration_seconds\": float(bayes_duration),\n",
    "    \"bayes_best_cv_mae\": bayes_best_mae,\n",
    "    \"bayes_best_n_estimators\": int(study.best_params[\"n_estimators\"]),\n",
    "    \"bayes_best_max_depth\": int(study.best_params[\"max_depth\"]),\n",
    "    \"bayes_best_min_samples_split\": int(study.best_params[\"min_samples_split\"])\n",
    "})\n",
    "\n",
    "\n",
    "\n",
    "def _to_builtin_int_dict(params):\n",
    "    return {k: int(v) for k, v in params.items()}\n",
    "\n",
    "search_results = {\n",
    "    \"Grid Search\": {\n",
    "        \"best_params\": _to_builtin_int_dict(grid_search.best_params_),\n",
    "        \"best_cv_mae\": grid_best_mae,\n",
    "        \"duration_seconds\": grid_duration,\n",
    "        \"best_curve\": grid_best_curve\n",
    "    },\n",
    "    \"Random Search\": {\n",
    "        \"best_params\": _to_builtin_int_dict(random_search.best_params_),\n",
    "        \"best_cv_mae\": random_best_mae,\n",
    "        \"duration_seconds\": random_duration,\n",
    "        \"best_curve\": random_best_curve\n",
    "    },\n",
    "    \"Bayesian Optimization\": {\n",
    "        \"best_params\": _to_builtin_int_dict(study.best_params),\n",
    "        \"best_cv_mae\": bayes_best_mae,\n",
    "        \"duration_seconds\": bayes_duration,\n",
    "        \"best_curve\": bayes_best_curve\n",
    "    }\n",
    "}\n",
    "\n",
    "print(\"Optimization completed with updated search spaces.\")\n",
    "for method_name, result in search_results.items():\n",
    "    print(\n",
    "        f\"{method_name}: best CV MAE={result['best_cv_mae']:.4f}, \"\n",
    "        f\"duration={result['duration_seconds']:.2f}s, params={result['best_params']}\"\n",
    "    )"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9394b000",
   "metadata": {},
   "source": [
    "## 3. Evaluation & Plots\n",
    "Plot the compute trials (iterations) vs. cross-validation error, and plot the hyperparameter space to visualize how the Bayesian method explored the space."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "4faf41cb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.plotly.v1+json": {
       "config": {
        "plotlyServerURL": "https://plot.ly"
       },
       "data": [
        {
         "type": "scatter",
         "xaxis": "x",
         "yaxis": "y"
        },
        {
         "colorbar": {
          "title": {
           "text": "Objective Value"
          }
         },
         "colorscale": [
          [
           0,
           "rgb(247,251,255)"
          ],
          [
           0.125,
           "rgb(222,235,247)"
          ],
          [
           0.25,
           "rgb(198,219,239)"
          ],
          [
           0.375,
           "rgb(158,202,225)"
          ],
          [
           0.5,
           "rgb(107,174,214)"
          ],
          [
           0.625,
           "rgb(66,146,198)"
          ],
          [
           0.75,
           "rgb(33,113,181)"
          ],
          [
           0.875,
           "rgb(8,81,156)"
          ],
          [
           1,
           "rgb(8,48,107)"
          ]
         ],
         "connectgaps": true,
         "contours": {
          "coloring": "heatmap"
         },
         "hoverinfo": "none",
         "line": {
          "smoothing": 1.3
         },
         "reversescale": true,
         "showscale": true,
         "type": "contour",
         "x": [
          9,
          10,
          11,
          12,
          14,
          15,
          16,
          18,
          19,
          20,
          21,
          22,
          23,
          24,
          25,
          26,
          27,
          28,
          29,
          30,
          31
         ],
         "xaxis": "x4",
         "y": [
          1.6,
          2,
          3,
          4,
          5,
          6,
          7,
          8,
          9,
          10,
          10.4
         ],
         "yaxis": "y4",
         "z": {
          "bdata": "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",
          "dtype": "f8",
          "shape": "11, 21"
         }
        },
        {
         "marker": {
          "color": "black",
          "line": {
           "color": "Gray",
           "width": 2
          }
         },
         "mode": "markers",
         "name": "Feasible Trial",
         "showlegend": false,
         "type": "scatter",
         "x": [
          20,
          27,
          22,
          26,
          10,
          29,
          30,
          14,
          25,
          12,
          18,
          30,
          26,
          28,
          23,
          23,
          16,
          23,
          20,
          24,
          28,
          22,
          21,
          18,
          18,
          25,
          27,
          28,
          28,
          26,
          21,
          26,
          26,
          25,
          27,
          27,
          27,
          29,
          27,
          30,
          24,
          26,
          29,
          27,
          26,
          24,
          29,
          25,
          25,
          28,
          30,
          28,
          28,
          29,
          29,
          28,
          28,
          30,
          28,
          11,
          28,
          28,
          28,
          30,
          29,
          28,
          15,
          25,
          19,
          22,
          25,
          27,
          27,
          25,
          23,
          25,
          24,
          26,
          25,
          24
         ],
         "xaxis": "x4",
         "y": [
          10,
          4,
          9,
          6,
          2,
          10,
          4,
          8,
          9,
          7,
          4,
          4,
          4,
          2,
          2,
          2,
          2,
          3,
          5,
          3,
          6,
          2,
          3,
          2,
          3,
          5,
          2,
          3,
          5,
          2,
          3,
          2,
          2,
          3,
          2,
          2,
          4,
          3,
          7,
          2,
          9,
          2,
          2,
          3,
          2,
          4,
          3,
          2,
          4,
          2,
          7,
          2,
          2,
          2,
          3,
          2,
          3,
          10,
          2,
          3,
          2,
          2,
          2,
          2,
          3,
          2,
          3,
          2,
          2,
          8,
          3,
          2,
          2,
          2,
          2,
          2,
          3,
          6,
          2,
          2
         ],
         "yaxis": "y4"
        },
        {
         "colorbar": {
          "title": {
           "text": "Objective Value"
          }
         },
         "colorscale": [
          [
           0,
           "rgb(247,251,255)"
          ],
          [
           0.125,
           "rgb(222,235,247)"
          ],
          [
           0.25,
           "rgb(198,219,239)"
          ],
          [
           0.375,
           "rgb(158,202,225)"
          ],
          [
           0.5,
           "rgb(107,174,214)"
          ],
          [
           0.625,
           "rgb(66,146,198)"
          ],
          [
           0.75,
           "rgb(33,113,181)"
          ],
          [
           0.875,
           "rgb(8,81,156)"
          ],
          [
           1,
           "rgb(8,48,107)"
          ]
         ],
         "connectgaps": true,
         "contours": {
          "coloring": "heatmap"
         },
         "hoverinfo": "none",
         "line": {
          "smoothing": 1.3
         },
         "reversescale": true,
         "showscale": false,
         "type": "contour",
         "x": [
          9,
          10,
          11,
          12,
          14,
          15,
          16,
          18,
          19,
          20,
          21,
          22,
          23,
          24,
          25,
          26,
          27,
          28,
          29,
          30,
          31
         ],
         "xaxis": "x7",
         "y": [
          43.6,
          51,
          53,
          54,
          58,
          61,
          62,
          64,
          65,
          66,
          67,
          68,
          69,
          71,
          73,
          74,
          76,
          78,
          79,
          81,
          83,
          84,
          86,
          89,
          90,
          92,
          93,
          94,
          96,
          100,
          104,
          106,
          114,
          123,
          134,
          137,
          143,
          146,
          151,
          152,
          153,
          156,
          157,
          159,
          163,
          164,
          166,
          167,
          170,
          171,
          172,
          173,
          178,
          179,
          180,
          181,
          183,
          184,
          185,
          186,
          187,
          189,
          190,
          191,
          192,
          193,
          197,
          199,
          206.4
         ],
         "yaxis": "y7",
         "z": {
          "bdata": "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",
          "dtype": "f8",
          "shape": "69, 21"
         }
        },
        {
         "marker": {
          "color": "black",
          "line": {
           "color": "Gray",
           "width": 2
          }
         },
         "mode": "markers",
         "name": "Feasible Trial",
         "showlegend": false,
         "type": "scatter",
         "x": [
          20,
          27,
          22,
          26,
          10,
          29,
          30,
          14,
          25,
          12,
          18,
          30,
          26,
          28,
          23,
          23,
          16,
          23,
          20,
          24,
          28,
          22,
          21,
          18,
          18,
          25,
          27,
          28,
          28,
          26,
          21,
          26,
          26,
          25,
          27,
          27,
          27,
          29,
          27,
          30,
          24,
          26,
          29,
          27,
          26,
          24,
          29,
          25,
          25,
          28,
          30,
          28,
          28,
          29,
          29,
          28,
          28,
          30,
          28,
          11,
          28,
          28,
          28,
          30,
          29,
          28,
          15,
          25,
          19,
          22,
          25,
          27,
          27,
          25,
          23,
          25,
          24,
          26,
          25,
          24
         ],
         "xaxis": "x7",
         "y": [
          163,
          68,
          167,
          73,
          189,
          199,
          114,
          114,
          152,
          179,
          53,
          86,
          84,
          89,
          54,
          51,
          100,
          134,
          96,
          71,
          137,
          51,
          58,
          66,
          83,
          100,
          61,
          78,
          62,
          94,
          114,
          93,
          106,
          74,
          64,
          65,
          67,
          76,
          62,
          79,
          69,
          92,
          123,
          58,
          104,
          90,
          81,
          156,
          151,
          156,
          171,
          153,
          157,
          157,
          156,
          143,
          146,
          164,
          179,
          185,
          171,
          172,
          173,
          193,
          180,
          170,
          159,
          181,
          178,
          197,
          166,
          183,
          190,
          187,
          184,
          192,
          192,
          186,
          199,
          191
         ],
         "yaxis": "y7"
        },
        {
         "colorbar": {
          "title": {
           "text": "Objective Value"
          }
         },
         "colorscale": [
          [
           0,
           "rgb(247,251,255)"
          ],
          [
           0.125,
           "rgb(222,235,247)"
          ],
          [
           0.25,
           "rgb(198,219,239)"
          ],
          [
           0.375,
           "rgb(158,202,225)"
          ],
          [
           0.5,
           "rgb(107,174,214)"
          ],
          [
           0.625,
           "rgb(66,146,198)"
          ],
          [
           0.75,
           "rgb(33,113,181)"
          ],
          [
           0.875,
           "rgb(8,81,156)"
          ],
          [
           1,
           "rgb(8,48,107)"
          ]
         ],
         "connectgaps": true,
         "contours": {
          "coloring": "heatmap"
         },
         "hoverinfo": "none",
         "line": {
          "smoothing": 1.3
         },
         "reversescale": true,
         "showscale": false,
         "type": "contour",
         "x": [
          1.6,
          2,
          3,
          4,
          5,
          6,
          7,
          8,
          9,
          10,
          10.4
         ],
         "xaxis": "x2",
         "y": [
          9,
          10,
          11,
          12,
          14,
          15,
          16,
          18,
          19,
          20,
          21,
          22,
          23,
          24,
          25,
          26,
          27,
          28,
          29,
          30,
          31
         ],
         "yaxis": "y2",
         "z": {
          "bdata": "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",
          "dtype": "f8",
          "shape": "21, 11"
         }
        },
        {
         "marker": {
          "color": "black",
          "line": {
           "color": "Gray",
           "width": 2
          }
         },
         "mode": "markers",
         "name": "Feasible Trial",
         "showlegend": false,
         "type": "scatter",
         "x": [
          10,
          4,
          9,
          6,
          2,
          10,
          4,
          8,
          9,
          7,
          4,
          4,
          4,
          2,
          2,
          2,
          2,
          3,
          5,
          3,
          6,
          2,
          3,
          2,
          3,
          5,
          2,
          3,
          5,
          2,
          3,
          2,
          2,
          3,
          2,
          2,
          4,
          3,
          7,
          2,
          9,
          2,
          2,
          3,
          2,
          4,
          3,
          2,
          4,
          2,
          7,
          2,
          2,
          2,
          3,
          2,
          3,
          10,
          2,
          3,
          2,
          2,
          2,
          2,
          3,
          2,
          3,
          2,
          2,
          8,
          3,
          2,
          2,
          2,
          2,
          2,
          3,
          6,
          2,
          2
         ],
         "xaxis": "x2",
         "y": [
          20,
          27,
          22,
          26,
          10,
          29,
          30,
          14,
          25,
          12,
          18,
          30,
          26,
          28,
          23,
          23,
          16,
          23,
          20,
          24,
          28,
          22,
          21,
          18,
          18,
          25,
          27,
          28,
          28,
          26,
          21,
          26,
          26,
          25,
          27,
          27,
          27,
          29,
          27,
          30,
          24,
          26,
          29,
          27,
          26,
          24,
          29,
          25,
          25,
          28,
          30,
          28,
          28,
          29,
          29,
          28,
          28,
          30,
          28,
          11,
          28,
          28,
          28,
          30,
          29,
          28,
          15,
          25,
          19,
          22,
          25,
          27,
          27,
          25,
          23,
          25,
          24,
          26,
          25,
          24
         ],
         "yaxis": "y2"
        },
        {
         "type": "scatter",
         "xaxis": "x5",
         "yaxis": "y5"
        },
        {
         "colorbar": {
          "title": {
           "text": "Objective Value"
          }
         },
         "colorscale": [
          [
           0,
           "rgb(247,251,255)"
          ],
          [
           0.125,
           "rgb(222,235,247)"
          ],
          [
           0.25,
           "rgb(198,219,239)"
          ],
          [
           0.375,
           "rgb(158,202,225)"
          ],
          [
           0.5,
           "rgb(107,174,214)"
          ],
          [
           0.625,
           "rgb(66,146,198)"
          ],
          [
           0.75,
           "rgb(33,113,181)"
          ],
          [
           0.875,
           "rgb(8,81,156)"
          ],
          [
           1,
           "rgb(8,48,107)"
          ]
         ],
         "connectgaps": true,
         "contours": {
          "coloring": "heatmap"
         },
         "hoverinfo": "none",
         "line": {
          "smoothing": 1.3
         },
         "reversescale": true,
         "showscale": false,
         "type": "contour",
         "x": [
          1.6,
          2,
          3,
          4,
          5,
          6,
          7,
          8,
          9,
          10,
          10.4
         ],
         "xaxis": "x8",
         "y": [
          43.6,
          51,
          53,
          54,
          58,
          61,
          62,
          64,
          65,
          66,
          67,
          68,
          69,
          71,
          73,
          74,
          76,
          78,
          79,
          81,
          83,
          84,
          86,
          89,
          90,
          92,
          93,
          94,
          96,
          100,
          104,
          106,
          114,
          123,
          134,
          137,
          143,
          146,
          151,
          152,
          153,
          156,
          157,
          159,
          163,
          164,
          166,
          167,
          170,
          171,
          172,
          173,
          178,
          179,
          180,
          181,
          183,
          184,
          185,
          186,
          187,
          189,
          190,
          191,
          192,
          193,
          197,
          199,
          206.4
         ],
         "yaxis": "y8",
         "z": {
          "bdata": "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",
          "dtype": "f8",
          "shape": "69, 11"
         }
        },
        {
         "marker": {
          "color": "black",
          "line": {
           "color": "Gray",
           "width": 2
          }
         },
         "mode": "markers",
         "name": "Feasible Trial",
         "showlegend": false,
         "type": "scatter",
         "x": [
          10,
          4,
          9,
          6,
          2,
          10,
          4,
          8,
          9,
          7,
          4,
          4,
          4,
          2,
          2,
          2,
          2,
          3,
          5,
          3,
          6,
          2,
          3,
          2,
          3,
          5,
          2,
          3,
          5,
          2,
          3,
          2,
          2,
          3,
          2,
          2,
          4,
          3,
          7,
          2,
          9,
          2,
          2,
          3,
          2,
          4,
          3,
          2,
          4,
          2,
          7,
          2,
          2,
          2,
          3,
          2,
          3,
          10,
          2,
          3,
          2,
          2,
          2,
          2,
          3,
          2,
          3,
          2,
          2,
          8,
          3,
          2,
          2,
          2,
          2,
          2,
          3,
          6,
          2,
          2
         ],
         "xaxis": "x8",
         "y": [
          163,
          68,
          167,
          73,
          189,
          199,
          114,
          114,
          152,
          179,
          53,
          86,
          84,
          89,
          54,
          51,
          100,
          134,
          96,
          71,
          137,
          51,
          58,
          66,
          83,
          100,
          61,
          78,
          62,
          94,
          114,
          93,
          106,
          74,
          64,
          65,
          67,
          76,
          62,
          79,
          69,
          92,
          123,
          58,
          104,
          90,
          81,
          156,
          151,
          156,
          171,
          153,
          157,
          157,
          156,
          143,
          146,
          164,
          179,
          185,
          171,
          172,
          173,
          193,
          180,
          170,
          159,
          181,
          178,
          197,
          166,
          183,
          190,
          187,
          184,
          192,
          192,
          186,
          199,
          191
         ],
         "yaxis": "y8"
        },
        {
         "colorbar": {
          "title": {
           "text": "Objective Value"
          }
         },
         "colorscale": [
          [
           0,
           "rgb(247,251,255)"
          ],
          [
           0.125,
           "rgb(222,235,247)"
          ],
          [
           0.25,
           "rgb(198,219,239)"
          ],
          [
           0.375,
           "rgb(158,202,225)"
          ],
          [
           0.5,
           "rgb(107,174,214)"
          ],
          [
           0.625,
           "rgb(66,146,198)"
          ],
          [
           0.75,
           "rgb(33,113,181)"
          ],
          [
           0.875,
           "rgb(8,81,156)"
          ],
          [
           1,
           "rgb(8,48,107)"
          ]
         ],
         "connectgaps": true,
         "contours": {
          "coloring": "heatmap"
         },
         "hoverinfo": "none",
         "line": {
          "smoothing": 1.3
         },
         "reversescale": true,
         "showscale": false,
         "type": "contour",
         "x": [
          43.6,
          51,
          53,
          54,
          58,
          61,
          62,
          64,
          65,
          66,
          67,
          68,
          69,
          71,
          73,
          74,
          76,
          78,
          79,
          81,
          83,
          84,
          86,
          89,
          90,
          92,
          93,
          94,
          96,
          100,
          104,
          106,
          114,
          123,
          134,
          137,
          143,
          146,
          151,
          152,
          153,
          156,
          157,
          159,
          163,
          164,
          166,
          167,
          170,
          171,
          172,
          173,
          178,
          179,
          180,
          181,
          183,
          184,
          185,
          186,
          187,
          189,
          190,
          191,
          192,
          193,
          197,
          199,
          206.4
         ],
         "xaxis": "x3",
         "y": [
          9,
          10,
          11,
          12,
          14,
          15,
          16,
          18,
          19,
          20,
          21,
          22,
          23,
          24,
          25,
          26,
          27,
          28,
          29,
          30,
          31
         ],
         "yaxis": "y3",
         "z": {
          "bdata": "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",
          "dtype": "f8",
          "shape": "21, 69"
         }
        },
        {
         "marker": {
          "color": "black",
          "line": {
           "color": "Gray",
           "width": 2
          }
         },
         "mode": "markers",
         "name": "Feasible Trial",
         "showlegend": false,
         "type": "scatter",
         "x": [
          163,
          68,
          167,
          73,
          189,
          199,
          114,
          114,
          152,
          179,
          53,
          86,
          84,
          89,
          54,
          51,
          100,
          134,
          96,
          71,
          137,
          51,
          58,
          66,
          83,
          100,
          61,
          78,
          62,
          94,
          114,
          93,
          106,
          74,
          64,
          65,
          67,
          76,
          62,
          79,
          69,
          92,
          123,
          58,
          104,
          90,
          81,
          156,
          151,
          156,
          171,
          153,
          157,
          157,
          156,
          143,
          146,
          164,
          179,
          185,
          171,
          172,
          173,
          193,
          180,
          170,
          159,
          181,
          178,
          197,
          166,
          183,
          190,
          187,
          184,
          192,
          192,
          186,
          199,
          191
         ],
         "xaxis": "x3",
         "y": [
          20,
          27,
          22,
          26,
          10,
          29,
          30,
          14,
          25,
          12,
          18,
          30,
          26,
          28,
          23,
          23,
          16,
          23,
          20,
          24,
          28,
          22,
          21,
          18,
          18,
          25,
          27,
          28,
          28,
          26,
          21,
          26,
          26,
          25,
          27,
          27,
          27,
          29,
          27,
          30,
          24,
          26,
          29,
          27,
          26,
          24,
          29,
          25,
          25,
          28,
          30,
          28,
          28,
          29,
          29,
          28,
          28,
          30,
          28,
          11,
          28,
          28,
          28,
          30,
          29,
          28,
          15,
          25,
          19,
          22,
          25,
          27,
          27,
          25,
          23,
          25,
          24,
          26,
          25,
          24
         ],
         "yaxis": "y3"
        },
        {
         "colorbar": {
          "title": {
           "text": "Objective Value"
          }
         },
         "colorscale": [
          [
           0,
           "rgb(247,251,255)"
          ],
          [
           0.125,
           "rgb(222,235,247)"
          ],
          [
           0.25,
           "rgb(198,219,239)"
          ],
          [
           0.375,
           "rgb(158,202,225)"
          ],
          [
           0.5,
           "rgb(107,174,214)"
          ],
          [
           0.625,
           "rgb(66,146,198)"
          ],
          [
           0.75,
           "rgb(33,113,181)"
          ],
          [
           0.875,
           "rgb(8,81,156)"
          ],
          [
           1,
           "rgb(8,48,107)"
          ]
         ],
         "connectgaps": true,
         "contours": {
          "coloring": "heatmap"
         },
         "hoverinfo": "none",
         "line": {
          "smoothing": 1.3
         },
         "reversescale": true,
         "showscale": false,
         "type": "contour",
         "x": [
          43.6,
          51,
          53,
          54,
          58,
          61,
          62,
          64,
          65,
          66,
          67,
          68,
          69,
          71,
          73,
          74,
          76,
          78,
          79,
          81,
          83,
          84,
          86,
          89,
          90,
          92,
          93,
          94,
          96,
          100,
          104,
          106,
          114,
          123,
          134,
          137,
          143,
          146,
          151,
          152,
          153,
          156,
          157,
          159,
          163,
          164,
          166,
          167,
          170,
          171,
          172,
          173,
          178,
          179,
          180,
          181,
          183,
          184,
          185,
          186,
          187,
          189,
          190,
          191,
          192,
          193,
          197,
          199,
          206.4
         ],
         "xaxis": "x6",
         "y": [
          1.6,
          2,
          3,
          4,
          5,
          6,
          7,
          8,
          9,
          10,
          10.4
         ],
         "yaxis": "y6",
         "z": {
          "bdata": "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",
          "dtype": "f8",
          "shape": "11, 69"
         }
        },
        {
         "marker": {
          "color": "black",
          "line": {
           "color": "Gray",
           "width": 2
          }
         },
         "mode": "markers",
         "name": "Feasible Trial",
         "showlegend": false,
         "type": "scatter",
         "x": [
          163,
          68,
          167,
          73,
          189,
          199,
          114,
          114,
          152,
          179,
          53,
          86,
          84,
          89,
          54,
          51,
          100,
          134,
          96,
          71,
          137,
          51,
          58,
          66,
          83,
          100,
          61,
          78,
          62,
          94,
          114,
          93,
          106,
          74,
          64,
          65,
          67,
          76,
          62,
          79,
          69,
          92,
          123,
          58,
          104,
          90,
          81,
          156,
          151,
          156,
          171,
          153,
          157,
          157,
          156,
          143,
          146,
          164,
          179,
          185,
          171,
          172,
          173,
          193,
          180,
          170,
          159,
          181,
          178,
          197,
          166,
          183,
          190,
          187,
          184,
          192,
          192,
          186,
          199,
          191
         ],
         "xaxis": "x6",
         "y": [
          10,
          4,
          9,
          6,
          2,
          10,
          4,
          8,
          9,
          7,
          4,
          4,
          4,
          2,
          2,
          2,
          2,
          3,
          5,
          3,
          6,
          2,
          3,
          2,
          3,
          5,
          2,
          3,
          5,
          2,
          3,
          2,
          2,
          3,
          2,
          2,
          4,
          3,
          7,
          2,
          9,
          2,
          2,
          3,
          2,
          4,
          3,
          2,
          4,
          2,
          7,
          2,
          2,
          2,
          3,
          2,
          3,
          10,
          2,
          3,
          2,
          2,
          2,
          2,
          3,
          2,
          3,
          2,
          2,
          8,
          3,
          2,
          2,
          2,
          2,
          2,
          3,
          6,
          2,
          2
         ],
         "yaxis": "y6"
        },
        {
         "type": "scatter",
         "xaxis": "x9",
         "yaxis": "y9"
        }
       ],
       "layout": {
        "font": {
         "size": 12
        },
        "height": 700,
        "paper_bgcolor": "white",
        "plot_bgcolor": "white",
        "template": {
         "data": {
          "bar": [
           {
            "error_x": {
             "color": "#2a3f5f"
            },
            "error_y": {
             "color": "#2a3f5f"
            },
            "marker": {
             "line": {
              "color": "#E5ECF6",
              "width": 0.5
             },
             "pattern": {
              "fillmode": "overlay",
              "size": 10,
              "solidity": 0.2
             }
            },
            "type": "bar"
           }
          ],
          "barpolar": [
           {
            "marker": {
             "line": {
              "color": "#E5ECF6",
              "width": 0.5
             },
             "pattern": {
              "fillmode": "overlay",
              "size": 10,
              "solidity": 0.2
             }
            },
            "type": "barpolar"
           }
          ],
          "carpet": [
           {
            "aaxis": {
             "endlinecolor": "#2a3f5f",
             "gridcolor": "white",
             "linecolor": "white",
             "minorgridcolor": "white",
             "startlinecolor": "#2a3f5f"
            },
            "baxis": {
             "endlinecolor": "#2a3f5f",
             "gridcolor": "white",
             "linecolor": "white",
             "minorgridcolor": "white",
             "startlinecolor": "#2a3f5f"
            },
            "type": "carpet"
           }
          ],
          "choropleth": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "type": "choropleth"
           }
          ],
          "contour": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "colorscale": [
             [
              0,
              "#0d0887"
             ],
             [
              0.1111111111111111,
              "#46039f"
             ],
             [
              0.2222222222222222,
              "#7201a8"
             ],
             [
              0.3333333333333333,
              "#9c179e"
             ],
             [
              0.4444444444444444,
              "#bd3786"
             ],
             [
              0.5555555555555556,
              "#d8576b"
             ],
             [
              0.6666666666666666,
              "#ed7953"
             ],
             [
              0.7777777777777778,
              "#fb9f3a"
             ],
             [
              0.8888888888888888,
              "#fdca26"
             ],
             [
              1,
              "#f0f921"
             ]
            ],
            "type": "contour"
           }
          ],
          "contourcarpet": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "type": "contourcarpet"
           }
          ],
          "heatmap": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "colorscale": [
             [
              0,
              "#0d0887"
             ],
             [
              0.1111111111111111,
              "#46039f"
             ],
             [
              0.2222222222222222,
              "#7201a8"
             ],
             [
              0.3333333333333333,
              "#9c179e"
             ],
             [
              0.4444444444444444,
              "#bd3786"
             ],
             [
              0.5555555555555556,
              "#d8576b"
             ],
             [
              0.6666666666666666,
              "#ed7953"
             ],
             [
              0.7777777777777778,
              "#fb9f3a"
             ],
             [
              0.8888888888888888,
              "#fdca26"
             ],
             [
              1,
              "#f0f921"
             ]
            ],
            "type": "heatmap"
           }
          ],
          "histogram": [
           {
            "marker": {
             "pattern": {
              "fillmode": "overlay",
              "size": 10,
              "solidity": 0.2
             }
            },
            "type": "histogram"
           }
          ],
          "histogram2d": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "colorscale": [
             [
              0,
              "#0d0887"
             ],
             [
              0.1111111111111111,
              "#46039f"
             ],
             [
              0.2222222222222222,
              "#7201a8"
             ],
             [
              0.3333333333333333,
              "#9c179e"
             ],
             [
              0.4444444444444444,
              "#bd3786"
             ],
             [
              0.5555555555555556,
              "#d8576b"
             ],
             [
              0.6666666666666666,
              "#ed7953"
             ],
             [
              0.7777777777777778,
              "#fb9f3a"
             ],
             [
              0.8888888888888888,
              "#fdca26"
             ],
             [
              1,
              "#f0f921"
             ]
            ],
            "type": "histogram2d"
           }
          ],
          "histogram2dcontour": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "colorscale": [
             [
              0,
              "#0d0887"
             ],
             [
              0.1111111111111111,
              "#46039f"
             ],
             [
              0.2222222222222222,
              "#7201a8"
             ],
             [
              0.3333333333333333,
              "#9c179e"
             ],
             [
              0.4444444444444444,
              "#bd3786"
             ],
             [
              0.5555555555555556,
              "#d8576b"
             ],
             [
              0.6666666666666666,
              "#ed7953"
             ],
             [
              0.7777777777777778,
              "#fb9f3a"
             ],
             [
              0.8888888888888888,
              "#fdca26"
             ],
             [
              1,
              "#f0f921"
             ]
            ],
            "type": "histogram2dcontour"
           }
          ],
          "mesh3d": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "type": "mesh3d"
           }
          ],
          "parcoords": [
           {
            "line": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "parcoords"
           }
          ],
          "pie": [
           {
            "automargin": true,
            "type": "pie"
           }
          ],
          "scatter": [
           {
            "fillpattern": {
             "fillmode": "overlay",
             "size": 10,
             "solidity": 0.2
            },
            "type": "scatter"
           }
          ],
          "scatter3d": [
           {
            "line": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scatter3d"
           }
          ],
          "scattercarpet": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scattercarpet"
           }
          ],
          "scattergeo": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scattergeo"
           }
          ],
          "scattergl": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scattergl"
           }
          ],
          "scattermap": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scattermap"
           }
          ],
          "scattermapbox": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scattermapbox"
           }
          ],
          "scatterpolar": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scatterpolar"
           }
          ],
          "scatterpolargl": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scatterpolargl"
           }
          ],
          "scatterternary": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scatterternary"
           }
          ],
          "surface": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "colorscale": [
             [
              0,
              "#0d0887"
             ],
             [
              0.1111111111111111,
              "#46039f"
             ],
             [
              0.2222222222222222,
              "#7201a8"
             ],
             [
              0.3333333333333333,
              "#9c179e"
             ],
             [
              0.4444444444444444,
              "#bd3786"
             ],
             [
              0.5555555555555556,
              "#d8576b"
             ],
             [
              0.6666666666666666,
              "#ed7953"
             ],
             [
              0.7777777777777778,
              "#fb9f3a"
             ],
             [
              0.8888888888888888,
              "#fdca26"
             ],
             [
              1,
              "#f0f921"
             ]
            ],
            "type": "surface"
           }
          ],
          "table": [
           {
            "cells": {
             "fill": {
              "color": "#EBF0F8"
             },
             "line": {
              "color": "white"
             }
            },
            "header": {
             "fill": {
              "color": "#C8D4E3"
             },
             "line": {
              "color": "white"
             }
            },
            "type": "table"
           }
          ]
         },
         "layout": {
          "annotationdefaults": {
           "arrowcolor": "#2a3f5f",
           "arrowhead": 0,
           "arrowwidth": 1
          },
          "autotypenumbers": "strict",
          "coloraxis": {
           "colorbar": {
            "outlinewidth": 0,
            "ticks": ""
           }
          },
          "colorscale": {
           "diverging": [
            [
             0,
             "#8e0152"
            ],
            [
             0.1,
             "#c51b7d"
            ],
            [
             0.2,
             "#de77ae"
            ],
            [
             0.3,
             "#f1b6da"
            ],
            [
             0.4,
             "#fde0ef"
            ],
            [
             0.5,
             "#f7f7f7"
            ],
            [
             0.6,
             "#e6f5d0"
            ],
            [
             0.7,
             "#b8e186"
            ],
            [
             0.8,
             "#7fbc41"
            ],
            [
             0.9,
             "#4d9221"
            ],
            [
             1,
             "#276419"
            ]
           ],
           "sequential": [
            [
             0,
             "#0d0887"
            ],
            [
             0.1111111111111111,
             "#46039f"
            ],
            [
             0.2222222222222222,
             "#7201a8"
            ],
            [
             0.3333333333333333,
             "#9c179e"
            ],
            [
             0.4444444444444444,
             "#bd3786"
            ],
            [
             0.5555555555555556,
             "#d8576b"
            ],
            [
             0.6666666666666666,
             "#ed7953"
            ],
            [
             0.7777777777777778,
             "#fb9f3a"
            ],
            [
             0.8888888888888888,
             "#fdca26"
            ],
            [
             1,
             "#f0f921"
            ]
           ],
           "sequentialminus": [
            [
             0,
             "#0d0887"
            ],
            [
             0.1111111111111111,
             "#46039f"
            ],
            [
             0.2222222222222222,
             "#7201a8"
            ],
            [
             0.3333333333333333,
             "#9c179e"
            ],
            [
             0.4444444444444444,
             "#bd3786"
            ],
            [
             0.5555555555555556,
             "#d8576b"
            ],
            [
             0.6666666666666666,
             "#ed7953"
            ],
            [
             0.7777777777777778,
             "#fb9f3a"
            ],
            [
             0.8888888888888888,
             "#fdca26"
            ],
            [
             1,
             "#f0f921"
            ]
           ]
          },
          "colorway": [
           "#636efa",
           "#EF553B",
           "#00cc96",
           "#ab63fa",
           "#FFA15A",
           "#19d3f3",
           "#FF6692",
           "#B6E880",
           "#FF97FF",
           "#FECB52"
          ],
          "font": {
           "color": "#2a3f5f"
          },
          "geo": {
           "bgcolor": "white",
           "lakecolor": "white",
           "landcolor": "#E5ECF6",
           "showlakes": true,
           "showland": true,
           "subunitcolor": "white"
          },
          "hoverlabel": {
           "align": "left"
          },
          "hovermode": "closest",
          "mapbox": {
           "style": "light"
          },
          "paper_bgcolor": "white",
          "plot_bgcolor": "#E5ECF6",
          "polar": {
           "angularaxis": {
            "gridcolor": "white",
            "linecolor": "white",
            "ticks": ""
           },
           "bgcolor": "#E5ECF6",
           "radialaxis": {
            "gridcolor": "white",
            "linecolor": "white",
            "ticks": ""
           }
          },
          "scene": {
           "xaxis": {
            "backgroundcolor": "#E5ECF6",
            "gridcolor": "white",
            "gridwidth": 2,
            "linecolor": "white",
            "showbackground": true,
            "ticks": "",
            "zerolinecolor": "white"
           },
           "yaxis": {
            "backgroundcolor": "#E5ECF6",
            "gridcolor": "white",
            "gridwidth": 2,
            "linecolor": "white",
            "showbackground": true,
            "ticks": "",
            "zerolinecolor": "white"
           },
           "zaxis": {
            "backgroundcolor": "#E5ECF6",
            "gridcolor": "white",
            "gridwidth": 2,
            "linecolor": "white",
            "showbackground": true,
            "ticks": "",
            "zerolinecolor": "white"
           }
          },
          "shapedefaults": {
           "line": {
            "color": "#2a3f5f"
           }
          },
          "ternary": {
           "aaxis": {
            "gridcolor": "white",
            "linecolor": "white",
            "ticks": ""
           },
           "baxis": {
            "gridcolor": "white",
            "linecolor": "white",
            "ticks": ""
           },
           "bgcolor": "#E5ECF6",
           "caxis": {
            "gridcolor": "white",
            "linecolor": "white",
            "ticks": ""
           }
          },
          "title": {
           "x": 0.05
          },
          "xaxis": {
           "automargin": true,
           "gridcolor": "white",
           "linecolor": "white",
           "ticks": "",
           "title": {
            "standoff": 15
           },
           "zerolinecolor": "white",
           "zerolinewidth": 2
          },
          "yaxis": {
           "automargin": true,
           "gridcolor": "white",
           "linecolor": "white",
           "ticks": "",
           "title": {
            "standoff": 15
           },
           "zerolinecolor": "white",
           "zerolinewidth": 2
          }
         }
        },
        "title": {
         "text": "Optuna Hyperparameter Space Exploration"
        },
        "width": 1200,
        "xaxis": {
         "anchor": "y",
         "domain": [
          0,
          0.2888888888888889
         ],
         "matches": "x7",
         "range": [
          9,
          31
         ],
         "showticklabels": false
        },
        "xaxis2": {
         "anchor": "y2",
         "domain": [
          0.35555555555555557,
          0.6444444444444445
         ],
         "matches": "x8",
         "range": [
          1.6,
          10.4
         ],
         "showticklabels": false
        },
        "xaxis3": {
         "anchor": "y3",
         "domain": [
          0.7111111111111111,
          1
         ],
         "matches": "x9",
         "range": [
          43.6,
          206.4
         ],
         "showticklabels": false
        },
        "xaxis4": {
         "anchor": "y4",
         "domain": [
          0,
          0.2888888888888889
         ],
         "matches": "x7",
         "range": [
          9,
          31
         ],
         "showticklabels": false
        },
        "xaxis5": {
         "anchor": "y5",
         "domain": [
          0.35555555555555557,
          0.6444444444444445
         ],
         "matches": "x8",
         "range": [
          1.6,
          10.4
         ],
         "showticklabels": false
        },
        "xaxis6": {
         "anchor": "y6",
         "domain": [
          0.7111111111111111,
          1
         ],
         "matches": "x9",
         "range": [
          43.6,
          206.4
         ],
         "showticklabels": false
        },
        "xaxis7": {
         "anchor": "y7",
         "domain": [
          0,
          0.2888888888888889
         ],
         "range": [
          9,
          31
         ],
         "title": {
          "text": "max_depth"
         }
        },
        "xaxis8": {
         "anchor": "y8",
         "domain": [
          0.35555555555555557,
          0.6444444444444445
         ],
         "range": [
          1.6,
          10.4
         ],
         "title": {
          "text": "min_samples_split"
         }
        },
        "xaxis9": {
         "anchor": "y9",
         "domain": [
          0.7111111111111111,
          1
         ],
         "range": [
          43.6,
          206.4
         ],
         "title": {
          "text": "n_estimators"
         }
        },
        "yaxis": {
         "anchor": "x",
         "domain": [
          0.7333333333333333,
          1
         ],
         "range": [
          9,
          31
         ],
         "title": {
          "text": "max_depth"
         }
        },
        "yaxis2": {
         "anchor": "x2",
         "domain": [
          0.7333333333333333,
          1
         ],
         "matches": "y",
         "range": [
          9,
          31
         ],
         "showticklabels": false
        },
        "yaxis3": {
         "anchor": "x3",
         "domain": [
          0.7333333333333333,
          1
         ],
         "matches": "y",
         "range": [
          9,
          31
         ],
         "showticklabels": false
        },
        "yaxis4": {
         "anchor": "x4",
         "domain": [
          0.36666666666666664,
          0.6333333333333333
         ],
         "range": [
          1.6,
          10.4
         ],
         "title": {
          "text": "min_samples_split"
         }
        },
        "yaxis5": {
         "anchor": "x5",
         "domain": [
          0.36666666666666664,
          0.6333333333333333
         ],
         "matches": "y4",
         "range": [
          1.6,
          10.4
         ],
         "showticklabels": false
        },
        "yaxis6": {
         "anchor": "x6",
         "domain": [
          0.36666666666666664,
          0.6333333333333333
         ],
         "matches": "y4",
         "range": [
          1.6,
          10.4
         ],
         "showticklabels": false
        },
        "yaxis7": {
         "anchor": "x7",
         "domain": [
          0,
          0.26666666666666666
         ],
         "range": [
          43.6,
          206.4
         ],
         "title": {
          "text": "n_estimators"
         }
        },
        "yaxis8": {
         "anchor": "x8",
         "domain": [
          0,
          0.26666666666666666
         ],
         "matches": "y7",
         "range": [
          43.6,
          206.4
         ],
         "showticklabels": false
        },
        "yaxis9": {
         "anchor": "x9",
         "domain": [
          0,
          0.26666666666666666
         ],
         "matches": "y7",
         "range": [
          43.6,
          206.4
         ],
         "showticklabels": false
        }
       }
      }
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# TODO: Generate and save trials_vs_error.png\n",
    "# X-axis: Number of iterations\n",
    "# Y-axis: Best CV error found so far\n",
    "# Overlay Grid, Random, and Bayesian methods on the same plot.\n",
    "\n",
    "plt.figure(figsize=(10, 6))\n",
    "plt.plot(np.arange(1, len(grid_best_curve) + 1), grid_best_curve, label=\"Grid Search\", linewidth=2)\n",
    "plt.plot(np.arange(1, len(random_best_curve) + 1), random_best_curve, label=\"Random Search\", linewidth=2)\n",
    "plt.plot(np.arange(1, len(bayes_best_curve) + 1), bayes_best_curve, label=\"Bayesian Optimization\", linewidth=2)\n",
    "plt.xlabel(\"Number of iterations/trials\")\n",
    "plt.ylabel(\"Best mean CV error (MAE) found so far\")\n",
    "plt.title(\"Trials vs Error: Grid vs Random vs Bayesian\")\n",
    "plt.grid(alpha=0.3)\n",
    "plt.legend()\n",
    "plt.tight_layout()\n",
    "plt.savefig(PLOTS_DIR / \"trials_vs_error.png\", dpi=300)\n",
    "plt.show()\n",
    "\n",
    "# TODO: Generate and save optuna_hyperparameter_space.png\n",
    "\n",
    "fig = ov.plot_contour(study, params=[\"n_estimators\", \"max_depth\", \"min_samples_split\"])\n",
    "\n",
    "fig.update_layout(\n",
    "    title=\"Optuna Hyperparameter Space Exploration\",\n",
    "    width=1200,\n",
    "    height=700,\n",
    "    paper_bgcolor=\"white\",\n",
    "    plot_bgcolor=\"white\",\n",
    "    font=dict(size=12)\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "16845ec1",
   "metadata": {},
   "source": [
    "## 4. Final Testing & Model Saving\n",
    "Report the best hyperparameters found, train your overall best model on the entire `train.csv`, evaluate on `test.csv`, and save the model file."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "01fbd667",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best hyperparameters by method:\n",
      "Grid Search: {'max_depth': 25, 'min_samples_split': 2, 'n_estimators': 200} | CV MAE=13268.9343\n",
      "Random Search: {'n_estimators': 176, 'min_samples_split': 2, 'max_depth': 26} | CV MAE=13280.8876\n",
      "Bayesian Optimization: {'n_estimators': 199, 'max_depth': 25, 'min_samples_split': 2} | CV MAE=13269.5724\n",
      "\n",
      "Selected overall best method: Grid Search\n",
      "Selected hyperparameters: {'max_depth': 25, 'min_samples_split': 2, 'n_estimators': 200}\n",
      "Final Test MAE: 12465.3490\n",
      "* Run finished. Uploading logs to Trackio (please wait...)\n",
      "Saved model artifacts:\n",
      "- models/best_rf_model.pkl\n",
      "- models/label_encoders.pkl\n",
      "- models/feature_columns.pkl\n",
      "- models/feature_metadata.pkl\n",
      "- models/model_metadata.pkl\n",
      "- models/inference_bundle.pkl\n"
     ]
    }
   ],
   "source": [
    "# TODO: Print the best hyperparameters found by all 3 methods\n",
    "print(\"Best hyperparameters by method:\")\n",
    "for method_name, result in search_results.items():\n",
    "    print(f\"{method_name}: {result['best_params']} | CV MAE={result['best_cv_mae']:.4f}\")\n",
    "\n",
    "best_method_name, best_method_result = min(\n",
    "    search_results.items(),\n",
    "    key=lambda item: item[1][\"best_cv_mae\"]\n",
    ")\n",
    "best_params = best_method_result[\"best_params\"]\n",
    "\n",
    "print()\n",
    "print(f\"Selected overall best method: {best_method_name}\")\n",
    "print(f\"Selected hyperparameters: {best_params}\")\n",
    "\n",
    "# TODO: Train the best model found on the full X_train\n",
    "\n",
    "best_model = RandomForestRegressor(\n",
    "    **best_params,\n",
    "    random_state=SEED,\n",
    "    n_jobs=-1\n",
    ")\n",
    "best_model.fit(X_train, y_train)\n",
    "\n",
    "# TODO: Evaluate the model on X_test (Report MAE)\n",
    "test_predictions = best_model.predict(X_test)\n",
    "test_mae = mean_absolute_error(y_test, test_predictions)\n",
    "print(f\"Final Test MAE: {test_mae:.4f}\")\n",
    "\n",
    "# TODO: Save best_model.pkl and any necessary encoders to the models/ folder\n",
    "model_metadata = {\n",
    "    \"target_column\": TARGET_COL,\n",
    "    \"categorical_columns\": categorical_cols,\n",
    "    \"feature_columns\": feature_cols,\n",
    "    \"best_method\": best_method_name,\n",
    "    \"best_params\": best_params,\n",
    "    \"best_cv_mae\": float(best_method_result[\"best_cv_mae\"]),\n",
    "    \"test_mae\": float(test_mae),\n",
    "    \"unknown_category_token\": UNKNOWN_CATEGORY_TOKEN,\n",
    "    \"all_results\": {\n",
    "        method_name: {\n",
    "            \"best_params\": result[\"best_params\"],\n",
    "            \"best_cv_mae\": float(result[\"best_cv_mae\"]),\n",
    "            \"duration_seconds\": float(result[\"duration_seconds\"])\n",
    "        }\n",
    "        for method_name, result in search_results.items()\n",
    "    }\n",
    "}\n",
    "\n",
    "with open(MODELS_DIR / \"model_metadata.pkl\", \"wb\") as f:\n",
    "    pickle.dump(model_metadata, f)\n",
    "\n",
    "inference_bundle = {\n",
    "    \"model\": best_model,\n",
    "    \"label_encoders\": label_encoders,\n",
    "    \"feature_columns\": feature_cols,\n",
    "    \"feature_metadata\": feature_metadata,\n",
    "    \"model_metadata\": model_metadata\n",
    "}\n",
    "with open(MODELS_DIR / \"inference_bundle.pkl\", \"wb\") as f:\n",
    "    pickle.dump(inference_bundle, f)\n",
    "\n",
    "trackio.log({\n",
    "    \"final_test_mae\": float(test_mae),\n",
    "    \"final_best_method\": 0 if best_method_name == \"Grid Search\" else (1 if best_method_name == \"Random Search\" else 2)\n",
    "})\n",
    "trackio.finish()\n",
    "\n",
    "print(\"Saved model artifacts:\")\n",
    "print(\"- models/best_rf_model.pkl\")\n",
    "print(\"- models/label_encoders.pkl\")\n",
    "print(\"- models/feature_columns.pkl\")\n",
    "print(\"- models/feature_metadata.pkl\")\n",
    "print(\"- models/model_metadata.pkl\")\n",
    "print(\"- models/inference_bundle.pkl\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "stt-ai",
   "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": "3.12.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}