{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Flagging Performance Monitoring\n",
    "\n",
    "## Initial setup\n",
    "This first section just ensures that the connection to DWH works correctly."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# This script connects to a Data Warehouse (DWH) using PostgreSQL. \n",
    "# This should be common for all Notebooks, but you might need to adjust the path to the `dwh_utils` module.\n",
    "\n",
    "import sys\n",
    "import os\n",
    "sys.path.append(os.path.abspath(\"../utils\"))  # Adjust path if needed\n",
    "\n",
    "from dwh_utils import read_credentials, create_postgres_engine, query_to_dataframe, test_connection\n",
    "\n",
    "# --- Connect to DWH ---\n",
    "creds = read_credentials()\n",
    "dwh_pg_engine = create_postgres_engine(creds)\n",
    "\n",
    "# --- Test Query ---\n",
    "test_connection()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data Extraction\n",
    "In this section we extract the data from the Flagging Performance Analysis within DWH."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import numpy as np\n",
    "from datetime import date"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Query to extract data\n",
    "data_extraction_query = \"\"\"\n",
    "select *\n",
    "from intermediate.int_flagging_performance_analysis  \n",
    "\"\"\"\n",
    "\n",
    "# Retrieve Data from Query\n",
    "df = query_to_dataframe(engine=dwh_pg_engine, query=data_extraction_query)\n",
    "print(df.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_confusion_matrix_from_df(df, flagging_analysis_type):\n",
    "\n",
    "    # Subset - just retrieve one row depending on the flagging_analysis_type\n",
    "    row = df[df['flagging_analysis_type'] == flagging_analysis_type].iloc[0]\n",
    "\n",
    "    # Define custom x-axis labels and wording\n",
    "    if flagging_analysis_type == 'RISK_VS_CLAIM':\n",
    "        x_labels = ['With Submitted Claim', 'Without Submitted Claim']\n",
    "        outcome_label = \"submitted claim\"\n",
    "    elif flagging_analysis_type == 'RISK_VS_SUBMITTED_PAYOUT':\n",
    "        x_labels = ['With Submitted Payout', 'Without Submitted Payout']\n",
    "        outcome_label = \"submitted payout\"\n",
    "    else:\n",
    "        x_labels = ['Actual Positive', 'Actual Negative']  \n",
    "        outcome_label = \"outcome\"\n",
    "\n",
    "    # Confusion matrix structure\n",
    "    cm = np.array([\n",
    "        [row['count_true_positive'], row['count_false_positive']],\n",
    "        [row['count_false_negative'], row['count_true_negative']]\n",
    "    ])\n",
    "\n",
    "    # Create annotations for the confusion matrix\n",
    "    labels = [['True Positives', 'False Positives'], ['False Negatives', 'True Negatives']]\n",
    "    counts = [[f\"{v:,}\" for v in [row['count_true_positive'], row['count_false_positive']]],\n",
    "              [f\"{v:,}\" for v in [row['count_false_negative'], row['count_true_negative']]]]\n",
    "    percentages = [[f\"{round(100*v,2):,}\" for v in [row['true_positive_score'], row['false_positive_score']]],\n",
    "                   [f\"{round(100*v,2):,}\" for v in [row['false_negative_score'], row['true_negative_score']]]]\n",
    "    annot = [[f\"{labels[i][j]}\\n{counts[i][j]} ({percentages[i][j]}%)\" for j in range(2)] for i in range(2)]\n",
    "\n",
    "    # Scores formatted as percentages\n",
    "    recall = row['recall_score'] * 100\n",
    "    precision = row['precision_score'] * 100\n",
    "    f1 = row['f1_score'] * 100\n",
    "    f2 = row['f2_score'] * 100\n",
    "\n",
    "    # Set up figure and axes manually for precise control\n",
    "    fig = plt.figure(figsize=(9, 8))\n",
    "    grid = fig.add_gridspec(nrows=4, height_ratios=[2, 3, 15, 2])\n",
    "\n",
    "    \n",
    "    ax_main_title = fig.add_subplot(grid[0])\n",
    "    ax_main_title.axis('off')\n",
    "    ax_main_title.set_title(f\"Flagged as Risk vs. {outcome_label.title()}\", fontsize=14, weight='bold')\n",
    "    \n",
    "    # Business explanation text\n",
    "    ax_text = fig.add_subplot(grid[1])\n",
    "    ax_text.axis('off')\n",
    "    business_text = (\n",
    "        f\"Flagging performance analysis:\\n\\n\"\n",
    "        f\"- Of all the bookings we flagged as at Risk, {precision:.2f}% actually turned into a {outcome_label}.\\n\"\n",
    "        f\"- Of all the bookings that resulted in a {outcome_label}, we correctly flagged {recall:.2f}% of them.\\n\"\n",
    "        f\"- The pure balance between these two is summarized by a score of {f1:.2f}%.\\n\"\n",
    "        f\"- If we prioritise better probability of detection of a {outcome_label}, the balanced score is {f2:.2f}%.\\n\"\n",
    "    )\n",
    "    ax_text.text(0.0, 0.0, business_text, fontsize=10.5, ha='left', va='bottom', wrap=False, linespacing=1.5)\n",
    "\n",
    "    # Heatmap\n",
    "    ax_heatmap = fig.add_subplot(grid[2])\n",
    "    ax_heatmap.set_title(f\"Confusion Matrix – Risk vs. {outcome_label.title()}\", fontsize=12, weight='bold', ha='center', va='center', wrap=False)\n",
    "\n",
    "    cmap = sns.light_palette(\"#318450\", as_cmap=True)\n",
    "\n",
    "    sns.heatmap(cm, annot=annot, fmt='', cmap=cmap, cbar=False,\n",
    "                xticklabels=x_labels,\n",
    "                yticklabels=['Flagged as Risk', 'Flagged as No Risk'],\n",
    "                ax=ax_heatmap,\n",
    "                linewidths=1.0,\n",
    "                annot_kws={'fontsize': 10, 'linespacing': 1.2})\n",
    "    ax_heatmap.set_xlabel(\"Resolution Outcome (Actual)\", fontsize=11, labelpad=10)\n",
    "    ax_heatmap.set_ylabel(\"Booking Status (Prediction)\", fontsize=11, labelpad=10)\n",
    "    \n",
    "    # Make borders visible\n",
    "    for _, spine in ax_heatmap.spines.items():\n",
    "        spine.set_visible(True)\n",
    "\n",
    "    # Footer with metrics and date\n",
    "    ax_footer = fig.add_subplot(grid[3])\n",
    "    ax_footer.axis('off')\n",
    "    metrics_text = f\"Total Booking Count: {row['count_total']}   |   Recall: {recall:.2f}%   |   Precision: {precision:.2f}%   |   F1 Score: {f1:.2f}%   |   F2 Score: {f2:.2f}%\"\n",
    "    date_text = f\"Generated on {date.today().strftime('%B %d, %Y')}\"\n",
    "    ax_footer.text(0.5, 0.7, metrics_text, ha='center', fontsize=9)\n",
    "    ax_footer.text(0.5, 0.1, date_text, ha='center', fontsize=8, color='gray')\n",
    "\n",
    "    plt.tight_layout()\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Plot confusion matrix for claim scenario\n",
    "plot_confusion_matrix_from_df(df, 'RISK_VS_CLAIM')\n",
    "\n",
    "# Plot confusion matrix for submitted payout scenario\n",
    "plot_confusion_matrix_from_df(df, 'RISK_VS_SUBMITTED_PAYOUT')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "venv",
   "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}