{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e27f22a3-f39e-4007-a048-56ccc9af915e",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "bd40a9e0-faab-4999-9ad5-f74e7ae8b272",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('models/Credit_Reporting_model.pkl', 'rb') as f:\n",
    "   trained_model_cr= pickle.load(f)\n",
    "\n",
    "with open('models/Credit_Prepaid_Card_model.pkl', 'rb') as f:\n",
    "   trained_model_cp= pickle.load(f)\n",
    "\n",
    "with open('models/Checking_saving_model.pkl', 'rb') as f:\n",
    "    trained_model_cs=pickle.load(f)\n",
    "\n",
    "with open('models/loan_model.pkl', 'rb') as f:\n",
    "   trained_model_l= pickle.load(f)\n",
    "\n",
    "with open('models/Debt_model.pkl', 'rb') as f:\n",
    "   trained_model_d= pickle.load(f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "d1ad5fb9-36bf-4637-a137-17fca19224f6",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('models/Product_model.pkl', 'rb') as f:\n",
    "   product_model= pickle.load(f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "b946427b-b259-4eb2-a40b-ed7b7e476354",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.pipeline import Pipeline\n",
    "\n",
    "# Define the pipeline steps\n",
    "trained_product_model=product_model\n",
    "\n",
    "\n",
    "# Define a function to select the appropriate subproduct prediction model based on the predicted product\n",
    "def select_subproduct_model(predicted_product):\n",
    "    if predicted_product == 'Credit Reporting' :\n",
    "        return trained_model_cr\n",
    "    elif predicted_product == 'Credit/Prepaid Card':\n",
    "        return trained_model_cp\n",
    "    elif predicted_product == 'Checking or savings account':\n",
    "        return trained_model_cs\n",
    "    elif predicted_product == 'Loans / Mortgage':\n",
    "        return trained_model_l\n",
    "    elif predicted_product == 'Debt collection':\n",
    "        return trained_model_d\n",
    "    else:\n",
    "        raise ValueError(\"Invalid predicted product category\")\n",
    "\n",
    "def custom_predict(narrative):\n",
    "    # Predict product category\n",
    "    predicted_product = product_model.predict([narrative])[0]\n",
    "    \n",
    "    # Load the appropriate subproduct prediction model\n",
    "    subproduct_model = select_subproduct_model(predicted_product)\n",
    "    \n",
    "    # Predict subproduct category using the selected model\n",
    "    predicted_subproduct = subproduct_model.predict([narrative])\n",
    "    return predicted_product, predicted_subproduct"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "982521ea-364e-4521-889e-fe586c186701",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Predicted product: Credit/Prepaid Card\n",
      "Predicted subproduct: ['Checking account']\n"
     ]
    }
   ],
   "source": [
    "narrative = \"I have a problem with my credit card bill.\"\n",
    "#narrative = \"it is absurd that i have consistently made timely payments for this account and have never been overdue. i kindly request that you promptly update my account to reflect this accurately.\"\n",
    "predicted_product, predicted_subproduct = custom_predict(narrative)\n",
    "print(\"Predicted product:\", predicted_product)\n",
    "print(\"Predicted subproduct:\", predicted_subproduct)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "88529ef1-6ed2-41b9-a266-e550a50b831f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Product Prediction Accuracy: 0.9110859728506787\n",
      "Product Prediction Precision: 0.6634108079865927\n",
      "Subproduct Prediction Accuracy: 0.8377989657401422\n",
      "Subproduct Prediction Precision: 0.5058767033148038\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score, precision_score\n",
    "import pandas as pd\n",
    "\n",
    "# Load the test dataset\n",
    "test_data = pd.read_csv('../data_splits/test-data-split.csv')  \n",
    "\n",
    "# Initialize lists to store predicted and actual labels\n",
    "predicted_products = []\n",
    "predicted_subproducts = []\n",
    "actual_products = test_data['Product']\n",
    "actual_subproducts = test_data['Sub-product']\n",
    "\n",
    "# Iterate over each complaint narrative in the test set\n",
    "for narrative in test_data['Consumer complaint narrative']:\n",
    "    # Predict product and subproduct using the custom_predict function\n",
    "    predicted_product, predicted_subproduct = custom_predict(narrative)\n",
    "    \n",
    "    # Append predicted labels to lists\n",
    "    predicted_products.append(predicted_product)\n",
    "    predicted_subproducts.append(predicted_subproduct)\n",
    "\n",
    "# Calculate accuracy and precision\n",
    "accuracy_product = accuracy_score(actual_products, predicted_products)\n",
    "precision_product = precision_score(actual_products, predicted_products, average='macro',zero_division=1)\n",
    "accuracy_subproduct = accuracy_score(actual_subproducts, predicted_subproducts)\n",
    "precision_subproduct = precision_score(actual_subproducts, predicted_subproducts, average='macro',zero_division=1)\n",
    "\n",
    "# Print the results\n",
    "print(\"Product Prediction Accuracy:\", accuracy_product)\n",
    "print(\"Product Prediction Precision:\", precision_product)\n",
    "print(\"Subproduct Prediction Accuracy:\", accuracy_subproduct)\n",
    "print(\"Subproduct Prediction Precision:\", precision_subproduct)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ce982e0a",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.19"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}