{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Indicator Harmonizer"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The goal of this code is to provide a recommendation of indicators and detect cases where we migh need to create new"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 1 Load required packages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Functions loaded\n",
      "Functions loaded\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<module 'functions' from '/Users/alanfortunysicart/Documents/GitHub/IndicatorHarmonizer/functions.py'>"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import re\n",
    "import numpy as np\n",
    "import importlib\n",
    "import importlib\n",
    "from seatable_api import Base, context\n",
    "from pandas import json_normalize\n",
    "import importlib\n",
    "import functions as f\n",
    "importlib.reload(f)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 2. Load the required data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Load the request data including the generic indicator requests"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "table1 = pd.read_excel('/Users/alanfortunysicart/Downloads/Indicators_Indicators_Frameworks_Default View(1).xlsx')\n",
    "table2 = pd.read_excel('/Users/alanfortunysicart/Downloads/Indicators_Indicators_Default view(14).xlsx')\n",
    "# columns to use for embeddings on table 1\n",
    "\n",
    "columns_embeddings_col1 = ['Indicator Name']\n",
    "\n",
    "# columns to use for embeddings on table 2\n",
    "columns_embeddings_col2 = ['Indicator name (leonardo)']\n",
    "\n",
    "harmonization=True"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "if 'Indicator ID' in table1.columns:\n",
    "    table1['ID'] = table1['Indicator ID'].astype(str)\n",
    "else:\n",
    "    table1['ID'] = table1['ID'].astype(str)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Create a column concatenating the column's content to be used for the embeddings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "table1 = f.concatenate_columns(table1, columns=f.columns_embeddings_col1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Concatenate topic and indicator request name to help the indicator search"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "table2 = f.concatenate_columns(table2,columns=f.columns_embeddings_col2)\n",
    "\n",
    "if 'Indicator ID' in table2.columns:\n",
    "    table2['ID'] = table2['Indicator ID'].astype(str)\n",
    "else:\n",
    "    table2['ID'] = table2['ID'].astype(str)\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 3. Compute the similarity between leonardo. indicator and the requested names"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "result_final = f.process_similarity_results(table1, table2, harmonization=True,columns_embeddings_col1=f.columns_embeddings_col1,columns_embeddings_col2=f.columns_embeddings_col2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 4. Export the results and submit"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "result_final.to_csv('Indicator_Framework_Harmonizer_Definition_new_order.csv')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "seatableToKobo",
   "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": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}