Aggregates MODIS's tabular 8-days data into monthly

Aggregates_MODIS_8day_to_monthly.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "ea9ecc52",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Processing columns: 100%|████████████████████████████████████████████████| 3/3 [00:01<00:00,  2.34it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Completed\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from tqdm import tqdm\n",
    "\n",
    "def aggregate_monthly(data):\n",
    "    # Define the monthly date ranges\n",
    "    monthly_periods = {\n",
    "        \"Jan\": (\"01\", \"01\", \"01\", \"26\"),\n",
    "        \"Feb\": (\"02\", \"01\", \"02\", \"19\"),\n",
    "        \"Mar\": (\"02\", \"25\", \"03\", \"23\"),\n",
    "        \"Apr\": (\"03\", \"28\", \"04\", \"24\"),\n",
    "        \"May\": (\"04\", \"29\", \"05\", \"26\"),\n",
    "        \"Jun\": (\"05\", \"31\", \"06\", \"27\"),\n",
    "        \"Jul\": (\"07\", \"01\", \"07\", \"21\"),\n",
    "        \"Aug\": (\"07\", \"25\", \"08\", \"22\"),\n",
    "        \"Sep\": (\"08\", \"26\", \"09\", \"23\"),\n",
    "        \"Oct\": (\"09\", \"27\", \"10\", \"25\"),\n",
    "        \"Nov\": (\"10\", \"29\", \"11\", \"26\"),\n",
    "        \"Dec\": (\"12\", \"01\", \"12\", \"28\")\n",
    "    }\n",
    "    \n",
    "    # Create new dataframe for aggregated data\n",
    "    aggregated_data = pd.DataFrame()\n",
    "\n",
    "    # Copy the first two columns\n",
    "    aggregated_data[\"No\"] = data[\"No\"]\n",
    "    aggregated_data[\"ADM3_PCODE\"] = data[\"ADM3_PCODE\"]\n",
    "\n",
    "    new_columns = []  # Store the new columns here\n",
    "\n",
    "    # For each year\n",
    "    for year in range(2002, 2024):\n",
    "        # For each month\n",
    "        for month, days in monthly_periods.items():\n",
    "            # Create the start and end dates\n",
    "            start_date = f\"{year}{days[0]}{days[1]}\"\n",
    "            end_date = f\"{year}{days[-2]}{days[-1]}\"\n",
    "            \n",
    "            # Extract columns between start and end dates\n",
    "            relevant_columns = [col for col in data.columns if start_date <= col <= end_date]\n",
    "            \n",
    "            # Calculate the mean for each row and store in new_columns list\n",
    "            new_column = data[relevant_columns].mean(axis=1)\n",
    "            new_column.name = f\"{month}-{str(year)[2:]}\"\n",
    "            new_columns.append(new_column)\n",
    "\n",
    "    # Concatenate all the new columns to the aggregated_data DataFrame\n",
    "    aggregated_data = pd.concat([aggregated_data] + new_columns, axis=1)\n",
    "\n",
    "    # Return the aggregated data\n",
    "    return aggregated_data\n",
    "\n",
    "# Define iso3 and column_names\n",
    "iso3 = 'syr'\n",
    "column_names = ['MIN', 'MAX', 'MEAN']\n",
    "\n",
    "for column_name in tqdm(column_names, desc=\"Processing columns\"):\n",
    "    # Construct the input file path\n",
    "    input_file = f'/mnt/x/Temp/modis/{iso3}/gee/13_tables/zonal/csv/{iso3}_phy_evi_da_all_2002_2022_{column_name}_mxd13q1_adm3.csv'\n",
    "    \n",
    "    # Load the data\n",
    "    data = pd.read_csv(input_file, na_values='')\n",
    "    \n",
    "    # Aggregate the data\n",
    "    aggregated_data = aggregate_monthly(data)\n",
    "    \n",
    "    # Construct the output file path and save the aggregated data to a new CSV file\n",
    "    output_file = f'/mnt/x/Temp/modis/{iso3}/gee/13_tables/zonal/csv/{iso3}_phy_evi_da_all_2002_2022_{column_name}_mxd13q1_adm3_monthly.csv'\n",
    "    aggregated_data.to_csv(output_file, index=False)\n",
    "\n",
    "print('Completed')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3fe4fca2",
   "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": "3.10.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}