feat(ch4): add jupyter notebook

.gitignore

@@ -6,11 +6,11 @@
 /storage/**/*.zip
 /storage/basemaps
 /download
-*.ipynb
+.ipynb*
 .DS_Store
 assets/legend-images/
 
 pipeline/logs
 pipeline/workdir
 pipeline/*/__pycache__
-service-account.json
+service-account.json

data/ch4-csv-netcdf4.ipynb

@@ -0,0 +1,119 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7d28e820-0ad0-43b1-ae6d-253460083110",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import glob\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from netCDF4 import Dataset\n",
+    "\n",
+    "# Configuration\n",
+    "csv_folder = '/data'\n",
+    "lat_column = 'Latitude'  # Adjust according to your CSV column name\n",
+    "lon_column = 'Longitude'  # Adjust according to your CSV column name\n",
+    "value_column = 'XCH4'  # Adjust according to your CSV column name\n",
+    "lat_min, lat_max = -90, 90\n",
+    "lon_min, lon_max = -180, 180\n",
+    "lat_resolution = 0.1\n",
+    "lon_resolution = 0.1\n",
+    "\n",
+    "# Define grid parameters\n",
+    "lat_bins = np.arange(lat_min, lat_max + lat_resolution, lat_resolution)\n",
+    "lon_bins = np.arange(lon_min, lon_max + lon_resolution, lon_resolution)\n",
+    "lat_grid = (lat_bins[:-1] + lat_bins[1:]) / 2\n",
+    "lon_grid = (lon_bins[:-1] + lon_bins[1:]) / 2\n",
+    "\n",
+    "# Initialize an empty grid with NaN values\n",
+    "def initialize_empty_grid():\n",
+    "    return np.full((len(lat_grid), len(lon_grid)), np.nan)\n",
+    "\n",
+    "# Function to process each CSV file and return data grid and timestamp\n",
+    "def process_csv_file(csv_file):\n",
+    "    print(csv_file)\n",
+    "    df = pd.read_csv(csv_file)\n",
+    "    df = df[[lat_column, lon_column, value_column]]\n",
+    "\n",
+    "    # Extract timestamp from filename\n",
+    "    timestamp = os.path.basename(csv_file).split('_')[4]  # Adjust based on filename pattern\n",
+    "\n",
+    "    lat_indices = np.digitize(df[lat_column], lat_bins) - 1\n",
+    "    lon_indices = np.digitize(df[lon_column], lon_bins) - 1\n",
+    "\n",
+    "    mask = (lat_indices >= 0) & (lat_indices < len(lat_grid)) & \\\n",
+    "           (lon_indices >= 0) & (lon_indices < len(lon_grid))\n",
+    "\n",
+    "    xch4_grid = initialize_empty_grid()\n",
+    "    xch4_grid[lat_indices[mask], lon_indices[mask]] = df[value_column][mask]\n",
+    "    return timestamp, xch4_grid\n",
+    "\n",
+    "# Process all CSV files and gather the data grids\n",
+    "for csv_file in glob.glob(os.path.join(csv_folder, '*.csv')):\n",
+    "    data_grids = {}\n",
+    "    timestamp, xch4_grid = process_csv_file(csv_file)\n",
+    "    output_netcdf = '/data/' + timestamp + '01.nc'\n",
+    "    data_grids[timestamp] = xch4_grid\n",
+    "\n",
+    "    # Create a new NetCDF file\n",
+    "    nc = Dataset(output_netcdf, 'w', format='NETCDF4')\n",
+    "    \n",
+    "    # Create dimensions\n",
+    "    nc.createDimension('latitude', len(lat_grid))\n",
+    "    nc.createDimension('longitude', len(lon_grid))\n",
+    "    \n",
+    "    # Create coordinate variables\n",
+    "    latitudes = nc.createVariable('latitude', 'f4', ('latitude',))\n",
+    "    longitudes = nc.createVariable('longitude', 'f4', ('longitude',))\n",
+    "    \n",
+    "    # Assign data to coordinate variables\n",
+    "    latitudes[:] = lat_grid\n",
+    "    longitudes[:] = lon_grid\n",
+    "    \n",
+    "    # Create a variable for each timestamp's XCH4 values\n",
+    "    for timestamp, grid in data_grids.items():\n",
+    "        var = nc.createVariable('xch4', 'f4', ('latitude', 'longitude',), fill_value=np.nan)\n",
+    "        var[:, :] = grid\n",
+    "        var.units = 'ppb'\n",
+    "    \n",
+    "    # Assign units and other attributes\n",
+    "    latitudes.units = 'degrees_north'\n",
+    "    longitudes.units = 'degrees_east'\n",
+    "    \n",
+    "    # Add global attributes\n",
+    "    nc.title = 'Global Gridded XCH4 Values'\n",
+    "    nc.source = 'Generated from multiple CSV files'\n",
+    "    nc.timestamps = ', '.join(data_grids.keys())\n",
+    "    \n",
+    "    # Close the NetCDF file\n",
+    "    nc.close()\n",
+    "    print(f\"NetCDF file created at {output_netcdf}\")"
+   ]
+  }
+ ],
+ "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": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}