MXD13Q1 monthly statistics data, long-term average, max, min and stdev

modis_monthlystats.py

# -*- coding: utf-8 -*-
"""
NAME
    modis_monthlystats.py
    MXD13Q1 monthly statistics data, long-term average, max, min and stdev
DESCRIPTION
    Input data for this script will use MXD13Q1 monthly data generate from modis_8day2monthly.py
    This script can do annual statistics calculation (AVERAGE, MAXIMUM, MINIMUM and STD)
REQUIREMENT
    ArcGIS must installed before using this script, as it required arcpy module.
EXAMPLES
    C:\\Program Files\\ArcGIS\\Pro\\bin\\Python\\envs\\arcgispro-py3\\python modis_monthlystats.py
NOTES
    This script is designed to work with MODIS naming convention
    If using other data, some adjustment are required: parsing filename and directory
CONTACT
    Benny Istanto
    Climate Geographer
    GOST/DECAT/DECDG, The World Bank
LICENSE
    This script is in the public domain, free from copyrights or restrictions.
VERSION
    $Id$
TODO
    xx
"""
import os
import arcpy

# To avoid overwriting outputs, change overwriteOutput option to False.
arcpy.env.overwriteOutput = True

# ISO3 Country Code
iso3 = "tur" # Syria: syr, Myanmar: mmr, Lebanon: lbn

# Define the range of years
start_year = 2003
end_year = 2022

# Change the data and output folder
monthly_data_folder = "X:\\Temp\\modis\\{}\\gee\\02_positive\\temp".format(iso3)
long_term_stats_folder = "X:\\Temp\\modis\\{}\\gee\\03_statistics\\temp".format(iso3)

# Define statistic names
# Statistics type.
    # MEAN — The mean (average) of the inputs will be calculated.
    # MAJORITY — The majority (value that occurs most often) of the inputs will be determined.
    # MAXIMUM — The maximum (largest value) of the inputs will be determined.
    # MEDIAN — The median of the inputs will be calculated. Note: The input must in integers
    # MINIMUM — The minimum (smallest value) of the inputs will be determined.
    # MINORITY — The minority (value that occurs least often) of the inputs will be determined.
    # RANGE — The range (difference between largest and smallest value) of the inputs will be calculated.
    # STD — The standard deviation of the inputs will be calculated.
    # SUM — The sum (total of all values) of the inputs will be calculated.
    # VARIETY — The variety (number of unique values) of the inputs will be calculated.

# Define the statistic names for file naming and their corresponding arcpy names for processing
stat_names = {
    "max": "MAXIMUM",
    "min": "MINIMUM",
    "avg": "MEAN",
    "med": "MEDIAN",
    "std": "STD"
}

# Monthlys
monthlys = ["01", "02", "03", "04", "05", "06", "07", "08", "09", "10", "11", "12"]

for monthly in monthlys:
    monthly_files = []

    # Gather all the monthly mean files for each monthly across all years
    for year in range(start_year, end_year + 1):
        monthly_mean_name = f"{iso3}_phy_mxd13q1_evi_mean_{year}{monthly}.tif"
        monthly_mean_path = os.path.join(monthly_data_folder, monthly_mean_name)
        
        if arcpy.Exists(monthly_mean_path):
            monthly_files.append(monthly_mean_path)

    # Calculate the long-term statistics for the monthly
    for stat_short, stat_long in stat_names.items():
        out_raster_name = f"{iso3}_phy_mxd13q1_{monthly}_{start_year}_{end_year}_{stat_short}.tif"
        out_raster_path = os.path.join(long_term_stats_folder, out_raster_name)
        
        if not arcpy.Exists(out_raster_path) and monthly_files:
            arcpy.CheckOutExtension("spatial")
            outCellStatistics = arcpy.sa.CellStatistics(monthly_files, stat_long, "DATA")
            outCellStatistics.save(out_raster_path)
            arcpy.CheckInExtension("spatial")
            print(f"{out_raster_name} completed")
        elif monthly_files:
            print(f"{out_raster_name} exists")
        else:
            print(f"No monthly mean files found for {monthly}")