Global IMERG daily to monthly

IMERG_daily2monthly.py

# -*- coding: utf-8 -*-
"""
NAME
    imerg_daily2monthly.py
    Global IMERG daily to monthly
DESCRIPTION
    Input data for this script will use IMERG daily data generated by imerg_nc2tif.py or other 
    IMERG-based daily products. Example: daily wetdays to monthly sum, daily cdd to monthly max
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 imerg_daily2monthly.py
NOTES
    This script is designed to work with global IMERG data (Final or Late Run)
    If using other data, some adjustment are required: parsing filename, directory, threshold
    All IMERG data and products are available at s3://wbgdecinternal-ntl/climate/
CONTACT
    Benny Istanto
    Climate Geographer
    GOST, The World Bank
LICENSE
    This script is in the public domain, free from copyrights or restrictions.
VERSION
    $Id$
TODO
    xx
"""
import os
import arcpy
from collections import defaultdict


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


# Change the data and output folder
input_folder = "X:\\Temp\\imerg\\products\\cwd\\cwd_1mm"
output_folder = "X:\\Temp\\imerg\\products\\cwd\\monthly_1mm"

# Create file collection based on MM information
groups = defaultdict(list)

for file_monthly in os.listdir(input_folder):
    if file_monthly.endswith(".tif") or file_monthly.endswith(".tiff"):
        # Parsing the filename to get YYYYMM information
        i_imerg = file_monthly.index('imerg_')
        # 6 is length of 'imerg_', and 6+6 is length of 'imerg_' and yyyymm
        groupkey = file_monthly[i_imerg + 6:i_imerg+6+6]
        fpath = os.path.join(input_folder, file_monthly)
        groups[groupkey].append(fpath)

for groupkey, files in groups.items():
    print(files)

    ext = ".tif"

    # Output filename
    newfilename_monthly_stat1 = 'wld_cli_cwd_1mm_monthly_max_imerg_{0}{1}'.format(groupkey, ext)
    print(newfilename_monthly_stat1)

    # 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.

    # To get another stats, you can duplicate 7 lines below and adjust the statistics type.
    # Don't forget to add additional output file name, you can copy from line 59.
    if arcpy.Exists(os.path.join(output_folder, newfilename_monthly_stat1)):
        print(newfilename_monthly_stat1 + " exists")
    else:
        arcpy.CheckOutExtension("spatial")
        outCellStatistics_stat1 = arcpy.sa.CellStatistics(files, "MAXIMUM", "DATA")
        outCellStatistics_stat1.save(os.path.join(output_folder, newfilename_monthly_stat1))
        arcpy.CheckInExtension("spatial")