Good fossil specimen datasets about gbif-dataset-metrics

[peterdesmet]

For reference: script I used to get datasets with geological info:

import sys
import csv

def check_arguments():
    if len(sys.argv) != 3:
        print 'Missing arguments. Usage: python fossil_specimens.py <gbif_download_file.txt> <output_file.tab>'
        sys.exit(-1)
    return sys.argv[1:]

def get_columns(download_file,selected_columns):
    my_selection = []
    with open(download_file) as file:
        reader = csv.reader(file, delimiter='\t', quoting=csv.QUOTE_NONE)
        # QUOTE_NONE: to solve http://stackoverflow.com/questions/15063936/csv-error-field-larger-than-field-limit-131072
        for row in reader:
            my_selection.append([row[x-1] for x in selected_columns])
    return my_selection

def get_datasets_with_geological(my_data):
    # Expects a two-dimensional array with datasetKey at index 0
    datasets = {}
    number_of_columns = len(my_data[0][1:]) # Ignoring datasetKey at index 0
    datasets['datasetKey'] = my_data[0][1:] # Store headers

    for row in my_data[1:]: # Start after header line
        dataset_key = row[0]
        if dataset_key not in datasets: # New dataset
            datasets[dataset_key] = [0 for x in range(1,number_of_columns+1)]
        counter = 0
        for value in row[1:]: # Loop over other 5 columns
            if value is not '':
                datasets[dataset_key][counter] += 1 # Increase value
            counter += 1
    return datasets # A dictionary

def write_datasets_with_geological(my_datasets,output_file):
    with open(output_file, 'w+') as file:
        writer = csv.writer(file, delimiter=',', lineterminator='\n')
        for key in my_datasets:
            writer.writerow([key] + my_datasets[key])
    return True

def main ():
    gbif_download_file, output_file = check_arguments()
    columns = [197,83,130,85,132,86,133,84,131,82,129]
    reduced_download_file = get_columns(gbif_download_file,columns)
    geological_datasets = get_datasets_with_geological(reduced_download_file)
    write_datasets_with_geological(geological_datasets,output_file)

main()

[bartaelterman]

👍

[peterdesmet]

Won't invest time to implement this. Labelled wontfix.