run_classification.py

import constants as cst
import subprocess as sp
import re
import os


def run_random_forest1(base_dir_name, experiment_name):
    file_path = cst.BASE + base_dir_name + "/" + experiment_name + "/out.arff"
    if not os.path.exists(file_path):
        return None
    try:
        output = str(sp.check_output(["java", "-cp", cst.WEKA_BIN,
                                      "weka.classifiers.trees.RandomForest", '-P', '100', '-I',
                                      '100', '-num-slots', '1', '-K', '0', '-M', '1.0', '-V', '0.001', '-S', '1',
                                      "-t", file_path], timeout=30))
        match = re.search('Correctly Classified Instances\s+\d+\s+(\d+\.\d+)\s+%', output)
        if match:
            return experiment_name + "," + match.group(1)
        return experiment_name + ",?"
    except sp.TimeoutExpired:
        print("timeout exceeded", experiment_name)
        return experiment_name + ",?"


def classify_experiments(base_dir_name):
    results = []
    for experiment in os.listdir(cst.BASE + base_dir_name):
        if 'cubes' not in experiment:
            continue
        classification = run_random_forest1(base_dir_name, experiment)
        results.append(classification)
        results.append("\n")
    return results

if __name__ == '__main__':
    base_dir_name = "logs_test"
    res = classify_experiments(base_dir_name)
    with open(cst.BASE + base_dir_name + "/Classification.csv", "w") as f:
        f.writelines(res)