Thesis » QuynhNguyen-MS

import numpy as np

def get_statistical_for_column(col):

    """Returns the min, max, avg, std

    """

    stats = [np.amin(col), np.amax(col), np.average(col), np.std(col)]

    return stats

def get_statistical_data(input_data, index_column_name, value_column_name):

    categories = np.unique(input_data[index_column_name])

    result_dict = dict()

    for cat in categories:

        values = input_data[input_data[index_column_name] == cat][value_column_name]

        stats = get_statistical_for_column(values)

        result_dict[cat] = stats

    return result_dict

def write_to_file(output_filepath, output_data, dtype={}):

    np.savetxt(output_filepath, output_data, fmt='%s', delimiter=',')

def read_out1(input_filepath):

    result = np.loadtxt(input_filepath,

        dtype={

            'names': ('filename', 'graphtype', 'numberofnodes', 'runindex', 'bc_time', 'hbc_time',

                'start_bc_clock', 'end_bc_clock', 'start_hbc_clock', 'end_hbc_clock'),

            'formats': ('a40', 'a2', 'i4', 'i4', 'f8', 'f8', 'f8', 'f8', 'f8', 'f8'),

        },

        delimiter=',',

    )

    return result

def format_output_data(bc_result, hbc_result):

    output_data = list()

    for key in bc_result.keys():

        tmp_list = []

        tmp_index = key.find('_')

        typo_code = key

        if tmp_index != -1:

            typo_code = key[:tmp_index]

        graph_type = typo_code[:2]

        num_of_nodes = typo_code[2:]

        bc_values = bc_result[key]

        hbc_values = hbc_result[key]

        tmp_list.append(key)

        tmp_list.append(typo_code)

        # print typo_code

        tmp_list.append(graph_type)

        tmp_list.append(num_of_nodes)

        tmp_list.append(bc_values[2])

        tmp_list.append(hbc_values[2])

        tmp_list.append(bc_values[3])

        tmp_list.append(hbc_values[3])

        output_data.append(tmp_list)

    return output_data

def read_out2(input_filepath):

    result = np.loadtxt(input_filepath,

        dtype={

            'names': ('filename', 'typotype', 'graphtype', 'numofnodes', 'avg_bc', 'avg_hbc', 'std_bc', 'std_hbc'),

            'formats': ('a40', 'a6', 'a2', 'i4', 'f8', 'f8', 'f8', 'f8'),

        },

        delimiter=',',

    )

    return result