modelverse/performance/perf2tex.py

"""Converts performance data files (as produced by utils.py) to LaTeX charts."""

import argparse
import colorsys
import utils

# Generated LaTeX is based on the accepted answer to
# http://tex.stackexchange.com/questions/101320/grouped-bar-chart

# pylint: disable=I0011,W0141

COLOR_SCHEME_MIN_COLOR = (36, 255, 106)
COLOR_SCHEME_MAX_COLOR = (216, 33, 0)

LATEX_HEADER = r"""\documentclass[12pt,a4paper,onecolumn,openright]{report}
\usepackage[landscape]{geometry}
\usepackage{xcolor}
\usepackage{pgfplots}
\usepackage{tikz}
\usepgfplotslibrary{units}

% Define bar chart colors
%"""

LATEX_DOCUMENT_HEADER = r"""\begin{document}
\begin{tikzpicture}"""

LATEX_DOCUMENT_FOOTER = r"""\end{tikzpicture}
\end{document}"""

def encode_latex_string(value):
    """Encodes the given string as a LaTeX string."""
    # I guess this is good enough for now. This may need to be
    # revisited if we encounter more complicated names.
    return '{%s}' % value.replace('_', '\\_')

def assemble_latex_chart(optimization_levels, color_defs, test_names, data):
    """Assembles a LaTeX chart from the given components."""
    lines = []
    lines.append(LATEX_HEADER)
    for color_name, (red, green, blue) in color_defs:
        lines.append(r'\definecolor{%s}{HTML}{%02X%02X%02X}' % (color_name, red, green, blue))
    lines.append(LATEX_DOCUMENT_HEADER)
    lines.append(r"""
    \begin{axis}[
        width = 0.85*\textwidth,
        height = 8cm,
        major x tick style = transparent,
        ybar=2*\pgflinewidth,
        bar width=14pt,
        ymajorgrids = true,
        ylabel = {Run time},
        symbolic x coords={%s},
        xtick = data,
        scaled y ticks = false,
        enlarge x limits=0.25,
        ymin=0,
        y unit=s,
        legend cell align=left,
        legend style={
                at={(1,1.05)},
                anchor=south east,
                column sep=1ex
        }
    ]""" % ','.join(map(encode_latex_string, test_names)))
    for color_name, points in data:
        lines.append(r"""
        \addplot[style={%s,fill=%s,mark=none}]
            coordinates {%s};""" % (
                color_name, color_name,
                ' '.join([('(%s,%s)' % (encode_latex_string(name), measurement))
                          for name, measurement in points])))
    lines.append(r"""
        \legend{%s}""" % ','.join(map(encode_latex_string, optimization_levels)))
    lines.append(r"""
    \end{axis}""")
    lines.append(LATEX_DOCUMENT_FOOTER)
    return '\n'.join(lines)

def create_latex_chart(perf_data):
    """Creates a LaTeX chart for the given performance data."""
    sorted_opt_levels = sort_by_runtime(perf_data)
    color_scheme = generate_color_scheme(sorted_opt_levels)
    opt_levels = []
    color_defs = []
    test_names = []
    data = []
    for i, optimization_level in enumerate(sorted_opt_levels):
        measurements = perf_data[optimization_level]
        color = color_scheme[optimization_level]
        color_name = 'chartColor%d' % i
        opt_levels.append(optimization_level)
        color_defs.append((color_name, color))
        data.append((color_name, measurements.items()))
        for name, _ in measurements.items():
            if name not in test_names:
                test_names.append(name)

    return assemble_latex_chart(opt_levels, color_defs, test_names, data)

def get_mean_runtimes(perf_data):
    """Computes the mean run-time of every optimization level in the given
       performance data."""
    return {
        opt_level: utils.mean(perf_data[opt_level].values())
        for opt_level in perf_data.keys()
    }

def get_baseline_optimization_level(perf_data):
    """Gets a baseline optimization level from the given performance data.
       This baseline optimization level is guaranteed to be for every test case.
       If no baseline optimization level can be found, then None is returned."""
    # First find the name of all test cases.
    all_test_names = set()
    for optimization_level, measurements in perf_data.items():
        all_test_names.update(measurements.keys())

    # Filter optimization levels which are used for every test case.
    candidate_opt_levels = []
    for optimization_level, measurements in perf_data.items():
        if len(all_test_names) == len(measurements):
            candidate_opt_levels.append(optimization_level)

    if len(candidate_opt_levels) == 0:
        # Looks like there is no baseline optimization level.
        return None

    # Pick the optimization level with the lowest total run-time as the baseline.
    return min(candidate_opt_levels, key=lambda opt_level: sum(perf_data[opt_level].values()))

def get_relative_measurements(perf_data, baseline_optimization_level):
    """Computes a map of measurements that are relative to the given optimization level."""
    results = {}
    for optimization_level, measurements in perf_data.items():
        results[optimization_level] = {}
        for test_name, data_point in measurements.items():
            results[optimization_level][test_name] = (
                data_point / perf_data[baseline_optimization_level][test_name])

    return results

def perf_list_to_dict(perf_list):
    """Converts performance data from a list representation to a dictionary representation."""
    return {opt_level: dict(tests) for opt_level, tests in perf_list}

def perf_dict_to_list(perf_dict):
    """Converts performance data from a dictionary representation to a list representation."""
    return [(opt_level, tests.items()) for opt_level, tests in perf_dict.items()]

def interpolate(value_range, index, length):
    """Uses an index and a length to interpolate in the given range."""
    min_val, max_val = value_range
    if length == 1:
        return max_val
    else:
        return min_val + float(index) * (max_val - min_val) / float(length - 1)

def sort_by_runtime(perf_data):
    """Sorts the optimization levels by mean relative runtimes."""
    baseline_opt_level = get_baseline_optimization_level(perf_data)
    relative_perf = get_relative_measurements(perf_data, baseline_opt_level)
    # Sort the optimization levels by their mean runtimes.
    mean_runtimes = get_mean_runtimes(relative_perf)
    return list(sorted(mean_runtimes.keys(), key=lambda opt_level: mean_runtimes[opt_level]))

def generate_color_scheme(sorted_opt_levels):
    """Assigns a color to every optimization level in the given performance data."""
    # Assign colors to the optimization levels.
    color_scheme = {}
    min_hue, min_sat, min_val = colorsys.rgb_to_hsv(
        *[c / float(255) for c in COLOR_SCHEME_MIN_COLOR])
    max_hue, max_sat, max_val = colorsys.rgb_to_hsv(
        *[c / float(255) for c in COLOR_SCHEME_MAX_COLOR])
    for i, opt_level in enumerate(sorted_opt_levels):
        hue = interpolate((min_hue, max_hue), i, len(sorted_opt_levels))
        sat = interpolate((min_sat, max_sat), i, len(sorted_opt_levels))
        val = interpolate((min_val, max_val), i, len(sorted_opt_levels))
        color = [component * 255 for component in colorsys.hsv_to_rgb(hue, sat, val)]
        color_scheme[opt_level] = color

    return color_scheme

def main():
    arg_parser = argparse.ArgumentParser()
    arg_parser.add_argument('input', help='The performance data file.')
    arg_parser.add_argument(
        '-q', '--quantity', type=str,
        help="The quantity to build a bar chart for. Defaults to '%s'" % utils.TOTAL_TIME_QUANTITY,
        default=utils.TOTAL_TIME_QUANTITY)
    arg_parser.add_argument(
        '-O', '--opt', type=str, nargs='*',
        help="Filters on optimization levels.")
    arg_parser.add_argument(
        '-t', '--test', type=str, nargs='*',
        help="Filters on tests.")
    arg_parser.add_argument(
        '-r', '--relative', action='store_const', const=True,
        help="Produce bars that are relative to some baseline.", default=False)

    args = arg_parser.parse_args()

    perf_data = utils.parse_perf_data(args.input)[args.quantity]

    if args.opt:
        optimization_set = set(args.opt)
        perf_data = [
            (optimization_level, measurements)
            for optimization_level, measurements in perf_data
            if optimization_level in optimization_set]

    if args.test:
        test_set = set(args.test)
        new_perf_data = []
        for optimization_level, measurements in perf_data:
            new_measurements = []
            for test_name, data_point in measurements:
                if test_name in test_set:
                    new_measurements.append((test_name, data_point))

            if len(new_measurements) > 0:
                new_perf_data.append((optimization_level, new_measurements))
        perf_data = new_perf_data

    perf_data_dict = perf_list_to_dict(perf_data)

    if args.relative:
        baseline_opt_level = get_baseline_optimization_level(perf_data_dict)
        perf_data_dict = get_relative_measurements(perf_data_dict, baseline_opt_level)

    print(create_latex_chart(perf_data_dict))

if __name__ == '__main__':
    main()