scripts/system-tests/generate-plots.py

   1 # Copyright (C) 2017 - Francis Deslauriers <francis.deslauriers@efficios.com>
   2 #
   3 # This program is free software: you can redistribute it and/or modify
   4 # it under the terms of the GNU General Public License as published by
   5 # the Free Software Foundation, either version 3 of the License, or
   6 # (at your option) any later version.
   7 #
   8 # This program is distributed in the hope that it will be useful,
   9 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  10 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  11 # GNU General Public License for more details.
  12 #
  13 # You should have received a copy of the GNU General Public License
  14 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
  15
  16
  17 import os, sys
  18 import numpy as np
  19 import pandas as pd
  20
  21 #Set Matplotlib to use the PNG non interactive backend
  22 import matplotlib as mpl
  23 mpl.use('Agg')
  24
  25 import matplotlib.pyplot as plt
  26 from matplotlib.ticker import MaxNLocator
  27 from cycler import cycler
  28 from collections import OrderedDict
  29
  30 def rename_cols(df):
  31     new_cols = {'baseline_1thr_peritermean': 'basel_1thr',
  32             'baseline_2thr_peritermean': 'basel_2thr',
  33             'baseline_4thr_peritermean': 'basel_4thr',
  34             'baseline_8thr_peritermean': 'basel_8thr',
  35             'baseline_16thr_peritermean': 'basel_16thr',
  36             'lttng_1thr_peritermean': 'lttng_1thr',
  37             'lttng_2thr_peritermean': 'lttng_2thr',
  38             'lttng_4thr_peritermean': 'lttng_4thr',
  39             'lttng_8thr_peritermean': 'lttng_8thr',
  40             'lttng_16thr_peritermean': 'lttng_16thr',
  41             'baseline_1thr_periterstdev': 'basel_1thr_stdev',
  42             'baseline_2thr_periterstdev': 'basel_2thr_stdev',
  43             'baseline_4thr_periterstdev': 'basel_4thr_stdev',
  44             'baseline_8thr_periterstdev': 'basel_8thr_stdev',
  45             'baseline_16thr_periterstdev': 'basel_16thr_stdev',
  46             'lttng_1thr_periterstdev': 'lttng_1thr_stdev',
  47             'lttng_2thr_periterstdev': 'lttng_2thr_stdev',
  48             'lttng_4thr_periterstdev': 'lttng_4thr_stdev',
  49             'lttng_8thr_periterstdev': 'lttng_8thr_stdev',
  50             'lttng_16thr_periterstdev': 'lttng_16thr_stdev'
  51             }
  52     df.rename(columns=new_cols, inplace=True)
  53     return df
  54
  55 def convert_us_to_ns(df):
  56     cols = [col for col in df.columns if 'periter' in col]
  57     df[cols] = df[cols].apply(lambda x: x*1000)
  58     return df
  59
  60 def create_plot(df, graph_type):
  61     # We map all test configurations and their
  62     # respective color
  63     conf_to_color = OrderedDict([
  64         ('basel_1thr','lightcoral'),
  65         ('lttng_1thr','red'),
  66         ('basel_2thr','gray'),
  67         ('lttng_2thr','black'),
  68         ('basel_4thr','chartreuse'),
  69         ('lttng_4thr','forestgreen'),
  70         ('basel_8thr','deepskyblue'),
  71         ('lttng_8thr','mediumblue'),
  72         ('basel_16thr','orange'),
  73         ('lttng_16thr','saddlebrown')])
  74
  75     # We create a list for each of the subplots
  76     baseline = [x for x in conf_to_color.keys() if 'basel' in x]
  77     lttng = [x for x in conf_to_color.keys() if 'lttng' in x]
  78     one_thr = [x for x in conf_to_color.keys() if '_1thr' in x]
  79     two_thr = [x for x in conf_to_color.keys() if '_2thr' in x]
  80     four_thr = [x for x in conf_to_color.keys() if '_4thr' in x]
  81     eight_thr = [x for x in conf_to_color.keys() if '_8thr' in x]
  82     sixteen_thr = [x for x in conf_to_color.keys() if '_16thr' in x]
  83
  84     plots = [baseline, lttng, one_thr, two_thr, four_thr, eight_thr, sixteen_thr]
  85
  86     title='Meantime per event for {} testcase'.format(graph_type)
  87
  88     # Create a axe object for each sub-plots
  89     f, arrax = plt.subplots(len(plots), sharex=True, figsize=(16, 25))
  90     f.suptitle(title, fontsize=20)
  91
  92     for (ax, data_cols)  in zip(arrax, plots):
  93         curr_df = df[data_cols]
  94
  95         stdev_cols = ['{}_stdev'.format(x) for x in data_cols]
  96         # Extract the color for each configuration
  97         colors = [conf_to_color[x] for x in data_cols]
  98
  99         # set the color cycler for this plot
 100         ax.set_prop_cycle(cycler('color', colors))
 101
 102         # Plot each line and its errorbars
 103         for (data, stdev) in  zip(data_cols, stdev_cols):
 104             ax.errorbar(x=df.index.values, y=df[data].values, yerr=df[stdev].values, marker='o')
 105
 106         ax.set_ylim(0)
 107         ax.grid()
 108         ax.set_xlabel('Jenkins Build ID')
 109         ax.set_ylabel('Meantime per event [us]')
 110
 111         ax.xaxis.set_major_locator(MaxNLocator(integer=True, nbins=30))
 112
 113         ax.legend(prop={'family': 'monospace'},
 114                     labels=curr_df.columns.values, bbox_to_anchor=(1.2,1))
 115
 116     plt.subplots_adjust(top=0.95)
 117     plt.savefig('{}.png'.format(graph_type), bbox_inches='tight')
 118
 119 # Writes a file that contains commit id of all configurations shown in the
 120 # plots
 121 def create_metadata_file(res_dir):
 122     list_ = []
 123     for dirname, dirnames, res_files in os.walk('./'+res_dir):
 124         if len(dirnames) > 0:
 125             continue
 126         try:
 127             metadata = pd.read_csv(os.path.join(dirname, 'metadata.csv'))
 128         except Exception:
 129             print('Omitting run {} because metadata.csv is missing'.format(dirname))
 130             continue
 131         list_.append(metadata)
 132
 133     df = pd.concat(list_, sort=True)
 134     df.index=df.build_id
 135     df.sort_index(inplace=True)
 136     df.to_csv('metadata.csv', index=False)
 137
 138 #Iterates over a result directory and creates the plots for the different
 139 #testcases
 140 def create_plots(res_dir):
 141     df = pd.DataFrame()
 142     metadata_df = pd.DataFrame()
 143     list_ = []
 144     for dirname, dirnames, res_files in os.walk('./'+res_dir):
 145         if len(dirnames) > 0:
 146             continue
 147         try:
 148             metadata = pd.read_csv(os.path.join(dirname, 'metadata.csv'))
 149         except Exception:
 150             print('Omitting run {} because metadata.csv is missing'.format(dirname))
 151             continue
 152
 153         for res in res_files:
 154             if res in 'metadata.csv':
 155                 continue
 156             tmp = pd.read_csv(os.path.join(dirname, res))
 157             #Use the build id as the index for the dataframe for filtering
 158             tmp.index = metadata.build_id
 159             #Add the testcase name to the row for later filtering
 160             tmp['testcase'] = res.split('.')[0]
 161             list_.append(tmp)
 162
 163         df = pd.concat(list_, sort=True)
 164         df = convert_us_to_ns(df)
 165         df = rename_cols(df)
 166         df.sort_index(inplace=True)
 167
 168     #Go over the entire dataframe by testcase and create a plot for each type
 169     for testcase in df.testcase.unique():
 170         df_testcase  = df.loc[df['testcase'] == testcase]
 171         create_plot(df=df_testcase, graph_type=testcase)
 172
 173 def main():
 174     res_path = sys.argv[1]
 175     create_plots(os.path.join(res_path))
 176     create_metadata_file(os.path.join(res_path))
 177
 178 if __name__ == '__main__':
 179     main()