confluent/confluent_client/bin/stats

#!/usr/bin/env python
# vim: tabstop=4 shiftwidth=4 softtabstop=4

# Copyright 2019 Lenovo
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import argparse
import io
import numpy as np

import os
import sixel
import subprocess
import sys
import tempfile

class DumbWriter(sixel.SixelWriter):
    def restore_position(self, output):
        return


def plot(gui, output, plotdata):
    import matplotlib as mpl
    if not gui:
        mpl.use('Agg')
    import matplotlib.pyplot as plt
    n, bins, patches = plt.hist(plotdata, 20)
    plt.show()
    if not gui:
        if output:
            tdata = output
        else:
            tdata = io.BytesIO()
        plt.savefig(tdata)
    if not gui and not output:
        writer = DumbWriter()
        writer.draw(tdata)

histogram = False
aparser = argparse.ArgumentParser(description='Quick access to common statistics')
aparser.add_argument('-c', type=int, default=0, help='Column number to analyze')
aparser.add_argument('-s', default=False, action='store_true', help='Output histogram in sixel format')
aparser.add_argument('-g', default=False, action='store_true', help='Open histogram in separate graphical window')
aparser.add_argument('-o', default=None, help='Output histogram to the specified filename in PNG format')
args = aparser.parse_args(sys.argv[1:])
plotdata = []
data = sys.stdin.readline()
while data:
    datum = float(data.split()[args.c - 1])
    plotdata.append(datum)
    data = sys.stdin.readline()
if args.g or args.o or args.s:
    plot(args.g, args.o, plotdata)
print('Samples: {5} Min: {3} Median: {0} Mean: {1} Max: {4} StandardDeviation: {2}'.format(np.median(plotdata), np.mean(plotdata), np.std(plotdata), np.min(plotdata), np.max(plotdata), len(plotdata)))