print_histo.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
print_histo.py

Visualize histogram as text.
"""

import sys
import numpy
import exceptions


class State(object):
    def __init__(self, limit=100000, bar_width=48):
        self.limit = limit
        self.bar_width = bar_width
        self.count = 0
        self.xs = []

    def parse(self, s):
        if self.limit <= self.count:
            raise RuntimeError("Number of data is reached to limit: %d" % self.limit)
        try:
            self.xs.append(float(s))
            self.count += 1
        except exceptions.ValueError:
            # Ignore input.
            pass

    def __str__(self):
        freqs, bins = numpy.histogram(self.xs)

        # Functions for string
        justify = lambda ss, func: [func(s)(max(map(len, ss))) for s in ss]
        rjust = lambda ss: justify(ss, lambda s: s.rjust)
        ljust = lambda ss: justify(ss, lambda s: s.ljust)

        # Labels
        bs = rjust(['%.3f' % b for b in bins])
        labels = ['[%s, %s)' % x for x in zip(bs[:-1], bs[1:])]
        labels[-1] = labels[-1][:-1] + ']'

        # Frequency
        f = lambda x: 0 if x == 0 else max(1, x * self.bar_width / max(freqs))
        bars = ljust(['*' * f(freq) for freq in freqs])

        # Assembles them.
        buf = ('%s: %s %6d' % x for x in zip(labels, bars, freqs))
        return '\n'.join(buf)


def process(function):
    paths = (sys.argv + [None])[1:max(2, len(sys.argv))]
    for path in paths:
        try:
            fp = sys.stdin if path is None else open(path)
            for line in fp:
                function(line.rstrip("\n"))
        except (KeyboardInterrupt, EOFError):
            pass
        except Exception:
            exc_type, exc = sys.exc_info()[:2]
            print('%s: %s: %s' % (sys.argv[0], exc_type.__name__, exc))
            return


if __name__ == '__main__':
    s = State()
    process(s.parse)
    print(s)