import numpy

from util import load_binary_file
from stats import iqr_remove_outliers, iqr_cutoff


def get_data(fname, scale, extent, cutoff=None, maxval=1000.0,
             stdev=False, manual=None):
    data = load_binary_file(fname)

    if cutoff and len(data) > cutoff:
        data = data[:cutoff]

    if not scale is None:
        data *= scale

    data.sort()

    if stdev:
        # standard deviations filter
        std = numpy.std(data, ddof=1)
        avg = numpy.mean(data)
        lower = avg - std * extent
        upper = avg + std * extent
    elif extent:
        # IQR filter
        lower, upper = iqr_cutoff(data, extent)
    else:
        lower = 0
        upper = maxval

    min_idx, max_idx = numpy.searchsorted(data, [lower, upper])

    if manual:
        max_idx -= manual

    return [data, max_idx, min_idx, upper, lower]


def compact_file(*args, **kargs):
    data, max_idx, min_idx, iqr_max, iqr_min = get_data(*args, **kargs)

    samples = data[min_idx:max_idx]

    filtered = len(data) - len(samples)
    max = samples[-1]
    min = samples[0]
    med = numpy.median(samples)
    avg = numpy.mean(samples)

    std = numpy.std(samples, ddof=1)
    var = numpy.var(samples)

    return [len(data), filtered, max, avg, min, med, std, var, iqr_max, iqr_min]