import scipy.stats as s
import numpy as np

from util import select


def iqr(vect):
    "return inter-quartile range of a vector"
    q25 = s.scoreatpercentile(vect, 25)
    q75 = s.scoreatpercentile(vect, 75)
    return (q75 - q25, q25, q75)

def cutoff_max(vect, percentile=99):
    return s.scoreatpercentile(vect, percentile)

def iqr_cutoff(vect, extend):
    (spread, low, high) = iqr(vect)
    min_val = low  - extend * spread
    max_val = high + extend * spread
    return min_val, max_val

def iqr_is_not_outlier(table, col=1, extend=1.5):
    "create a filter function that flags outliers"
    (spread, low, high) = iqr(table[:,col])
    min_val = low  - extend * spread
    max_val = high + extend * spread
    return lambda row: min_val <= row[col] <= max_val

def iqr_remove_outliers(table, col=1, extend=1.5):
    """Return a copy that only includes rows that
    fall within the IQR-based window.
    """
    valid = iqr_is_not_outlier(table, col, extend)
    return select(valid, table)