eia_data_part.py 文件源码

def outlier_processing(intervals):
    """Outlier processing"""

    left = [x[0] for x in intervals]
    right = [x[1] for x in intervals]

    # Compute Q(0.25), Q(0.75) and IQR for left-ends
    lq25, lq75 = np.percentile(left, [25, 75])
    liqr = lq75 - lq25

    # Compute Q(0.25), Q(0.75) and IQR for right-ends
    rq25, rq75 = np.percentile(right, [25, 75])
    riqr = rq75 - rq25

    # Outlier processing for Left and Right bounds
    left_filtered = [x for x in intervals if (lq25 - 1.5 * liqr) <= x[0] <= (lq75 + 1.5 * liqr)]
    right_filtered = [x for x in left_filtered if (rq25 - 1.5 * riqr) <= x[1] <= (rq75 + 1.5 * riqr)]

    # Compute Q(0.25), Q(0.75) and IQR for interval length
    len_values = [x[1] - x[0] for x in right_filtered]
    lenq25, lenq75 = np.percentile(len_values, [25, 75])
    leniqr = lenq75 - lenq25

    # Outlier processing for interval length
    len_filtered = [x if (lenq25 - 1.5 * leniqr) <= x <= (lenq75 + 1.5 * leniqr) else None for x in len_values]
    selectors = [x is not None for x in len_filtered]
    filtered_intervals = list(itertools.compress(right_filtered, selectors))
    return filtered_intervals