metrics.py 文件源码

 复制代码def __init__(self, metric, dimensions, ascending=True, name=None):
    """Initializes distribution estimator.

    Args:
      metric: Thing to calculate
      dimensions: Dimensions to distribute things over.
      ascending: list of bools to pass to pandas.sort_index that say to sort
        each dimension ascending or descending.
      name: A string for the column name of results.
    """

    def _calculate(data, weights):
      """Calculates cumulative distribution metric."""
      total = 1.0 * _weighted_sum(data[metric].values, weights)

      dimension_tuples = pd.lib.fast_zip([data[ii].values for ii in dimensions])
      factors, keys = pd.factorize(dimension_tuples, sort=True)
      results = np.zeros(len(keys))

      for ii in xrange(len(keys)):
        results[ii] = _weighted_sum(data[metric].values,
                                    weights * (factors == ii)) / total

      output = pd.DataFrame(results,
                            index=pd.MultiIndex.from_tuples(keys,
                                                            names=dimensions),
                            columns=[""])
      output = output.sort_index(ascending=ascending).cumsum()
      return output

    if name is None:
      name = "{} Cumulative Distribution".format(metric)

    super(CumulativeDistribution, self).__init__(name, _calculate, "dataframe")