Python FastRBTree.succ_item方法代码示例

# 需要导入模块: from bintrees import FastRBTree [as 别名]
# 或者: from bintrees.FastRBTree import succ_item [as 别名]

#.........这里部分代码省略.........

    def batch_update(self, values, w=1):
        """
        Update the t-digest with an iterable of values. This assumes all points have the 
        same weight.
        """
        for x in values:
            self.update(x, w)
        self.compress()
        return

    def compress(self):
        T = TDigest(self.delta, self.K)
        C = list(self.C.values())
        shuffle(C)
        for c_i in C:
            T.update(c_i.mean, c_i.count)
        self.C = T.C

    def percentile(self, q):
        """ 
        Computes the percentile of a specific value in [0,1], ie. computes F^{-1}(q) where F^{-1} denotes
        the inverse CDF of the distribution. 

        """
        if not (0 <= q <= 1):
            raise ValueError("q must be between 0 and 1, inclusive.")

        t = 0
        q *= self.n

        for i, key in enumerate(self.C.keys()):
            c_i = self.C[key]
            k = c_i.count
            if q < t + k:
                if i == 0:
                    return c_i.mean
                elif i == len(self) - 1:
                    return c_i.mean
                else:
                    delta = (self.C.succ_item(key)[1].mean - self.C.prev_item(key)[1].mean) / 2.
                return c_i.mean + ((q - t) / k - 0.5) * delta

            t += k
        return self.C.max_item()[1].mean

    def quantile(self, q):
        """ 
        Computes the quantile of a specific value, ie. computes F(q) where F denotes
        the CDF of the distribution. 

        """
        t = 0
        N = float(self.n)

        for i, key in enumerate(self.C.keys()):
            c_i = self.C[key]
            if i == len(self) - 1:
                delta = (c_i.mean - self.C.prev_item(key)[1].mean) / 2.
            else:
                delta = (self.C.succ_item(key)[1].mean - c_i.mean) / 2.
            z = max(-1, (q - c_i.mean) / delta)

            if z < 1:
                return t / N + c_i.count / N * (z + 1) / 2

            t += c_i.count
        return 1

    def trimmed_mean(self, q1, q2):
        """
        Computes the mean of the distribution between the two percentiles q1 and q2.
        This is a modified algorithm than the one presented in the original t-Digest paper. 

        """
        if not (q1 < q2):
            raise ValueError("q must be between 0 and 1, inclusive.")

        s = k = t = 0
        q1 *= self.n
        q2 *= self.n
        for i, key in enumerate(self.C.keys()):
            c_i = self.C[key]
            k_i = c_i.count
            if q1 < t + k_i:
                if i == 0:
                    delta = self.C.succ_item(key)[1].mean - c_i.mean
                elif i == len(self) - 1:
                    delta = c_i.mean - self.C.prev_item(key)[1].mean
                else:
                    delta = (self.C.succ_item(key)[1].mean - self.C.prev_item(key)[1].mean) / 2.
                nu = ((q1 - t) / k_i - 0.5) * delta
                s += nu * k_i * c_i.mean
                k += nu * k_i

            if q2 < t + k_i:
                return s/k
            t += k_i

        return s/k

# 需要导入模块: from bintrees import FastRBTree [as 别名]
# 或者: from bintrees.FastRBTree import succ_item [as 别名]
class ExclusiveRangeDict(object):
  """A class like dict whose key is a range [begin, end) of integers.

  It has an attribute for each range of integers, for example:
  [10, 20) => Attribute(0),
  [20, 40) => Attribute(1),
  [40, 50) => Attribute(2),
  ...

  An instance of this class is accessed only via iter_range(begin, end).
  The instance is accessed as follows:

  1) If the given range [begin, end) is not covered by the instance,
  the range is newly created and iterated.

  2) If the given range [begin, end) exactly covers ranges in the instance,
  the ranges are iterated.
  (See test_set() in tests/range_dict_tests.py.)

  3) If the given range [begin, end) starts at and/or ends at a mid-point of
  an existing range, the existing range is split by the given range, and
  ranges in the given range are iterated.  For example, consider a case that
  [25, 45) is given to an instance of [20, 30), [30, 40), [40, 50).  In this
  case, [20, 30) is split into [20, 25) and [25, 30), and [40, 50) into
  [40, 45) and [45, 50).  Then, [25, 30), [30, 40), [40, 45) are iterated.
  (See test_split() in tests/range_dict_tests.py.)

  4) If the given range [begin, end) includes non-existing ranges in an
  instance, the gaps are filled with new ranges, and all ranges are iterated.
  For example, consider a case that [25, 50) is given to an instance of
  [30, 35) and [40, 45).  In this case, [25, 30), [35, 40) and [45, 50) are
  created in the instance, and then [25, 30), [30, 35), [35, 40), [40, 45)
  and [45, 50) are iterated.
  (See test_fill() in tests/range_dict_tests.py.)
  """
  class RangeAttribute(object):
    def __init__(self):
      pass

    def __str__(self):
      return '<RangeAttribute>'

    def __repr__(self):
      return '<RangeAttribute>'

    def copy(self):  # pylint: disable=R0201
      return ExclusiveRangeDict.RangeAttribute()

  def __init__(self, attr=RangeAttribute):
    self._tree = FastRBTree()
    self._attr = attr

  def iter_range(self, begin=None, end=None):
    if not begin:
      begin = self._tree.min_key()
    if not end:
      end = self._tree.max_item()[1][0]

    # Assume that self._tree has at least one element.
    if self._tree.is_empty():
      self._tree[begin] = (end, self._attr())

    # Create a beginning range (border)
    try:
      bound_begin, bound_value = self._tree.floor_item(begin)
      bound_end = bound_value[0]
      if begin >= bound_end:
        # Create a blank range.
        try:
          new_end, _ = self._tree.succ_item(bound_begin)
        except KeyError:
          new_end = end
        self._tree[begin] = (min(end, new_end), self._attr())
      elif bound_begin < begin and begin < bound_end:
        # Split the existing range.
        new_end = bound_value[0]
        new_value = bound_value[1]
        self._tree[bound_begin] = (begin, new_value.copy())
        self._tree[begin] = (new_end, new_value.copy())
      else:  # bound_begin == begin
        # Do nothing (just saying it clearly since this part is confusing)
        pass
    except KeyError:  # begin is less than the smallest element.
      # Create a blank range.
      # Note that we can assume self._tree has at least one element.
      self._tree[begin] = (min(end, self._tree.min_key()), self._attr())

    # Create an ending range (border)
    try:
      bound_begin, bound_value = self._tree.floor_item(end)
      bound_end = bound_value[0]
      if end > bound_end:
        # Create a blank range.
        new_begin = bound_end
        self._tree[new_begin] = (end, self._attr())
      elif bound_begin < end and end < bound_end:
        # Split the existing range.
        new_end = bound_value[0]
        new_value = bound_value[1]
        self._tree[bound_begin] = (end, new_value.copy())
#.........这里部分代码省略.........