Python tensorflow.python.ops.math_ops.is_nan() Examples

def _prob(self, x):
    broadcasted_x = x * array_ops.ones(self.batch_shape_tensor())
    return array_ops.where(
        math_ops.is_nan(broadcasted_x),
        broadcasted_x,
        array_ops.where(
            math_ops.logical_or(broadcasted_x < self.low,
                                broadcasted_x >= self.high),
            array_ops.zeros_like(broadcasted_x),
            array_ops.ones_like(broadcasted_x) / self.range())) 

def _apply_transform(self, input_tensors, **kwargs):
    """Applies the transformation to the `transform_input`.

    Args:
      input_tensors: a list of Tensors representing the input to
        the Transform.
      **kwargs: Additional keyword arguments, unused here.

    Returns:
        A namedtuple of Tensors representing the transformed output.
    """
    d = input_tensors[0]

    if self.strip_value is np.nan:
      strip_hot = math_ops.is_nan(d)
    else:
      strip_hot = math_ops.equal(d,
                                 array_ops.constant([self.strip_value],
                                                    dtype=d.dtype))
    keep_hot = math_ops.logical_not(strip_hot)

    length = array_ops.reshape(array_ops.shape(d), [])
    indices = array_ops.boolean_mask(math_ops.range(length), keep_hot)
    values = array_ops.boolean_mask(d, keep_hot)

    sparse_indices = array_ops.reshape(
        math_ops.cast(indices, dtypes.int64), [-1, 1])
    shape = math_ops.cast(array_ops.shape(d), dtypes.int64)

    # pylint: disable=not-callable
    return self.return_type(
        sparse_tensor.SparseTensor(sparse_indices, values, shape)) 

def _apply_transform(self, input_tensors, **kwargs):
    """Applies the transformation to the `transform_input`.

    Args:
      input_tensors: a list of Tensors representing the input to
        the Transform.
      **kwargs: Additional keyword arguments, unused here.

    Returns:
        A namedtuple of Tensors representing the transformed output.
    """
    d = input_tensors[0]

    if self.strip_value is np.nan:
      strip_hot = math_ops.is_nan(d)
    else:
      strip_hot = math_ops.equal(d,
                                 array_ops.constant([self.strip_value],
                                                    dtype=d.dtype))
    keep_hot = math_ops.logical_not(strip_hot)

    length = array_ops.reshape(array_ops.shape(d), [])
    indices = array_ops.boolean_mask(math_ops.range(length), keep_hot)
    values = array_ops.boolean_mask(d, keep_hot)

    sparse_indices = array_ops.reshape(
        math_ops.cast(indices, dtypes.int64), [-1, 1])
    shape = math_ops.cast(array_ops.shape(d), dtypes.int64)

    # pylint: disable=not-callable
    return self.return_type(
        sparse_tensor.SparseTensor(sparse_indices, values, shape)) 

def _prob(self, x):
    broadcasted_x = x * array_ops.ones(self.batch_shape())
    return array_ops.where(
        math_ops.is_nan(broadcasted_x),
        broadcasted_x,
        array_ops.where(
            math_ops.logical_or(broadcasted_x < self.a,
                                broadcasted_x > self.b),
            array_ops.zeros_like(broadcasted_x),
            (1. / self.range()) * array_ops.ones_like(broadcasted_x))) 

def _apply_transform(self, input_tensors, **kwargs):
    """Applies the transformation to the `transform_input`.

    Args:
      input_tensors: a list of Tensors representing the input to
        the Transform.
      **kwargs: Additional keyword arguments, unused here.

    Returns:
        A namedtuple of Tensors representing the transformed output.
    """
    d = input_tensors[0]

    if self.strip_value is np.nan:
      strip_hot = math_ops.is_nan(d)
    else:
      strip_hot = math_ops.equal(d,
                                 array_ops.constant([self.strip_value],
                                                    dtype=d.dtype))
    keep_hot = math_ops.logical_not(strip_hot)

    length = array_ops.reshape(array_ops.shape(d), [])
    indices = array_ops.boolean_mask(math_ops.range(length), keep_hot)
    values = array_ops.boolean_mask(d, keep_hot)

    sparse_indices = array_ops.reshape(
        math_ops.cast(indices, dtypes.int64), [-1, 1])
    shape = math_ops.cast(array_ops.shape(d), dtypes.int64)

    # pylint: disable=not-callable
    return self.return_type(
        sparse_tensor.SparseTensor(sparse_indices, values, shape)) 

def _prob(self, x):
    broadcasted_x = x * array_ops.ones(self.batch_shape())
    return math_ops.select(
        math_ops.is_nan(broadcasted_x),
        broadcasted_x,
        math_ops.select(
            math_ops.logical_or(broadcasted_x < self.a,
                                broadcasted_x > self.b),
            array_ops.zeros_like(broadcasted_x),
            (1. / self.range()) * array_ops.ones_like(broadcasted_x))) 

def _prob(self, x):
    broadcasted_x = x * array_ops.ones(self.batch_shape_tensor())
    return array_ops.where(
        math_ops.is_nan(broadcasted_x),
        broadcasted_x,
        array_ops.where(
            math_ops.logical_or(broadcasted_x < self.low,
                                broadcasted_x >= self.high),
            array_ops.zeros_like(broadcasted_x),
            array_ops.ones_like(broadcasted_x) / self.range())) 

def _apply_transform(self, input_tensors, **kwargs):
    """Applies the transformation to the `transform_input`.

    Args:
      input_tensors: a list of Tensors representing the input to
        the Transform.
      **kwargs: Additional keyword arguments, unused here.

    Returns:
        A namedtuple of Tensors representing the transformed output.
    """
    d = input_tensors[0]

    if self.strip_value is np.nan:
      strip_hot = math_ops.is_nan(d)
    else:
      strip_hot = math_ops.equal(d,
                                 array_ops.constant([self.strip_value],
                                                    dtype=d.dtype))
    keep_hot = math_ops.logical_not(strip_hot)

    length = array_ops.reshape(array_ops.shape(d), [])
    indices = array_ops.boolean_mask(math_ops.range(length), keep_hot)
    values = array_ops.boolean_mask(d, keep_hot)

    sparse_indices = array_ops.reshape(
        math_ops.cast(indices, dtypes.int64), [-1, 1])
    shape = math_ops.cast(array_ops.shape(d), dtypes.int64)

    # pylint: disable=not-callable
    return self.return_type(
        sparse_tensor.SparseTensor(sparse_indices, values, shape)) 

def _prob(self, x):
    broadcasted_x = x * array_ops.ones(self.batch_shape())
    return array_ops.where(
        math_ops.is_nan(broadcasted_x),
        broadcasted_x,
        array_ops.where(
            math_ops.logical_or(broadcasted_x < self.a,
                                broadcasted_x > self.b),
            array_ops.zeros_like(broadcasted_x),
            (1. / self.range()) * array_ops.ones_like(broadcasted_x))) 

def _calculate_acceptance_probabilities(init_probs, target_probs):
  """Calculate the per-class acceptance rates.

  Args:
    init_probs: The class probabilities of the data.
    target_probs: The desired class proportion in minibatches.
  Returns:
    A list of the per-class acceptance probabilities.

  This method is based on solving the following analysis:

  Let F be the probability of a rejection (on any example).
  Let p_i be the proportion of examples in the data in class i (init_probs)
  Let a_i is the rate the rejection sampler should *accept* class i
  Let t_i is the target proportion in the minibatches for class i (target_probs)

  ```
  F = sum_i(p_i * (1-a_i))
    = 1 - sum_i(p_i * a_i)     using sum_i(p_i) = 1
  ```

  An example with class `i` will be accepted if `k` rejections occur, then an
  example with class `i` is seen by the rejector, and it is accepted. This can
  be written as follows:

  ```
  t_i = sum_k=0^inf(F^k * p_i * a_i)
      = p_i * a_j / (1 - F)    using geometric series identity, since 0 <= F < 1
      = p_i * a_i / sum_j(p_j * a_j)        using F from above
  ```

  Note that the following constraints hold:
  ```
  0 <= p_i <= 1, sum_i(p_i) = 1
  0 <= a_i <= 1
  0 <= t_i <= 1, sum_i(t_i) = 1
  ```


  A solution for a_i in terms of the other variabes is the following:
    ```a_i = (t_i / p_i) / max_i[t_i / p_i]```
  """
  # Make list of t_i / p_i.
  ratio_l = target_probs / init_probs

  # Replace NaNs with 0s.
  ratio_l = array_ops.where(
      math_ops.is_nan(ratio_l), array_ops.zeros_like(ratio_l), ratio_l)

  # Calculate list of acceptance probabilities.
  max_ratio = math_ops.reduce_max(ratio_l)
  return ratio_l / max_ratio 

def _calculate_acceptance_probabilities(init_probs, target_probs):
  """Calculate the per-class acceptance rates.

  Args:
    init_probs: The class probabilities of the data.
    target_probs: The desired class proportion in minibatches.
  Returns:
    A list of the per-class acceptance probabilities.

  This method is based on solving the following analysis:

  Let F be the probability of a rejection (on any example).
  Let p_i be the proportion of examples in the data in class i (init_probs)
  Let a_i is the rate the rejection sampler should *accept* class i
  Let t_i is the target proportion in the minibatches for class i (target_probs)

  ```
  F = sum_i(p_i * (1-a_i))
    = 1 - sum_i(p_i * a_i)     using sum_i(p_i) = 1
  ```

  An example with class `i` will be accepted if `k` rejections occur, then an
  example with class `i` is seen by the rejector, and it is accepted. This can
  be written as follows:

  ```
  t_i = sum_k=0^inf(F^k * p_i * a_i)
      = p_i * a_j / (1 - F)    using geometric series identity, since 0 <= F < 1
      = p_i * a_i / sum_j(p_j * a_j)        using F from above
  ```

  Note that the following constraints hold:
  ```
  0 <= p_i <= 1, sum_i(p_i) = 1
  0 <= a_i <= 1
  0 <= t_i <= 1, sum_i(t_i) = 1
  ```


  A solution for a_i in terms of the other variabes is the following:
    ```a_i = (t_i / p_i) / max_i[t_i / p_i]```
  """
  # Make list of t_i / p_i.
  ratio_l = target_probs / init_probs

  # Replace NaNs with 0s.
  ratio_l = array_ops.where(
      math_ops.is_nan(ratio_l), array_ops.zeros_like(ratio_l), ratio_l)

  # Calculate list of acceptance probabilities.
  max_ratio = math_ops.reduce_max(ratio_l)
  return ratio_l / max_ratio 

def _calculate_acceptance_probabilities(init_probs, target_probs):
  """Calculate the per-class acceptance rates.

  Args:
    init_probs: The class probabilities of the data.
    target_probs: The desired class proportion in minibatches.
  Returns:
    A list of the per-class acceptance probabilities.

  This method is based on solving the following analysis:

  Let F be the probability of a rejection (on any example).
  Let p_i be the proportion of examples in the data in class i (init_probs)
  Let a_i is the rate the rejection sampler should *accept* class i
  Let t_i is the target proportion in the minibatches for class i (target_probs)

  ```
  F = sum_i(p_i * (1-a_i))
    = 1 - sum_i(p_i * a_i)     using sum_i(p_i) = 1
  ```

  An example with class `i` will be accepted if `k` rejections occur, then an
  example with class `i` is seen by the rejector, and it is accepted. This can
  be written as follows:

  ```
  t_i = sum_k=0^inf(F^k * p_i * a_i)
      = p_i * a_j / (1 - F)    using geometric series identity, since 0 <= F < 1
      = p_i * a_i / sum_j(p_j * a_j)        using F from above
  ```

  Note that the following constraints hold:
  ```
  0 <= p_i <= 1, sum_i(p_i) = 1
  0 <= a_i <= 1
  0 <= t_i <= 1, sum_i(t_i) = 1
  ```


  A solution for a_i in terms of the other variabes is the following:
    ```a_i = (t_i / p_i) / max_i[t_i / p_i]```
  """
  # Make list of t_i / p_i.
  ratio_l = target_probs / init_probs

  # Replace NaNs with 0s.
  ratio_l = array_ops.where(
      math_ops.is_nan(ratio_l), array_ops.zeros_like(ratio_l), ratio_l)

  # Calculate list of acceptance probabilities.
  max_ratio = math_ops.reduce_max(ratio_l)
  return ratio_l / max_ratio