def scale_by_min_max(x, output_min=0.0, output_max=1.0, name=None):
"""Scale a numerical column into the range [output_min, output_max].
Args:
x: A numeric `Tensor`.
output_min: The minimum of the range of output values.
output_max: The maximum of the range of output values.
name: (Optional) A name for this operation.
Returns:
A `Tensor` containing the input column scaled to [output_min, output_max].
Raises:
ValueError: If output_min, output_max have the wrong order.
"""
with tf.name_scope(name, 'scale_by_min_max'):
if output_min >= output_max:
raise ValueError('output_min must be less than output_max')
x = tf.to_float(x)
min_x_value = analyzers.min(x)
max_x_value = analyzers.max(x)
x_shape = tf.shape(x)
# If min==max, the result will be the mean of the requested range.
# Note that both the options of tf.where are computed, which means that this
# will compute unused NaNs.
scaled_result = tf.where(tf.fill(x_shape, min_x_value < max_x_value),
(x - min_x_value) /
(max_x_value - min_x_value),
tf.fill(x_shape, 0.5))
return (scaled_result * (output_max - output_min)) + output_min
def testCreatePhasesWithMultipleLevelsOfAnalyzers(self):
# Create graph similar to calling scale_to_0_1 except involving multiple
# interleavings of analyzers and transforms.
float_placeholder = tf.placeholder(tf.float32, shape=(None, ))
scaled_to_0 = float_placeholder - analyzers.min(float_placeholder)
scaled_to_0 / analyzers.max(scaled_to_0) # pylint: disable=expression-not-assigned
phases = impl_helper.create_phases()
self.assertEqual(len(phases), 2)
self.assertEqual(len(phases[0].analyzer_infos), 1)
self.assertEqual(len(phases[1].analyzer_infos), 1)
def testCreatePhasesWithTable(self):
# Create a graph with table that can only be run after the first analyzer
# has run. Note converting an integerized string into a float doesn't make
# much sense, but is a legal tensorflow computation.
string_placeholder = tf.placeholder(tf.string, shape=(None, ))
integerized = mappers.string_to_int(string_placeholder)
integerized = tf.to_float(integerized)
integerized / analyzers.max(integerized) # pylint: disable=expression-not-assigned
phases = impl_helper.create_phases()
self.assertEqual(len(phases), 2)
self.assertEqual(len(phases[0].analyzer_infos), 1)
self.assertEqual(len(phases[1].analyzer_infos), 1)
self.assertEqual(len(phases[0].table_initializers), 0)
self.assertEqual(len(phases[1].table_initializers), 1)
def scale_to_0_1(x):
"""Returns a column which is the input column scaled to have range [0,1].
Args:
x: A `Column` representing a numeric value.
Returns:
A `Column` representing the input column scaled to [0, 1].
"""
# A TITO function that scales x.
def scale(x, min_value, max_value):
return (x - min_value) / (max_value - min_value)
return api.map(scale, x, analyzers.min(x), analyzers.max(x))
def scale_by_min_max(x, output_min=0.0, output_max=1.0):
"""Scale a numerical column into the range [output_min, output_max].
Args:
x: A numeric `Tensor`.
output_min: The minimum of the range of output values.
output_max: The maximum of the range of output values.
Returns:
A `Tensor` containing the input column scaled to [output_min, output_max].
Raises:
ValueError: If output_min, output_max have the wrong order.
"""
if output_min >= output_max:
raise ValueError('output_min must be less than output_max')
min_x_value = analyzers.min(x)
max_x_value = analyzers.max(x)
return ((((x - min_x_value) * (output_max - output_min)) /
(max_x_value - min_x_value)) + output_min)
def scale_by_min_max(x, output_min=0.0, output_max=1.0):
"""Scale a numerical column into the range [output_min, output_max].
Args:
x: A `Column` representing a numeric value.
output_min: The minimum of the range of output values.
output_max: The maximum of the range of output values.
Returns:
A `Column` representing the input column scaled to [output_min, output_max].
Raises:
ValueError: If output_min, output_max have the wrong order.
"""
if output_min >= output_max:
raise ValueError('output_min must be less than output_max')
# A TITO function that scales x.
def _scale(x, min_x_value, max_x_value):
return ((((x - min_x_value) * (output_max - output_min)) /
(max_x_value - min_x_value)) + output_min)
return api.map(_scale, x, analyzers.min(x), analyzers.max(x))
def preprocessing_fn(inputs):
integerized = mappers.string_to_int(inputs['x'])
integerized = tf.to_float(integerized)
scaled_to_0_1 = integerized / analyzers.max(integerized)
return {'x_scaled': scaled_to_0_1}
def preprocessing_fn(inputs):
scaled_to_0 = inputs['x'] - analyzers.min(inputs['x'])
scaled_to_0_1 = scaled_to_0 / analyzers.max(scaled_to_0)
return {'x_scaled': scaled_to_0_1}
