Removing unused eval code (c71fcbc0) · Commits · aflab / astrogeology / Autocnet

autocnet/utils/evaluation_measures.py

deleted100644 → 0

+0 −297

Changes for autocnet/utils/evaluation_measures.py: 0 added lines, 297 removed lines.
Original line number	Diff line number	Diff line
		import numpy as np

		"""
		Code from: statsmodels - https://github.com/statsmodels/statsmodels

		Released under a BSD-3 license:

		Copyright (C) 2006, Jonathan E. Taylor
		All rights reserved.

		Copyright (c) 2006-2008 Scipy Developers.
		All rights reserved.

		Copyright (c) 2009-2012 Statsmodels Developers.
		All rights reserved.


		Redistribution and use in source and binary forms, with or without
		modification, are permitted provided that the following conditions are met:

		a. Redistributions of source code must retain the above copyright notice,
		this list of conditions and the following disclaimer.
		b. Redistributions in binary form must reproduce the above copyright
		notice, this list of conditions and the following disclaimer in the
		documentation and/or other materials provided with the distribution.
		c. Neither the name of Statsmodels nor the names of its contributors
		may be used to endorse or promote products derived from this software
		without specific prior written permission.


		THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
		AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
		IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
		ARE DISCLAIMED. IN NO EVENT SHALL STATSMODELS OR CONTRIBUTORS BE LIABLE FOR
		ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
		DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
		SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
		CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
		LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
		OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
		DAMAGE.
		"""


		def mse(x1, x2, axis=0):
		"""mean squared error
		Parameters
		----------
		x1, x2 : array_like
		The performance measure depends on the difference between these two
		arrays.
		axis : int
		axis along which the summary statistic is calculated
		Returns
		-------
		mse : ndarray or float
		mean squared error along given axis.
		Notes
		-----
		If ``x1`` and ``x2`` have different shapes, then they need to broadcast.
		This uses ``numpy.asanyarray`` to convert the input. Whether this is the
		desired result or not depends on the array subclass, for example
		numpy matrices will silently produce an incorrect result.
		"""
		x1 = np.asanyarray(x1)
		x2 = np.asanyarray(x2)
		return np.mean((x1-x2)**2, axis=axis)


		def rmse(x1, x2, axis=0):
		"""root mean squared error
		Parameters
		----------
		x1, x2 : array_like
		The performance measure depends on the difference between these two
		arrays.
		axis : int
		axis along which the summary statistic is calculated
		Returns
		-------
		rmse : ndarray or float
		root mean squared error along given axis.
		Notes
		-----
		If ``x1`` and ``x2`` have different shapes, then they need to broadcast.
		This uses ``numpy.asanyarray`` to convert the input. Whether this is the
		desired result or not depends on the array subclass, for example
		numpy matrices will silently produce an incorrect result.
		"""
		x1 = np.asanyarray(x1)
		x2 = np.asanyarray(x2)
		return np.sqrt(mse(x1, x2, axis=axis))


		def maxabs(x1, x2, axis=0):
		"""maximum absolute error
		Parameters
		----------
		x1, x2 : array_like
		The performance measure depends on the difference between these two
		arrays.
		axis : int
		axis along which the summary statistic is calculated
		Returns
		-------
		maxabs : ndarray or float
		maximum absolute difference along given axis.
		Notes
		-----
		If ``x1`` and ``x2`` have different shapes, then they need to broadcast.
		This uses ``numpy.asanyarray`` to convert the input. Whether this is the
		desired result or not depends on the array subclass.
		"""
		x1 = np.asanyarray(x1)
		x2 = np.asanyarray(x2)
		return np.max(np.abs(x1-x2), axis=axis)


		def meanabs(x1, x2, axis=0):
		"""mean absolute error
		Parameters
		----------
		x1, x2 : array_like
		The performance measure depends on the difference between these two
		arrays.
		axis : int
		axis along which the summary statistic is calculated
		Returns
		-------
		meanabs : ndarray or float
		mean absolute difference along given axis.
		Notes
		-----
		If ``x1`` and ``x2`` have different shapes, then they need to broadcast.
		This uses ``numpy.asanyarray`` to convert the input. Whether this is the
		desired result or not depends on the array subclass.
		"""
		x1 = np.asanyarray(x1)
		x2 = np.asanyarray(x2)
		return np.mean(np.abs(x1-x2), axis=axis)


		def medianabs(x1, x2, axis=0):
		"""median absolute error
		Parameters
		----------
		x1, x2 : array_like
		The performance measure depends on the difference between these two
		arrays.
		axis : int
		axis along which the summary statistic is calculated
		Returns
		-------
		medianabs : ndarray or float
		median absolute difference along given axis.
		Notes
		-----
		If ``x1`` and ``x2`` have different shapes, then they need to broadcast.
		This uses ``numpy.asanyarray`` to convert the input. Whether this is the
		desired result or not depends on the array subclass.
		"""
		x1 = np.asanyarray(x1)
		x2 = np.asanyarray(x2)
		return np.median(np.abs(x1-x2), axis=axis)


		def bias(x1, x2, axis=0):
		"""bias, mean error
		Parameters
		----------
		x1, x2 : array_like
		The performance measure depends on the difference between these two
		arrays.
		axis : int
		axis along which the summary statistic is calculated
		Returns
		-------
		bias : ndarray or float
		bias, or mean difference along given axis.
		Notes
		-----
		If ``x1`` and ``x2`` have different shapes, then they need to broadcast.
		This uses ``numpy.asanyarray`` to convert the input. Whether this is the
		desired result or not depends on the array subclass.
		"""
		x1 = np.asanyarray(x1)
		x2 = np.asanyarray(x2)
		return np.mean(x1-x2, axis=axis)


		def medianbias(x1, x2, axis=0):
		"""median bias, median error
		Parameters
		----------
		x1, x2 : array_like
		The performance measure depends on the difference between these two
		arrays.
		axis : int
		axis along which the summary statistic is calculated
		Returns
		-------
		medianbias : ndarray or float
		median bias, or median difference along given axis.
		Notes
		-----
		If ``x1`` and ``x2`` have different shapes, then they need to broadcast.
		This uses ``numpy.asanyarray`` to convert the input. Whether this is the
		desired result or not depends on the array subclass.
		"""
		x1 = np.asanyarray(x1)
		x2 = np.asanyarray(x2)
		return np.median(x1-x2, axis=axis)


		def vare(x1, x2, ddof=0, axis=0):
		"""variance of error
		Parameters
		----------
		x1, x2 : array_like
		The performance measure depends on the difference between these two
		arrays.
		axis : int
		axis along which the summary statistic is calculated
		Returns
		-------
		vare : ndarray or float
		variance of difference along given axis.
		Notes
		-----
		If ``x1`` and ``x2`` have different shapes, then they need to broadcast.
		This uses ``numpy.asanyarray`` to convert the input. Whether this is the
		desired result or not depends on the array subclass.
		"""
		x1 = np.asanyarray(x1)
		x2 = np.asanyarray(x2)
		return np.var(x1-x2, ddof=ddof, axis=axis)


		def stde(x1, x2, ddof=0, axis=0):
		"""standard deviation of error
		Parameters
		----------
		x1, x2 : array_like
		The performance measure depends on the difference between these two
		arrays.
		axis : int
		axis along which the summary statistic is calculated
		Returns
		-------
		stde : ndarray or float
		standard deviation of difference along given axis.
		Notes
		-----
		If ``x1`` and ``x2`` have different shapes, then they need to broadcast.
		This uses ``numpy.asanyarray`` to convert the input. Whether this is the
		desired result or not depends on the array subclass.
		"""
		x1 = np.asanyarray(x1)
		x2 = np.asanyarray(x2)
		return np.std(x1-x2, ddof=ddof, axis=axis)


		def iqr(x1, x2, axis=0):
		"""interquartile range of error
		rounded index, no interpolations
		this could use newer numpy function instead
		Parameters
		----------
		x1, x2 : array_like
		The performance measure depends on the difference between these two
		arrays.
		axis : int
		axis along which the summary statistic is calculated
		Returns
		-------
		mse : ndarray or float
		mean squared error along given axis.
		Notes
		-----
		If ``x1`` and ``x2`` have different shapes, then they need to broadcast.
		This uses ``numpy.asarray`` to convert the input, in contrast to the other
		functions in this category.
		"""
		x1 = np.asarray(x1)
		x2 = np.asarray(x2)
		if axis is None:
		x1 = np.ravel(x1)
		x2 = np.ravel(x2)
		axis = 0
		xdiff = np.sort(x1 - x2)
		nobs = x1.shape[axis]
		idx = np.round((nobs-1) * np.array([0.25, 0.75])).astype(int)
		sl = [slice(None)] * xdiff.ndim
		sl[axis] = idx
		iqr = np.diff(xdiff[sl], axis=axis)
		iqr = np.squeeze(iqr) # drop reduced dimension
		return iqr
		No newline at end of file

autocnet/utils/folds.py

deleted100644 → 0

+0 −36

Changes for autocnet/utils/folds.py: 0 added lines, 36 removed lines.
Original line number	Diff line number	Diff line
		# -- coding: utf-8 --
		"""
		Created on Fri Dec 4 12:51:34 2015

		@author: rbanderson
		"""
		from sklearn import cross_validation
		import numpy as np
		def random(df,nfolds=5,seed=10,groupby=None):
		df['Folds']='None' #Create an entry in the data frame that holds the folds
		foldslist=np.array(df['Folds'])
		if groupby==None: #if no column name is listed to group on, just create random folds
		n=len(df.index)
		folds=cross_validation.KFold(n,nfolds,shuffle=True,random_state=seed)
		i=1
		for train,test in folds:
		foldslist[test]='Fold'+str(i)
		i=i+1

		else:
		#if a column name is provided, get all the unique values and define folds
		#so that all rows of a given value fall in the same fold
		#(this is useful to ensure that training and test data are truly independent)
		unique_inds=np.unique(df[groupby])
		folds=cross_validation.KFold(len(unique_inds),nfolds,shuffle=True,random_state=seed)
		foldslist=np.array(df['Folds'])
		i=1
		for train,test in folds:
		tmp=unique_inds[test]
		tmp_full_list=np.array(df[groupby])
		tmp_ind=np.in1d(tmp_full_list,tmp)
		foldslist[tmp_ind]='Fold'+str(i)
		i=i+1

		df['Folds']=foldslist
		return df
		No newline at end of file

autocnet/utils/tests/test_eval_measures.py

deleted100644 → 0

+0 −109

Changes for autocnet/utils/tests/test_eval_measures.py: 0 added lines, 109 removed lines.
Original line number	Diff line number	Diff line
		import unittest
		import numpy as np
		from .. import evaluation_measures as em

		from numpy.testing import assert_equal, assert_almost_equal

		"""
		Code modifid from: statsmodels - https://github.com/statsmodels/statsmodels

		Released under a BSD-3 license:

		Copyright (C) 2006, Jonathan E. Taylor
		All rights reserved.

		Copyright (c) 2006-2008 Scipy Developers.
		All rights reserved.

		Copyright (c) 2009-2012 Statsmodels Developers.
		All rights reserved.


		Redistribution and use in source and binary forms, with or without
		modification, are permitted provided that the following conditions are met:

		a. Redistributions of source code must retain the above copyright notice,
		this list of conditions and the following disclaimer.
		b. Redistributions in binary form must reproduce the above copyright
		notice, this list of conditions and the following disclaimer in the
		documentation and/or other materials provided with the distribution.
		c. Neither the name of Statsmodels nor the names of its contributors
		may be used to endorse or promote products derived from this software
		without specific prior written permission.


		THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
		AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
		IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
		ARE DISCLAIMED. IN NO EVENT SHALL STATSMODELS OR CONTRIBUTORS BE LIABLE FOR
		ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
		DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
		SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
		CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
		LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
		OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
		DAMAGE.
		"""


		class TestEvalMeasures(unittest.TestCase):

		def setUp(self):
		pass

		def test_eval_measures(self):

		x = np.arange(20).reshape(4,5)
		y = np.ones((4,5))
		assert_equal(em.iqr(x, y), 5*np.ones(5))
		assert_equal(em.iqr(x, y, axis=1), 2*np.ones(4))
		assert_equal(em.iqr(x, y, axis=None), 9)

		assert_equal(em.mse(x, y),
		np.array([ 73.5, 87.5, 103.5, 121.5, 141.5]))
		assert_equal(em.mse(x, y, axis=1),
		np.array([ 3., 38., 123., 258.]))

		assert_almost_equal(em.rmse(x, y),
		np.array([ 8.5732141 , 9.35414347, 10.17349497,
		11.02270384, 11.89537725]))
		assert_almost_equal(em.rmse(x, y, axis=1),
		np.array([ 1.73205081, 6.164414,
		11.09053651, 16.0623784 ]))

		assert_equal(em.maxabs(x, y),
		np.array([ 14., 15., 16., 17., 18.]))
		assert_equal(em.maxabs(x, y, axis=1),
		np.array([ 3., 8., 13., 18.]))

		assert_equal(em.meanabs(x, y),
		np.array([ 7. , 7.5, 8.5, 9.5, 10.5]))
		assert_equal(em.meanabs(x, y, axis=1),
		np.array([ 1.4, 6. , 11. , 16. ]))
		assert_equal(em.meanabs(x, y, axis=0),
		np.array([ 7. , 7.5, 8.5, 9.5, 10.5]))

		assert_equal(em.medianabs(x, y),
		np.array([ 6.5, 7.5, 8.5, 9.5, 10.5]))
		assert_equal(em.medianabs(x, y, axis=1),
		np.array([ 1., 6., 11., 16.]))

		assert_equal(em.bias(x, y),
		np.array([ 6.5, 7.5, 8.5, 9.5, 10.5]))
		assert_equal(em.bias(x, y, axis=1),
		np.array([ 1., 6., 11., 16.]))

		assert_equal(em.medianbias(x, y),
		np.array([ 6.5, 7.5, 8.5, 9.5, 10.5]))
		assert_equal(em.medianbias(x, y, axis=1),
		np.array([ 1., 6., 11., 16.]))

		assert_equal(em.vare(x, y),
		np.array([ 31.25, 31.25, 31.25, 31.25, 31.25]))
		assert_equal(em.vare(x, y, axis=1),
		np.array([ 2., 2., 2., 2.]))

		assert_almost_equal(em.stde(x, y),
		np.array([5.59017, 5.59017, 5.59017, 5.59017, 5.59017]))
		assert_almost_equal(em.stde(x, y, axis=1),
		np.array([1.4142136, 1.4142136, 1.4142136, 1.4142136]))