ó áp7]c@s³dZddlmZmZddlZddlmZdefd„ƒYZ defd„ƒYZ d efd „ƒYZ d efd „ƒYZ d „Z defd„ƒYZdS(s! Utilities for cross validation. taken from scikits.learn # Author: Alexandre Gramfort , # Gael Varoquaux # License: BSD Style. # $Id$ changes to code by josef-pktd: - docstring formatting: underlines of headers iÿÿÿÿ(trangetlrangeN(t combinationst LeaveOneOutcBs)eZdZd„Zd„Zd„ZRS(ss Leave-One-Out cross validation iterator: Provides train/test indexes to split data in train test sets cCs ||_dS(s9 Leave-One-Out cross validation iterator: Provides train/test indexes to split data in train test sets Parameters ---------- n: int Total number of elements Examples -------- >>> from scikits.learn import cross_val >>> X = [[1, 2], [3, 4]] >>> y = [1, 2] >>> loo = cross_val.LeaveOneOut(2) >>> for train_index, test_index in loo: ... print "TRAIN:", train_index, "TEST:", test_index ... X_train, X_test, y_train, y_test = cross_val.split(train_index, test_index, X, y) ... print X_train, X_test, y_train, y_test TRAIN: [False True] TEST: [ True False] [[3 4]] [[1 2]] [2] [1] TRAIN: [ True False] TEST: [False True] [[1 2]] [[3 4]] [1] [2] N(tn(tselfR((sBlib/python2.7/site-packages/statsmodels/sandbox/tools/cross_val.pyt__init__sccs`|j}xPt|ƒD]B}tj|dtjƒ}t||>> from scikits.learn import cross_val >>> X = [[1, 2], [3, 4], [5, 6], [7, 8]] >>> y = [1, 2, 3, 4] >>> lpo = cross_val.LeavePOut(4, 2) >>> for train_index, test_index in lpo: ... print "TRAIN:", train_index, "TEST:", test_index ... X_train, X_test, y_train, y_test = cross_val.split(train_index, test_index, X, y) TRAIN: [False False True True] TEST: [ True True False False] TRAIN: [False True False True] TEST: [ True False True False] TRAIN: [False True True False] TEST: [ True False False True] TRAIN: [ True False False True] TEST: [False True True False] TRAIN: [ True False True False] TEST: [False True False True] TRAIN: [ True True False False] TEST: [False False True True] N(Rtp(RRR((sBlib/python2.7/site-packages/statsmodels/sandbox/tools/cross_val.pyRQs ccs|j}|j}tt|ƒ|ƒ}xS|D]K}tj|dtjƒ}t|tj|ƒ>> from scikits.learn import cross_val >>> X = [[1, 2], [3, 4], [1, 2], [3, 4]] >>> y = [1, 2, 3, 4] >>> kf = cross_val.KFold(4, k=2) >>> for train_index, test_index in kf: ... print "TRAIN:", train_index, "TEST:", test_index ... X_train, X_test, y_train, y_test = cross_val.split(train_index, test_index, X, y) TRAIN: [False False True True] TEST: [ True True False False] TRAIN: [ True True False False] TEST: [False False True True] Notes ----- All the folds have size trunc(n/k), the last one has the complementary iscannot have k below 1s cannot have k=%d greater than %dN(tAssertionErrort ValueErrorRtk(RRR((sBlib/python2.7/site-packages/statsmodels/sandbox/tools/cross_val.pyRŒs( ccs²|j}|j}ttj||ƒƒ}x€t|ƒD]r}tj|dtjƒ}||dkr‚t||||d|+nt|||)tj |ƒ}||fVq8WdS(NRi( RRtintRtceilRR R R R (RRRtjR RR((sBlib/python2.7/site-packages/statsmodels/sandbox/tools/cross_val.pyR®s  cCs&d|jj|jj|j|jfS(Ns%s.%s(n=%i, k=%i)(RRRRR(R((sBlib/python2.7/site-packages/statsmodels/sandbox/tools/cross_val.pyR½s   (RRRRRR(((sBlib/python2.7/site-packages/statsmodels/sandbox/tools/cross_val.pyR†s " tLeaveOneLabelOutcBs)eZdZd„Zd„Zd„ZRS(sy Leave-One-Label_Out cross-validation iterator: Provides train/test indexes to split data in train test sets cCs ||_dS(sö Leave-One-Label_Out cross validation: Provides train/test indexes to split data in train test sets Parameters ---------- labels : list List of labels Examples -------- >>> from scikits.learn import cross_val >>> X = [[1, 2], [3, 4], [5, 6], [7, 8]] >>> y = [1, 2, 1, 2] >>> labels = [1, 1, 2, 2] >>> lol = cross_val.LeaveOneLabelOut(labels) >>> for train_index, test_index in lol: ... print "TRAIN:", train_index, "TEST:", test_index ... X_train, X_test, y_train, y_test = cross_val.split(train_index, test_index, X, y) ... print X_train, X_test, y_train, y_test TRAIN: [False False True True] TEST: [ True True False False] [[5 6] [7 8]] [[1 2] [3 4]] [1 2] [1 2] TRAIN: [ True True False False] TEST: [False False True True] [[1 2] [3 4]] [[5 6] [7 8]] [1 2] [1 2] N(tlabels(RR#((sBlib/python2.7/site-packages/statsmodels/sandbox/tools/cross_val.pyRÍs ccs~tj|jdtƒ}x_tj|ƒD]N}tjt|ƒdtjƒ}t|||k>> from scikits.learn import cross_val >>> X = [[1, 2], [3, 4]] >>> y = [1, 2] >>> loo = cross_val.LeaveOneOut(2) >>> for train_index, test_index in loo: ... print "TRAIN:", train_index, "TEST:", test_index ... X_train, X_test, y_train, y_test = cross_val.split(train_index, test_index, X, y) ... print X_train, X_test, y_train, y_test TRAIN: [False True] TEST: [ True False] [[3 4]] [[1 2]] [2] [1] TRAIN: [ True False] TEST: [False True] [[1 2]] [[3 4]] [1] [2] gÐ?N( RRtNoneRRttrunctstarttkallt return_slice(RRRR4R5R6((sBlib/python2.7/site-packages/statsmodels/sandbox/tools/cross_val.pyR"s'     c cs9|j}|j}|j}|jrœxt|||ƒD]]}td|dƒ}|jrot|||ƒ}nt||d||ƒ}||fVq8Wn™x–t|||ƒD]}tj |dtj ƒ}t ||*tj |dtj ƒ}|jr t ||||+nt |||d||+||fVq°WdS(NiR( RRR4R6RtsliceR2R5RR R R ( RRRR4R t train_slicet test_sliceRR((sBlib/python2.7/site-packages/statsmodels/sandbox/tools/cross_val.pyRRs$       cCs d|jj|jj|jfS(Ns %s.%s(n=%i)(RRRR(R((sBlib/python2.7/site-packages/statsmodels/sandbox/tools/cross_val.pyRms  N(RRRR2R RRR(((sBlib/python2.7/site-packages/statsmodels/sandbox/tools/cross_val.pyR1s0 (Rtstatsmodels.compat.pythonRRtnumpyRt itertoolsRtobjectRRRR"R0R1(((sBlib/python2.7/site-packages/statsmodels/sandbox/tools/cross_val.pyts 4<A;