M/Ph.dZddlmZddlZddlmZGddZGddZGd d Z Gd d Z d Z GddZ dS)a! 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 )lrangeN) combinationsc$eZdZdZdZdZdZdS) LeaveOneOutzs Leave-One-Out cross validation iterator: Provides train/test indexes to split data in train test sets c||_dS)a9 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)n)selfrs c/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/statsmodels/sandbox/tools/cross_val.py__init__zLeaveOneOut.__init__s2c#K|j}t|D]<}tj|t}d||<tj|}||fV=dSNdtypeT)rrangenpzerosbool logical_not)r ri test_index train_indexs r __iter__zLeaveOneOut.__iter__8sl Fq * *A(1D111J JqM.44Kz) ) ) ) )  * *r cDd|jj|jj|jfzSNz %s.%s(n=%i) __class__ __module____name__rr s r __repr__zLeaveOneOut.__repr__A( 9 $ 7 $ "" "r Nrr __qualname____doc__r rr!r r rrsK 8***"""""r rc$eZdZdZdZdZdZdS) LeavePOutzq Leave-P-Out cross validation iterator: Provides train/test indexes to split data in train test sets c"||_||_dS)aV Leave-P-Out cross validation iterator: Provides train/test indexes to split data in train test sets Parameters ---------- n: int Total number of elements p: int Size test sets Examples -------- >>> 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)rp)r rr*s r r zLeavePOut.__init__Ps8r c#K|j}|j}tt||}|D]N}t j|t }d|t j|<t j|}||fVOdSr) rr*rrrrrarrayr)r rr*combidxrrs r rzLeavePOut.__iter__ps F FF1IIq)) * *C!4000J(,Jrx}} %.44Kz) ) ) ) )  * *r cPd|jj|jj|j|jfzS)Nz%s.%s(n=%i, p=%i))rrrrr*r s r r!zLeavePOut.__repr__{." $ 9 $ 7 $ $ &"" "r Nr#r&r r r(r(JsL @***"""""r r(c$eZdZdZdZdZdZdS)KFoldzm K-Folds cross validation iterator: Provides train/test indexes to split data in train test sets c|dksJtd||ksJtd||fz||_||_dS)a K-Folds cross validation iterator: Provides train/test indexes to split data in train test sets Parameters ---------- n: int Total number of elements k: int number of folds Examples -------- >>> from scikits.learn import cross_val >>> X = [[1, 2], [3, 4], [1, 2], [3, 4]] >>> y = [1, 2, 3, 4] >>> kf = cross_val.KFold(4, k=2) >>> for train_index, test_index in kf: ... print "TRAIN:", train_index, "TEST:", test_index ... X_train, X_test, y_train, y_test = cross_val.split(train_index, test_index, X, y) TRAIN: [False False True True] TEST: [ True True False False] TRAIN: [ True True False False] TEST: [False False True True] Notes ----- All the folds have size trunc(n/k), the last one has the complementary rzcannot have k below 1z cannot have k=%d greater than %dN) ValueErrorrk)r rr5s r r zKFold.__init__sW8sssJ677ssssssJAAq6IJJsssr c#DK|j}|j}ttj||z }t |D][}tj|t}||dz krd|||z|dz|z<n d|||zd<tj|}||fV\dS)NrT) rr5intrceilrrrr)r rr5jrrrs r rzKFold.__iter__s F F !  q * *A(1D111J1uu*. 1Q3!Qw;''#' 1Q344 .44Kz) ) ) ) ) * *r cPd|jj|jj|j|jfzS)Nz%s.%s(n=%i, k=%i))rrrrr5r s r r!zKFold.__repr__r0r Nr#r&r r r2r2sL D * * *"""""r r2c$eZdZdZdZdZdZdS)LeaveOneLabelOutzy Leave-One-Label_Out cross-validation iterator: Provides train/test indexes to split data in train test sets c||_dS)a 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)labels)r r?s r r zLeaveOneLabelOut.__init__s> r c#Ktj|jd}tj|D]M}tjt |t }d|||k<tj|}||fVNdS)NT)copyr)rr,r?uniquerlenrr)r r?rrrs r rzLeaveOneLabelOut.__iter__s$+D1116"" * *A(3v;;d;;;J$(Jvqy !.44Kz) ) ) ) )  * *r cbd|jj|jj|jS)Nz{}.{}(labels={}))formatrrrr?r s r r!zLeaveOneLabelOut.__repr__s/!(( $ 9 $ 7 $ "" "r Nr#r&r r r=r=sL D***"""""r r=cg}|D]P}tj|}||}||}||||Q|S)zx For each arg return a train and test subsets defined by indexes provided in train_indexes and test_indexes )r asanyarrayappend) train_indexes test_indexesargsretarg arg_trainarg_tests r splitrPsg CmC   &  % 9 8 Jr c&eZdZdZddZdZdZdS) KStepAheadzn KStepAhead cross validation iterator: Provides fit/test indexes to split data in sequential sets r7NTc||_||_|$ttj|dz}||_||_||_dS)a= KStepAhead cross validation iterator: Provides train/test indexes to split data in train test sets Parameters ---------- n: int Total number of elements k : int number of steps ahead start : int initial size of data for fitting kall : bool if true. all values for up to k-step ahead are included in the test index. If false, then only the k-th step ahead value is returnd Notes ----- I do not think this is really useful, because it can be done with a very simple loop instead. Useful as a plugin, but it could return slices instead for faster array access. 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] Ng?)rr5r8rtruncstartkall return_slice)r rr5rUrVrWs r r zKStepAhead.__init__ sON =4(())E  (r c#K|j}|j}|j}|jrct |||z D]M}t d|d}|jrt |||z}nt ||zdz ||z}||fVNdSt |||z D]g}tj|t}d|d|<tj|t}|jr d||||z<nd|||zdz ||z<||fVhdS)Nr7rT) rr5rUrWrslicerVrrr) r rr5rUr train_slice test_slicerrs r rzKStepAhead.__iter__PsW F F    .5!A#&& . .#D!T22 93!&q!A#JJ!&qs1uac!2!2J!:-----  . .5!A#&& . .!x666 "& BQB hq555 91(,Jq1u%%,0Jqs1uQqSy)":----- . .r cDd|jj|jj|jfzSrrr s r r!zKStepAhead.__repr__kr"r )r7NTTr#r&r r rRrRsQ -)-)-)-)`...6"""""r rR) r%statsmodels.compat.pythonrnumpyr itertoolsrrr(r2r=rPrRr&r r r`s5  -,,,,,""""""/"/"/"/"/"/"/"/"h7"7"7"7"7"7"7"7"v="="="="="="="="B7"7"7"7"7"7"7"7"t   U"U"U"U"U"U"U"U"U"U"r