def do_all(options):
if options.k_max != "auto":
k_values = range_log2(np.minimum(int(options.k_max),
options.n_features),
add_n=True)
else:
k_values = range_log2(options.n_features, add_n=True)
C_values = [1, 10]
random_state = 0
#print options
#sys.exit(0)
if options.trace:
from epac import conf
conf.TRACE_TOPDOWN = True
## 1) Build dataset
## ================
X, y = datasets.make_classification(n_samples=options.n_samples,
n_features=options.n_features,
n_informative=options.n_informative)
## 2) Build Workflow
## =================
time_start = time.time()
## CV + Grid search of a pipeline with a nested grid search
cls = Methods(*[
Pipe(SelectKBest(k=k), SVC(kernel="linear", C=C)) for C in C_values
for k in k_values
])
pipeline = CVBestSearchRefit(cls,
n_folds=options.n_folds_nested,
random_state=random_state)
wf = Perms(CV(pipeline, n_folds=options.n_folds),
n_perms=options.n_perms,
permute="y",
random_state=random_state)
print "Time ellapsed, tree construction:", time.time() - time_start
## 3) Run Workflow
## ===============
time_fit_predict = time.time()
wf.run(X=X, y=y)
print "Time ellapsed, fit predict:", time.time() - time_fit_predict
time_reduce = time.time()
## 4) Reduce Workflow
## ==================
print wf.reduce()
print "Time ellapsed, reduce:", time.time() - time_reduce
def do_all(options):
if options.k_max != "auto":
k_values = range_log2(np.minimum(int(options.k_max),
options.n_features), add_n=True)
else:
k_values = range_log2(options.n_features, add_n=True)
C_values = [1, 10]
random_state = 0
#print options
#sys.exit(0)
if options.trace:
from epac import conf
conf.TRACE_TOPDOWN = True
## 1) Build dataset
## ================
X, y = datasets.make_classification(n_samples=options.n_samples,
n_features=options.n_features,
n_informative=options.n_informative)
## 2) Build Workflow
## =================
time_start = time.time()
## CV + Grid search of a pipeline with a nested grid search
cls = Methods(*[Pipe(SelectKBest(k=k),
SVC(kernel="linear", C=C))
for C in C_values
for k in k_values])
pipeline = CVBestSearchRefit(cls,
n_folds=options.n_folds_nested,
random_state=random_state)
wf = Perms(CV(pipeline, n_folds=options.n_folds),
n_perms=options.n_perms,
permute="y",
random_state=random_state)
print "Time ellapsed, tree construction:", time.time() - time_start
## 3) Run Workflow
## ===============
time_fit_predict = time.time()
wf.run(X=X, y=y)
print "Time ellapsed, fit predict:", time.time() - time_fit_predict
time_reduce = time.time()
## 4) Reduce Workflow
## ==================
print wf.reduce()
print "Time ellapsed, reduce:", time.time() - time_reduce
def test_perm_cv(self):
X, y = datasets.make_classification(n_samples=20,
n_features=5,
n_informative=2)
n_perms = 3
n_folds = 2
rnd = 0
# = With EPAC
wf = Perms(CV(SVC(kernel="linear"),
n_folds=n_folds,
reducer=ClassificationReport(keep=True)),
n_perms=n_perms,
permute="y",
random_state=rnd,
reducer=None)
r_epac = wf.run(X=X, y=y)
# = With SKLEARN
from sklearn.cross_validation import StratifiedKFold
clf = SVC(kernel="linear")
r_sklearn = [[None] * n_folds for i in xrange(n_perms)]
perm_nb = 0
for perm in Permutations(n=y.shape[0],
n_perms=n_perms,
random_state=rnd):
y_p = y[perm]
fold_nb = 0
for idx_train, idx_test in StratifiedKFold(y=y_p, n_folds=n_folds):
X_train = X[idx_train, :]
X_test = X[idx_test, :]
y_p_train = y_p[idx_train, :]
clf.fit(X_train, y_p_train)
r_sklearn[perm_nb][fold_nb] = clf.predict(X_test)
fold_nb += 1
perm_nb += 1
cmp_key = 'y' + conf.SEP + conf.TEST + conf.SEP + conf.PREDICTION
# Comparison
for iperm in range(n_perms):
for icv in range(n_folds):
comp = np.all(
np.asarray(r_epac[iperm][icv][cmp_key]) == np.asarray(
r_sklearn[iperm][icv]))
self.assertTrue(comp, u'Diff Perm / CV: EPAC vs sklearn')
# test reduce
for iperm in range(n_perms):
for icv in range(n_folds):
## iperm = 0
## icv = 0
comp = np.all(
np.asarray(wf.reduce().values()[iperm][cmp_key][icv]) ==
np.asarray(r_sklearn[iperm][icv]))
self.assertTrue(comp, u'Diff Perm / CV: EPAC reduce')
def test_perm_cv(self):
X, y = datasets.make_classification(n_samples=20, n_features=5,
n_informative=2)
n_perms = 3
n_folds = 2
rnd = 0
# = With EPAC
wf = Perms(CV(SVC(kernel="linear"), n_folds=n_folds,
reducer=ClassificationReport(keep=True)),
n_perms=n_perms, permute="y",
random_state=rnd, reducer=None)
r_epac = wf.run(X=X, y=y)
# = With SKLEARN
from sklearn.cross_validation import StratifiedKFold
clf = SVC(kernel="linear")
r_sklearn = [[None] * n_folds for i in xrange(n_perms)]
perm_nb = 0
for perm in Permutations(n=y.shape[0], n_perms=n_perms,
random_state=rnd):
y_p = y[perm]
fold_nb = 0
for idx_train, idx_test in StratifiedKFold(y=y_p,
n_folds=n_folds):
X_train = X[idx_train, :]
X_test = X[idx_test, :]
y_p_train = y_p[idx_train, :]
clf.fit(X_train, y_p_train)
r_sklearn[perm_nb][fold_nb] = clf.predict(X_test)
fold_nb += 1
perm_nb += 1
cmp_key = 'y' + conf.SEP + conf.TEST + conf.SEP + conf.PREDICTION
# Comparison
for iperm in range(n_perms):
for icv in range(n_folds):
comp = np.all(
np.asarray(r_epac[iperm][icv][cmp_key]) ==
np.asarray(r_sklearn[iperm][icv])
)
self.assertTrue(comp, u'Diff Perm / CV: EPAC vs sklearn')
# test reduce
for iperm in range(n_perms):
for icv in range(n_folds):
## iperm = 0
## icv = 0
comp = np.all(
np.asarray(wf.reduce().values()[iperm][cmp_key][icv])
==
np.asarray(r_sklearn[iperm][icv])
)
self.assertTrue(comp, u'Diff Perm / CV: EPAC reduce')
# -*- coding: utf-8 -*-
"""
Created on Thu May 23 15:21:35 2013
@author: ed203246
"""
from sklearn import datasets
from sklearn.svm import LinearSVC as SVM
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA
from sklearn.feature_selection import SelectKBest
from epac.map_reduce.reducers import PvalPerms
import numpy
X, y = datasets.make_classification(n_samples=100,
n_features=200,
n_informative=2)
X = numpy.random.rand(*X.shape)
from epac import Perms, CV, Methods
perms_cv_svm = Perms(CV(Methods(SVM(loss="l1"), SVM(loss="l2"))), n_perms=100)
perms_cv_svm.run(X=X, y=y)
perms_cv_svm.reduce()
self = perms_cv_svm
key = 'LinearSVC(loss=l1)'
self = PvalPerms()
# -*- coding: utf-8 -*- """ Created on Thu May 23 15:21:35 2013 @author: ed203246 """ from sklearn import datasets from sklearn.svm import LinearSVC as SVM from sklearn.lda import LDA from sklearn.feature_selection import SelectKBest X, y = datasets.make_classification(n_samples=100, n_features=200, n_informative=2) X = numpy.random.rand(*X.shape) from epac import Perms, CV, Methods perms_cv_svm = Perms(CV(Methods(SVM(loss="l1"), SVM(loss="l2"))), n_perms=100) perms_cv_svm.run(X=X, y=y) perms_cv_svm.reduce() self = perms_cv_svm key = "LinearSVC(loss=l1)" self = PvalPerms()
