def test_cvbestsearchrefit_select_k_best(self):
list_C_value = range(2, 10, 1)
# print repr(list_C_value)
for C_value in list_C_value:
# C_value = 2
# print C_value
X, y = datasets.make_classification(n_samples=100, n_features=500, n_informative=5)
n_folds_nested = 2
# random_state = 0
k_values = [2, 3, 4, 5, 6]
key_y_pred = "y" + conf.SEP + conf.PREDICTION
# With EPAC
methods = Methods(*[Pipe(SelectKBest(k=k), SVC(C=C_value, kernel="linear")) for k in k_values])
wf = CVBestSearchRefitParallel(methods, n_folds=n_folds_nested)
wf.run(X=X, y=y)
r_epac = wf.reduce().values()[0]
# - Without EPAC
from sklearn.pipeline import Pipeline
r_sklearn = dict()
clf = Pipeline([("anova", SelectKBest(k=3)), ("svm", SVC(C=C_value, kernel="linear"))])
parameters = {"anova__k": k_values}
cv_nested = StratifiedKFold(y=y, n_folds=n_folds_nested)
gscv = grid_search.GridSearchCV(clf, parameters, cv=cv_nested)
gscv.fit(X, y)
r_sklearn[key_y_pred] = gscv.predict(X)
r_sklearn[conf.BEST_PARAMS] = gscv.best_params_
r_sklearn[conf.BEST_PARAMS]["k"] = r_sklearn[conf.BEST_PARAMS]["anova__k"]
# - Comparisons
comp = np.all(r_epac[key_y_pred] == r_sklearn[key_y_pred])
self.assertTrue(comp, u"Diff CVBestSearchRefitParallel: prediction")
for key_param in r_epac[conf.BEST_PARAMS][0]:
if key_param in r_sklearn[conf.BEST_PARAMS]:
comp = r_sklearn[conf.BEST_PARAMS][key_param] == r_epac[conf.BEST_PARAMS][0][key_param]
self.assertTrue(comp, u"Diff CVBestSearchRefitParallel: best parameters")
def test_cvbestsearchrefit(self):
X, y = datasets.make_classification(n_samples=12,
n_features=10,
n_informative=2)
n_folds_nested = 2
#random_state = 0
C_values = [.1, 0.5, 1, 2, 5]
kernels = ["linear", "rbf"]
key_y_pred = 'y' + conf.SEP + conf.PREDICTION
# With EPAC
methods = Methods(*[SVC(C=C, kernel=kernel)
for C in C_values for kernel in kernels])
wf = CVBestSearchRefitParallel(methods, n_folds=n_folds_nested)
wf.run(X=X, y=y)
r_epac = wf.reduce().values()[0]
# - Without EPAC
r_sklearn = dict()
clf = SVC(kernel="linear")
parameters = {'C': C_values, 'kernel': kernels}
cv_nested = StratifiedKFold(y=y, n_folds=n_folds_nested)
gscv = grid_search.GridSearchCV(clf, parameters, cv=cv_nested)
gscv.fit(X, y)
r_sklearn[key_y_pred] = gscv.predict(X)
r_sklearn[conf.BEST_PARAMS] = gscv.best_params_
# - Comparisons
comp = np.all(r_epac[key_y_pred] == r_sklearn[key_y_pred])
self.assertTrue(comp, u'Diff CVBestSearchRefitParallel: prediction')
for key_param in r_epac[conf.BEST_PARAMS][0]:
if key_param in r_sklearn[conf.BEST_PARAMS]:
comp = r_sklearn[conf.BEST_PARAMS][key_param] == \
r_epac[conf.BEST_PARAMS][0][key_param]
self.assertTrue(
comp,
u'Diff CVBestSearchRefitParallel: best parameters')
def test_cvbestsearchrefit(self):
X, y = datasets.make_classification(n_samples=12, n_features=10, n_informative=2)
n_folds_nested = 2
# random_state = 0
C_values = [0.1, 0.5, 1, 2, 5]
kernels = ["linear", "rbf"]
key_y_pred = "y" + conf.SEP + conf.PREDICTION
# With EPAC
methods = Methods(*[SVC(C=C, kernel=kernel) for C in C_values for kernel in kernels])
wf = CVBestSearchRefitParallel(methods, n_folds=n_folds_nested)
wf.run(X=X, y=y)
r_epac = wf.reduce().values()[0]
# - Without EPAC
r_sklearn = dict()
clf = SVC(kernel="linear")
parameters = {"C": C_values, "kernel": kernels}
cv_nested = StratifiedKFold(y=y, n_folds=n_folds_nested)
gscv = grid_search.GridSearchCV(clf, parameters, cv=cv_nested)
gscv.fit(X, y)
r_sklearn[key_y_pred] = gscv.predict(X)
r_sklearn[conf.BEST_PARAMS] = gscv.best_params_
# - Comparisons
comp = np.all(r_epac[key_y_pred] == r_sklearn[key_y_pred])
self.assertTrue(comp, u"Diff CVBestSearchRefitParallel: prediction")
for key_param in r_epac[conf.BEST_PARAMS][0]:
if key_param in r_sklearn[conf.BEST_PARAMS]:
comp = r_sklearn[conf.BEST_PARAMS][key_param] == r_epac[conf.BEST_PARAMS][0][key_param]
self.assertTrue(comp, u"Diff CVBestSearchRefitParallel: best parameters")
def test_cvbestsearchrefit_select_k_best(self):
list_C_value = range(2, 10, 1)
# print repr(list_C_value)
for C_value in list_C_value:
# C_value = 2
# print C_value
X, y = datasets.make_classification(n_samples=100,
n_features=500,
n_informative=5)
n_folds_nested = 2
#random_state = 0
k_values = [2, 3, 4, 5, 6]
key_y_pred = 'y' + conf.SEP + conf.PREDICTION
# With EPAC
methods = Methods(*[Pipe(SelectKBest(k=k),
SVC(C=C_value, kernel="linear"))
for k in k_values])
wf = CVBestSearchRefitParallel(methods, n_folds=n_folds_nested)
wf.run(X=X, y=y)
r_epac = wf.reduce().values()[0]
# - Without EPAC
from sklearn.pipeline import Pipeline
r_sklearn = dict()
clf = Pipeline([('anova', SelectKBest(k=3)),
('svm', SVC(C=C_value, kernel="linear"))])
parameters = {'anova__k': k_values}
cv_nested = StratifiedKFold(y=y, n_folds=n_folds_nested)
gscv = grid_search.GridSearchCV(clf, parameters, cv=cv_nested)
gscv.fit(X, y)
r_sklearn[key_y_pred] = gscv.predict(X)
r_sklearn[conf.BEST_PARAMS] = gscv.best_params_
r_sklearn[conf.BEST_PARAMS]['k'] = \
r_sklearn[conf.BEST_PARAMS]['anova__k']
# - Comparisons
comp = np.all(r_epac[key_y_pred] == r_sklearn[key_y_pred])
self.assertTrue(comp,
u'Diff CVBestSearchRefitParallel: prediction')
for key_param in r_epac[conf.BEST_PARAMS][0]:
if key_param in r_sklearn[conf.BEST_PARAMS]:
comp = r_sklearn[conf.BEST_PARAMS][key_param] == \
r_epac[conf.BEST_PARAMS][0][key_param]
self.assertTrue(
comp,
u'Diff CVBestSearchRefitParallel: best parameters')
def test_peristence_perm_cv_parmethods_pipe_vs_sklearn(self):
key_y_pred = 'y' + conf.SEP + conf.PREDICTION
X, y = datasets.make_classification(n_samples=12,
n_features=10,
n_informative=2)
n_folds_nested = 2
#random_state = 0
C_values = [.1, 0.5, 1, 2, 5]
kernels = ["linear", "rbf"]
# With EPAC
methods = Methods(
*[SVC(C=C, kernel=kernel) for C in C_values for kernel in kernels])
wf = CVBestSearchRefitParallel(methods, n_folds=n_folds_nested)
# Save workflow
# -------------
import tempfile
#store = StoreFs("/tmp/toto", clear=True)
store = StoreFs(tempfile.mktemp())
wf.save_tree(store=store)
wf = store.load()
wf.run(X=X, y=y)
## Save results
wf.save_tree(store=store)
wf = store.load()
r_epac = wf.reduce().values()[0]
# - Without EPAC
r_sklearn = dict()
clf = SVC(kernel="linear")
parameters = {'C': C_values, 'kernel': kernels}
cv_nested = StratifiedKFold(y=y, n_folds=n_folds_nested)
gscv = grid_search.GridSearchCV(clf, parameters, cv=cv_nested)
gscv.fit(X, y)
r_sklearn[key_y_pred] = gscv.predict(X)
r_sklearn[conf.BEST_PARAMS] = gscv.best_params_
r_sklearn[conf.BEST_PARAMS]['name'] = 'SVC'
# - Comparisons
comp = np.all(r_epac[key_y_pred] == r_sklearn[key_y_pred])
self.assertTrue(comp, u'Diff CVBestSearchRefitParallel: prediction')
comp = np.all([
r_epac[conf.BEST_PARAMS][0][p] == r_sklearn[conf.BEST_PARAMS][p]
for p in r_sklearn[conf.BEST_PARAMS]
])
self.assertTrue(comp,
u'Diff CVBestSearchRefitParallel: best parameters')
def test_cv_best_search_refit_parallel(self):
n_folds = 2
n_folds_nested = 3
k_values = [1, 2]
C_values = [1, 2]
n_samples = 500
n_features = 10000
n_cores = 2
X, y = datasets.make_classification(n_samples=n_samples,
n_features=n_features,
n_informative=5)
# epac workflow for paralle computing
pipelines = Methods(*[
Pipe(SelectKBest(
k=k), Methods(*[SVC(kernel="linear", C=C) for C in C_values]))
for k in k_values
])
pipeline = CVBestSearchRefitParallel(pipelines, n_folds=n_folds_nested)
wf = CV(pipeline, n_folds=n_folds)
sfw_engine = SomaWorkflowEngine(tree_root=wf,
num_processes=n_cores,
remove_finished_wf=False,
remove_local_tree=False)
sfw_engine_wf = sfw_engine.run(X=X, y=y)
# epac workflow for normal node computing
pipelines2 = Methods(*[
Pipe(SelectKBest(
k=k), Methods(*[SVC(kernel="linear", C=C) for C in C_values]))
for k in k_values
])
pipeline2 = CVBestSearchRefitParallel(pipelines2,
n_folds=n_folds_nested)
wf2 = CV(pipeline2, n_folds=n_folds)
wf2.run(X=X, y=y)
self.assertTrue(compare_two_node(sfw_engine_wf, wf2))
self.assertTrue(comp_2wf_reduce_res(sfw_engine_wf, wf2))
def get_workflow(self):
n_folds = 2
n_folds_nested = 3
k_values = [1, 2]
C_values = [1, 2]
pipelines = Methods(*[Pipe(SelectKBest(k=k),
Methods(*[SVC(kernel="linear", C=C)
for C in C_values]))
for k in k_values])
pipeline = CVBestSearchRefitParallel(pipelines,
n_folds=n_folds_nested)
wf = CV(pipeline, n_folds=n_folds)
return wf
def test_peristence_perm_cv_parmethods_pipe_vs_sklearn(self):
key_y_pred = 'y' + conf.SEP + conf.PREDICTION
X, y = datasets.make_classification(n_samples=12, n_features=10,
n_informative=2)
n_folds_nested = 2
#random_state = 0
C_values = [.1, 0.5, 1, 2, 5]
kernels = ["linear", "rbf"]
# With EPAC
methods = Methods(*[SVC(C=C, kernel=kernel)
for C in C_values for kernel in kernels])
wf = CVBestSearchRefitParallel(methods, n_folds=n_folds_nested)
# Save workflow
# -------------
import tempfile
#store = StoreFs("/tmp/toto", clear=True)
store = StoreFs(tempfile.mktemp())
wf.save_tree(store=store)
wf = store.load()
wf.run(X=X, y=y)
## Save results
wf.save_tree(store=store)
wf = store.load()
r_epac = wf.reduce().values()[0]
# - Without EPAC
r_sklearn = dict()
clf = SVC(kernel="linear")
parameters = {'C': C_values, 'kernel': kernels}
cv_nested = StratifiedKFold(y=y, n_folds=n_folds_nested)
gscv = grid_search.GridSearchCV(clf, parameters, cv=cv_nested)
gscv.fit(X, y)
r_sklearn[key_y_pred] = gscv.predict(X)
r_sklearn[conf.BEST_PARAMS] = gscv.best_params_
r_sklearn[conf.BEST_PARAMS]['name'] = 'SVC'
# - Comparisons
comp = np.all(r_epac[key_y_pred] == r_sklearn[key_y_pred])
self.assertTrue(comp, u'Diff CVBestSearchRefitParallel: prediction')
comp = np.all([r_epac[conf.BEST_PARAMS][0][p] ==
r_sklearn[conf.BEST_PARAMS][p]
for p in r_sklearn[conf.BEST_PARAMS]])
self.assertTrue(comp,
u'Diff CVBestSearchRefitParallel: best parameters')
def test_peristence_load_and_fit_predict(self):
X, y = datasets.make_classification(n_samples=20,
n_features=10,
n_informative=2)
n_folds = 2
n_folds_nested = 3
k_values = [1, 2]
C_values = [1, 2]
pipelines = Methods(*[
Pipe(SelectKBest(
k=k), Methods(*[SVC(kernel="linear", C=C) for C in C_values]))
for k in k_values
])
pipeline = CVBestSearchRefitParallel(pipelines, n_folds=n_folds_nested)
tree_mem = CV(pipeline,
n_folds=n_folds,
reducer=ClassificationReport(keep=False))
# Save Tree
import tempfile
store = StoreFs(dirpath=tempfile.mkdtemp(), clear=True)
tree_mem.save_tree(store=store)
tree_mem.run(X=X, y=y)
res_mem = tree_mem.reduce().values()[0]
# Reload Tree
tree_fs_noresults = store.load()
tree_fs_noresults.run(X=X, y=y)
res_fs_noresults = tree_fs_noresults.reduce().values()[0]
# Save with results
tree_fs_noresults.save_tree(store=store)
tree_fs_withresults = store.load()
res_fs_withresults = tree_fs_withresults.reduce().values()[0]
# Compare
comp = np.all([
np.all(np.asarray(res_mem[k]) == np.asarray(res_fs_noresults[k]))
and np.all(
np.asarray(res_fs_noresults[k]) == np.asarray(
res_fs_withresults[k])) for k in res_mem
])
self.assertTrue(comp)
def get_workflow(self, n_features=int(1E03)):
random_state = 0
C_values = [1, 10]
k_values = 0
k_max = "auto"
n_folds_nested = 5
n_folds = 10
n_perms = 10
if k_max != "auto":
k_values = range_log2(np.minimum(int(k_max), n_features),
add_n=True)
else:
k_values = range_log2(n_features, add_n=True)
cls = Methods(*[Pipe(SelectKBest(k=k), SVC(C=C, kernel="linear"))
for C in C_values
for k in k_values])
pipeline = CVBestSearchRefitParallel(cls,
n_folds=n_folds_nested,
random_state=random_state)
wf = Perms(CV(pipeline, n_folds=n_folds),
n_perms=n_perms,
permute="y",
random_state=random_state)
return wf