def func_memm_local():
print "memm_local pt1"
## 1) Build a dataset and convert to np.memmap (for big matrix)
## ============================================================
X, y = datasets.make_classification(n_samples=500,
n_features=5000,
n_informative=2,
random_state=1)
print "memm_local pt2"
X = convert2memmap(X)
y = convert2memmap(y)
Xy = dict(X=X, y=y)
## 2) Build two workflows respectively
## =======================================================
print "memm_local pt3"
from sklearn.svm import SVC
from epac import CV, Methods
cv_svm_local = CV(Methods(*[SVC(kernel="linear"),
SVC(kernel="rbf")]),
n_folds=3)
print "memm_local pt4"
# from epac import LocalEngine
# local_engine = LocalEngine(cv_svm_local, num_processes=2)
# cv_svm = local_engine.run(**Xy)
cv_svm_local.run(**Xy)
print cv_svm_local.reduce()
print "memm_local pt5"
def func_memm_local():
print("memm_local pt1")
## 1) Build a dataset and convert to np.memmap (for big matrix)
## ============================================================
X, y = datasets.make_classification(n_samples=500,
n_features=5000,
n_informative=2,
random_state=1)
print("memm_local pt2")
X = convert2memmap(X)
y = convert2memmap(y)
Xy = dict(X=X, y=y)
## 2) Build two workflows respectively
## =======================================================
print("memm_local pt3")
from sklearn.svm import SVC
from epac import CV, Methods
cv_svm_local = CV(Methods(*[SVC(
kernel="linear"), SVC(kernel="rbf")]),
n_folds=3)
print("memm_local pt4")
# from epac import LocalEngine
# local_engine = LocalEngine(cv_svm_local, num_processes=2)
# cv_svm = local_engine.run(**Xy)
cv_svm_local.run(**Xy)
print(cv_svm_local.reduce())
print("memm_local pt5")
def test_mem():
X, y = datasets.make_classification(n_samples=2000,
n_features=10000,
n_informative=2,
random_state=1)
# f = open("/home/jinpeng/x.log", "w")
# pickle.dump(X, f) # =>> 474 MB
# f.close()
# np.savez ("/home/jinpeng/np_x.log", dict(X=X)) # ===> 160 MB
cv_svm = CV(Methods(*[SVC(kernel="linear"), SVC(kernel="rbf")]),
n_folds=10)
cv_svm.run(X=X, y=y) # Top-down process: computing recognition rates, etc.
# local_engine = LocalEngine(cv_svm, num_processes=2)
# cv_svm = local_engine.run(X=X, y=y)
print cv_svm.reduce() # Bottom-up process: computing p-values, etc.
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 = CVBestSearchRefit(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 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 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 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))
# difference between input agrument of fit and predict. The true y will also figure
# in the result with key "y/true"
class MySVM:
def __init__(self, C=1.0):
self.C = C
def fit(self, X, y):
from sklearn.svm import SVC
self.svc = SVC(C=self.C)
self.svc.fit(X, y)
def predict(self, X):
return self.svc.predict(X)
svms = Methods(MySVM(C=1.0), MySVM(C=2.0))
cv = CV(svms, cv_key="y", cv_type="stratified", n_folds=2,
reducer=None)
cv.run(X=X, y=y) # top-down process to call transform
cv.reduce() # buttom-up process
from sklearn.decomposition import PCA
class MyPCA(PCA):
"""PCA with predict method"""
def predict(self, X):
"""Project to X PCs then project back to original space
If X is not singular, self.fit(X).predict(X) == X"""
return np.dot(self.transform(X), self.components_) + self.mean_
pcas = Methods(MyPCA(n_components=1), MyPCA(n_components=2))
cv = CV(pcas, n_folds=2, reducer=None)
cv.run(X=X, y=y) # top-down process to call transform
cv.reduce() # buttom-up process
Xd.CB_EXPO[Xd.CB_EXPO == 0] = -1
X = np.asarray(Xd)
y = np.asarray(yd)
C_values = [0.01, 0.05, .1, .5, 1, 5, 10]
# SVM L1
# ======
svms = Methods(*[
SVM(dual=False, class_weight='auto', penalty="l1", C=C) for C in C_values
])
cv = CV(svms, cv_type="stratified", n_folds=10)
cv.run(X=X, y=y)
cv_results = cv.reduce()
#print cv_results
epac.export_csv(
cv, cv_results,
os.path.join(WD, "results", "cv10_caarms+pas+canabis_svmsl1.csv"))
# SVM L1 with CVBestSearchRefit
# =============================
svms_cv = CVBestSearchRefit(svms, n_folds=10, cv_type="stratified")
cv = CV(svms_cv, cv_type="stratified", n_folds=10)
cv.run(X=X, y=y)
cv_results = cv.reduce()
print cv_results
from epac import Pipe, Methods, CV, Perms
from epac import ClassificationReport, PvalPerms
from epac import StoreFs
from epac import CVBestSearchRefit
from epac.sklearn_plugins import Permutations
from epac.configuration import conf
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 = CVBestSearchRefit(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)
tree_mem.reduce()
#k_values = [1, 2, 3, 4, 5, 10, 15, 20, 25, 27]
C_values = [0.01, 0.05, .1, .5, 1, 5, 10]
# SVM L1
# ======
svms = Methods(*[SVM(dual=False, class_weight='auto', penalty="l1", C=C) for C in C_values])
#
#anova_svms = Methods(*[Pipe(SelectKBest(k=k), #preprocessing.StandardScaler(),
# Methods(*[SVM(C=C, penalty=penalty, class_weight='auto', dual=False) for C in C_values for penalty in ['l1', 'l2']])) for k in k_values])
cv = CV(svms, cv_type="stratified", n_folds=10)
cv.run(X=X, y=y)
cv_results = cv.reduce()
#print cv_results
epac.export_csv(cv, cv_results, os.path.join(WD, "results", "cv10_svmsl1.csv"))
# SVM L1 with CVBestSearchRefit
# =============================
svms_cv = CVBestSearchRefit(svms, n_folds=10)
cv = CV(svms_cv, cv_type="stratified", n_folds=10)
cv.run(X=X, y=y)
cv_results = cv.reduce()
print cv_results
#[{'key': CVBestSearchRefit, 'y/test/score_f1': [ 0.84848485 0.76190476], 'y/test/recall_pvalues': [ 0.01086887 0.03000108], 'y/test/score_precision': [ 0.82352941 0.8 ], 'y/test/recall_mean_pvalue': 0.00592461228371, 'y/test/score_recall': [ 0.875 0.72727273], 'y/test/score_accuracy': 0.814814814815, 'y/test/score_recall_mean': 0.801136363636}])
#
anovas_svm.run(X=X, y=y) print(anovas_svm.reduce()) # Cross-validation # ---------------- # CV of LDA # CV (Splitter) # / | \ # 0 1 2 Folds (Slicer) # | | # Methods (Splitter) # / \ # LDA SVM Classifier (Estimator) from epac import CV, Methods cv = CV(Methods(LDA(), SVM())) cv.run(X=X, y=y) print(cv.reduce()) # Model selection using CV # ------------------------ # CVBestSearchRefit # Methods (Splitter) # / \ # SVM(C=1) SVM(C=10) Classifier (Estimator) from epac import Pipe, CVBestSearchRefit, Methods # CV + Grid search of a simple classifier wf = CVBestSearchRefit(Methods(SVM(C=1), SVM(C=10))) wf.run(X=X, y=y) print(wf.reduce()) # Feature selection combined with SVM and LDA
print anovas_svm.reduce() # Cross-validation # ---------------- # CV of LDA # CV (Splitter) # / | \ # 0 1 2 Folds (Slicer) # | | # Methods (Splitter) # / \ # LDA SVM Classifier (Estimator) from epac import CV, Methods cv = CV(Methods(LDA(), SVM())) cv.run(X=X, y=y) print cv.reduce() # Model selection using CV # ------------------------ # CVBestSearchRefit # Methods (Splitter) # / \ # SVM(C=1) SVM(C=10) Classifier (Estimator) from epac import Pipe, CVBestSearchRefit, Methods # CV + Grid search of a simple classifier wf = CVBestSearchRefit(Methods(SVM(C=1), SVM(C=10))) wf.run(X=X, y=y) print wf.reduce()
