def calculate_params_for_d_score(classifier, experiment):
score = classifier.score(experiment, True)
experiment.set_and_rerank("classifier_score", score)
td_scores = experiment.get_top_decoy_peaks()["classifier_score"]
mu, nu = mean_and_std_dev(td_scores)
return mu, nu
def calculate_params_for_d_score(classifier, experiment):
score = classifier.score(experiment, True)
experiment.set_and_rerank("classifier_score", score)
td_scores = experiment.get_top_decoy_peaks()["classifier_score"]
mu, nu = mean_and_std_dev(td_scores)
return mu, nu
def learn_randomized(self, experiment):
assert isinstance(experiment, Experiment)
num_iter = CONFIG.get("semi_supervised_learner.num_iter")
logging.info("start learn_randomized")
fraction = CONFIG.get("xeval.fraction")
is_test = CONFIG.get("is_test")
experiment.split_for_xval(fraction, is_test)
train = experiment.get_train_peaks()
train.rank_by("main_score")
params, clf_scores = self.start_semi_supervised_learning(train)
train.set_and_rerank("classifier_score", clf_scores)
# semi supervised iteration:
for inner in range(num_iter):
params, clf_scores = self.iter_semi_supervised_learning(train)
train.set_and_rerank("classifier_score", clf_scores)
# after semi supervised iteration: classify full dataset
clf_scores = self.score(experiment, params)
mu, nu = mean_and_std_dev(clf_scores)
experiment.set_and_rerank("classifier_score", clf_scores)
td_scores = experiment.get_top_decoy_peaks()["classifier_score"]
mu, nu = mean_and_std_dev(td_scores)
experiment["classifier_score"] = (experiment["classifier_score"] -
mu) / nu
experiment.rank_by("classifier_score")
top_test_peaks = experiment.get_top_test_peaks()
top_test_target_scores = top_test_peaks.get_target_peaks(
)["classifier_score"]
top_test_decoy_scores = top_test_peaks.get_decoy_peaks(
)["classifier_score"]
logging.info("end learn_randomized")
return top_test_target_scores, top_test_decoy_scores, params
def calculate_params_for_d_score(self, classifier, experiment):
score = classifier.score(experiment, True)
experiment.set_and_rerank("classifier_score", score)
if (CONFIG.get("final_statistics.fdr_all_pg")):
td_scores = experiment.get_decoy_peaks()["classifier_score"]
else:
td_scores = experiment.get_top_decoy_peaks()["classifier_score"]
mu, nu = mean_and_std_dev(td_scores)
return mu, nu, score
def calculate_params_for_d_score(classifier, experiment):
score = classifier.score(experiment, True)
experiment.set_and_rerank("classifier_score", score)
if (CONFIG.get("final_statistics.fdr_all_pg")):
td_scores = experiment.get_decoy_peaks()["classifier_score"]
else:
td_scores = experiment.get_top_decoy_peaks()["classifier_score"]
mu, nu = mean_and_std_dev(td_scores)
return mu, nu
def learn_randomized(self, experiment):
assert isinstance(experiment, Experiment)
num_iter = CONFIG.get("semi_supervised_learner.num_iter")
logging.info("start learn_randomized")
fraction = CONFIG.get("xeval.fraction")
is_test = CONFIG.get("is_test")
experiment.split_for_xval(fraction, is_test)
train = experiment.get_train_peaks()
train.rank_by("main_score")
params, clf_scores = self.start_semi_supervised_learning(train)
train.set_and_rerank("classifier_score", clf_scores)
# semi supervised iteration:
for inner in range(num_iter):
params, clf_scores = self.iter_semi_supervised_learning(train)
train.set_and_rerank("classifier_score", clf_scores)
# after semi supervised iteration: classify full dataset
clf_scores = self.score(experiment, params)
mu, nu = mean_and_std_dev(clf_scores)
experiment.set_and_rerank("classifier_score", clf_scores)
td_scores = experiment.get_top_decoy_peaks()["classifier_score"]
mu, nu = mean_and_std_dev(td_scores)
experiment["classifier_score"] = (experiment["classifier_score"] - mu) / nu
experiment.rank_by("classifier_score")
top_test_peaks = experiment.get_top_test_peaks()
top_test_target_scores = top_test_peaks.get_target_peaks()["classifier_score"]
top_test_decoy_scores = top_test_peaks.get_decoy_peaks()["classifier_score"]
logging.info("end learn_randomized")
return top_test_target_scores, top_test_decoy_scores, params
def pvalues(self, target_scores, decoy_scores): #print "LOG NORMAL NULL MODEL:" corr = - np.min(decoy_scores) + 0.0001 mu, nu = mean_and_std_dev(np.log(decoy_scores + corr)) #print mu, nu, np.min(decoy_scores) return 1.0 - pnorm(np.log(target_scores + corr), mu, nu)
def pvalues(self, target_scores, decoy_scores): mu, nu = mean_and_std_dev(decoy_scores) return 1.0 - pnorm(target_scores, mu, nu)