def recursive_feature_elimination(config_learning, config_data, number_features):
output = open(os.path.expanduser(config_data.get("Learner", "models")) + "/" + "feature_ranks.txt", "w")
feature_names = FeatureExtractor.get_combinations_from_config_file_unsorted(config_data)
x_train = read_features_file(config_learning.get('x_train'), '\t')
y_train = read_reference_file(config_learning.get('y_train'), '\t')
x_test = read_features_file(config_learning.get('x_test'), '\t')
estimator, scorers = learn_model.set_learning_method(config_learning, x_train, y_train)
scale = config_learning.get("scale", True)
if scale:
x_train, x_test = scale_datasets(x_train, x_test)
rfe = RFE(estimator, number_features, step=1)
rfe.fit(x_train, y_train)
for i, name in enumerate(feature_names):
output.write(name + "\t" + str(rfe.ranking_[i]) + "\n")
print(name + "\t" + str(rfe.ranking_[i]))
predictions = rfe.predict(x_test)
output.close()
return predictions
def test_learn_to_rank_coefficients(config_learning, config):
x_train = read_features_file(config_learning.get('x_train'), '\t')
x_test = read_features_file(config_learning.get('x_test'), '\t')
scale = config_learning.get("scale", True)
if scale:
x_train, x_test = scale_datasets(x_train, x_test)
learner = config_learning.get("learning", None)
method_name = learner.get("method", None)
estimator = joblib.load(os.path.expanduser(config.get('Learner', 'models')) + '/' + method_name + '.pkl')
coefficients = estimator.coef_[0]
predictions = []
for instance in x_test:
result = 0.0
for k, val in enumerate(instance):
result += val * coefficients[k]
predictions.append(result)
return predictions
def test_learn_to_rank(config_learning, config):
x_train = read_features_file(config_learning.get('x_train'), '\t')
x_test = read_features_file(config_learning.get('x_test'), '\t')
scale = config_learning.get("scale", True)
if scale:
x_train, x_test = scale_datasets(x_train, x_test)
learner = config_learning.get("learning", None)
method_name = learner.get("method", None)
estimator = joblib.load(os.path.expanduser(config.get('Learner', 'models')) + '/' + method_name + '.pkl')
return [x[0] for x in estimator.predict_proba(x_test)]
def train_save(config_learning, config_data):
learning_config = config_learning.get("learning", None)
method_name = learning_config.get("method", None)
x_train = read_features_file(config_learning.get('x_train'), '\t')
y_train = read_reference_file(config_learning.get('y_train'), '\t')
x_test = read_features_file(config_learning.get('x_test'), '\t')
scale = config_learning.get("scale", True)
if scale:
x_train, x_test = scale_datasets(x_train, x_test)
estimator, scorers = learn_model.set_learning_method(config_learning, x_train, y_train)
estimator.fit(x_train, y_train)
joblib.dump(estimator, os.path.expanduser(config_data.get('Learner', 'models')) + '/' + method_name + '.pkl')
def load_predict(config_learning, config_data):
learning_config = config_learning.get("learning", None)
method_name = learning_config.get("method", None)
x_train = read_features_file(config_learning.get('x_train'), '\t')
y_train = read_reference_file(config_learning.get('y_train'), '\t')
x_test = read_features_file(config_learning.get('x_test'), '\t')
y_test = read_reference_file(config_learning.get('y_test'), '\t')
scale = config_learning.get("scale", True)
if scale:
x_train, x_test = scale_datasets(x_train, x_test)
estimator = joblib.load(os.path.expanduser(config_data.get("Learner", "models")) + "/" + method_name + ".pkl")
predictions = estimator.predict(x_test)
return predictions
def recursive_feature_elimination_cv(config_learning, config_data):
output = open(os.path.expanduser(config_data.get("Learner", "models")) + "/" + "feature_ranks.txt", "w")
feature_names = FeatureExtractor.get_features_from_config_file_unsorted(config_data)
combination_methods = FeatureExtractor.get_combinations_from_config_file_unsorted(config_data)
x_train = read_features_file(config_learning.get('x_train'), '\t')
y_train = read_reference_file(config_learning.get('y_train'), '\t')
x_test = read_features_file(config_learning.get('x_test'), '\t')
estimator, scorers = learn_model.set_learning_method(config_learning, x_train, y_train)
scale = config_learning.get("scale", True)
if scale:
x_train, x_test = scale_datasets(x_train, x_test)
rfecv = RFECV(estimator=estimator, step=1, cv=StratifiedKFold(y_train, 2), scoring='accuracy')
rfecv.fit(x_train, y_train)
feature_list = []
for i, feature_name in enumerate(feature_names):
if combination_methods[i] == 'both':
feature_list.append(feature_name)
feature_list.append(feature_name)
else:
feature_list.append(feature_name)
for i, name in enumerate(feature_list):
output.write(name + "\t" + str(rfecv.ranking_[i]) + "\n")
output.close()
predictions = rfecv.predict(x_test)
return predictions
