# train
training_features = np.column_stack(
(den_training, eig_0_training, eig_1_training, eig_2_training, log_mass))
print(training_features.shape)
cv = True
third_features = int((training_features.shape[1] - 1) / 3)
param_grid = {
"n_estimators": [1000, 1300, 1600],
"max_features": [third_features, "sqrt", 25, 40],
"min_samples_leaf": [5, 15],
#"criterion": ["mse", "mae"],
}
clf = ml.MLAlgorithm(training_features,
method="regression",
cross_validation=cv,
split_data_method=None,
n_jobs=60,
save=True,
path=saving_path + "classifier/classifier.pkl",
param_grid=param_grid)
if cv is True:
print(clf.best_estimator)
print(clf.algorithm.best_params_)
print(clf.algorithm.best_score_)
np.save(saving_path + "f_imp.npy", clf.feature_importances)
features_training = np.load(
"/home/lls/mlhalos_code/stored_files/50k_features.npy")
features_training = np.column_stack(
(features_training[:, :-1], features_training[:,
-1], features_training[:,
-1]))
features_test = np.load(
"/home/lls/mlhalos_code/stored_files/features_test.npy")
features_test = np.column_stack(
(features_test[:, :-1], features_test[:, -1], features_test[:, -1]))
# train algorithm
algo = ml.MLAlgorithm(features_training,
split_data_method=None,
cross_validation=False,
num_cv_folds=10,
n_jobs=22)
# predict probabilities
pred = algo.classifier.predict(features_test[:, :-1])
true = features_test[:, -1]
np.save(
"/home/lls/mlhalos_code/stored_files/true_label_feature/predicted_probabilities.npy",
pred)
np.save(
"/home/lls/mlhalos_code/stored_files/true_label_feature/true_labels.npy",
true)
min_halo = 0
max_halo = 400
min_mass = ic_all.halo[max_halo]['mass'].sum()
max_mass = ic_all.halo[min_halo]['mass'].sum()
ic = parameters.InitialConditionsParameters(min_halo_number=min_halo,
max_halo_number=max_halo,
min_mass_scale=min_mass,
max_mass_scale=max_mass)
feat_w_EPS = features.extract_labeled_features(initial_parameters=ic,
add_EPS_label=True,
n_samples=50000)
# Train the algorithm
algorithm_50k = ml.MLAlgorithm(features_training)
np.save('/Users/lls/Documents/CODE/stored_files/all_out/train_set_x.npy',
algorithm_50k.X_train)
np.save('/Users/lls/Documents/CODE/stored_files/all_out/test_set_x.npy',
algorithm_50k.X_test)
np.save('/Users/lls/Documents/CODE/stored_files/all_out/train_set_y.npy',
algorithm_50k.y_train)
np.save('/Users/lls/Documents/CODE/stored_files/all_out/test_set_y.npy',
algorithm_50k.y_true)
# Make predictions on all particles other than the training set
features_left = features_full_mass[~np.in1d(np.arange(len(features_full_mass)
), index_training)]
predicted_probabilities = algorithm_50k.classifier.predict_proba(
testing_ind = np.load("/share/data1/lls/regression/50k_testing_ids.npy")
except IOError:
print("Generating training/testing indices and saving")
training_ind = np.random.choice(len(traj), 50000)
np.save("/share/data1/lls/regression/50k_training_ids.npy", training_ind)
testing_ind = np.arange(len(traj))[~np.in1d(range(len(traj)), training_ind)]
np.save("/share/data1/lls/regression/50k_testing_ids.npy", testing_ind)
feat_training = np.column_stack((traj[training_ind], halo_mass[training_ind]))
X_test = traj[testing_ind]
y_test = halo_mass[testing_ind]
del traj
del halo_mass
cv = True
path_clf="/share/data1/lls/regression/CV/classifier/classifier.pkl"
clf = ml.MLAlgorithm(feat_training, method="regression", split_data_method=None, n_jobs=60, save=True,
cross_validation=cv, path=path_clf)
if cv is True:
print(clf.best_estimator)
print(clf.algorithm.best_params_)
print(clf.algorithm.best_score_)
np.save("/share/data1/lls/regression/CV/f_imp.npy", clf.feature_importances)
y_predicted = clf.algorithm.predict(X_test)
np.save("/share/data1/lls/regression/CV/predicted_halo_mass.npy", y_predicted)
np.save("/share/data1/lls/regression/CV/true_halo_mass.npy", y_test)
training_ind)
testing_ind = np.arange(
len(traj))[~np.in1d(range(len(traj)), training_ind)]
np.save("/share/data1/lls/try_classifier/50k_testing_ids.npy",
training_ind)
feat_training = np.column_stack(
(traj[training_ind], true_labels[training_ind]))
# X_test = traj[testing_ind]
# y_test = halo_mass[testing_ind]
del traj
del true_labels
clf = ml.MLAlgorithm(
feat_training,
method="classification",
split_data_method=None,
n_jobs=60,
save=True,
path="/share/data1/lls/regression/try_classifier/classifier.pkl")
print(clf.best_estimator)
print(clf.algorithm.best_params_)
print(clf.algorithm.best_score_)
np.save("/share/data1/lls/regression/try_classifier/f_imp.npy",
clf.feature_importances)
# y_predicted = clf.algorithm.predict(X_test)
# np.save("/share/data1/lls/regression/predicted_halo_mass.npy", y_predicted)
# np.save("/share/data1/lls/regression/true_halo_mass.npy", y_test)
import sys
sys.path.append("/home/lls/mlhalos_code/scripts")
import numpy as np
from mlhalos import machinelearning as ml
density_shear_features = np.load("/home/lls/stored_files/shear_and_density/density_shear_features.npy")
aucs = np.zeros((10, 2))
for i in range(10):
index_training_i = np.random.choice(range(len(density_shear_features)), 100000)
features = density_shear_features[index_training_i]
trained_algo = ml.MLAlgorithm(features, split_data_method="train_test_split", train_size=50000, n_jobs=60)
print(trained_algo.classifier.best_params_)
auc_validation = trained_algo.classifier.best_score_
auc_test = ml.get_auc_score(trained_algo.predicted_proba_test, trained_algo.true_label_test)
aucs[i, 0] = auc_validation
aucs[i, 1] = auc_test
np.save("/home/lls/stored_files/shear_and_density/aucs_val_test.npy", aucs)
(den_features[training_ind], eig_0[training_ind],
class_labels[training_ind]))
# X_test = np.column_stack((den_features[testing_ids], eig_0[testing_ids]))
cv = True
param_grid = {
"n_estimators": [800, 1000, 1300],
"max_features": ["auto", 0.4],
"min_samples_leaf": [15, 5],
"criterion": ["gini", "entropy"]
}
clf = ml.MLAlgorithm(feat_training,
method="classification",
cross_validation=cv,
split_data_method=None,
n_jobs=60,
save=True,
param_grid=param_grid,
path=saving_path + "classifier/classifier.pkl")
if cv is True:
print(clf.best_estimator)
print(clf.algorithm.best_params_)
print(clf.algorithm.best_score_)
np.save(saving_path + "f_imp.npy", clf.feature_importances)
# classify
clf = joblib.load(saving_path + "classifier/classifier.pkl")
testing_ids = np.load(saving_path + "testing_ids.npy")
X_test = np.column_stack((den_features[testing_ids], eig_0[testing_ids]))
density_shear_features = np.load(
"/home/lls/stored_files/shear_and_density/density_shear_features.npy")
index_training = np.load("/home/lls/stored_files/50k_features_index.npy")
training_den_shear_features = density_shear_features[index_training, :]
np.save(
"/home/lls/stored_files/shear_and_density/training_density_shear_features.npy",
training_den_shear_features)
# train only on density+prolateness
training_features = np.column_stack(
(training_den_shear_features[:, :50], training_den_shear_features[:,
100:]))
trained_algo = ml.MLAlgorithm(
training_features,
split_data_method=None,
n_jobs=60,
save=True,
path=
"/home/lls/stored_files/shear_and_density/den+prol/classifier/classifier.pkl"
)
print(trained_algo.classifier.best_score_)
print(trained_algo.classifier.best_estimator_)
print(trained_algo.classifier.best_params_)
np.save(
"/home/lls/stored_files/shear_and_density/den+prol/feature_importances.npy",
trained_algo.feature_importances)
# for i in range(50):
# plt.hist(training_den_shear_features[np.where(training_den_shear_features[:,-1]==1)[0], i], label="in",
# normed=True, histtype="step", bins=30)
# plt.hist(training_den_shear_features[np.where(training_den_shear_features[:, -1] == -1)[0], i], label="out",
# normed=True, histtype="step", bins=30)
# plt.xlabel("feature " + str(i))
# plt.legend(loc="best")
# plt.savefig("/Users/lls/Documents/CODE/stored_files/all_out/distributions_50k/feature_" + str(i) +".pdf")
# plt.clf()
# training_den_shear_features = np.column_stack((training_den_shear_features[:,50:100], training_den_shear_features[:,
# -1]))
trained_algo = ml.MLAlgorithm(
training_den_shear_features,
cross_validation=True,
split_data_method=None,
n_jobs=60,
save=True,
path=
"/home/lls/stored_files/shear_and_density/full_eigenvalues/not_rescaled/"
"classifier/classifier.pkl")
print(trained_algo.classifier.best_score_)
print(trained_algo.classifier.best_estimator_)
print(trained_algo.classifier.best_params_)
np.save(
"/home/lls/stored_files/shear_and_density/full_eigenvalues/not_rescaled/feature_importances.npy",
trained_algo.feature_importances)
def train_algorithm(features):
trained_algorithm = ml.MLAlgorithm(features)
return trained_algorithm
"""
This should be done on hypatia.
"""
import numpy as np
from mlhalos import machinelearning as ml
# load training and test features with EPS label as feature
features_training = np.load("/home/lls/mlhalos_code/stored_files/with_EPS_label/50k_features_w_EPS_label.npy")
features_test = np.load("/home/lls/mlhalos_code/stored_files/with_EPS_label/features_w_EPS_test.npy")
# train algorithm
algo = ml.MLAlgorithm(features_training, split_data_method=None, num_cv_folds=10, n_jobs=22)
# predict probabilities
pred = algo.classifier.predict_proba(features_test[:, :-1])
true = features_test[:, -1]
np.save("/home/lls/mlhalos_code/stored_files/with_EPS_label/predicted_probabilities.npy", pred)
np.save("/home/lls/mlhalos_code/stored_files/with_EPS_label/true_labels.npy", true)
# save classifier details
f_imp = algo.classifier.best_estimator_.feature_importances_
np.save("/home/lls/mlhalos_code/stored_files/with_EPS_label/feature_importances.npy", f_imp)
def find_predicted_and_true_labels(trained_algorithm, features):
predicted_probabilities = trained_algorithm.algorithm.predict_proba(
features[:, :-1])
true_labels = features[:, -1]
return predicted_probabilities, true_labels
######################## SCRIPT ########################
if __name__ == "__main__":
# Train the algorithm
features_training = load_features(features_type="training")
trained_classifier = ml.MLAlgorithm(features_training)
# Make predictions on all particles other than the training set
test_features = load_features(features_type="test")
predicted_probabilities, true_labels = find_predicted_and_true_labels(
trained_classifier, test_features)
np.save(
'/Users/lls/Documents/CODE/stored_files/all_out/predicted_probabilities.npy',
predicted_probabilities)
np.save('/Users/lls/Documents/CODE/stored_files/all_out/true_labels.npy',
true_labels)
# # Plot feature importance
#
traj = np.load(
"/share/data1/lls/shear_quantities/quantities_id_ordered/density_trajectories.npy"
)
feat_training = np.column_stack((traj[training_ind], halo_mass[training_ind]))
X_test = traj[testing_ind]
del traj
del halo_mass
cv = False
clf = ml.MLAlgorithm(
feat_training,
method="regression",
cross_validation=cv,
split_data_method=None,
n_jobs=60,
save=True,
path=
"/share/data1/lls/regression/balanced_training_set/classifier/classifier.pkl"
)
if cv is True:
print(clf.best_estimator)
print(clf.algorithm.best_params_)
print(clf.algorithm.best_score_)
np.save("/share/data1/lls/regression/balanced_training_set/f_imp.npy",
clf.feature_importances)
# classify
y_predicted = clf.algorithm.predict(X_test)
features_all)
#### TRAINING #####
# Select 50,000 particles to use as training set
index_training = np.random.choice(len(features_all), size=50000, replace=False)
features_training = features_all[index_training]
np.save("/home/lls/stored_files/non_rescaled/features_training_index.npy",
index_training)
np.save("/home/lls/stored_files/non_rescaled/50k_features_training.npy",
features_training)
# Train the algorithm
RF = ml.MLAlgorithm(features_training, split_data_method=None, n_jobs=24)
#### PREDICT PROBABILITIES ON REMAINING PARTICLES IN THE BOX ######
features_left = features_all[~np.in1d(np.arange(len(features_all)
), index_training)]
predicted_probabilities = RF.classifier.predict_proba(features_left[:, :-1])
true_labels = features_left[:, -1]
np.save('/home/lls/stored_files/non_rescaled/pred_proba_features_left.npy',
predicted_probabilities)
np.save('/home/lls/stored_files/non_rescaled/rue_labels_features_left.npy',
true_labels)
#### EPS PREDICTIONS ON REMAINING PARTICLES IN THE BOX ######
training_features = np.column_stack(
(den_training, eig_0_training, log_mass))
print(training_features.shape)
cv = True
third_features = int((training_features.shape[1] - 1) / 3)
param_grid = {
"n_estimators": [1000, 1300],
"max_features": [third_features, "sqrt", 5, 10],
"min_samples_leaf": [5, 15],
# "criterion": ["mse", "mae"],
}
clf = ml.MLAlgorithm(training_features,
method="regression",
cross_validation=cv,
split_data_method=None,
n_jobs=60,
param_grid=param_grid)
if cv is True:
print(clf.best_estimator)
print(clf.algorithm.best_params_)
print(clf.algorithm.best_score_)
np.save(saving_path + "f_imp_" + str(i) + ".npy",
clf.feature_importances)
f_imp_all[i] = clf.feature_importances
np.save(saving_path + "f_imp_all.npy", f_imp_all)
import sys
sys.path.append("/Users/lls/Documents/mlhalos_code/")
import numpy as np
from mlhalos import machinelearning as ml
traj = np.load("/Users/lls/Documents/mlhalos_files/stored_files/shear/shear_quantities/density_trajectories.npy")
halo_mass = np.load("/Users/lls/Documents/mlhalos_files/stored_files/halo_mass_particles.npy")
training_ind = np.random.choice(len(traj), 50000)
feat_training = np.column_stack((traj[training_ind], halo_mass[training_ind]))
clf = ml.MLAlgorithm(feat_training, method="regression", split_data_method=None)
print(clf.best_estimator)
print(clf.algorithm.best_params_)
print(clf.algorithm.best_score_)
