30f8696647af482f34e88661c43bf373b84a8da5,plasma/models/shallow_runner.py,,train,#Any#Any#Any#Any#,158

Before Change

    print("validate: {} shots, {} disruptive".format(len(shot_list_validate),shot_list_validate.num_disruptive()))
    print("training: {} shots, {} disruptive".format(len(shot_list_train),shot_list_train.num_disruptive()))

    if not os.path.isfile(dataset_path):
        feature_extractor = FeatureExtractor(loader)
        shot_list_train = shot_list_train.random_sublist(debug_use_shots)
        X,Y = feature_extractor.load_shots(shot_list_train,sample_prob = 1.0)
        np.savez(dataset_path,X=X,Y=Y)
    else:
        print("dataset exists.")
        dat = np.load(dataset_path)
        X = dat["X"]
        Y = dat["Y"]
    print("Total data: {} samples, {} positive".format(len(X),np.sum(Y > 0)))
    max_samples = 40000
    num_samples = min(max_samples,len(Y))
    indices = np.random.choice(np.array(range(len(Y))),num_samples,replace=False)

After Change

    feature_extractor = FeatureExtractor(loader)
    shot_list_train = shot_list_train.random_sublist(debug_use_shots)
    X,Y,_ = feature_extractor.load_shots(shot_list_train,sample_prob = 1.0)
    Xv,Yv,_ = feature_extractor.load_shots(shot_list_validate,sample_prob = 1.0)
    X = np.concatenate(X,axis=0)
    Y = np.concatenate(Y,axis=0)
    Xv = np.concatenate(Xv,axis=0)

Instances