e8115b9d2ea60e3d7757f79fb028f778698f00fa,plasma/models/shallow_runner.py,,train,#Any#Any#Any#Any#,170

Before Change

    print("Total data: {} samples, {} positive".format(len(X),np.sum(Y > 0)))
    max_samples = 100000
    num_samples = min(max_samples,len(Y))
    indices = np.random.choice(np.array(range(len(Y))),num_samples,replace=False)
    X = X[indices]
    Y = Y[indices]
    
    print("fitting on {} samples, {} positive".format(len(X),np.sum(Y > 0)))

After 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()))

    sample_prob = conf["data"]["shallow_sample_prob"]
    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 = sample_prob)
    Xv,Yv,_ = feature_extractor.load_shots(shot_list_validate,sample_prob = sample_prob)

Instances