modelData.py 文件源码

def get_bootstrapped_trainset(trainSet, y_train, bootstrap_data, es, estimator, th_bs):
    new_train_set = list(trainSet)
    new_y_train = list(y_train)

    trainAndBSData = trainSet + bootstrap_data

    generateDataDrivenFeats(trainSet, trainAndBSData, es)

    featurized = featurize(trainAndBSData)

    train_feats = [featurized[idx] for idx in range(0, len(trainSet), 1)]
    test_feats = [featurized[idx] for idx in range(len(trainSet), len(trainAndBSData), 1)]

    #Do feature selection on train data
    train_feats = fs.runFeatureSelection(train_feats, y_train, es)
    train_feats, y_train, train_bucket = ss.runSampleSelection(train_feats, y_train,[i for i in range(0, len(trainSet), 1)], es)

    # calculate Inter-annotator weighting. 
    weights_train = getWeights(trainAndBSData, train_bucket, es.weighInterAnnot)

    vectorizer = DictVectorizer()   
    x_train = vectorizer.fit_transform(train_feats)
    x_test = vectorizer.transform(test_feats)

    if es.scaleData:
        min_max_scalar = MinMaxScaler()
        x_train = min_max_scalar.fit_transform(x_train.toarray())
        x_test = min_max_scalar.transform(x_test.toarray())

    model = train(estimator, x_train, y_train, weights_train, model=None)

    y_pred_prob = model.predict_proba(x_test)
    for i, cur_y in enumerate(y_pred_prob):
        if np.max(cur_y) > th_bs:
            new_train_set.append(bootstrap_data[i])
            new_y_train.append(np.argmax(cur_y))

    return (new_train_set, new_y_train) #update none to confidence vector