baselines.py 文件源码

def KMeansAccuracy():
    clusterer = KMeans(n_clusters=2, n_init=30)
    tdm = pickle.load(open(DATASET_PATH + "BOW.p", "rb"))
    predictions = clusterer.fit_predict(tdm)
    true_labels = pickle.load(open(OUTFILE_STANCE, "rb"))[0]
    numerical_mapped_1 = [0 if i == "Israeli" else 1 for i in true_labels]
    numerical_mapped_2 = [1 if i == "Israeli" else 0 for i in true_labels]
    one = f1_score(numerical_mapped_1, predictions)
    two = f1_score(numerical_mapped_2, predictions)
    print("The F1 score of KMeans on BOW is: " + str(max(one, two)))

    clusterer = KMeans(n_clusters=2, n_init=30)
    predictions = clusterer.fit_predict(tdm)
    true_labels = pickle.load(open(OUTFILE_STANCE, "rb"))[0]
    accuracy = predict_accuracy(true_labels, predictions)
    print("The F1 score of KMeans on BOW (w/Tdidf) is: " + accuracy)