ClassficationBase.py 文件源码

def gmmRemovingOutlierForClassifier():
    """
    use GMM model to remove outlier
    :return: NA
    """
    # load data
    X_train = np.load('inputClf_small/X_train.npy')
    y_train = np.load('inputClf_small/y_train.npy')
    y_train_price = np.load('inputClf_small/y_train_price.npy')

    # classifier initialize
    classifier = GMM(n_components=2,covariance_type='full', init_params='wmc', n_iter=20)

    # cluster initializing
    X_train1 = X_train[np.where(y_train==0)[0], :]
    X_train2 = X_train[np.where(y_train==1)[0], :]
    cluster1 = KMeans(init='random', n_clusters=1, random_state=0).fit(X_train1)
    cluster1 = cluster1.cluster_centers_
    cluster2 = KMeans(init='random', n_clusters=1, random_state=0).fit(X_train2)
    cluster2 = cluster2.cluster_centers_
    clusters = np.concatenate((cluster1, cluster2), axis=0)

    classifier.means_ = clusters

    # Train the other parameters using the EM algorithm.
    classifier.fit(X_train)

    # predict
    y_train_pred = classifier.predict(X_train)
    train_accuracy = np.mean(y_train_pred.ravel() == y_train.ravel()) * 100
    print "Keep {}% data.".format(train_accuracy)


    # keep the data which are not outliers
    y_train_pred = y_train_pred.reshape((y_train_pred.shape[0], 1))
    X_train = X_train[np.where(y_train==y_train_pred)[0], :]
    y_train_price = y_train_price[np.where(y_train==y_train_pred)[0], :]
    y_train = y_train[np.where(y_train==y_train_pred)[0], :]
    np.save('inputClf_GMMOutlierRemoval/X_train', X_train)
    np.save('inputClf_GMMOutlierRemoval/y_train', y_train)
    np.save('inputClf_GMMOutlierRemoval/y_train_price', y_train_price)