96416b889c76f3b6d15af0e3dfd0d4cb2b8b2d23,examples/paillier_logistic_regression.py,,download_data,#,40

Before Change

        // Second folder -> test set
        print("Downloading 2/2:", url2)
        with urlopen(url2) as remotedata:
            with open(foldertar, "wb") as tar:
                tar.write(remotedata.read())

        with tarfile.open(foldertar) as tar:

After Change

    n_datasets = 2

    for d in range(1, n_datasets):
        if not os.path.isdir("examples/enron%d" % d):

            print("Downloading %d/%d:" % (d, n_datasets), url1)
            foldertar = "examples/emails.tar.gz"

            with urlopen(url1) as remotedata:
                with open(foldertar, "wb") as tar:
                    tar.write(remotedata.read())

            with tarfile.open(foldertar) as tar:
                tar.extractall("examples/")
            os.remove(foldertar)


def preprocess_data():
    
    Get the Enron emails from disk.
    Represent them as bag-of-words.

Instances