How to use datasets.fetch_mldata() in sklearn?

Question

I am trying to run the following code for a brief machine learning algorithm:

import re
import argparse
import csv
from collections import Counter
from sklea         


        

Answer 1

Apart from what @szymon has mentioned you can alternatively load dataset using:

from six.moves import urllib
from sklearn.datasets import fetch_mldata

from scipy.io import loadmat
mnist_alternative_url = "https://github.com/amplab/datascience-sp14/raw/master/lab7/mldata/mnist-original.mat"
mnist_path = "./mnist-original.mat"
response = urllib.request.urlopen(mnist_alternative_url)
with open(mnist_path, "wb") as f:
    content = response.read()
    f.write(content)
mnist_raw = loadmat(mnist_path)
mnist = {
    "data": mnist_raw["data"].T,
    "target": mnist_raw["label"][0],
    "COL_NAMES": ["label", "data"],
    "DESCR": "mldata.org dataset: mnist-original",
}

Answer 2

I experienced the same issue and found different file size of mnist-original.mat at different times while I use my poor WiFi. I switched to LAN and it works fine. It maybe the issue of networking.

Answer 3

If you didn't give the data_home, program look the ${yourprojectpath}/mldata/minist-original.mat you can download the program and put the file the correct path

Answer 4

Try it like this:

dataDict = fetch_mldata('MNIST original')

This worked for me. Since you used the from ... import ... syntax, you shouldn't prepend datasets when you use it

Answer 5

I also had this problem in the past. It is due to the dataset is quite large (about 55.4 mb), I run the "fetch_mldata" but because of the internet connection, it took awhile to download them all. I did not know and interrupt the process.

The dataset is corrupted and that why the error happened.