Lab -- Publicly Accessible Datasets | Submission Template¶

import pandas as pd

def do_openml():
  # Use url hacking to get a direct download url from the OpenML page for the dataset.
  
  # For this lab, do _not_ use sklearn's fetch_openml(). 
  # The generalization described in the lab doc does _not work_ consistently.
  # But I'm leaving it as-is because the purpose of this is to teach you url hacking.
  df = pd.read_csv()
  return df
do_openml()

def do_github():
  # Upload the dataset to a github repository, and use a direct download link for it below
  
  df = pd.read_csv()
  return df
do_github()

def do_cloud_storage():
  # Upload the phish_url dataset to one of the following cloud storage providers:
  # * Google Drive
  # * Dropbox
  #
  # Use url hacking to get a direct download link for it, and use it below.
  df = pd.read_csv()
  return df
do_cloud_storage()

def do_gcp():
  # Create a public GCP bucket, and upload the dataset to it. 
  # Use a direct download link to load the file below.
  df = pd.read_csv()
  return df
do_gcp()

def do_aws():
  # Create a public aws s3 bucket, and upload the dataset to it. 
  # Use a direct download link to load the file below.
  df = pd.read_csv()
  return df
do_aws()