#! /usr/bin/env python3
#
import os
import tarfile
from six.moves import urllib

DOWNLOAD_ROOT = "https://raw.githubusercontent.com/ageron/handson-ml/master/"
HOUSING_PATH = os.path.join ( "datasets", "housing" )
HOUSING_URL = DOWNLOAD_ROOT + "datasets/housing/housing.tgz"

def housing_data_fetch ( housing_url = HOUSING_URL, housing_path = HOUSING_PATH ):

#*****************************************************************************80
#
## housing_data_fetch() retrieves a specific data file.
#
#  Licensing:
#
#    This code is distributed under the MIT license.
#
#  Modified:
#
#    01 October 2021
#
#  Author:
#
#    Aurelien Geron
#    Modifications by John Burkardt
#
#  Reference:
#
#    Aurelien Geron,
#    Hands-on Machine Learning with Scikit-Learn and TensorFlow,
#    OReilly, 2017,
#    ISBN13: 978-1-491-96229-9
#
#  Input:
#
#    string housing_url, the URL for the data file.
#
#    string housing_path, the local directory where the data file should
#    be stored.
#
  import platform
  import sklearn

  print ( "" )
  print ( "housing_data_fetch():" )
  print ( '  python version: %s' % ( platform.python_version ( ) ) )
  print ( '  scikit-learn version is %s' % ( sklearn.__version__ ) )
  print ( "  Retrieve housing datafile from github." )
#
#  Create the local directory for the data, if it doesn't already exist.
#
  if ( not os.path.isdir ( housing_path ) ):
    print ( "" )
    print ( "Creating dataset subdirectory", housing_path )
    os.makedirs ( housing_path )
  else:
    print ( "" )
    print ( "Dataset subdirectory", housing_path, "already exists." )
#
#  Construct the full name of the dataset to be downloaded.
#
  tgz_path = os.path.join ( housing_path, "housing.tgz" )
#
#  Send the request for the dataset.
#
  urllib.request.urlretrieve ( housing_url, tgz_path )
#
#  Create a TAR file to hold the dataset.
#
  housing_tgz = tarfile.open ( tgz_path )
#
#  Once the dataset has been copied, extract it from the TAR file.
#
  housing_tgz.extractall ( path = housing_path )
#
#  Close the TAR file.
#
  housing_tgz.close ( )
#
#  Terminate.
#
  print ( "" )
  print ( "housing_data_fetch():" )
  print ( "  Normal end of execution." )

  return

def timestamp ( ):

#*****************************************************************************80
#
## timestamp() prints the date as a timestamp.
#
#  Licensing:
#
#    This code is distributed under the MIT license. 
#
#  Modified:
#
#    21 August 2019
#
#  Author:
#
#    John Burkardt
#
  import time

  t = time.time ( )
  print ( time.ctime ( t ) )

  return

if ( __name__ == '__main__' ):
  timestamp ( )
  housing_data_fetch ( )
  timestamp ( )