Google Prediction Script for KDD Cup 2008 Breast Cancer (PredicSis API vs Google Prediction)

gistfile1.py

# -*- coding: utf-8 -*-
#
# Copyright (C) 2013 Google Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#      http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""Command-line skeleton application for Prediction API.
Usage:
  $ python score.py

You can also get help on all the command-line flags the program understands
by running:

  $ python score.py --help

"""

import argparse
import pprint
import httplib2
import os
import sys
import json
import time
import errno
import socket
import threading
import thread

from apiclient import discovery
from oauth2client import file
from oauth2client import client
from oauth2client import tools

# Parser for command-line arguments.
parser = argparse.ArgumentParser(
    description=__doc__,
    formatter_class=argparse.RawDescriptionHelpFormatter,
    parents=[tools.argparser])

parser.add_argument('input_file', help='Local path of csv input data (ex test.csv)')
parser.add_argument('output_file', help='Local path of csv output data (ex result.csv)')


# CLIENT_SECRETS is name of a file containing the OAuth 2.0 information for this
# application, including client_id and client_secret. You can see the Client ID
# and Client secret on the APIs page in the Cloud Console:
# <https://cloud.google.com/console#/project/55732917986/apiui>
CLIENT_SECRETS = os.path.join(os.path.dirname(__file__), 'client_secrets.json')

# Set up a Flow object to be used for authentication.
# Add one or more of the following scopes. PLEASE ONLY ADD THE SCOPES YOU
# NEED. For more information on using scopes please see
# <https://developers.google.com/+/best-practices>.
FLOW = client.flow_from_clientsecrets(CLIENT_SECRETS,
  scope=[
      'https://www.googleapis.com/auth/devstorage.full_control',
      'https://www.googleapis.com/auth/devstorage.read_only',
      'https://www.googleapis.com/auth/devstorage.read_write',
      'https://www.googleapis.com/auth/prediction',
    ],
    message=tools.message_if_missing(CLIENT_SECRETS))

def print_header(line):
  '''Format and print header block sized to length of line'''
  header_str = '='
  header_line = header_str * len(line)
  print '\n' + header_line
  print line
  print header_line

class Printdot(threading.Thread): 
  def __init__(self, nom = ''): 
    threading.Thread.__init__(self) 
    self.nom = nom 
    self._stopevent = threading.Event()
  def run(self):
    while not self._stopevent.isSet():
      sys.stdout.flush()
      sys.stdout.write('.')
      time.sleep(1)
  def stop(self):
      self._stopevent.set()
  
def main(argv):
  # Parse the command-line flags.
  flags = parser.parse_args(argv[1:])

  # If the credentials don't exist or are invalid run through the native client
  # flow. The Storage object will ensure that if successful the good
  # credentials will get written back to the file.
  storage = file.Storage('sample.dat')
  credentials = storage.get()
  if credentials is None or credentials.invalid:
    credentials = tools.run_flow(FLOW, storage, flags)

  # Create an httplib2.Http object to handle our HTTP requests and authorize it
  # with our good Credentials.
  http = httplib2.Http()
  http = credentials.authorize(http)

  # Construct the service object for the interacting with the Prediction API.
  service = discovery.build('prediction', 'v1.6', http=http)

  try:
    prj = 'YOUR_PROJECT_ID'
    papi = service.trainedmodels()
   
    print """
	  ____                   _           ____               _ _      _   _             
	 / ___| ___   ___   __ _| | ___     |  _ \ _ __ ___  __| (_) ___| |_(_) ___  _ __  
	| |  _ / _ \ / _ \ / _` | |/ _ \\    | |_) | '__/ _ \/ _` | |/ __| __| |/ _ \| '_ \ 
	| |_| | (_) | (_) | (_| | |  __/    |  __/| | |  __/ (_| | | (__| |_| | (_) | | | |
	 \____|\___/ \___/ \__, |_|\___|    |_|   |_|  \___|\__,_|_|\___|\__|_|\___/|_| |_|
	                   |___/                                                           """ 

    print '\n' + "Data source: http://www.sigkdd.org/kdd-cup-2008-breast-cancer"
    print '\n' + "Building model"
    start_model = time.time()
    thrd = Printdot()
    thrd.start()
    	
    model_body = { 'id': 'YOUR_ID', 'storageDataLocation': 'genesys/kdd_2008_breast_cancer_train.txt' }
    model = papi.insert(project=prj,body=model_body).execute()

    model = papi.get(project=prj, id='YOUR_ID').execute()
    while (model['trainingStatus'] ==  'RUNNING'):
        time.sleep(1)
        model = papi.get(project=prj, id='YOUR_ID').execute()

    thrd.stop()
    end_model = time.time()
    print '\n' + "Completed in %.2f seconds" % (end_model - start_model) + '\n'


    # Make a prediction using the newly trained model.
    print 'Generating predictions'
    fin = open(flags.input_file, 'r')
    fout = open(flags.output_file, 'w')
    nbLines = 0
    start_predictions = time.time()
    thrd = Printdot()
    thrd.start()

    try:
        for line in fin:
      	    lineItems = line.split('\n')[0].replace('"','').split(',')
    	    body = {'input': {'csvInstance': lineItems[1:]}}
    	    result = papi.predict(project=prj, id='YOUR_ID', body=body).execute()
   	    scoreOui = next(score['score'] for score in result['outputMulti'] if score['label'] =='True')
    	    scoreNon = next(score['score'] for score in result['outputMulti'] if score['label'] =='False')
    	    fout.write(scoreOui+','+scoreNon+'\n')
    	nbLines+=1
    	if not nbLines%10:
   	    fout.flush()
    	    os.fsync(fout)
    except socket.error, v:
    	errorcode=v[0]
   	print 'error code '+errorcode+''

    thrd.stop()
    end_predictions = time.time()
    print '\n' + "Completed in %.2f seconds" % (end_predictions - start_predictions) + '\n'
    print "Google Prediction terminated in %.2f seconds" % (end_predictions - start_model) + '\n'

  except client.AccessTokenRefreshError:
    print ("The credentials have been revoked or expired, please re-run"
      "the application to re-authorize")

if __name__ == '__main__':
  main(sys.argv)