In [2]:

    

import os
from boto.s3.connection import S3Connection
from boto.s3.key import Key
import h2o
import numpy as np
import pandas as pd
from tabulate import tabulate
# initialize the model scoring server
h2o.init(nthreads=2,max_mem_size=2, start_h2o=True)


    

    




Checking whether there is an H2O instance running at http://localhost:54321..... not found.
Attempting to start a local H2O server...
  Java Version: openjdk version "1.8.0_121"; OpenJDK Runtime Environment (build 1.8.0_121-8u121-b13-0ubuntu1.16.04.2-b13); OpenJDK 64-Bit Server VM (build 25.121-b13, mixed mode)
  Starting server from /usr/local/lib/python2.7/dist-packages/h2o/backend/bin/h2o.jar
  Ice root: /tmp/tmp6YJ23Y
  JVM stdout: /tmp/tmp6YJ23Y/h2o_unknownUser_started_from_python.out
  JVM stderr: /tmp/tmp6YJ23Y/h2o_unknownUser_started_from_python.err
  Server is running at http://127.0.0.1:54321
Connecting to H2O server at http://127.0.0.1:54321... successful.






    





H2O cluster uptime:
02 secs
H2O cluster version:
3.10.4.5
H2O cluster version age:
7 days, 22 hours and 17 minutes 
H2O cluster name:
H2O_from_python_unknownUser_whjscj
H2O cluster total nodes:
1
H2O cluster free memory:
1.778 Gb
H2O cluster total cores:
8
H2O cluster allowed cores:
2
H2O cluster status:
accepting new members, healthy
H2O connection url:
http://127.0.0.1:54321
H2O connection proxy:
None
H2O internal security:
False
Python version:
2.7.12 final

In [3]:

    

# function to get files from s3
def pull_file_from_s3(key):
    def get_bucket():            
        access= os.environ['SECRET_ENV_AWS_ACCESS_KEY_BRETT'] 
        secret= os.environ['SECRET_ENV_AWS_SECRET_KEY_BRETT']
        customer = 'demonstration'
        conn = S3Connection(access,secret)
        b = conn.get_bucket('dsclouddata',validate=False)
        return b

    s3_bucket = get_bucket()
    payload = s3_bucket.get_key(key)
    local_file = payload.get_contents_to_filename(key)
    return key

    
# download the model from s3
downloaded_model = pull_file_from_s3('gbm_grid_binomial_model_1')


    

In [54]:

    

def churn_predict(State,AccountLength,AreaCode,Phone,IntlPlan,VMailPlan,VMailMessage,DayMins,DayCalls,DayCharge,EveMins,EveCalls,EveCharge,NightMins,NightCalls,NightCharge,IntlMins,IntlCalls,IntlCharge,CustServCalls):
    # connect to the model scoring service
    h2o.connect(verbose=False)

    # open the downloaded model
    ChurnPredictor = h2o.load_model(path=downloaded_model)  

    # define a feature vector to evaluate with the model
    newData = pd.DataFrame({'State' : State,
                            'Account Length' : AccountLength,
                            'Area Code' : AreaCode,
                            'Phone' : Phone,
                            'Int\'l Plan' : IntlPlan,
                            'VMail Plan' : VMailPlan,
                            'VMail Message' : VMailMessage,
                            'Day Mins' : DayMins,
                            'Day Calls' : DayCalls,
                            'Day Charge' : DayCharge,
                            'Eve Mins' : EveMins,
                            'Eve Calls' : EveCalls,
                            'Eve Charge' : EveCharge,
                            'Night Mins' : NightMins,
                            'Night Calls' : NightCalls,
                            'Night Charge' : NightCharge,
                            'Intl Mins' :IntlMins,
                            'Intl Calls' : IntlCalls,
                            'Intl Charge' : IntlCharge,
                            'CustServ Calls' : CustServCalls}, index=[0])
    
    # evaluate the feature vector using the model
    predictions = ChurnPredictor.predict(h2o.H2OFrame(newData))
    predictionsOut = h2o.as_list(predictions, use_pandas=False)    
    print tabulate(predictionsOut, tablefmt="pipe")
    prediction = predictionsOut[1][0]
    probabilityChurn = predictionsOut[1][1]
    probabilityRetain = predictionsOut[1][2]
    return "Prediction: " + str(prediction) + " |Probability to Churn: " + str(probabilityChurn) + " |Probability to Retain: " + str(probabilityRetain)


    

In [56]:

    

State = "KS"
AccountLength = 1 
AreaCode = 213
Phone = "362-1234"
IntlPlan = "no"
VMailPlan = "no"
VMailMessage = 0
DayMins = 0
DayCalls = 2
DayCharge = 20
EveMins = 120
EveCalls = 97
EveCharge = 7
NightMins = 2
NightCalls = 7
NightCharge = 10
IntlMins = 13
IntlCalls = 0
IntlCharge = 3.67
CustServCalls = 0
    

churn_predict(State,AccountLength,AreaCode,Phone,IntlPlan,VMailPlan,VMailMessage,DayMins,DayCalls,DayCharge,EveMins,EveCalls,EveCharge,NightMins,NightCalls,NightCharge,IntlMins,IntlCalls,IntlCharge,CustServCalls)


    

    




Parse progress: |█████████████████████████████████████████████████████████| 100%
gbm prediction progress: |████████████████████████████████████████████████| 100%
|:--------|:---------------------|:-------------------|
| predict | Churn                | Retain             |
| Retain  | 0.027787091253621388 | 0.9722129087463786 |






    
Out[56]:





'Prediction: Retain |Probability to Churn: 0.027787091253621388 |Probability to Retain: 0.9722129087463786'