import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
import pickle
import tabpy_client
# Connect to TabPy server using the client library
connection = tabpy_client.Client('http://localhost:9004/')
# load the model from disk
def tableau_classifier(arg2,arg3,arg4,arg5,arg6,arg7,arg8,arg9):
inputs_df = pd.DataFrame(
{
'Perf-Low': arg2,
'Perf-Mid': arg3,
'Perf-Mid-High': arg4,
'Perf-Undet': arg5,
'Ven-Low': arg6,
'Ven-Mid': arg7,
'Ven-Mid-High': arg8,
'Ven-Undet': arg9
}
)
loaded_model = pickle.load(open('/Users/arturoroman/Desktop/Udemy/lr_model.sav', 'rb'))
return loaded_model.predict(inputs_df).tolist()
# Publish the tableau_classifier function to TabPy server so it can be used from Tableau
# Using the name DiagnosticsDemo and a short description of what it does
connection.deploy('EventCalssifier',
import tabpy_client
from tabpy.tabpy_tools.client import Client
client = tabpy_client.Client('http://localhost:9004/')
def fraud_predictor5(_arg1, _arg2, _arg3):
import pandas as pd
row = {
'shipping': _arg1,
'shipping scheduled': _arg2,
'country_str': _arg3
}
#Convert it into a dataframe
test_data = pd.DataFrame(data=row, index=[0])
from sklearn import preprocessing
le = preprocessing.LabelEncoder()
test_data['country_str'] = le.fit_transform(test_data['country_str'])
#Predict the Fraud
predprob_survival = random_forest.predict_proba(test_data)
#Return only the probability
return [probability[1] for probability in predprob_survival]
def late_delivery(_arg1, _arg2):
import pandas as pd
row = {'shipping scheduled': _arg1, 'country_str': _arg2}
#Convert it into a dataframe
test_data = pd.DataFrame(data=row, index=[0])
from sklearn import preprocessing
le = preprocessing.LabelEncoder()
test_data['country_str'] = le.fit_transform(test_data['country_str'])
import tabpy_client
client = tabpy_client.Client('http://127.0.0.1:9004')
def external_services_say_hello(message, service):
import requests
if service == 'PYTHON':
r = requests.post('http://127.0.0.1:5000/python_says_hello',
data={'message': message})
elif service == 'R':
r = requests.post('http://127.0.0.1:6313/r_says_hello',
data={
'message': message,
})
serviceResult = r.json()
return serviceResult['result']
client.deploy('external_services_say_hello',
external_services_say_hello,
'Make Python or R say Hello or anything you want.',
override=True)
print('*** Model deployed successfully ***')
import Algorithmia
import tabpy_client
ALGORITHMIA_API_KEY = 'YOUR_API_KEY' #algorithmia.com/user#credentials
TABPY_SERVER_URL = 'http://localhost:9004/'
DEBUG = True
def algorithmia(algorithm_name, input):
if DEBUG: print("algorithm: %sinput: %s\n" % (algorithm_name, input))
try:
client = Algorithmia.client(ALGORITHMIA_API_KEY)
algo = client.algo(algorithm_name)
result = algo.pipe(input).result
except Exception as x:
if DEBUG: print(x)
raise Exception(str(x))
if DEBUG: print("result: %s" % result)
return result
tabpy_conn = tabpy_client.Client(TABPY_SERVER_URL)
tabpy_conn.deploy(
'algorithmia',
algorithmia,
'Run a function on Algorithmia: algorithmia(algorithm_name, input)',
override=True)