def training(data):
print('inside controller')
# removing rows with label values
data = data.dropna(subset=[label])
tabclient = Client(tabpy_serverurl)
# dataframe to json
input_data = json.loads(data.to_json(orient='records'))
returnResult = tabclient.query('RapidMiner_Train', go_url, go_username, go_password, input_data, label,cost_matrix,high_value,low_value,selection_criteria, max_min_crietria_selector, platform)
final_out = json_normalize(returnResult['response'])
return final_out
def quick_training(training_data):
# removing rows with label values
training_data = training_data.dropna(subset=[label])
tabclient = Client(tabpy_serverurl)
# dataframe to json+
responseJSON = training_data.to_json(orient='records')
input_data = json.loads(responseJSON)
returnResult = tabclient.query('Rapidminer_Quick_Training', go_url, go_username, go_password, input_data, label,selection_criteria,max_min_crietria_selector,'tabprep')
final_out = json_normalize(returnResult['response'])
return final_out
TASK_STATE = 'state'
FINISHED_STATUS = 'FINISHED'
ERROR_STATUS = 'ERROR'
COMPLETE_STATUS = [FINISHED_STATUS, ERROR_STATUS]
DATA_ID = 'id'
DEPLOYMENT_ID = 'DeploymentID'
STATUS = 'Deployment_Status'
MODEL = 'Deployed_Model'
MODELING_ID = 'Modeling_ID'
URL = 'URL'
depID = ''
AUTODEPLOY = True
client = ''
tabclient = Client('http://localhost:9004/')
#new update
def rapidminer_quick_training(go_url, gouser, gopassword, input_data, label,
selection_criteria, max_min_crietria_selector,
platform):
from rapidminer_go_python import rapidminergoclient as amw
# To get the AMW instance
client = amw.RapidMinerGoClient(go_url, gouser, gopassword)
data = client.convert_json_to_dataframe(input_data)
trainingResult = client.quick_automodel(data, label, AUTODEPLOY,
selection_criteria,
go_url = 'https://go.rapidminer.com'
go_username = ''
go_password = ''
#values to be changed based on data
label = 'Survived'
cost_matrix =[[1,-1],[-1,1]]
high_value = 'Yes'
low_value = 'No'
#### possible values,
selection_criteria = 'performance_accuracy'
max_min_crietria_selector = 'max' #or 'min'
should_deploy = True
platform = 'tabprep'
tabclient = Client(tabpy_serverurl)
STATUS = 'Deployment_Status'
MODEL = 'Deployed_Model'
DEPLOYMENT_ID = 'DeploymentID'
MODELING_ID = 'Modeling_ID'
URL = 'URL'
def training(data):
print('inside controller')
# removing rows with label values
data = data.dropna(subset=[label])
tabclient = Client(tabpy_serverurl)
# dataframe to json
input_data = json.loads(data.to_json(orient='records'))
returnResult = tabclient.query('RapidMiner_Train', go_url, go_username, go_password, input_data, label,cost_matrix,high_value,low_value,selection_criteria, max_min_crietria_selector, platform)
import tabpy
import json
from tabpy_client import Client
import pandas as pd
tabclient = Client('http://localhost:9004/')
go_url = 'https://go.rapidminer.com'
go_username = ''
go_password = ''
#values to be changed based on data
deployment_ID = ''
label = 'Survived'
PREDICTION = 'prediction(' + label + ')'
def score(test):
#removing rows with label values
test = test[pd.isnull(test[label])]
# dataframe to json
input_data = json.loads(test.to_json(orient='records'))
returnResult = tabclient.query('RapidMiner_Score', go_url, go_username,
go_password, input_data, label,
deployment_ID)
test[PREDICTION] = returnResult['response']
return test
#This function defines the output schema
#***Change the schema according to your result***
def get_output_schema():
for x in variables_categoricas:
df[x] = df[x].astype(str)
for x in variables_binarias:
df[x] = df[x].fillna(0)
df[x] = df[x].astype(np.int8)
for x in variables_numericas:
df[x] = df[x].apply(lambda c: getCleanPrice(c))
df[x] = df[x].astype(float)
full_pipeline.transform(df)
tree_predictions = tree_reg.predict(listing_prepared)
tree_mse = mean_squared_error(listing_label, tree_predictions)
tree_rmse = np.sqrt(tree_mse)
tree_mae = mean_absolute_error(listing_label, tree_predictions)
print("DecisionTreeRegressor:\nRMSE = ${:.4f}\nMAE = ${:.4f}".format(
tree_rmse, tree_mae))
print("-" * 100)
forest_predictions = forest_reg.predict(listing_prepared)
forest_mse = mean_squared_error(listing_label, forest_predictions)
forest_rmse = np.sqrt(forest_mse)
forest_mae = mean_absolute_error(listing_label, forest_predictions)
print("RandomForestRegressor:\nRMSE = ${:.4f}\nMAE = ${:.4f}".format(
forest_rmse, forest_mae))
return [price for price in forest_predictions]
cliente = Client("http://localhost:9004")
cliente.deploy("hostPricePredictor",
hostPricePredictor,
"Calcula el precio del hosting segun los parametros recibidos",
override=True)