ecdedios

df.shape
df.head()

ecdedios

# sampling the data to select only 1000 tweets
df = df.sample(1000, random_state=493).reset_index(drop=True)

ecdedios

# load the data into a dataframe
df = pd.read_csv('trump_20200530_clean.csv')

ecdedios

# PyCaret's NLP module
from pycaret.nlp import *

# for working with dataframes
import pandas as pd

# to print out all the outputs
from IPython.core.interactiveshell import InteractiveShell
InteractiveShell.ast_node_interactivity = "all"

ecdedios

print("POST to url", service.scoring_uri)
print("label:", y_test[sample_index])
print("prediction:", resp.text)

ecdedios

resp = requests.post(service.scoring_uri, input_data, headers=headers)

ecdedios

sample_index = 68

input_data = '{"data": [' + str(list(X_test[sample_index])) + "]}"

headers = {"Content-Type": "application/json"}

ecdedios

%%time
import uuid
from azureml.core.model import InferenceConfig
from azureml.core.environment import Environment
from azureml.core.model import Model

# get the registered model
model = Model(ws, "credit_card_model")

# create an inference config i.e. the scoring script and environment

ecdedios

# create environment for the deploy
from azureml.core.environment import Environment
from azureml.core.conda_dependencies import CondaDependencies
from azureml.core.webservice import AciWebservice

# get a curated environment
env = Environment.get(
    workspace=ws, 
    name="AzureML-sklearn-1.0-ubuntu20.04-py38-cpu",
    version=1

ecdedios

# register the model
model_uri = "runs:/{}/model".format(run.info.run_id)
model = mlflow.register_model(model_uri, "credit_card_model")