Deploying ML model #1692

from sagemaker import get_execution_role
import sagemaker
import argparse
import numpy as np
import os
import pandas as pd
from sklearn.externals import joblib
pd.options.mode.chained_assignment = None
import datetime as dt
from sklearn.model_selection import train_test_split
from sklearn import preprocessing
import io
from sagemaker.sklearn.estimator import SKLearn
import s3fs


prefix = 'FP'
sagemaker_session = sagemaker.Session()
role = get_execution_role()

data = pd.read_csv("df.csv", header = 0, usecols = ["col1", "col2"])


os.makedirs('./data_DM', exist_ok=True)
data.to_csv('./data_DM/orders.csv')

WORK_DIRECTORY = 'data_DM'

train_input = sagemaker_session.upload_data(WORK_DIRECTORY, key_prefix="{}/{}".format(prefix, WORK_DIRECTORY) )


script_path = './data_DM/My_script.py'

sklearn = SKLearn(
    entry_point=script_path,
    train_instance_type="ml.m5.2xlarge",
    role=role,
    sagemaker_session=sagemaker_session)

sklearn.fit({'train': train_input})

predictor = sklearn.deploy(initial_instance_count=1, instance_type="ml.m4.xlarge")

import argparse
import numpy as np
import os
import pandas as pd
from sklearn.externals import joblib
pd.options.mode.chained_assignment = None
import datetime as dt
from sklearn.model_selection import train_test_split
from sklearn import preprocessing
import io
from sklearn import tree
import boto3, re, sys, math, json, urllib.request

def cleaning(data):
     lots of cleaning
     return cleaned data


if __name__ =='__main__':
    
    bucket_name = 'ciao'
    file_name = 'df.csv 


    data_location = 's3://{}/{}'.format(bucket_name, file_name)

    parser = argparse.ArgumentParser()

    parser.add_argument('--output-data-dir', type=str, default=os.environ['SM_OUTPUT_DATA_DIR'])
    parser.add_argument('--model-dir', type=str, default=os.environ['SM_MODEL_DIR'])
    parser.add_argument('--train', type=str, default=os.environ['SM_CHANNEL_TRAIN'])

    args = parser.parse_args()

    data = pd.read_csv(data_location, header = 0, usecols = ["col1", "col2"])

    data_ml = cleaning(data) 

    y = data_ml.loc[:,"event"]
    X = data_ml.loc[:, data_ml.columns != 'event']

    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)
    
    

    model =  tree.DecisionTreeClassifier(n_estimators=600, class_weight = "balanced", random_state=42)
    model.fit(X_train, y_train)

    #Save the model to the location specified by args.model_dir
    joblib.dump(model, os.path.join(args.model_dir, "model.joblib"))



def model_fn(model_dir):
    model = joblib.load(os.path.join(model_dir, "model.joblib"))
    return model


def input_fn(request_body, request_content_type):
    if request_content_type == 'text/csv':
        samples = []
        for r in request_body.split('|'):
            samples.append(list(map(float,r.split(','))))
        return np.array(samples)
    else:
        raise ValueError("Thie model only supports text/csv input")

def predict_fn(input_data, model):
    return model.predict_proba(cleaning(input_data))

def output_fn(prediction, content_type):
    return ' | '.join([INDEX_TO_LABEL[t] for t in prediction])