findtharun

import pandas_profiling
data.profile_report().to_file("pandas_profile_report.html")

findtharun

eda=sv.analyze([data,"Data"],target_feat='Occupancy')
eda.show_html()

findtharun

import sweetviz as sv
sweetviz_eda=sv.analyze(data)
sweetviz_eda.show_html()

findtharun

if __name__ == '__main__':
	app.run(host='0.0.0.0')

findtharun

import numpy as np
import pandas as pd
from flask import Flask, request, jsonify, render_template
import pickle

app = Flask(__name__,template_folder='templates')
model = pickle.load(open('model.pkl', 'rb'))

@app.route('/')

findtharun

import os
import io
import boto3
import json
import csv

# grab environment variables
ENDPOINT_NAME = os.environ['ENDPOINT_NAME']
runtime= boto3.client('runtime.sagemaker')

findtharun

endpoint_name = sess.endpoint_from_job(
    job_name=job_name,
    initial_instance_count=1,
    instance_type='ml.m4.xlarge',
    deployment_image=image_name,
    role=role
)

print ('endpoint name: {0}'.format(endpoint_name))

findtharun

estimator.fit({'train':s3_input_train,'validation':s3_input_validation})

findtharun

estimator.set_hyperparameters(alpha=1.448983,colsample_bytree=0.6897649,eta=0.246274,gamma=0.546408,lamda=0.0003157054,
max_depth=18,min_child_weight=0.00282088,num_class=3,num_round=8, objective='multi:softmax',subsample=0.538571908)

findtharun

base_job_name='iris-lamba-api'

from sagemaker.amazon.amazon_estimator import get_image_uri
image_name = get_image_uri(boto3.Session().region_name, 'xgboost')

estimator = sagemaker.estimator.Estimator(
    sagemaker_session=sess,
    image_name=image_name,
    role=role,
    train_instance_count=1,