findtharun

train_data, validation_data, test_data = np.split(dataset.sample(frac=1, random_state=1729), [int(0.7 * len(dataset)), int(0.9 * len(dataset))])
train_data.to_csv('train.csv', header=False, index=False)
validation_data.to_csv('validation.csv', header=False, index=False)

#UPLOADING AND TRAINING AND VALIDATION TO DATA TO S3 BUCKET

s3_input_train = boto3.Session().resource('s3').Bucket(bucket).Object(os.path.join(prefix, 'train/train.csv')).upload_file('train.csv')
s3_input_validation = boto3.Session().resource('s3').Bucket(bucket).Object(os.path.join(prefix, 'validation/validation.csv')).upload_file('validation.csv')

#MAKING DATA AS LIBSVM or CSV FORMAT

findtharun

from sklearn.preprocessing import LabelEncoder
le=LabelEncoder()
dataset['variety']=le.fit_transform(dataset['variety'])
dataset = pd.concat([dataset['variety'], dataset.drop(['variety'], axis=1)], axis=1)
dataset.head(3)

findtharun

findtharun

findtharun

bucket = 'testawslearn'
prefix = 'git'

# Define IAM role
import boto3
import re
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import os

findtharun

{
    "inputContentType": "CSV",
    "outputContentType": "CSV",
        "input": [
                    {
                        "name": "sepal.length",
                        "type": "DECIMAL"
                    },
                    {
                        "name": "sepal.width",

findtharun

{
    "inputContentType": "CSV",
    "outputContentType": "CSV",
        "input": [
                    {
                        "name": "sepal.length",
                        "type": "DECIMAL"
                    },
                    {
                        "name": "sepal.width",

findtharun

{
    "inputContentType": "CSV",
    "outputContentType": "CSV",
        "input": [
                    {
                        "name": "sepal.length",
                        "type": "DECIMAL"
                    },
                    {
                        "name": "sepal.width",