AWSBoto3Hacks/MachineLearningWithAmazonSagemaker.py - main - osbornray/PythonHacks

AWSBoto3Hacks/MachineLearningWithAmazonSagemaker.py
92 строки6 KB
RekhuGopal
SageMaker
14 янв 2022, 12:12
14 янв 2022, 12:12737858e
#################################### Step 1.Create an Amazon SageMaker notebook instance for data preparation ###############################

#################################### Step 2. Prepare the data ###############################################################################
#imports the required libraries and defines the environment variables.
import boto3, re, sys, math, json, os, sagemaker, urllib.request
from sagemaker import get_execution_role
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from IPython.display import Image
from IPython.display import display
from time import gmtime, strftime
from sagemaker.predictor import csv_serializer
# Define IAM role
role = get_execution_role()
prefix = 'sagemaker/DEMO-xgboost-dm'
my_region = boto3.session.Session().region_name # set the region of the instance
# this line automatically looks for the XGBoost image URI and builds an XGBoost container.
xgboost_container = sagemaker.image_uris.retrieve("xgboost", my_region, "latest")
print("Success - the MySageMakerInstance is in the " + my_region + " region. You will use the " + xgboost_container + " container for your SageMaker endpoint.")


# Create the S3 bucket to store your data.
bucket_name = 'mlbucketdemocqpocs' # <--- CHANGE THIS VARIABLE TO A UNIQUE NAME FOR YOUR BUCKET
s3 = boto3.resource('s3')
try:
    if  my_region == 'us-east-1':
      s3.create_bucket(Bucket=bucket_name)
    else: 
      s3.create_bucket(Bucket=bucket_name, CreateBucketConfiguration={ 'LocationConstraint': my_region })
    print('S3 bucket created successfully')
except Exception as e:
    print('S3 error: ',e)
	
# Download the data to your SageMaker instance and load the data into a dataframe
try:
  urllib.request.urlretrieve ("https://d1.awsstatic.com/tmt/build-train-deploy-machine-learning-model-sagemaker/bank_clean.27f01fbbdf43271788427f3682996ae29ceca05d.csv", "bank_clean.csv")
  print('Success: downloaded bank_clean.csv.')
except Exception as e:
  print('Data load error: ',e)

try:
  model_data = pd.read_csv('./bank_clean.csv',index_col=0)
  print('Success: Data loaded into dataframe.')
except Exception as e:
    print('Data load error: ',e)
	
# Shuffle and split the data into training data (70%) and test data (30%).

train_data, test_data = np.split(model_data.sample(frac=1, random_state=1729), [int(0.7 * len(model_data))])
print(train_data.shape, test_data.shape)
############################################################################################################################################

###################################### Step 3. Train the ML model ##########################################################################
# Use your training dataset to train your machine learning model.
pd.concat([train_data['y_yes'], train_data.drop(['y_no', 'y_yes'], axis=1)], axis=1).to_csv('train.csv', index=False, header=False)
boto3.Session().resource('s3').Bucket(bucket_name).Object(os.path.join(prefix, 'train/train.csv')).upload_file('train.csv')
s3_input_train = sagemaker.inputs.TrainingInput(s3_data='s3://{}/{}/train'.format(bucket_name, prefix), content_type='csv')

# Set up the Amazon SageMaker session, create an instance of the XGBoost model (an estimator), and define the model’s hyperparameters.
sess = sagemaker.Session()
xgb = sagemaker.estimator.Estimator(xgboost_container,role, instance_count=1, instance_type='ml.m4.xlarge',output_path='s3://{}/{}/output'.format(bucket_name, prefix),sagemaker_session=sess)
xgb.set_hyperparameters(max_depth=5,eta=0.2,gamma=4,min_child_weight=6,subsample=0.8,silent=0,objective='binary:logistic',num_round=100)

# Start the training job
xgb.fit({'train': s3_input_train})
############################################################################################################################################

######################################## Step 4. Deploy the model ##########################################################################
# Deploys the model on a server and creates a SageMaker endpoint that you can access. This step may take a few minutes to complete.
xgb_predictor = xgb.deploy(initial_instance_count=1,instance_type='ml.m4.xlarge')

# To predict whether customers in the test data enrolled for the bank product or not
from sagemaker.serializers import CSVSerializer
test_data_array = test_data.drop(['y_no', 'y_yes'], axis=1).values #load the data into an array
xgb_predictor.serializer = CSVSerializer() # set the serializer type
predictions = xgb_predictor.predict(test_data_array).decode('utf-8') # predict!
predictions_array = np.fromstring(predictions[1:], sep=',') # and turn the prediction into an array
print(predictions_array.shape)
############################################################################################################################################

######################################### Step 5. Evaluate model performance ###############################################################
# Evaluate the performance and accuracy of the machine learning model.
# This code compares the actual vs. predicted values in a table called a confusion matrix.
cm = pd.crosstab(index=test_data['y_yes'], columns=np.round(predictions_array), rownames=['Observed'], colnames=['Predicted'])
tn = cm.iloc[0,0]; fn = cm.iloc[1,0]; tp = cm.iloc[1,1]; fp = cm.iloc[0,1]; p = (tp+tn)/(tp+tn+fp+fn)*100
print("\n{0:<20}{1:<4.1f}%\n".format("Overall Classification Rate: ", p))
print("{0:<15}{1:<15}{2:>8}".format("Predicted", "No Purchase", "Purchase"))
print("Observed")
print("{0:<15}{1:<2.0f}% ({2:<}){3:>6.0f}% ({4:<})".format("No Purchase", tn/(tn+fn)*100,tn, fp/(tp+fp)*100, fp))
print("{0:<16}{1:<1.0f}% ({2:<}){3:>7.0f}% ({4:<}) \n".format("Purchase", fn/(tn+fn)*100,fn, tp/(tp+fp)*100, tp))
############################################################################################################################################