List of Listings

Chapter 2. Should you send a purchase order to a technical approver?

Listing 2.1. Setting up the S3 bucket and subfolder

Listing 2.2. Importing modules

Listing 2.3. Viewing the dataset

Listing 2.4. Determining how many rows were sent for technical approval

Listing 2.5. Converting text values to columns

Listing 2.6. Identifying correlated columns

Listing 2.7. Showing only correlated columns

Listing 2.8. Splitting data into train, validate, and test datasets

Listing 2.9. Converting the data to CSV

Listing 2.10. Saving the CSV file to S3

Listing 2.11. Preparing the CSV data for SageMaker

Listing 2.12. Training the model

Listing 2.13. Hosting the model

Listing 2.14. Getting the predictions

Listing 2.15. Testing the model

Chapter 3. Should you call a customer because they are at risk of churning?

Listing 3.1. Setting up the notebook and storing the data

Listing 3.2. Importing the modules

Listing 3.3. Loading and viewing the data

Listing 3.4. Number of churned customers in the dataset

Listing 3.5. Removing the categorical data

Listing 3.6. Creating the training, validation, and test datasets

Listing 3.7. Converting the datasets to CSV and saving to S3

Listing 3.8. Training the model

Listing 3.9. Training rounds output

Listing 3.10. Hosting the model

Listing 3.11. Making predictions using the test data

Listing 3.12. Checking the predictions made using the test data

Listing 3.13. Creating the confusion matrix

Listing 3.14. Sample code used to access SageMaker’s XGBoost model.tar.gz

Listing 3.15. Deleting the notebook

Chapter 4. Should an incident be escalated to your support team?

Listing 4.1. Say where you are storing the data

Listing 4.2. Importing the modules

Listing 4.3. Sample JSON format

Listing 4.4. Loading and viewing the data

Listing 4.5. Showing the number of escalated tweets in the dataset

Listing 4.6. Total number of tweets and the number of escalated tweets

Listing 4.7. Creating train and validate datasets

Listing 4.8. Transforming each row to the format used by BlazingText

Listing 4.9. Transforming the data for BlazingText

Listing 4.10. Preprocessing and writing training data

Listing 4.11. Creating the training, validation, and test datasets

Listing 4.12. Training the model

Listing 4.13. Training rounds output

Listing 4.14. Hosting the model

Listing 4.15. Creating a new endpoint to host the model

Listing 4.16. Making predictions using the test data

Listing 4.17. Deleting the notebook

Chapter 5. Should you question an invoice sent by a supplier?

Listing 5.1. Say where you are storing the data

Listing 5.2. Importing the modules

Listing 5.3. Loading and viewing the data

Listing 5.4. Displaying the error rate

Listing 5.5. Total number of tweets and the number of escalated tweets

Listing 5.6. Describing the data

Listing 5.7. Viewing the data description

Listing 5.8. Creating the train and validate data

Listing 5.9. Creating training and validation datasets

Listing 5.10. Training the model

Listing 5.11. Hosting the model: deleting existing endpoints

Listing 5.12. Hosting the model: setting machine size

Listing 5.13. Hosting the model: converting to a workable format

Listing 5.14. Adding scores to validation data

Listing 5.15. Reviewing erroneous lines

Listing 5.16. Calculating errors greater than 1.5 (the median score)

Listing 5.17. Viewing false positives

Listing 5.18. Displaying the results in a pandas DataFrame

Listing 5.19. Deleting the notebook

Chapter 6. Forecasting your company’s monthly power usage

Listing 6.1. Displaying charts

Listing 6.2. Inputting the time-series data

Listing 6.3. Inputting time-series data for the whole family

Listing 6.4. Standard way to loop through a list

Listing 6.5. Standard output when you run the command to loop through a list

Listing 6.6. Standard way to enumerate through a loop

Listing 6.7. Output when enumerating through the loop

Listing 6.8. Charting time-series data for the whole family

Listing 6.9. Say where you are storing the data

Listing 6.10. Importing the modules

Listing 6.11. Loading and viewing the data

Listing 6.12. Viewing the number of rows and columns

Listing 6.13. Converting data to daily figures

Listing 6.14. Viewing the data in daily intervals

Listing 6.15. Replacing missing values

Listing 6.16. Creating charts to show each site over a period of months

Listing 6.17. Sample JSON file

Listing 6.18. Converting a DataFrame to a list of series

Listing 6.19. Setting the length of the prediction period

Listing 6.20. Creating a Python dictionary in same structure as a JSON file

Listing 6.21. Saving the JSON files to S3

Listing 6.22. Setting up a server to train the model

Listing 6.23. Setting up an estimator to hold training parameters

Listing 6.24. Inserting parameters for the estimator

Listing 6.25. Training the model

Listing 6.26. Deleting existing endpoints

Listing 6.27. Setting up the predictor class

Listing 6.28. Setting up the predictor class

Listing 6.29. Setting up a function that allows charting

Listing 6.30. Running the function that creates the chart

Listing 6.31. Running the predictor

Listing 6.32. Calculating the Mean Absolute Percentage Error (MAPE)

Listing 6.33. Running the MAPE function

Listing 6.34. Deleting the notebook

Chapter 7. Improving your company’s monthly power usage forecast

Listing 7.1. Setting up the notebook

Listing 7.2. Importing Python modules and libraries

Listing 7.3. Importing the meter data

Listing 7.4. Displaying information about the meter data

Listing 7.5. Displaying information about the site categories

Listing 7.6. Displaying information about holidays for each site

Listing 7.7. Displaying information about maximum temperatures for each site

Listing 7.8. Checking for missing energy consumption data

Listing 7.9. Checking for missing category data and holiday data

Listing 7.10. Checking for missing maximum temperature data

Listing 7.11. Fixing missing maximum temperature data

Listing 7.12. Fixing missing maximum temperature data

Listing 7.13. Converting category data to a list of numbers

Listing 7.14. Converting power consumption data to a list of lists

Listing 7.15. Converting holidays to a list of lists

Listing 7.16. Converting maximum temperatures to a list of lists

Listing 7.17. Setting the start and end dates for testing and training data

Listing 7.18. Creating a function that writes data to S3

Listing 7.19. Creating training and test datasets

Listing 7.20. Setting up the SageMaker session and server to create the model

Listing 7.21. Calculating MAPE

Listing 7.22. The DeepAR predictor function used in chapter 6

Listing 7.23. Setting up the estimator

Listing 7.24. Setting up the endpoint

Listing 7.25. Building and deploying the model

Listing 7.26. Checking the predictions from the model

Listing 7.27. Getting predictions for all sites during February 2019

Listing 7.28. Calculating MAPE

Listing 7.29. Displaying plots of sites

Listing 7.30. Plotting several sites and the February predictions

Listing 7.31. Deleting the endpoint

Chapter 8. Serving predictions over the web

Listing 8.1. Chalice’s default app.py code

Listing 8.2. The default app.py code

Listing 8.3. Contents of policy-dev.json

Listing 8.4. Contents of requirements.txt