Machine Learning

Benchmarking calling Oracle Machine Learning using REST

Posted on Updated on

Over the past year I’ve been presenting, blogging and sharing my experiences of using REST to expose Oracle Machine Learning models to developers in other languages, for example Python.

One of the questions I’ve been asked is, Does it scale?

Although I’ve used it in several projects to great success, there are no figures I can report publicly on how many REST API calls can be serviced 😦

But this can be easily done, and the results below are based on using and Oracle Autonomous Data Warehouse (ADW) on the Oracle Always Free.

The machine learning model is built on a Wine reviews data set, using Oracle Machine Learning Notebook as my tool to write some SQL and PL/SQL to build out a model to predict Good or Bad wines, based on the Prices and other characteristics of the wine. A REST API was built using this model to allow for a developer to pass in wine descriptors and returns two values to indicate if it would be a Good or Bad wine and the probability of this prediction.

No data is stored in the database. I only use the machine learning model to make the prediction

I built out the REST API using APEX, and here is a screenshot of the GET API setup.

Here is an example of some Python code to call the machine learning model to make a prediction.

import json
import requests

country = 'Portugal'
province = 'Douro'
variety = 'Portuguese Red'
price = '30'

resp = requests.get('https://jggnlb6iptk8gum-adw2.adb.us-ashburn-1.oraclecloudapps.com/ords/oml_user/wine/wine_pred/'+country+'/'+province+'/'+'variety'+'/'+price)
json_data = resp.json()
print (json.dumps(json_data, indent=2))

—–

{
  "pred_wine": "LT_90_POINTS",
  "prob_wine": 0.6844716987704507
}

But does this scale, as in how many concurrent users and REST API calls can it handle at the same time.

To test this I multi-threaded processes in Python to call a Python function to call the API, while ensuring a range of values are used for the input parameters. Some additional information for my tests.

  • Each function call included two REST API calls
  • Test effect of creating X processes, at same time
  • Test effect of creating X processes in batches of Y agents
  • Then, the above, with function having one REST API call and also having two REST API calls, to compare timings
  • Test in range of parallel process from 10 to 1,000 (generating up to 2,000 REST API calls at a time)

Some of the results. The table shows the time(*) in seconds to complete the number of processes grouped into batches (agents). My laptop was the limiting factor in these tests. It wasn’t able to test when the number of parallel processes when above 500. That is why I broke them into batches consisting of X agents

* this is the total time to run all the Python code, including the time taken to create each process.

Some observations:

  • Time taken to complete each function/process was between 0.45 seconds and 1.65 seconds, for two API calls.
  • When only one API call, time to complete each function/process was between 0.32 seconds and 1.21 seconds
  • Average time for each function/process was 0.64 seconds for one API functions/processes, and 0.86 for two API calls in function/process
  • Table above illustrates the overhead associated with setting up, calling, and managing these processes

As you can see, even with the limitations of my laptop, using an Oracle Database, in-database machine learning and REST can be used to create a Micro-Service type machine learning scoring engine. Based on these numbers, this machine learning micro-service would be able to handle and process a large number of machine learning scoring in Real-Time, and these numbers would be well within the maximum number of such calls in most applications. I’m sure I could process more parallel processes if I deployed on a different machine to my laptop and maybe used a number of different machines at the same time

How many applications within you enterprise needs to process move than 6,000 real-time machine learning scoring per minute?  This shows us the Oracle Always Free offering is capable and suitable for most applications.

Now, if you are processing more than those numbers per minutes then perhaps you need to move onto the paid options.

What next? I’ll spin up two VMs on Oracle Always Free, install Python, copy code into these VMs and have then run in parallel 🙂

 

OCI Data Science – Create a Project & Notebook, and Explore the Interface

Posted on Updated on

In my previous blog post I went through the steps of setting up OCI to allow you to access OCI Data Science. Those steps showed the setup and configuration for your Data Science Team.

Screenshot 2020-02-11 20.46.42

In this post I will walk through the steps necessary to create an OCI Data Science Project and Notebook, and will then Explore the basic Notebook environment.

1 – Create a Project

From the main menu on the Oracle Cloud home page select Data Science -> Projects from the menu.

Screenshot 2020-02-12 12.07.19

Select the appropriate Compartment in the drop-down list on the left hand side of the screen. In my previous blog post I created a separate Compartment for my Data Science work and team. Then click on the Create Projects button.

Screenshot 2020-02-12 12.09.11Enter a name for your project. I called this project, ‘DS-Demo-Project’. Click Create button.

Screenshot 2020-02-12 12.13.44

Screenshot 2020-02-12 12.14.44

That’s the Project created.

2 – Create a Notebook

After creating a project (see above) you can not create one or many Notebook Sessions.

To create a Notebook Session click on the Create Notebook Session button (see the above image).  This will create a VM to contain your notebook and associated work. Just like all VM in Oracle Cloud, they come in various different shapes. These can be adjusted at a later time to scale up and then back down based on the work you will be performing.

The following example creates a Notebook Session using the basic VM shape. I call the Notebook ‘DS-Demo-Notebook’. I also set the Block Storage size to 50G, which is the minimum value. The VNC details have been defaulted to those assigned to the Compartment. Click Create button at the bottom of the page.

Screenshot 2020-02-12 12.22.24

The Notebook Session VM will be created. This might take a few minutes. When created you will see a screen like the following.

Screenshot 2020-02-12 12.31.21

3 – Open the Notebook

After completing the above steps you can now open the Notebook Session in your browser.  Either click on the Open button (see above image), or copy the link and share with your data science team.

Important: There are a few important considerations when using the Notebooks. While the session is running you will be paying for it, even if the session got terminated at the browser or you lost connect. To manage costs, you may need to stop the Notebook session. More details on this in a later post.

After clicking on the Open button, a new browser tab will open and will ask you to log-in.

Screenshot 2020-02-12 12.35.26

After logging in you will see your Notebook.

Screenshot 2020-02-12 12.37.42

4 – Explore the Notebook Environment

The Notebook comes pre-loaded with lots of goodies.

The menu on the left-hand side provides a directory with lots of sample Notebooks, access to the block storage and a sample getting started Notebook.

Screenshot 2020-02-12 12.41.09

When you are ready to create your own Notebook you can click on the icon for that.

Screenshot 2020-02-12 12.42.50

Or if you already have a Notebook, created elsewhere, you can load that into your OCI Data Science environment.

Screenshot 2020-02-12 12.44.50

The uploaded Notebook will appear in the list on the left-hand side of the screen.

OCI Data Science – Initial Setup and Configuration

Posted on Updated on

After a very, very, very long wait (18+ months) Oracle OCI Data Science platform is now available.

But before you jump straight into using OCI Data Science, there is a little bit of setup required for your Cloud Tenancy. There is the easy simple approach and then there is the slightly more involved approach. These are

  • Simple approach. Assuming you are just going to use the root tenancy and compartment, you just need to setup a new policy to enable the use of the OCI Data Science services. This assuming you have your VNC configuration complete with NAT etc. This can be done by creating a policy with the following policy statement. After creating this you can proceed with creating your first notebook in OCI Data Science.
allow service datascience to use virtual-network-family in tenancy

Screenshot 2020-02-11 19.46.38

  • Slightly more complicated approach. When you get into having a team based approach you will need to create some additional Oracle Cloud components to manage them and what resources are allocated to them. This involved creating Compartments, allocating users, VNCs, Policies etc. The following instructions brings you through these steps

IMPORTANT: After creating a Compartment or some of the other things listed below, and they are not displayed in the expected drop-down lists etc, then either refresh your screen or log-out and log back in again!

1. Create a Group for your Data Science Team & Add Users

The first step involves creating a Group to ‘group’ the various users who will be using the OCI Data Science services.

Go to Governance and Administration ->Identity and click on Groups.

Enter some basic descriptive information. I called my Group, ‘my-data-scientists’.

Now click on your Group in the list of Groups and add the users to the group.

You may need to create the accounts for the various users.

Screenshot 2020-02-11 12.03.58

2. Create a Compartment for your Data Science work

Now create a new Compartment to own the network resources and the Data Science resources.

Go to Governance and Administration ->Identity and click on Compartments.

Enter some basic descriptive information. I’ve called my compartment, ‘My-DS-Compartment’.

3. Create Network for your Data Science work

Creating and setting up the VNC can be a little bit of fun. You can do it the manual way whereby you setup and configure everything. Or you can use the wizard to do this. I;m going to show the wizard approach below.

But the first thing you need to do is to select the Compartment the VNC will belong to. Select this from the drop-down list on the left hand side of the Virtual Cloud Network page. If your compartment is not listed, then log-out and log-in!

To use the wizard approach click the Networking QuickStart button.

Screenshot 2020-02-11 20.15.28

Select the option ‘VCN with Internet Connectivity and click Start Workflow, as you will want to connect to it and to allow the service to connect to other cloud services.

Screenshot 2020-02-11 20.17.22

I called my VNC ‘My-DS-vnc’ and took the default settings. Then click the Next button.

Screenshot 2020-02-11 20.19.31

The next screen shows a summary of what will be done. Click the Create button, and all of these networking components will be created.

Screenshot 2020-02-11 20.22.39

All done with creating the VNC.

4. Create required Policies enable OCI Data Science for your Compartment

There are three policies needed to allocated the necessary resources to the various components we have just created. To create these go to Governance and Administration ->Identity and click on Policies.

Select your Compartment from the drop-down list. This should be ‘My-DS-Compartment’, then click on Create Policy.

The first policy allocates a group to a compartment for the Data Science services. I called this policy, ‘DS-Manage-Access’.

allow group My-data-scientists to manage data-science-family in compartment My-DS-Compartment

Screenshot 2020-02-11 20.30.10

The next policy is to give the Data Science users access to the network resources. I called this policy, ‘DS-Manage-Network’.

allow group My-data-scientists to use virtual-network-family in compartment My-DS-Compartment

Screenshot 2020-02-11 20.37.47

And the third policy is to give Data Science service access to the network resources. I called this policy, ‘DS-Network-Access’.

allow service datascience to use virtual-network-family in compartment My-DS-Compartment

Screenshot 2020-02-11 20.41.01

Job Done 🙂

You are now setup to run the OCI Data Science service.  Check out my Blog Post on creating your first OCI Data Science Notebook and exploring what is available in this Notebook.

Data Science (The MIT Press Essential Knowledge series) – available in English, Korean and Chinese

Posted on Updated on

Back in the middle of 2018 MIT Press published my Data Science book, co-written with John Kelleher. It book was published as part of their Essentials Series.

During the few months it was available in 2018 it became a best seller on Amazon, and one of the top best selling books for MIT Press. This happened again in 2019. Yes, two years running it has been a best seller!

2020 kicks off with the book being translated into Korean and Chinese. Here are the covers of these translated books.

The Japanese and Turkish translations will be available in a few months!

Go get the English version of the book on Amazon in print, Kindle and Audio formats.

https://amzn.to/2qC84KN

This book gives a concise introduction to the emerging field of data science, explaining its evolution, relation to machine learning, current uses, data infrastructure issues and ethical challenge the goal of data science is to improve decision making through the analysis of data. Today data science determines the ads we see online, the books and movies that are recommended to us online, which emails are filtered into our spam folders, even how much we pay for health insurance.

Go check it out.

Amazon.com.          Amazon.co.uk

Screenshot 2020-02-05 11.46.03

#GE2020 Analysing Party Manifestos using Python

Posted on

The general election is underway here in Ireland with polling day set for Saturday 8th February. All the politicians are out campaigning and every day the various parties are looking for publicity on whatever the popular topic is for that day. Each day is it a different topic.

Most of the political parties have not released their manifestos for the #GE2020 election (as of date of this post). I want to use some simple Python code to perform some analyse of their manifestos. As their new manifestos weren’t available (yet) I went looking for their manifestos from the previous general election. Michael Pidgeon has a website with party manifestos dating back to the early 1970s, and also has some from earlier elections. Check out his website.

I decided to look at manifestos from the 4 main political parties from the 2016 general election. Yes there are other manifestos available, and you can use the Python code, given below to analyse those, with only some minor edits required.

The end result of this simple analyse is a WordCloud showing the most commonly used words in their manifestos. This is graphical way to see what some of the main themes and emphasis are for each party, and also allows us to see some commonality between the parties.

Let’s begin with the Python code.

1 – Initial Setup

There are a number of Python Libraries available for processing PDF files. Not all of them worked on all of the Part Manifestos PDFs! It kind of depends on how these files were generated. In my case I used the pdfminer library, as it worked with all four manifestos. The common library PyPDF2 didn’t work with the Fine Gael manifesto document.

import io
import pdfminer
from pprint import pprint
from pdfminer.converter import TextConverter
from pdfminer.pdfinterp import PDFPageInterpreter
from pdfminer.pdfinterp import PDFResourceManager
from pdfminer.pdfpage import PDFPage

#directory were manifestos are located
wkDir = '.../General_Election_Ire/'

#define the names of the Manifesto PDF files & setup party flag
pdfFile = wkDir+'FGManifesto16_2.pdf'
party = 'FG'
#pdfFile = wkDir+'Fianna_Fail_GE_2016.pdf'
#party = 'FF'
#pdfFile = wkDir+'Labour_GE_2016.pdf'
#party = 'LB'
#pdfFile = wkDir+'Sinn_Fein_GE_2016.pdf'
#party = 'SF'

All of the following code will run for a given manifesto. Just comment in or out the manifesto you are interested in. The WordClouds for each are given below.

2 – Load the PDF File into Python

The following code loops through each page in the PDF file and extracts the text from that page.

I added some addition code to ignore pages containing the Irish Language. The Sinn Fein Manifesto contained a number of pages which were the Irish equivalent of the preceding pages in English. I didn’t want to have a mixture of languages in the final output.

SF_IrishPages = [14,15,16,17,18,19,20,21,22,23,24]
text = ""

pageCounter = 0
resource_manager = PDFResourceManager()
fake_file_handle = io.StringIO()
converter = TextConverter(resource_manager, fake_file_handle)
page_interpreter = PDFPageInterpreter(resource_manager, converter)

for page in PDFPage.get_pages(open(pdfFile,'rb'), caching=True, check_extractable=True):
    if (party == 'SF') and (pageCounter in SF_IrishPages):
        print(party+' - Not extracting page - Irish page', pageCounter)
    else:
        print(party+' - Extracting Page text', pageCounter)
        page_interpreter.process_page(page)

        text = fake_file_handle.getvalue()

    pageCounter += 1

print('Finished processing PDF document')
converter.close()
fake_file_handle.close()
FG - Extracting Page text 0
FG - Extracting Page text 1
FG - Extracting Page text 2
FG - Extracting Page text 3
FG - Extracting Page text 4
FG - Extracting Page text 5
...

3 – Tokenize the Words

The next step is to Tokenize the text. This breaks the text into individual words.

from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
tokens = []

tokens = word_tokenize(text)

print('Number of Pages =', pageCounter)
print('Number of Tokens =',len(tokens))
Number of Pages = 140
Number of Tokens = 66975

4 – Filter words, Remove Numbers & Punctuation

There will be a lot of things in the text that we don’t want included in the analyse. We want the text to only contain words. The following extracts the words and ignores numbers, punctuation, etc.

#converts to lower case, and removes punctuation and numbers
wordsFiltered = [tokens.lower() for tokens in tokens if tokens.isalpha()]
print(len(wordsFiltered))
print(wordsFiltered)
58198
['fine', 'gael', 'general', 'election', 'manifesto', 's', 'keep', 'the', 'recovery', 'going', 'gaelgeneral', 'election', 'manifesto', 'foreward', 'from', 'an', 'taoiseach', 'the', 'long', 'term', 'economic', 'three', 'steps', 'to', 'keep', 'the', 'recovery', 'going', 'agriculture', 'and', 'food', 'generational',
...

As you can see the number of tokens has reduced from 66,975 to 58,198.

5 – Setup Stop Words

Stop words are general words in a language that doesn’t contain any meanings and these can be removed from the data set. Python NLTK comes with a set of stop words defined for most languages.

#We initialize the stopwords variable which is a list of words like 
#"The", "I", "and", etc. that don't hold much value as keywords
stop_words = stopwords.words('english')
print(stop_words)
['i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you', "you're", "you've", "you'll", "you'd", 'your', 'yours', 'yourself',
....

Additional stop words can be added to this list. I added the words listed below. Some of these you might expect to be in the stop word list, others are to remove certain words that appeared in the various manifestos that don’t have a lot of meaning. I also added the name of the parties  and some Irish words to the stop words list.

#some extra stop words are needed after examining the data and word cloud
#these are added
extra_stop_words = ['ireland','irish','ł','need', 'also', 'set', 'within', 'use', 'order', 'would', 'year', 'per', 'time', 'place', 'must', 'years', 'much', 'take','make','making','manifesto','ð','u','part','needs','next','keep','election', 'fine','gael', 'gaelgeneral', 'fianna', 'fáil','fail','labour', 'sinn', 'fein','féin','atá','go','le','ar','agus','na','ár','ag','haghaidh','téarnamh','bplean','page','two','number','cothromfor']
stop_words.extend(extra_stop_words)
print(stop_words)

Now remove these stop words from the list of tokens.

# remove stop words from tokenised data set
filtered_words = [word for word in wordsFiltered if word not in stop_words]
print(len(filtered_words))
print(filtered_words)
31038
['general', 'recovery', 'going', 'foreward', 'taoiseach', 'long', 'term', 'economic', 'three', 'steps', 'recovery', 'going', 'agriculture', 'food',

The number of tokens is reduced to 31,038

6 – Word Frequency Counts

Now calculate how frequently these words occur in the list of tokens.

#get the frequency of each word
from collections import Counter

# count frequencies
cnt = Counter()
for word in filtered_words:
cnt[word] += 1

print(cnt)
Counter({'new': 340, 'support': 249, 'work': 190, 'public': 186, 'government': 177, 'ensure': 177, 'plan': 176, 'continue': 168, 'local': 150, 
...

7 – WordCloud

We can use the word frequency counts to add emphasis to the WordCloud. The more frequently it occurs the larger it will appear in the WordCloud.

#create a word cloud using frequencies for emphasis 
from wordcloud import WordCloud
import matplotlib.pyplot as plt

wc = WordCloud(max_words=100, margin=9, background_color='white',
scale=3, relative_scaling = 0.5, width=500, height=400,
random_state=1).generate_from_frequencies(cnt)

plt.figure(figsize=(20,10))
plt.imshow(wc)
#plt.axis("off")
plt.show()

#Save the image in the img folder:
wc.to_file(wkDir+party+"_2016.png")

The last line of code saves the WordCloud image as a file in the directory where the manifestos are located.

8 – WordClouds for Each Party

Screenshot 2020-01-21 11.10.25

Remember these WordClouds are for the manifestos from the 2016 general election.

When the parties have released their manifestos for the 2020 general election, I’ll run them through this code and produce the WordClouds for 2020. It will be interesting to see the differences between the 2016 and 2020 manifesto WordClouds.

Machine Learning Evaluation Measures

Posted on Updated on

When developing machine learning models there is a long list of possible evaluation measures. On one hand this can be good as it gives us lots of insights into the models and be able to select the best model that meets the requirements. (BTW this is different to choosing the best model based on the evaluation measures!). On the other hand it can be very confusing what all of these mean as there can appear to be so many of them.  In this post I’ll look at some of these evolution measures.

I’m not going to go into the basic set of evaluation measures that come from the typical use of the Confusion Matrix, including True/False Positives, True/False Negatives, Accuracy, Miss-classification rate, Precision, Recall, Sensitivity and F1 score.

The following evaluation measures will be discussed:

  • R-Squared (R2)
  • Mean Squared Error (MSE)
  • Sum of Squared Error (SSE)
  • Root Mean Square (RMSE)

R-Squared (R²)

R-squared measures how well your data fits a regression line. It measures the variation of the predicted values, from the model, from that of the actual value. It is typically given as a percentage or in the range of Zero to One (although you can have negative values). It is also known as Coefficient of Determination. The higher the value for R² the better.

R² is always between 0 and 100%:

  • 0% indicates that the model explains none of the variability of the response data around its mean.
  • 100% indicates that the model explains all the variability of the response data around its mean.

r2

But R² cannot determine whether the coefficient estimates and predictions are biased

Mean Squared Error (MSE)

MSE  measures average squared error of our predictions. For each point, it calculates square difference between the predictions and the target and then average those values. The higher this value, the worse the model is.

Screenshot 2019-12-20 11.20.14

The larger the number the larger the error. Error in this case means the difference between the observed values and the predicted values. Square each difference, this ensures negative and positive values do not cancel each other out.

Sum of Squared Error (SSE)

SSE is the sum of the squared differences between each observation and its group’s mean.  It measures the overall difference between your data and the values predicted by your estimation model.

Screenshot 2019-12-20 11.28.40

Root Mean Square Error (RMSE) 

RMSE is just the square root of MSE. The square root is introduced to make scale of the errors to be the same as the scale of targets. As the square root of a variance, RMSE can be interpreted as the standard deviation of the unexplained variance. Lower values of RMSE indicate better fit. RMSE is a good measure of how accurately the model predicts the response.

 

 

Applying a Machine Learning Model in OAC

Posted on Updated on

There are a number of different tools and languages available for machine learning projects. One such tool is Oracle Analytics Cloud (OAC).  Check out my article for Oracle Magazine that takes you through the steps of using OAC to create a Machine Learning workflow/dataflow.

Screenshot 2019-12-19 14.31.24

Oracle Analytics Cloud provides a single unified solution for analyzing data and delivering analytics solutions to businesses. Additionally, it provides functionality for processing data, allowing for data transformations, data cleaning, and data integration. Oracle Analytics Cloud also enables you to build a machine learning workflow, from loading, cleaning, and transforming data and creating a machine learning model to evaluating the model and applying it to new data—without the need to write a line of code. My Oracle Magazine article takes you through the various tasks for using Oracle Analytics Cloud to build a machine learning workflow.

That article covers the various steps with creating a machine learning model. This post will bring you through the steps of using that model to score/label new data.

In the Data Flows screen (accessed via Data->Data Flows) click on Create. We are going to create a new Data Flow to process the scoring/labeling of new data.

Screenshot 2019-12-19 15.08.39

Select Data Flow from the pop-up menu. The ‘Add Data Set’ window will open listing your available data sets. In my example, I’m going to use the same data set that I used in the Oracle Magazine article to build the model.  Click on the data set and then click on the Add button.

Screenshot 2019-12-19 15.14.44

The initial Data Flow will be created with the node for the Data Set. The screen will display all the attributes for the data set and from this you can select what attributes to include or remove. For example, if you want a subset of the attributes to be used as input to the machine learning model, you can select these attributes at this stage. These can be adjusted at a later stages, but the data flow will need to be re-run to pick up these changes.

Screenshot 2019-12-19 15.17.48

Next step is to create the Apply Model node. To add this to the data flow click on the small plus symbol to the right of the Data Node. This will pop open a window from which you will need to select the Apply Model.

Screenshot 2019-12-19 15.22.40

A pop-up window will appear listing the various machine learning models that exist in your OAC environment. Select the model you want to use and click the Ok button.

Screenshot 2019-12-19 15.24.42

Screenshot 2019-12-19 15.25.22

The next node to add to the data flow is to save the results/outputs from the Apply Model node. Click on the small plus icon to the right of the Apply Model node and select Save Results from the popup window.

Screenshot 2019-12-19 15.27.50.png

We now have a completed data flow. But before you finish edit the Save Data node to give a name for the Save Data Set, and you can edit what attributes/features you want in the result set.

Screenshot 2019-12-19 15.30.25.png

You can now save and run the Data Flow, and view the outputs from applying the machine learning model. The saved data set results can be viewed in the Data menu.

Screenshot 2019-12-19 15.35.11