Machine Learning

Machine Learning on Mobile Devices

Posted on Updated on

You: What? You can’t be serious?¬† Machine Learning on Mobile Devices?

Me: The simple answer is ‘Yes you can!”

You: But, what about all the complex data processing, CPU or GPU, and everything else that is needed for machine learning?

Me: Yes you are correct, those things might not be needed. What’s the answer to everything in IT?

You: It Depends ?

Me: Exactly. Yes It Depends on what you are doing. In most cases you don’t need large amounts of machine processing power to do machine learning. Except if you are doing image processing. Then you do need a bit of power to support that work.

You: But how can a mobile device be used for machine learning?

Screenshot 2019-07-19 14.24.22

Me: It Depends! ūüôā¬† It depends on what you are doing. Most of the data processing power needed is for creating the models. That is what most people talk about. Very few people talk about the deployment of machine learning. Deployment, as in, using the machine learning models in your applications.

You: But why mobile devices? That sounds a bit silly?

Me: It does a bit. But when you think about it, how much do you use your mobile phone and tablet?  Where else have you seen mobile devices being used?

You: I use these all the time, to do nearly everything. Just like everyone else I know.

Me: Exactly!  and where else have you seen mobile devices being used?

You: Everywhere! hotels, bars, shops, hospitals, everywhere!

Me: Exactly. And it kind of makes sense to have machine learning scoring done at the point of capture of the data and not some hours or days or weeks later in some data warehouse or something else.

You: But what about the processing power of these devices. They aren’t powerful enough to run the machine learning models? Or are they?

Me: What is a machine learning model? In a simple way it is a mathematical formula of the data that calculates a particular outcome. Something that is a bit more complicated than using a sum function.  Could a mobile device do that easily?

You: Yes. That should be really easy and fast for mobile devices? But machine learning is complex. People keep telling me how complex it is and how difficult it is!

Me: True it can be, but for most problems it can be as simple as writing a few lines of code to create a model. 3-4 lines of code in some languages. But the applying of the the machine learning model can be a simple task (maybe 1 line of code), although some simple data formatting might be needed, but that is a simple task too.

You: So, how can a machine learning model be run on a mobile device?

Me: Programmers write code to run applications on mobile devices. This code can be extended to include the machine learning model. This can be used to score or label the data or do some other processing. A few lines of code.  A good alternative is to create a web service to all the remove scoring of the data.

You: The programming languages used for mobile development are a bit different to most other applications. Surely those mobile device languages don’t support machine learning.

Me: You’d be surprised by what’s available.

You: OK, What languages can I try? Where can I get started?

Me: Check out Firebase ML Kit, Apple CoreML and TensorFlow Lite. Those should be more than enough for you to get started with. There are a few others. But start with those.

You. Brilliant, thank you Brendan. I’ll let you know how I get on with those.

 

 

Embedding Transformation Data Pipeline into ML Model using Oracle Data Mining

Posted on Updated on

I’ve written several blog posts about how to use the DBMS_DATA_MINING.TRANSFORM function to create various data transformations and how to apply these to your data. All of these steps can be simple enough to following and re-run in a lab environment. But the real value with data science and machine learning comes when you deploy the models into production and have the ML models scoring data as it is being produced, and your applications acting upon these predictions immediately, and not some hours or days later when the data finally arrives in the lab environment.

It would be useful to be able to bundle all the transformations into the same process the create the model. The transformations and model become one, together.  If this is possible, then that greatly simplifies how the ML model can be deployed into production. It then becomes a simple function or REST call. We need to keep this simple (KISS).

Using the examples from my previous blog posts performing various data transformations, the following example shows how you can bundle these up into one defined set of transformations and then embed these transformations as part of the ML model. To do this we need to define a list of transformations. We can do this using:

xform_list            IN TRANSFORM_LIST DEFAULT NULL

Where TRANSFORM_LIST has the following structure:

TRANFORM_REC IS RECORD (
     attribute_name       VARCHAR2(4000),
     attribute_subname    VARCHAR2(4000),
     expression           EXPRESSION_REC,
     reverse_expression   EXPRESSION_REC,
     attribute_spec       VARCHAR2(4000));

You can use the DBMS_DATA_MINING.SET_TRANSFORM function to defined the transformations. The following example illustrates the transformation of converting the BOOKKEEPING_APPLICATION attribute from a number data type to a character data type.

DECLARE
   transform_stack   dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
   dbms_data_mining_transform.SET_TRANSFORM(transform_stack,
                                  'BOOKKEEPING_APPLICATION',
                                  NULL,
                                  'to_char(BOOKKEEPING_APPLICATION)',
                                  'to_number(BOOKKEEPING_APPLICATION)',
                                  NULL);
END;

Alternatively you can use the SET_EXPRESSION function and then create the transformation using it.

You can Stack the transforms together. Using the above example you could express a number of transformations and have these stored in the TRANSFORM_STACK variable. You can then pass this variable into your CREATE_MODEL procedure and have these transformations embedded in your ML model.

 

DECLARE
   transform_stack   dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
   -- Define the transformation list
   dbms_data_mining_transform.SET_TRANSFORM(transform_stack,
                                  'BOOKKEEPING_APPLICATION',
                                  NULL,
                                  'to_char(BOOKKEEPING_APPLICATION)',
                                  'to_number(BOOKKEEPING_APPLICATION)',
                                  NULL);

   -- Create the data mining model
   DBMS_DATA_MINING.CREATE_MODEL(
      model_name           => 'DEMO_TRANSFORM_MODEL',
      mining_function      => dbms_data_mining.classification,
      data_table_name      => 'MINING_DATA_BUILD_V',
      case_id_column_name  => 'cust_id',
      target_column_name   => 'affinity_card',
      settings_table_name  => 'demo_class_dt_settings',
      xform_list           => transform_stack);
END;

My previous blog posts showed how to create various types of transformations. These transformations were then used to create a view of the data set that included these transformations. To embed these transformations in the ML Model we need to use the  STACK function. The following examples illustrate the stacking of the transformations created in the previous blog posts. These transformations are added (or stacked) to a transformation list and then added to the CREATE_MODEL function, embedding these transformations in the model.

 

DECLARE
   transform_stack   dbms_data_mining_transform.TRANSFORM_LIST;
BEGIN
   -- Stack the missing numeric transformations
   dbms_data_mining_transform.STACK_MISS_NUM (
          miss_table_name   => 'TRANSFORM_MISSING_NUMERIC',
          xform_list        => transform_stack);

   -- Stack the missing categorical transformations
   dbms_data_mining_transform.STACK_MISS_CAT (
          miss_table_name   => 'TRANSFORM_MISSING_CATEGORICAL',
          xform_list        => transform_stack);

   -- Stack the outlier treatment for AGE
   dbms_data_mining_transform.STACK_CLIP (
          clip_table_name   => 'TRANSFORM_OUTLIER',
          xform_list        => transform_stack);

   -- Stack the normalization transformation
   dbms_data_mining_transform.STACK_NORM_LIN (
          norm_table_name   => 'MINING_DATA_NORMALIZE',
          xform_list        => transform_stack);

   -- Create the data mining model
   DBMS_DATA_MINING.CREATE_MODEL(
      model_name           => 'DEMO_STACKED_MODEL',
      mining_function      => dbms_data_mining.classification,
      data_table_name      => 'MINING_DATA_BUILD_V',
      case_id_column_name => 'cust_id',
      target_column_name   => 'affinity_card',
      settings_table_name => 'demo_class_dt_settings',
      xform_list           => transform_stack);
END;

To view the embedded transformations in your data mining model you can use the GET_MODEL_TRANSFORMATIONS function.

SELECT TO_CHAR(expression)
FROM TABLE (dbms_data_mining.GET_MODEL_TRANSFORMATIONS('DEMO_STACKED_MODEL'));

 

TO_CHAR(EXPRESSION)
--------------------------------------------------------------------------------
(CASE  WHEN (NVL("AGE",38.892)<18) THEN 18 WHEN (NVL("AGE",38.892)>70) THEN 70 E
LSE NVL("AGE",38.892) END -18)/52

NVL("BOOKKEEPING_APPLICATION",.880667)
NVL("BULK_PACK_DISKETTES",.628)
NVL("FLAT_PANEL_MONITOR",.582)
NVL("HOME_THEATER_PACKAGE",.575333)
NVL("OS_DOC_SET_KANJI",.002)
NVL("PRINTER_SUPPLIES",1)
(CASE  WHEN (NVL("YRS_RESIDENCE",4.08867)<1) THEN 1 WHEN (NVL("YRS_RESIDENCE",4.
08867)>8) THEN 8 ELSE NVL("YRS_RESIDENCE",4.08867) END -1)/7

NVL("Y_BOX_GAMES",.286667)
NVL("COUNTRY_NAME",'United States of America')
NVL("CUST_GENDER",'M')
NVL("CUST_INCOME_LEVEL",'J: 190,000 - 249,999')
NVL("CUST_MARITAL_STATUS",'Married')
NVL("EDUCATION",'HS-grad')
NVL("HOUSEHOLD_SIZE",'3')
NVL("OCCUPATION",'Exec.')

Transforming Outliers in Oracle Data Mining

Posted on Updated on

In previous posts I’ve shown how to use the DBMS_DATA_MINING.TRANSFORM function to transform data is various ways including, normalization and missing data. In this post I’ll build upon these to show how to outliers can be handled.

The following example will show you how you can transform data to identify outliers and transform them. In the example, Winsorsizing transformation is performed where the outlier values are replaced by the nearest value that is not an outlier.

The transformation process takes place in three stages. For the first stage a table is created to contain the outlier transformation data. The second stage calculates the outlier transformation data and store these in the table created in stage 1. One of the parameters to the outlier procedure requires you to list the attributes you do not the transformation procedure applied to (this is instead of listing the attributes you do want it applied to).  The third stage is to create a view (MINING_DATA_V_2) that contains the data set with the outlier transformation rules applied. The input data set to this stage can be the output from a previous transformation process (e.g. DATA_MINING_V).

BEGIN
   -- Clean-up : Drop the previously created tables
   BEGIN
      execute immediate 'drop table TRANSFORM_OUTLIER';
   EXCEPTION
      WHEN others THEN
         null;
   END;

   -- Stage 1 : Create the table for the transformations
   -- Perform outlier treatment for: AGE and YRS_RESIDENCE
   --
   DBMS_DATA_MINING_TRANSFORM.CREATE_CLIP (
      clip_table_name => 'TRANSFORM_OUTLIER');

   -- Stage 2 : Transform the categorical attributes
   --   Exclude the number attributes you do not want transformed
   DBMS_DATA_MINING_TRANSFORM.INSERT_CLIP_WINSOR_TAIL (
      clip_table_name => 'TRANSFORM_OUTLIER',
      data_table_name => 'MINING_DATA_V',
      tail_frac       => 0.025,
      exclude_list    => DBMS_DATA_MINING_TRANSFORM.COLUMN_LIST (
                          'affinity_card',
                          'bookkeeping_application',
                          'bulk_pack_diskettes',
                          'cust_id',
                          'flat_panel_monitor',
                          'home_theater_package',
                          'os_doc_set_kanji',
                          'printer_supplies',
                          'y_box_games'));

   -- Stage 3 : Create the view with the transformed data
   DBMS_DATA_MINING_TRANSFORM.XFORM_CLIP(
      clip_table_name => 'TRANSFORM_OUTLIER',
      data_table_name => 'MINING_DATA_V',
      xform_view_name => 'MINING_DATA_V_2');
END;

The view MINING_DATA_V_2 will now contain the data from the original data set transformed to process missing data for numeric and categorical data (from previous blog post), and also has outlier treatment for the AGE attribute.

 

 

Examples of Machine Learning with Facial Recognition

Posted on Updated on

In a previous blog post I gave some examples of how facial images recognition and videos are being used in our daily lives. In this post I want to extend this with some additional examples. There are ethical issues around this and in some of these examples their usage has stopped. What is also interesting is the reaction on various social media channels about this. People don’t like it and and happen that some of these have stopped.

But how widespread is this technology? Based on these known examples, and this list is by no means anywhere near complete, but gives an indication of the degree of it’s deployment and how widespread it is.

Dubai is using facial recognition to measure customer satisfaction at four of the Roads and Transport Authority Customer Happiness Centers. They analyze the faces of their customers and rank their level of happiness. They can use this to generate alerts when the happiness levels falls below certain levels.

Screenshot 2019-05-20 10.48.39

Various department stores are using facial recognition throughout the stores and at checkout. These are being used to delivery personalized adverts to users on either in-store screen or on personalized screens on the shopping trolley. And can be used to verify a person’s age if they are buying alcohol or other products. Tesco‚Äôs have previously used face-scanning cameras at tills in petrol stations to target advertisements at customers depending on their age and approximate age.

Screenshot 2019-05-20 11.52.55

Some retail stores are using ML to monitor you, monitor what items you pick up and what you pay for at the checkout, identifying any differences and what steps to take next.

In a slight variation of facial recognition, some stores are using similar technology to monitor stock levels, monitor how people interact with different products (e.g pick up one product and then relate it with a similar product), and optimized location of products. Walmart has been a learner in the are of AI and Machine Learning in the retail section for some time now.

The New York Metropolitan Transport Authority has been using facial capture and recognition at several site across the city. Their proof of concept location was at the Robert F Kennedy Bridge. The company supplying the technology claimed 80% accuracy at predicting the person, through a widescreen while the car was traveling at low speed. These images can then be matched against government databases, such as driver license authorities, police databases and terrorist databases. The problem with this project was that it did not achieve one single positive match (within acceptable parameters) during the initial period of the project.

Screenshot 2019-05-20 11.10.56

There are some reports that similar technology is being use on the New York Subway system in Time Square to help with identifying fare dodgers.

How about using facial recognition at boarding gates for your new flight instead of showing your passport or other official photo id. JetBlue and other airlines are now using this technology. Some airports have been using this for many many years.

Screenshot 2019-05-20 11.16.47

San Francisco City government took steps in May 2019 to ban the use of facial recognition across all city functions. Other cities like Oakland and Sommerville in Massachusetts have implemented similar bans with other cities likely to follow. But it doesn’t ban the use by private companies.

Screenshot 2019-05-20 10.56.51

What about using this technology to automatically monitor and manage staff. Manage staff, as in to decide who should be fired and who should be reallocated elsewhere. It is reported that Amazon is using facial and other recognition systems to monitor staff productivity in their warehouses.

Screenshot 2019-05-20 11.00.20

A point I highlighted in my previous post was how are these systems/applications able to get enough images as training samples for their models. This is considering that most of the able systems/applications say they don’t keep any of the images they capture.

How many of us take pictures and post them on Facebook, Instagram, Snapchat, Twitter, etc. By doing this, you are making those images available to these companies to training their machine learning model. To do this they scrap the images for these sites and then have to manually label them with descriptive information. It is a combination of the image and descriptive information that is used by the machine learning algorithms to learn and build a model that suits their needs. See the MIT Technology Review article for more details and example on this topic.

Screenshot 2019-05-20 10.22.28

There are also reports of some mobile phone apps that turn on your mobile phone camera. The apps will detect if the phone is possibly mounted on the dashboard of a car, and then takes pictures of the inside of the car and also pictures of where you are driving. Similar reports exists about many apps and voice activated devices.

So be careful what you post on social media or anywhere else online, and be careful of what apps you have on your mobile phone!

There is a general backlash to the use of this technology, and with more people becoming aware of what is happening, we need to more aware of what when and where this technology is being used.

Transforming Missing Data using Oracle Data Mining

Posted on Updated on

In a previous post I showed how you can normalize data using the in-database machine learning feature using the DBMS_DATA_MINING.TRANSFORM function.  This same function can be used to perform many more data transformations with standardized routines. When it comes to missing data, where you have some case records where the value for an attribute is missing you have a number of options open to you. The first is to evaluate the degree of missing values for the attribute for the data set as a whole. If it is very high, you may want to remove that attribute from the data set. But in scenarios when you have a small number or percentage of missing values you will want to find an appropriate or an approximate value. Such calculations can involve the use of calculating the mean or mode.

To build this up using DBMS_DATA_MINING.TRANSFORM function, we need to follow a simple three stage process. The first stage creates a table that will contain the details of the transformations. The second stage defines and runs the transformation function to calculate the replacement values and finally, the third stage, to create the necessary records in the table created in the previous stage. These final two stages need to be followed for both numerical and categorical attributes. For the final stage you can create a new view that contains the data from the original table and has the missing data rules generated in the second stage applied to it. The following example illustrates these two stages for numerical and categorical attributes in the MINING_DATA_BUILD_V data set.

-- Transform missing data for numeric attributes
-- Stage 1 : Clean up, if previous run
--    transformed missing data for numeric and categorical
--    attributes.
BEGIN
   --
   -- Clean-up : Drop the previously created tables
   --
   BEGIN
      execute immediate 'drop table TRANSFORM_MISSING_NUMERIC';
   EXCEPTION
      WHEN others THEN
         null;
   END;

   BEGIN
      execute immediate 'drop table TRANSFORM_MISSING_CATEGORICAL';
   EXCEPTION
      WHEN others THEN
         null;
   END;

Now for stage 2 to define the functions to calculate the missing values for Numerical and Categorical variables.

-- Stage 2 : Perform the transformations
--    Exclude any attributes you don't want transformed
--      e.g. the case id and the target attribute

   --
   -- Transform the numeric attributes
   --
   dbms_data_mining_transform.CREATE_MISS_NUM (
      miss_table_name => 'TRANSFORM_MISSING_NUMERIC');

   dbms_data_mining_transform.INSERT_MISS_NUM_MEAN (
    miss_table_name => 'TRANSFORM_MISSING_NUMERIC',
    data_table_name => 'MINING_DATA_BUILD_V',
    exclude_list    => DBMS_DATA_MINING_TRANSFORM.COLUMN_LIST (
                       'affinity_card',
                       'cust_id'));

   --
   -- Transform the categorical attributes
   --
   dbms_data_mining_transform.CREATE_MISS_CAT (
      miss_table_name => 'TRANSFORM_MISSING_CATEGORICAL');

   dbms_data_mining_transform.INSERT_MISS_CAT_MODE (
      miss_table_name => 'TRANSFORM_MISSING_CATEGORICAL',
      data_table_name => 'MINING_DATA_BUILD_V',
      exclude_list    => DBMS_DATA_MINING_TRANSFORM.COLUMN_LIST (
                         'affinity_card',
                         'cust_id'));
END;

When the above code completes the two transformation tables, TRANSFORM_MISSING_NUMERIC and TRANSFORM_MISSING_CATEGORICAL, will exist in your schema.

Querying these two tables shows the table attributes along with the value to be used to relate the missing value. For example the following illustrates the missing data transformations for the categorical data.

SELECT col, 
       val 
FROM transform_missing_categorical;

For the sample data set used in these examples we get.

COL                       VAL
------------------------- -------------------------
CUST_GENDER               M
CUST_MARITAL_STATUS       Married
COUNTRY_NAME              United States of America
CUST_INCOME_LEVEL         J: 190,000 - 249,999
EDUCATION                 HS-grad
OCCUPATION                Exec.
HOUSEHOLD_SIZE            3

For stage three you will need to create a new view (MINING_DATA_V). This combines the data from original table and the missing data rules generated in the second stage applied to it. This is built in stages with an initial view (MINING_DATA_MISS_V) created that merges the data source and the transformations for the missing numeric attributes. This view (MINING_DATA_MISS_V) will then have the transformations for the missing categorical attributes applied to create the a new view called MINING_DATA_V that contains all the missing data transformations.

BEGIN
   -- xform input data to replace missing values
   -- The data source is MINING_DATA_BUILD_V
   -- The output is MINING_DATA_MISS_V

   DBMS_DATA_MINING_TRANSFORM.XFORM_MISS_NUM(
      miss_table_name => 'TRANSFORM_MISSING_NUMERIC',
      data_table_name => 'MINING_DATA_BUILD_V',
      xform_view_name => 'MINING_DATA_MISS_V');

   -- xform input data to replace missing values
   -- The data source is MINING_DATA_MISS_V
   -- The output is MINING_DATA_V
   DBMS_DATA_MINING_TRANSFORM.XFORM_MISS_CAT(
      miss_table_name => 'TRANSFORM_MISSING_CATEGORICAL',
      data_table_name => 'MINING_DATA_MISS_V',
      xform_view_name => 'MINING_DATA_V');
END;

You can now query the MINING_DATA_V view and see that the data displayed will not contain any null values for any of the attributes.

 

Examples of using Machine Learning on Video and Photo in Public

Posted on Updated on

Over the past 18 months or so most of the examples of using machine learning have been on looking at images and identifying objects in them. There are the typical examples of examining pictures looking for a Cat or a Dog, or some famous person, etc. Most of these examples are very noddy, although they do illustrate important examples.

But what if this same technology was used to monitor people going about their daily lives. What if pictures and/or video was captured of you as you walked down the street or on your way to work or to a meeting. These pictures and videos are being taken of you without you knowing.

And this raises a wide range of Ethical concerns. There are the ethics of deploying such solutions in the public domain, but there are also ethical concerns for the data scientists, machine learner, and other people working on these projects. “Just because we can, doesn’t mean we should”. People need to decide, if they are working on one of these projects, if they should be working on it and if not what they can do.

Ethics are the principals of behavior based on ideas of right and wrong. Ethical principles often focus on ideas such as fairness, respect, responsibility, integrity, quality, transparency and trust.  There is a lot in that statement on Ethics, but we all need to consider that is right and what is wrong. But instead of wrong, what is grey-ish, borderline scenarios.

Here are some examples that might fall into the grey-ish space between right and wrong. Why they might fall more towards the wrong is because most people are not aware their image is being captured and used, not just for a particular purpose at capture time, but longer term to allow for better machine learning models to be built.

Can you imagine walking down the street with a digital display in front of you. That display is monitoring you, and others, and then presents personalized adverts on the digital display aim specifically at you. A classify example of this is in the film Minority Report. This is no longer science fiction.

Screenshot 2019-05-10 14.12.55

This is happening at the Westfield shopping center in London and in other cities across UK and Europe. These digital advertisement screens are monitoring people, identifying their personal characteristics and then customizing the adverts to match in with the profile of the people walking past. This solutions has been developed and rolled out by Ocean Out Door. They are using machine learning to profile the individual people based on gender, age, facial hair, eye wear, mood, engagement, attention time, group size, etc. They then use this information to:

  1. Optimisation ‚Äď delivering the appropriate creative to the right audience at the right time.
  2. Visualise ‚Äď Gaze recognition to trigger creative or an interactive experience
  3. AR Enabled ‚Äď Using the HD cameras to create an augmented reality mirror or window effect, creating deep consumer engagement via the latest technology
  4. Analytics ‚Äď Understanding your brand‚Äôs audience, post campaign analysis and creative testing

Screenshot 2019-05-10 14.19.35.png

Face Plus Plus can monitor people walking down the street and do similar profiling, and can bring it to another level where by they can identify what clothing you are wearing and what the brand is. Image if you combine this with location based services. An example of this, imagine you are walking down the high street or a major retail district. People approach you trying to entice you into going into a particular store, and they offer certain discounts. But you are with a friend and the store is not interested in them.

Screenshot 2019-05-10 14.28.23

The store is using video monitoring, capturing details of every person walking down the street and are about to pass the store. The video is using machine/deep learning to analyze you profile and what brands you are wearing. The store as a team of people who are deployed to stop and engage with certain individuals, just because they make the brands or interests of the store and depending on what brands you are wearing can offer customized discounts and offers to you.

How comfortable would you be with this? How comfortable would you be about going shopping now?

For me, I would not like this at all, but I can understand why store and retail outlets are interested, as they are all working in a very competitive market trying to maximize every dollar or euro they can get.

Along side the ethical concerns, we also have some legal aspects to consider. Some of these are a bit in the grey-ish area, as some aspects of these kind of scenarios are slightly addresses by EU GDPR and the EU Artificial Intelligence guidelines. But what about other countries around the World. Then it comes to training and deploying these facial models, they are dependent on having a good training data set. This means they needs lots and lots of pictures of people and these pictures need to be labelled with descriptive information about the person. For these public deployments of facial recognition systems, then will need more and more training samples/pictures. This will allow the models to improve and evolve over time. But how will these applications get these new pictures? They claim they don’t keep any of the images of people. They only take the picture, use the model on it, and then perform some action. They claim they do not keep the images! But how can they improve and evolve their solution?

I’ll have another blog post giving more examples of how machine/deep learning, video and image captures are being used to monitor people going about their daily lives.

 

HiveMall: Transform Categorical features to Numerical

Posted on Updated on

HiveMall is a machine learning library that sits on top of Hive and provides SQL interface to wide range of data preparation and machine learning algorithms.

A common task faced for many machine learning exercises is to convert the data from the format it is captured in (raw data) into a format that is required by the machine learning algorithms. Most ML tools will either have functionality built into the algorithms to do this automatically or will provide functions to allow you to manage this process yourself.

In HiveMall we have the ‘quantified_features’ function and is used for transforming values of non-number columns to indexed numbers, but it does have some unusual but useful features.

In this example I’ll use the titanic data set to illustrate the usage of this feature.

Screenshot 2019-04-29 15.14.42

Here we have a mixture of features with categorical and numerical.

select 
  quantified_features(
    ${output_row}, PassengerId, Survived, Pclass, Sex, Age, SibSp, Parch, Fare, Cabin, Embarked) as features
from (
  select * from titanic
  order by Passengerid asc
) t
limit 5;

and we get the following output

[1.0,0.0,0.0,3.0,0.0,22.0,1.0,0.0,7.25,0.0,1.0]
[2.0,1.0,1.0,1.0,1.0,38.0,1.0,0.0,71.2833,1.0,2.0]
[3.0,1.0,1.0,3.0,1.0,26.0,0.0,0.0,7.9250,0.0,1.0]
[4.0,1.0,1.0,1.0,1.0,35.0,1.0,0.0,53.1,3.0,1.0]
[5.0,1.0,0.0,3.0,0.0,35.0,0.0,0.0,8.05,0.0,1.0]

The ordering within the attributes is important, and some thinking is needed if there is a defined order and you want this reflected in the outputs of the transformed features

If you are a numeric field that you want treated as a categorical, and transformed, you can cast it into a string

e.g.

cast(SibSp as string)

Migrating Python ML Models to other languages

Posted on Updated on

I’ve mentioned in a previous blog post about experiencing some performance issues with using Python ML in production. We needed something quicker and the possible languages we considered were C, C++, Java and Go Lang.

But the data science team used R and Python, with just a few more people using Python than R on the team.

One option was to rewrite everything into the language used in production. As you can imagine no-one wanted to do that and there was no way of ensure a bug free solution and one that gave similar results to the R and Python models. The other option was to look for some code to convert the models from one language to another.

The R users was well versed in using PMML. Predictive Model Markup Language (PMML) has been around a long time and well known and used by certain groups of data scientists who have been around a while. It is also widely supported by many analytics vendors, and provides an inter-change format to allow predictive models to be described and exchanged. For newer people, they hadn’t heard of it. PMML is an XML based interchange specification.

But with PMML there are some limitation. Not with the specification but how it is implemented by the various vendors that support it. PMML supports the exchange of the model pipeline including the data transformations as well as the model specification. Most vendors only support some elements of this and maybe just a couple of models. And there-in lies the problem. How can a ML pipeline be migrated from, as Python, to some other language and/or tool. There are limitations.

If you do want to explore PMML with Python check out the sklearn2pmml package and is also available on PyPl. This package allows you to export the ML pipeline and the model specification. As with most other implementations of PMML there are some parts of the PMML specification not implement, but it is better than post of the other implementation out there.

An alternative is to look at code translations options. With these we want something that will take our ML pipeline and convert it to another programming language like C++, JAVA, Go, etc. There aren’t too many solutions available to do this. One such solution we’ve explored over the past couple of weeks is called m2cgen.

m2cgen (Model 2 Code Generator) is a lightweight library which provides an easy way to transpile trained statistical models into a native code (Python, C, Java, Go). You can supply M2cgen with a range of models (linear, SVM, tree, random forest, or boosting, etc) and the tool will output code in the chosen language that will represent the trained model. The code generated will generated into native code without dependencies. Other packages or libraries are not dependent or required in the translated language. For example here is an example Decision Tree translated into a number of different languages.

 

C

#include <string.h>
void score(double * input, double * output) {
    double var0[3];
    if ((input[2]) <= (2.6)) {
        memcpy(var0, (double[]){1.0, 0.0, 0.0}, 3 * sizeof(double));
    } else {
        if ((input[2]) <= (4.8500004)) {
            if ((input[3]) <= (1.6500001)) {
                memcpy(var0, (double[]){0.0, 1.0, 0.0}, 3 * sizeof(double));
            } else {
                memcpy(var0, (double[]){0.0, 0.3333333333333333, 0.6666666666666666}, 3 * sizeof(double));
            }
        } else {
            if ((input[3]) <= (1.75)) {
                memcpy(var0, (double[]){0.0, 0.42857142857142855, 0.5714285714285714}, 3 * sizeof(double));
            } else {
                memcpy(var0, (double[]){0.0, 0.0, 1.0}, 3 * sizeof(double));
            }
        }
    }
    memcpy(output, var0, 3 * sizeof(double));
}

Java

public class Model {

    public static double[] score(double[] input) {
        double[] var0;
        if ((input[2]) <= (2.6)) {
            var0 = new double[] {1.0, 0.0, 0.0};
        } else {
            if ((input[2]) <= (4.8500004)) {
                if ((input[3]) <= (1.6500001)) {
                    var0 = new double[] {0.0, 1.0, 0.0};
                } else {
                    var0 = new double[] {0.0, 0.3333333333333333, 0.6666666666666666};
                }
            } else {
                if ((input[3]) <= (1.75)) {
                    var0 = new double[] {0.0, 0.42857142857142855, 0.5714285714285714};
                } else {
                    var0 = new double[] {0.0, 0.0, 1.0};
                }
            }
        }
        return var0;
    }
}

Go Lang

func score(input []float64) []float64 {
    var var0 []float64
    if (input[2]) <= (2.6) {
        var0 = []float64{1.0, 0.0, 0.0}
    } else {
        if (input[2]) <= (4.8500004) {
            if (input[3]) <= (1.6500001) {
                var0 = []float64{0.0, 1.0, 0.0}
            } else {
                var0 = []float64{0.0, 0.3333333333333333, 0.6666666666666666}
            }
        } else {
            if (input[3]) <= (1.75) {
                var0 = []float64{0.0, 0.42857142857142855, 0.5714285714285714}
            } else {
                var0 = []float64{0.0, 0.0, 1.0}
            }
        }
    }
    return var0
}

 

Machine Learning with Go Lang

Posted on Updated on

Recently I’ve been having a number of conversations with people in several countries about using Go Lang for machine learning. Most of these people have been struggling with using Python for machine learning and are looking for an alternative that will give them better performance. We have been experimenting with C++ and Go Lang to see what the performance differences are. Most of these are with the execution of the ML code. This is great and everyone is very happy with execution timings, compared to Python.

But, there is a flip side to this. Although we have faster execution timings, there is a down side in that the coding effort is higher, with more lines of code and fewer libraries/packages to support the various ML tasks. But most of these can be easily coded ourselves .

We also looked at some frameworks for converting ML models developed in one language but deployed in production using a different language. More on that in another post.

Overall the extra development work was considered worthwhile for the performance improvement and deployment gains.

Go Lang doesn’t really come with it’s own set of libraries/packages for ML, but those have a number of these that can be used to code up the necessary functions we need for our everyday ML needs.

But are there any Go Lang libraries/packages developed for ML, just like we have for the R Language, etc?  The simple answer is YES we have. But the number of these is small in comparison to R and Python. Both of these languages are interpreted languages. But those available for Go are slowly growing.

Here is list of the Go Lang libraries/packages that we examined and evaluated for these projects. Some are available from the Go Lang website/wiki and others are available on Github.

  • Anna – Artificial Neural Network Aspiration, aims to be self-learning and self-improving software.
  • bayesian – A naive bayes classifier.
  • Dialex – Dialex is a smart pipe that unscrambles text and makes it machine-readable.
  • Cloudforest – Ensembles of decision trees
  • ctw – Context Tree Weighting and Rissanen-Langdon Arithmetic Coding
  • eaopt – An evolutionary optimization library.
  • evo – a framework for implementing evolutionary algorithms in Go.
  • gobrain – Neural Networks
  • Go Learn – Machine Learning for Go
  • go-algs/maxflow Maxflow (graph-cuts) energy minimization library.
  • go-graph – Graph library for Go/Golang language
  • go-galib – Genetic algorithms.
  • go-pr – Pattern recognition package in Go lang
  • golinear – Linear SVM and logistic regression.
  • go-mind – A neural network library built in Go
  • go_ml – Linear Regression, Logistic Regression, Neural Networks, Collaborative Filtering, Gaussian Multivariate Distribution.
  • go-ml-transpiler – An open source Go transpiler for machine learning models.
  • go-mxnet-predictor – Go binding for MXNet c_predict_api to do inference with pre-trained model.
  • gorgonia – Neural network primitives library (like Theano or Tensorflow but for Go)
  • go-porterstemmer – An efficient native Go clean room implementation of the Porter Stemming algorithm.
  • go-pr – Gaussian classifier.
  • ntmNeural Turing Machines implementation
  • paicehusk – Go implementation of the Paice/Husk Stemmer
  • RF – Random forests implementation in Go
  • tfgo – Tensorflow + Go, the gopher way.

 

Machine Learning Tools and Workbenches

Posted on Updated on

The following is a list of the most commonly used tools and workbenches for machine learning. These are specific to machine learning only. This list does not include any library or frameworks. These are tools and workbenches only. Most offering machine learning tools will include the following features:

  • Easy drag and drop capabilities
  • Data collection
  • Data preparation and cleaning
  • Model building
  • Data Visualization
  • Model Deployment
  • Integration with other tools and languages

As more and more organizations implement machine learning, there are two core aims they want to achieve.

  1. Employee Productivity: Who wants to spend days or weeks writing mundane code to load data, clean data, etc etc etc. No one wants to do this and especially employers don’t want their staff wasting time on this. Instead they are happy to invest in tools and workbenches where a lot or most or all of these mundane tasks are automated for you. You can not concentrate on the important tasks of adding value to your organisation. This saves money, improves employee productivity and employee value.
  2. Integration with Technical Architecture: Many of these tools and workbenches allow for easy integration with the technical architecture and thereby allowing easy and quick integration of machine learning withe the day to day activities of the organization. This saves money, improves employee productivity and employee value.

SAS

SAS software has been around for every and is the great grand-daddy of analytics and machine learning. They have built a large number of machine learning tools and solutions built upon these for various industries. Their core machine learning tools include SAS Enterprise Miner and SAS Visual Data Mining and Machine Learning.

Microsoft

Microsoft have been improving their Machine Learning offering over the years and most of this is based on the Azure cloud platform with Microsoft Azure Machine Learning Studio and Azure Databricks.

SAP

SAP Leonardo is a cloud based platform for machine learning and supports tight integration with other SAP software.

Oracle

Oracle have a number of machine learning tools and supports for the main machine learning languages. They have built a large number of applications (both cloud and on-premises) with in-built machine learning. Their main tools for machine learning include Oracle Data Miner, Oracle Machine Learning and Oracle Analytics (OAC or DVD versions)

Cloudera

If you work with hadoop and big data then you are probably using Cloudera in some way. Cloudera have hired Hilary Mason as their GM of ML. By taking an ‚ÄúAI factory‚ÄĚ approach to turning data into decisions, you can make the process of building, scaling, and deploying enterprise ML and AI solutions automated, repeatable, and predictable‚ÄĒboring even. Cloudera Data Science Workbench is their solution.

Screenshot 2019-04-17 13.10.46

IBM

IBM have a number of machine learning tools, one of them being a long standing member of the machine learning community, SPSS Modeler. Other machine learning tools include Watson Studio, IBM Machine Learning for z/OS, and IBM Watson Explorer.

Google

Google have a large number of machine learning solutions including everything from traditional machine learning, into NLP, in Image processing, Video processing, etc. It’s a long list. Many of these come with various APIs to access these features. Most of these revolve around their Google AI Cloud offering. But sticking with the tools and workbenches we have AI Platform Notebooks, Kubeflow, and BigQuery ML.

TensorBoard

TensorBoard is a suite of tools for graphical representation of different aspects and stages of machine learning in TensorFlow.

Amazon

A bit like Goolge, Amazon has a large number of solutions for machine learning and AI, and most of these are available via an API or some cloud service. Amazon SageMaker is their main service.

Looker

Looker connects directly with Google BQML reduces additional complexity for data scientists by eliminating the need to move outputs of predictive models back into the database for use, while also increases the time-to-value for business users, allowing them to operationalize the outputs of predictive metrics to make better decisions every day.

Weka

Weka has been around for a long time and still popular in some research groups. Weka is a collection of machine learning algorithms for data mining tasks. It contains tools for data preparation, classification, regression, clustering, association rules mining, and visualization.

RapidMiner

RapidMiner Studio has been around for a long time and is one of the few more visual workflow tools (that everyone else should be doing).

Databricks

From the people who created Spark, we have another notebook solution for your machine learning projects called Databricks Workbench.

KNIME

KNIME Analytics Platform is the open source software for creating data science applications and services.

Dataiku

Dataiki Data Science (DSS) is a collaborative data science software workflow platform enabling data exploration, prototyping and delivery of analytical and machine learning solutions.

 

I’ve not included the tools like R Studio and Notebooks in this list as they don’t really address the aims listed above. But you will notice a lot of the above solutions are really Jupyter Notebooks. Most of these vendors have a long way to go to make the tasks of machine learning boring.

This list does not cover all available tools and workbenches, but it does list the most common one you will come across.

Data Sets for Analytics

Posted on Updated on

When working with analytics, in whatever flavor, one of the key things you need is some data. But data comes in many different shapes and sizes, but where can you get some useful data, be it transactional, time-series, meta-data, analytical, master, categorical, numeric, regression, clustering, etc.

Many of the popular analytics languages have some data sets built into them. For example the R language comes pre-loaded with data sets and these can be accessed using

data()

but many of the R packages also come with data sets.

Similarly if you are using Python, it comes with some pre-loaded data sets and similarly many of the Python libraries have data sets build into them. For example scikit learn.

from sklearn import datasets

But where else can you get data sets. There are lots and lots of website available with data sets and the list could be very long. The following is a list of, what I consider, the websites with the best data sets.

Kaggle

Amazon Open Data

UCI Machine Learning Repository

Google Search Engine

Google Open Images Data

Google Fiance

Microsoft Open Data

Awesome Public Datasets Collection

EU Open Data

US Government Data

US Census Bureau

Ireland Open Data

Northern Ireland Public Open Data

UK Open Data

UK Data Services data sets

Image Processing Data

Carnegie Mellon University Data Sets

World Bank Open Data

IMF Open Data

Movie Reviews Data Set

Amazon Reviews

Amazon public data sets

IMDb Datasets

Github List of Public Data Sets

Computer Vision data sets

Boston Housing Data Set and from here

ODSC – 25 picks of open data sets

NHS Open Data Sets – including prescriptions issued in England

 

Time Series Forecasting in Oracle – Part 1

Posted on

 

Time-series analysis comprises methods for analyzing time series data in order to extract meaningful statistics and other characteristics of the data. In this blog post I’ll introduce what time-series analysis is, the different types of time-series analysis and introduce how you can do this using SQL and PL/SQL in Oracle Database. I’ll have additional blog posts giving more detailed examples of Oracle functions and how they can be used for different time-series data problems.

Time-series forecasting is the use of a model to predict future values based on previously observed/historical values. It is a form of regression analysis with additions to facilitate trends, seasonal effects and various other combinations.

Screenshot 2019-04-13 12.59.56

Time-series forecasting is not an exact science but instead consists of a set of statistical tools and techniques that support human judgment and intuition, and only forms part of a solution. It can be used to automate the monitoring and control of data flows and can then indicate certain trends, alerts, rescheduling, etc., as in most business scenarios it is used for predict some future customer demand and/or products or services needs.

Typical application areas of Time-series forecasting include:

  • Operations management: forecast of product sales; demand for services
  • Marketing: forecast of sales response to advertisement procedures, new promotions etc.
  • Finance & Risk management: forecast returns from investments
  • Economics: forecast of major economic variables, e.g. GDP, population growth, unemployment rates, inflation; useful for monetary & fiscal policy; budgeting plans & decisions
  • Industrial Process Control: forecasts of the quality characteristics of a production process
  • Demography: forecast of population; of demographic events (deaths, births, migration); useful for policy planning

When working with time-series data we are looking for a pattern or trend in the data. What we want to achieve is the find a way to model this pattern/trend and to then project this onto our data and into the future. The graphs in the following image illustrate examples of the different kinds of scenarios we want to model.

Most time-series data sets will have one or more of the following components:

  • Seasonal: Regularly occurring, systematic variation in a time series according to the time of year.
  • Trend: The tendency of a variable to grow over time, either positively or negatively.
  • Cycle: Cyclical patterns in a time series which are generally irregular in depth and duration.¬†Such cycles often correspond to periods of economic expansion or contraction.¬† Also know as the business cycle.¬†
  • Irregular: The Unexplained variation in a time series.

When approaching time-series problems you will use a combination of visualizations and time-series forecasting methods to examine the data and to build a suitable model. This is where the skills and experience of the data scientist becomes very important.

Oracle provided a algorithm to support time-series analysis in Oracle 18c. This function is called Exponential Smoothing. This algorithm allows for a number of different types of time-series data and patterns, and provides a wide range of statistical measures to support the analysis and predictions, in a similar way to Holt-Winters.

Screenshot 2019-04-15 11.57.40

The first parameter for the Exponential Smoothing function is the name of the model to use. Oracle provides a comprehensive list of models and these are listed in the following table.

Screenshot 2019-04-15 11.57.40

Check out my other blog posts on performing time-series analysis using the Exponential Smoothing function in Oracle Database. These will give more detailed examples of how the Oracle time-series functions, using the Exponential Smoothing algorithm, can be used for different time-series data problems. I’ll also look at example of the different configurations.