Dimensionality reduction has been a standard methodology to deal with datasets that have a lot of features, more than a typical model can handle effectively. Reducing the number of features can also save time and storage space, while when it comes to sensitive data it can be a big plus as it enables anonymity in the people involved. What’s more, in some cases, a reduced dimensionality dataset can be more effective as there is less noise in it. However, conventional dimensionality reduction methods don’t always do the trick due to the inherent limitations they have. For example, PCA only considers linear relationships among the variables and a linear combination of features, as a solution.
Of course, other people are not sitting idle when it comes to this issue. There are several dimensionality reduction options that are being pursued, the most interesting of which is autoencoders. This AI-based method involves a data-driven approach to figuring out the nature of the data and creating new variables that can represent the underlying signal, by minimizing the error. The issue with this is that it often requires a lot of data and some specialized know-how in order to configure optimally. Also, this whole process may be fairly slow, due to the large number of computations involved.
An alternative approach has to do with feature fusion in a non-AI way. The idea is to maintain transparency to the extent this is possible, while at the same time optimize the whole process in terms of speed. The use of multiple operators, some linear and some non-linear, is essential, while the option of dropping useless features is also very useful. Naturally, this whole process would be more effective in the presence of a target variable, but it should be able to work without it, for better applicability. Whatever the case, the use of a metric able to handle non-linear correlations is paramount since the conventional correlation metric used leaves a lot to be desired.
Based on all this, it’s clear that the dimensionality reduction area is still capable of enhancements. Despite the great work that has been done already, there is still room for new methods that can address the limitations the existing methods have, which aren’t going away any time soon. Perhaps it would be best to explore this methodology of data engineering more, instead of focusing the latest and greatest system, which although intriguing, may sacrifice too much (e.g. transparency) in the name of accuracy, a trade-off that may no longer be cost-effective. Something to think about...
(Image by lazyprogrammer.me)
PCA has attracted a lot of questions among all of my mentees over the years, so I decided to make a fairly in-depth video on the topic. Unlike other education material on PCA, this one is light on the math, while there is a lot of emphasis on the concepts as well as how they apply to a data scientist's work. You can check out the video on Safari here.
Note that in order to view the video in its entirety you'll need a subscription to the Safari platform. Cheers!
Lately it’s hard to find someone who is a legit data scientist and yet doesn’t talk about Stats as if it’s a new religion or something. Don’t get me wrong; I find Stats a very useful tool in data analytics, especially data science. However, there are other, usually most suitable options out there to have in one’s data science toolbox.
First of all, Statistics is the state-of-the-art approach to data modeling, if you live in the mid 20th century. In our time, Stats, particularly frequentist Stats, is greatly outdated and many of the assumptions it makes about the data don’t make any sense. Also, transforming the data so that it fits the assumptions many Stats models make, is a time-consuming process which may or may not be worth the trouble. Of course if you know nothing else, or have trust issues with novel modeling options, then Stats may be the best option for you. In this case, however, it is best to brand yourself as a Stats professional instead of a data scientist, since the latter implies that you do more than just Stats.
In addition, pretty much all of the metrics used in Stats can be improved heavily by negating the normality assumption. The more data I come across, the more certain I am that this assumption may make sense in some cases, but in the majority of cases it doesn’t hold. So, using metrics that have this assumption embedded in them doesn’t really help anyone. What’s more, all this framework inevitably shapes one’s mindset and so if you get used to the unreasonable assumptions Stats usually makes about the data, you may not be able to think of the data in a different way.
Moreover, with the advent of A.I., especially the A.I. that’s directly applicable to data science, the data transformation and modeling options available to data scientists have increased dramatically. So, relying on Stats is more of a preference rather than a necessity. Besides, it’s extremely unlikely that a Stats model will be able to outperform an A.I. one when the latter is well configured.
Finally, there are other new data analytics methods waiting to be discovered and used in data science. Heuristics have made a comeback and are more and more popular in data science research, especially when it comes to complex datasets. So, sticking to Stats when there is a plethora of possibilities out there that can tackle a problem more effectively is just depressing.
Having said all that, Stats is a useful subject to learn, as it can aid one’s learning of the data science craft. Much like learning basic Mechanics can be useful if you want to being a Physics professional, learning Stats can be quite useful. Sticking to it and thinking of it as gospel, however, is not. That’s why after learning about it, it’s best to seek to expand your understanding of data analytics through delving into other frameworks, such as Machine Learning, A.I. based systems, and heuristics. Stats is just one of the tools available in the data scientist's toolbox...
Although the debate between Frequentist and Bayesian statisticians sometimes takes a more comical turn (XKCD strip), it is still important for a data scientist to know a few things about Bayesian Stats. Of course, purists of the craft will argue that Frequentist Stats will suffice but if you want to stand out of the crowd, it would definitely help going beyond the beaten path, when it comes to data analytics know-how.
This video I made recently highlights the key elements of Bayesian Stats, focusing on the concepts that although fairly straight-forward, may be obscure to the newcomer. Also, without disregarding the invaluable contribution of Frequentist Stats to data science, this video explores how the two differ and how Bayesian Stats has a lot in common with other, more modern, data analytics frameworks. Check it out when you get the chance!
Note that a subscription to the Safari platform is necessary in order to view the video in its entirety.
Dichotomy: a binary separation of a set into two mutually exclusive subsets
Data Science: the interdisciplinary field for analyzing data, building models, and bringing about insights and/or data products, which add value to an organization. Data science makes use of various frameworks and methodologies, including (but not limited) to Stats, ML, and A.I.
After getting these pesky definitions out of the way, in an effort to mitigate the chances of misunderstandings, let’s get to the gist of this fairly controversial topic. For starters, all this information here is for educational purposes and shouldn’t be taken as gospel since in data science there is plenty of room for experimentation and someone adept in it doesn’t need to abide to this taxonomy or any rules deriving from it.
The inaccurate dichotomy issues in data science, however, can be quite problematic for newcomers to the field as well as for managers involved in data related processes. After all, in order to learn about this field a considerable amount of time is required, something that is not within the temporal budget of most people involved in data science, particularly those who are starting off now. So, let’s get some misconceptions out of the way so that your understanding of the field is not contaminated by the garbage that roams the web, especially the social media, when it comes to data science.
Namely, there are (mis-)infographics out there that state that Stats and ML are mutually exclusive, or that there is no overlap between non-AI methods and ML. In other words, ML is part of AI, something that is considered blasphemy in the ML community. The reason is simple: ML as a field was developed independently of AI and has its own applications. AI can greatly facilitate ML through its various network-based models (among other systems), but ML stands on its own. After all, many ML models are not AI related, even if AI can be used to improve them in various ways. So, there is an overlap between ML and AI, but there are non-AI models that are under the ML umbrella.
Same goes with Statistics. This proud sub-field of Mathematics has been the main framework for data analytics for a long time before ML started to appear, revolting against the model-based approach dictated by Stats. However, things aren’t that clear-cut. Even if the majority of Stats models are model-based, there are also models that are hybrid, having elements of Stats and ML. Take Bayesian Networks for example, or some variants of the Naive Bayes model. Although these models are inherently Statistical, they have enough elements of ML that they can be considered ML models too. In other words, they lie on the nexus of the two sets of methods.
What about Stats and AI? Well, Variational AutoEncoders (VAEs) are an AI-based model for dimensionality reduction and data generation. So, there is no doubt that it lies within the AI set. However, if you look under the hood you’ll see that it makes use of Stats for the figuring out what the data generated by it would be like. Specifically, it makes use of distributions, a fundamentally statistical concept, for the understanding and the generation of the data involved. So, it wouldn’t be far-fetched to put VAEs in the Stats set too.
From all this I hope it becomes clear that the taxonomy of data science models isn’t that rigid as it may seem. If there was a time when this rigid separation of models made sense, this time is now gone as hybrid systems are becoming more and more popular, while at the same time the ML field expands in various directions outside AI. So, I’d recommend you take those (mis-)infographics with a pinch of salt. After all, most likely they were created by some overworked employee (perhaps an intern) with a limited understanding of data science.
A famous scientist from the Quantum Physics school of thought once said “asking the right question is more than halfway towards finding the answer.” Although it’s been years since I read this quote (which I may be paraphrasing, by the way), it still echoes a deep truth and helps guide my (non-academic) research in the data science and A.I. fields. So, I few weeks ago I put forward the question “what would a statistical framework framed around possibilities be like?”
At first glance, such a question may seem nonsensical since from an early age we’ve all be taught the core aspects of Stats and how it’s all about probabilities. There is no doubt that the probabilistic approach to modeling uncertainty has yielded a lot of fruits as the field grew, but all developments of Statistical methods were bound by the limitations of the assumptions made, mirrored by the various distributions used. In other words, if you want results with conventional Stats, you’ve got to use this or the other distribution and keep in mind that if the data you have doesn’t follow the distribution assumed, the results may not be reliable. What if the field of Stats was void of such restrictions by assuming a membership function instead of a distribution, to describe the data at hand?
I’m not going to describe in length where this rabbit hole leads, but suffice to say that the preliminary results of a framework based on this alternative approach exceeded my expectations. Also, there is no Stats process that I looked at which could not be replicated with the possibilistic approach. What’s more, since the possibilistic approach to data analytics is one of the oldest forms of A.I., it is sensible to say that such a statistical framework would be in essence AI-based, though not related to deep learning, since that’s a completely different approach to A.I. that has its own set of benefits. Nevertheless, I found that having a statistical framework that borrows an A.I. concept in its core, can provide an interesting way to bridge the gap between Stats-based data analytics and modern / A.I. based.
What’s even more interesting is that this can be a two-way street, with A.I. also being able to benefit from such a nexus between the two fields. After all, one of the biggest pain points of modern A.I. is the lack of transparency, something that’s a freebie when it comes to Stats modeling. So, an A.I. system that has elements of Stats at its core may indeed be a transparent one. However, this idea is still highly experimental, so it would be best to not discuss it further here.
Whatever the case, I have no doubt that the possibilistic approach to data has a lot of merit and hasn’t been explored enough. So, it is possible that it has a role to play in more modern data analytics systems. The question is, are you willing to accept this possibility?
Before someone says “yes, of course; you just need to apply a non-linear transformation to one of the variables!”, let me rephrase: can we measure a non-linear relationship between two variables, without any transformations whatsoever? In other words, is there a heuristic metric that can facilitate the task of establishing whether two variables are linked in some fashion, without any data engineering from our part?
The answer is “yes, of course” again. However, the relationship has to be monotonous for this to work. In other words, there needs to be a 1-1 relationship between the values of the two variables. Otherwise, it may not appear as strong, due to the nature of non-linearity.
So, if we have two variables x and y, and y is something like x^10 + exp(x), that’s a relationship that is clearly non-linear, but also monotonous. Also, the Pearson correlation of the two variables in this case is not particularly strong (for the variables tested, it was about 0.67). If it were measured by a different correlation metric, however, like a custom-built one I’ve recently developed, the relationship would be somewhat stronger (for these variables, it would be around 0.75) while Kendall's ranked correlation coefficient would produce a great result too (1.00 for these variables).
In a different scenario, where z = 1 / x, for example, the results of the correlation metrics differ more. Pearson’s correlation in this case would be something like -0.16, while the custom-made metric would yield something around -0.69. Also, Kendall’s coefficient would be -1.00.
Although the effect is not always pronounced, in cases like this one, a different metric can make the difference between a strong correlation and a not-so-strong one, affecting our decisions about the variables.
Bottom line, even if the Pearson correlation coefficient is the most popular method for measuring the relationship between two variables, it’s not the best choice when it comes to non-linear relationships. That’s why different metrics need to be used for evaluating the relationship between two variables, particularly if it’s a non-linear one.
Although I’ve talked about dimensionality reduction for data science in the corresponding video on Safari, covering various angles of the topic, I was never fully content with the methodologies out there. After all, all the good ones are fairly sophisticated, while all the easier ones are quite limited. Could there be a different (better) way of performing dimensionality reduction in a dataset? If so, what issue would such a method tackle?
First of all, conventional dimensionality reduction methods tend to come from Statistics. That’s great if the dataset is fairly simple, but methods like PCA focus on the linear relationships among the features, which although it’s a good place to start, it doesn’t cover all the bases. For example, what if features F1 and F2 have a non-linear relationship? Will PCA be able to spot that? Probably not, unless there is a strong linear component to it. Also, if F1 and F2 follow some strange distribution, the PCA method won’t work very well either.
What's more, what if you want to have meta-features that are independent to each other, yet still explain a lot of variance? Clearly PCA won’t always give you this sort of results, since for complex datasets the PCs will end up being tangled themselves. Also, ICA, a method designed for independent components, is not as easy to use since it’s hard to figure out exactly where to stop when it comes to selecting meta-features.
In addition, what’s the deal with outliers in the features? Surely they affect the end result, by changing the whole landscape of the features, breaking the whole scale equilibrium at times. Well, that’s one of the weak point of PCA and similar dimensionality reduction methods, since they require some data engineering before they can do their magic.
Finally, how much does each one of the original features contribute to the meta-features you end up with after using PCA? That’s a question that few people can answer although the answer is right there in front of them. Also, such a piece of information may be useful in evaluating the original features or providing some explanation of how much they are worth in terms of predictive potential, after the meta-features are used in a model.
All of these issues and more can be tackled by using a new approach to dimensionality reduction, one that is based on a new paradigm (the same one that can tackled the clustering issues mentioned in the previous post). Also, even though the new approach doesn’t use a network architecture, it can still be considered a type of A.I. as there is some kind of optimization involved. As for the specifics of the new approach, that’s something to be discussed in another post, when the time is right...
A/B testing is a crucial methodology / application in the data science field. Although it mainly relies on Statistics, it has a remained quite relevant in this machine learning and AI oriented era of our field. It's no coincidence that in Thinkful that's one of the first things data science students learn, once they get comfortable with descriptive Stats and basic data manipulation. So, I decided to do a video on this topic to help those interested in learning about it get a good perspective of it and understand better its relationship with Hypothesis Testing. It is my hope that this video can be a good supplement to one's learning on the subject. Enjoy!
Even though this topic may be a bit polarizing, especially among people who are new to data science, knowing more about it can be very useful, particularly if you value a sense of perspective more than a good grade in some data science crash course. The latter is bound to overemphasize either Stats or AI, depending on the instructor's knowledge and experience. However, some data science professionals, myself included, prefer a more balanced approach on the topic. This is the reason why I decided to make this video, which is now available on Safari for your viewing.
Note that this is by no means a complete tutorial on the topic, but it is a good overview of the various aspects of statistics related to data science, along with some programming resources in both Python and Julia, to get you started. Enjoy!
Zacharias Voulgaris, PhD
Passionate data scientist with a foxy approach to technology, particularly related to A.I.