Data Analysis From Scratch With Python: Step By Step Guide

What is Unsupervised Learning?
In contrast, Unsupervised Learning means there’s no supervision or guidance.
It’s often thought of as having no correct answers, just acceptable ones.
For example, in Clustering (this falls under Unsupervised Learning) we’re trying
to discover where data points aggregate (e.g. are there natural clusters?). Each
data point is not labeled anything so our model and computer won’t be learning
from examples. Instead, our computer is learning to identify patterns without any
external guidance.
This seems to be the essence of true Artificial Intelligence wherein the computer
can learn without human intervention. It’s about learning from the data itself and
trying to find the relationship between different inputs (notice there’s no
expected output here in contrast to Regression and Classification discussed
earlier). The focus is on inputs and trying to find the patterns and relationships
among them. Perhaps there are natural clusters or there are clear associations
among the inputs. It’s also possible that there’s no useful relationship at all.
How to Approach a Problem
Many data scientists approach a problem in a binary way. Does the task fall
under Supervised or Unsupervised Learning?
The quickest way to figure it out is by determining the expected output. Are we
trying to predict y values based on new x values (Supervised Learning,
Regression)? Is a new input under category A or category B based on previously

---

labeled data (Supervised Learning, Classification)? Are we trying to discover
and reveal how data points aggregate and if there are natural clusters
(Unsupervised Learning, Clustering)? Do inputs have an interesting relationship
with one another (do they have a high probability of co-occurrence)?
Many advanced data analysis problems fall under those general questions. After
all, the objective is always to predict something (based on previous examples) or
explore the data (find out if there are patterns).

---

10. Regression
In the previous chapter we’ve talked about Unsupervised and Supervised
Learning, including a bit about Linear Regression. In this chapter let’s focus on
Regression (predicting an output based on a new input and previous learning).
Basically, Regression Analysis allows us to discover if there’s a relationship
between an independent variable/s and a dependent variable (the target). For
example, in a Simple Linear Regression we want to know if there’s a
relationship between x and y. This is very useful in forecasting (e.g. where is the
trend going) and time series modelling (e.g. temperature levels by year and if
global warming is true).