Before we can talk about concrete machine learning algorithms, we have to talk about how best to store the data we will chew through. This is important as the most advanced learning algorithm will not be of any help to us if they will never finish. This may be simply because accessing the data is too slow. Or maybe its
representation forces the operating system to swap all day. Add to this that Python is an interpreted language (a highly optimized one, though) that is slow for many numerically heavy algorithms compared to C or Fortran. So we might ask why on earth so many scientists and companies are betting their fortune on Python even in the highly computation-intensive areas? The answer is that in Python, it is very easy to offload number-crunching tasks to the lower layer in the form of a C or Fortran extension.

That is exactly what NumPy and SciPy do (http://scipy.org/install.html). In this tandem, NumPy provides the support of highly optimized multidimensional arrays, which are the basic data structure of most state-of-the-art algorithms. SciPy uses those arrays to provide a set of fast numerical recipes. Finally, Matplotlib (http://matplotlib.org/) is probably the most convenient and feature-rich library to plot high-quality graphs using Python.

Installing Python Luckily, for all the major operating systems, namely Windows, Mac, and Linux,
there are targeted installers for NumPy, SciPy, and Matplotlib. If you are unsure about the installation process, you might want to install Enthought Python Distribution (https://www.enthought.com/products/epd_free.php) or Python(x,y) (http://code.google.com/p/pythonxy/wiki/Downloads), which
come with all the earlier mentioned packages included. Chewing data effciently with NumPy and
intelligently with SciPy Let us quickly walk through some basic NumPy examples and then take a look at
what SciPy provides on top of it. On the way, we will get our feet wet with plotting using the marvelous Matplotlib package.

You will find more interesting examples of what NumPy can offer at

http://www.scipy.org/Tentative_NumPy_Tutorial. You will also fnd the book NumPy Beginner’s Guide – Second Edition, Ivan Idris,Packt Publishing very valuable.

Additional tutorial style guides are at http://scipy-lectures.github.com;

you may also visit the offcial SciPy tutorial at
http://docs.scipy.org/doc/scipy/reference/tutorial.

This Blog will give you a broad overview of the types of learning algorithms that
are currently used in the diverse fields of machine learning and what to watch out
for when applying them. From our own experience, however, we know that doing
the “cool” stuff—using and tweaking machine learning algorithms such as support
vector machines (SVM), nearest neighbor search (NNS), or ensembles thereof—will
only consume a tiny fraction of the overall time of a good machine learning expert.
Looking at the following typical workflow, we see that most of our time will be spent
in rather mundane tasks:
1. Reading the data and cleaning it.
2. Exploring and understanding the input data.
3. Analyzing how best to present the data to the learning algorithm.
4. Choosing the right model and learning algorithm.
5. Measuring the performance correctly.
When talking about exploring and understanding the input data, we will need a
bit of statistics and basic math. But while doing this, you will see that those topics,
which seemed so dry in your math class, can actually be really exciting when you
use them to look at interesting data.
The journey begins when you read in the data. When you have to face issues such as
invalid or missing values, you will see that this is more an art than a precise science.
And a very rewarding one, as doing this part right will open your data to more
machine learning algorithms, and thus increase the likelihood of success.
With the data being ready in your program’s data structures, you will want to get a
real feeling of what kind of animal you are working with. Do you have enough data
to answer your questions? If not, you might want to think about additional ways to
get more of it. Do you maybe even have too much data? Then you probably want to
think about how best to extract a sample of it.Often you will not feed the data directly into your machine learning algorithm.Instead, you will find that you can refine parts of the data before training. Many
times, the machine learning algorithm will reward you with increased performance.You will even find that a simple algorithm with refined data generally outperforms a very sophisticated algorithm with raw data. This part of the machine learning workflow is called feature engineering, and it is generally a very exciting and
rewarding challenge. Creative and intelligent that you are, you will immediately see the results.

Choosing the right learning algorithm is not simply a shootout of the three or four that are in your toolbox (there will be more algorithms in your toolbox that you will see). It is more of a thoughtful process of weighing different performance and functional requirements. Do you need fast results and are willing to sacrifice quality? Or would you rather spend more time to get the best possible result? Do you have a
clear idea of the future data or should you be a bit more conservative on that side? Finally, measuring the performance is the part where most mistakes are waiting for the aspiring ML learner. There are easy ones, such as testing your approach with the  same data on which you have trained. But there are more difficult ones; for example, when you have imbalanced training data. Again, data is the part that determines
whether your undertaking will fail or succeed.

We see that only the fourth point is dealing with the fancy algorithms. Nevertheless,we hope that this book will convince you that the other four tasks are not simply chores, but can be equally important if not more exciting. Our hope is that by the end of the book you will have truly fallen in love with data instead of learned algorithms.To that end, we will not overwhelm you with the theoretical aspects of the diverse ML
algorithms, as there are already excellent books in that area (you will fnd pointers in Appendix, Where to Learn More about Machine Learning). Instead, we will try to provide an intuition of the underlying approaches in the individual chapters—just enough for you to get the idea and be able to undertake your first steps. Hence, this book is by no means “the definitive guide” to machine learning. It is more a kind of starter kit. We hope that it ignites your curiosity enough to keep you eager in trying to learn more
and more about this interesting field.

In the rest of this chapter, we will set up and get to know the basic Python libraries,NumPy and SciPy, and then train our first machine learning using scikit-learn. During this endeavor, we will introduce basic ML concepts that will later be used throughout the book. The rest of the chapters will then go into more detail through the five steps described earlier, highlighting different aspects of machine learning in Python using
diverse application scenarios.