Machine

Learning in Python

Dr. Hafeez
 Python and Scipy installa:on
•  Hi, You cannot get started with machine learning in Python un:l you have access
to the plaAorm

•  This lesson is easy, you must download and install the Python 3.6 plaAorm on your
computer
• 
•  Visit the Python homepage and download Python for your opera:ng system
(Linux, OS X or Windows). Install Python on your computer. You may need to use a
plaAorm specific package manager such as macports on OS X or yum on RedHat
Linux

•  You also need to install the SciPy plaAorm and the scikit-learn library. I
recommend using the same approach that you used to install Python. You can
install everything at once (much easier) with Anaconda. Anaconda is
recommended for beginners
•  Start Python for the first :me from command line by typing "python" at the
command line. Check the versions of everything you are going to need using the
code below:
 Python for first :me
•  # Python version
•  import sys
•  print('Python: {}'.format(sys.version))
•  # scipy
•  import scipy
•  print('scipy: {}'.format(scipy.__version__))
•  # numpy
•  import numpy
•  print('numpy: {}'.format(numpy.__version__))
•  # matplotlib
•  import matplotlib
•  print('matplotlib: {}'.format(matplotlib.__version__))
•  # pandas
•  import pandas
•  print('pandas: {}'.format(pandas.__version__))
•  # scikit-learn
•  import sklearn
•  print('sklearn: {}'.format(sklearn.__version__))
 ML in Python
•  Need more help? See this blog post:

>>How to Setup a Python Environment for
Machine Learning and Deep Learning with
Anaconda
•  In the next lesson, we will look at basic Python
and SciPy syntax

•  Take the next step and make fast progress
in Machine Learning Mastery With Python.
 Basic Python and Scipy Syntax
•  Ability to read and write basic Python scripts

•  As a developer, you can pick up new programming languages pre`y

quickly. Python is case sensi:ve, uses hash (#) for comments and
uses white space to indicate code blocks (white space ma`ers)

•  Today's task is to prac:ce the basic syntax of the Python

programming language and important SciPy data structures in the
Python interac:ve environment.

•  Prac:ce assignment, working with lists and flow control in Python.

•  Prac:ce working with NumPy arrays.
•  Prac:ce crea:ng simple plots in Matplotlib.
•  Prac:ce working with Pandas Series and DataFrames.
 Basic Python and Scipy Syntax
•  For example, below is a simple example of crea:ng a Pandas
DataFrame.
•  # dataframe
•  import numpy
•  import pandas
•  myarray = numpy.array([[1, 2, 3], [4, 5, 6]])
•  rownames = ['a', 'b']
•  colnames = ['one', 'two', 'three']
•  mydataframe = pandas.DataFrame(myarray, index=rownames,
columns=colnames)
•  print(mydataframe)

•  In the next lesson, we will look at loading data into Python.

 Load Datasets from CSV
•  Hi, Machine learning algorithms need data
•  You can load your own data from CSV files but when
you are gekng started with machine learning in
Python you should prac:ce on standard machine
learning datasets
•  Your task for today's lesson is to get comfortable
loading data into Python and to find and load standard
machine learning datasets
•  There are many excellent standard machine learning
datasets in CSV format that you can download and
prac:ce with on the UCI machine learning repository
 Load Datasets from CSV
•  Prac:ce loading CSV files into Python using
the CSV.reader() func:on in the standard
library.
•  Prac:ce loading CSV files using NumPy and
the numpy.loadtxt() func:on.
•  Prac:ce loading CSV files using Pandas and
the pandas.read_csv() func:on.
 Load Datasets from CSV
•  To get you started below is a snippet that will load the Pima Indians
onset of diabetes dataset using Pandas directly from the UCI
Machine Learning Repository:

•  # Load CSV using Pandas from URL

•  from pandas import read_csv
•  url = "h`ps://goo.gl/bDdBiA"
•  names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age',
'class']
•  data = read_csv(url, names=names)
•  print(data.shape)

•  In the next lesson, you will calculate descrip:ve sta:s:cs for your
data in Python.

 Understand Data with Descrip:ve
Stats
•  Hi, once you have loaded your data into Python
you need to be able to understand it.
•  The be`er you can understand your data, the
be`er and more accurate the models that you
can build. The first step to understanding your
data is to use descrip:ve sta:s:cs.
•  Today your lesson is to learn how to use
descrip:ve sta:s:cs to understand your data. I
recommend using the helper func:ons provided
on the Pandas DataFrame.
 Understand Data with Descrip:ve
Stats
•  Understand your data using the head() func:on
to look at the first few rows.
•  Review the dimensions of your data with
the shape property.
•  Look at the data types for each a`ribute with
the dtypes property.
•  Review the distribu:on of your data with
the describe() func:on.
•  Calculate pair-wise correla:on between your
variables using the corr() func:on.
 Understand Data with Descrip:ve
Stats
•  The below example loads the Pima Indians onset of diabetes
dataset and summarizes the distribu:on of each a`ribute.
•  # Sta:s:cal Summary
•  import pandas
•  url = "h`ps://goo.gl/bDdBiA"
•  names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age',
'class']
•  data = pandas.read_csv(url, names=names)
•  descrip:on = data.describe()
•  print(descrip:on)
•  In the next lesson, you will learn about data visualiza:on in Python.

 Understand Data with Data
visualiza:on
•  Hi, con:nuing on from the last lesson, you must
spend :me to be`er understand your data.
•  A second way to improve your understanding of
your data is by using data visualiza:on
techniques (e.g. plokng).
•  Today, your lesson is to learn how to use plokng
in Python to understand a`ributes alone and
their interac:ons. Again, I recommend using the
helper func:ons provided on the Pandas
DataFrame.
 Data visualiza:on
•  Use the hist() func:on to create a histogram
of each a`ribute.
•  Use the plot(kind='box') func:on to create box
and whisker plots of each a`ribute.
•  Use the pandas.sca8er_matrix() func:on to
create pair-wise sca`er plots of all a`ributes.
 Understand Data with Data
visualiza:on
•  For example, the snippet below will load the diabetes dataset and create a
sca`er plot matrix of the dataset.

•  # Sca`er Plot Matrix
•  import matplotlib.pyplot as plt
•  import pandas
•  from pandas.plokng import sca`er_matrix
•  url = "h`ps://goo.gl/bDdBiA"
•  names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
•  data = pandas.read_csv(url, names=names)
•  sca`er_matrix(data)
•  plt.show()

•  In the next lesson, you will learn how to pre-process your data in Python.