Data Science With Python | Python For Data Science | Python Data Science Course | Simplilearn

What’s in it for you?
What is Data Science?
Basics of Python for Data Analysis
Why learn Python?
How to Install Python?
Python Libraries for Data Analysis
Exploratory analysis using Pandas
Introduction to series and data frame
Loan Prediction Problem
Data Wrangling using Pandas
Building a Predictive Model using Scikit-Learn
Logistic Regression

What is Data Science?
Example
Restaurants can predict how many
customers will visit on a weekend
and plan their food inventory to
handle the demand
Service Planning
System can be trained based on
customer behavior pattern to
predict the likelihood of a
customer buying a product
Customer Prediction
Data Science is about finding and exploring data in real world, and then using that knowledge to solve
business problems

Why Python?
Let’s first understand, why we
want to use Python?

Why Python?
The usage statistics based on google trends depict that Python is currently more popular than R or SAS
for Data Science!

Why Python?
SPEED PACKAGES DESIGN GOAL
But, there are various factors you should consider before deciding which language is best for
your Data Analysis:

Why Python?
For instructor
Design Goal:
Syntax rules in python helps in building application with concise and readable code base
Packages:
There are numerous packages in Python to choose from like pandas to aggregate & manipulate data, Seaborn or
matplotlib to visualize relational data to mention a few
Speed:
Studies suggest that Python is faster than several widely used languages. Also, we can further speed up python
using algorithms and tools

Installing Python
Now, let’s install Python to
begin the fun

Installing Python
• Go to: http://continuum io/downloads
• Scroll down to download the graphical installer
suitable for your operating system
After successful installation, you can launch Jupyter notebook from Anaconda Navigator
Anaconda comes with pre-installed libraries
In this tutorial, we will be working on Jupyter notebook using Python 3

Python libraries for Data Analysis
Let’s get to know some
important Python libraries for
Data Analysis

There are many interesting libraries that have made Python popular with Data Scientists:

Most useful library for variety of high level science and engineering modules like discrete Fourier
transform, Linear Algebra, Optimization and Sparse matrices
Pandas for structured data operations and manipulations It is extensively
used for data munging and preparation
The most powerful feature of NumPy is n-dimensional array This library also contains basic linear algebra
functions, Fourier transforms, advanced random number capabilities
Matplotlib for plotting vast variety of graphs, starting from histograms to line plots to heat plots
contains a lot of efficient tools for machine learning and statistical modeling including classification,
regression, clustering and dimensional reduction
For instructor

Additional libraries, you might need:
Networkx & I graph
Tensorflow
BeautifulSoup
OS

os for Operating system and file operations
networkx and igraph for graph based data manipulations
TensorFlow
BeautifulSoup for scrapping web
For instructor

What is SciPy?
SciPy is a set of scientific and numerical tools for Python
• It currently supports special functions, integration, ordinary
differential equation (ODE) solvers, gradient optimization, and
others
• It has fully-featured versions of the linear algebra modules
• It is built on top of NumPy

What is NumPy?
NumPy is the fundamental package for scientific computing with
Python. It contains:
• Powerful N-dimensional array object
• Tools for integrating C/C++ and Fortran code
• It has useful linear algebra, Fourier transform, and random number
capabilities

What is Pandas?
• The most useful Data Analysis library in Python
• Instrumental in increasing the use of Python in Data Science
community
• It is extensively used for data munging and preparation
Pandas is used for structured data operations & manipulations

Let’s understand the two most common terms used in Pandas:
Series Dataframe

A Series is a one-dimensional object that can
hold any data type such as integers, floats
and strings
Series
A DataFrame is a two dimensional object
that can have columns with potential
different data types
DataFrame
Pandas

Default column
names
Default index
Default index
Series DataFrame

Problem Statement: Based on customer data, predict whether a particular customer’s loan
will be approved or not
LOAN

Now, let’s explore our data using Pandas!

Import the necessary libraries and read the dataset using read_csv() function:

You can call describe() function to describe all the columns:

Let’s see numercial values’ distribution
1 Loan Amount

2 Applicant Income

Categorical values’ distribution using matplotlib library:
Credit History

Hence, ‘loanAmount’ and ‘ApplicantIncome’ needs
Data Wrangling as some extreme values are observed!

Before proceeding further,
let’s understand what is
Data Wrangling and why we
need it?

Data Wrangling: Process of cleaning and unifying messy
and complex data sets
It reveals more information about your data
Enables decision-making skills in the organization
Helps to gather meaningful and precise data for the business

You can see if your data has missing values:

And then you can replace the missing values:

You can access the data types of each column in a DataFrame:

You can perform basic math operations to know more about your data:

You can combine your DataFrames:
Combining DataFrame objects can be done using simple concatenation (provided they have the same columns):
Creates an array of
specified shape and fills it
with random values using
numpy

Also, if your DataFrame do not have an identical structure:

You can create a merged dataframe using the merge() function based on the key:

Model Building using Scikit-learn
Now, that we have done data
wrangling, let’s build a
predictive model

We will use Scikit-learn
module as it provides a range
of supervised and
unsupervised learning
algorithms

Importing the required scikit-learn module:

Extracting the variables and then splitting the data into train and test:

In this case, we will use Logistic
Regression model
Logistic Regression is appropriate
when the dependent variable is
binary

Fitting the data into Logistic Regression model:

Predicting the test results:

To describe the performance of the model let’s build the confusion matrix on test data:

Let’s calculate ACCURACY and PRECISION from confusion matrix:
False Positive
True Positive
False Negative
True Negative

Let’s calculate ACCURACY and PRECISION from confusion matrix:
• Accuracy
Overall, how often is the classifier correct?
(TP+TN)/total = (103+18)/150 = 0.80
• Precision
When it predicts yes, how often is it correct?
TP/predicted yes = 103/130 = 0.79

We can also find the accuracy through Python module:

So , we have built a model with 80% accuracy

Summary
Data Science & its popularity with python Data Analysis Libraries in python Series and dataframe in pandas
Logistic Regression using scikitData wranglingExploratory analysis

Data Science With Python | Python For Data Science | Python Data Science Course | Simplilearn

Recommended

More Related Content

What's hot (20)

Similar to Data Science With Python | Python For Data Science | Python Data Science Course | Simplilearn (20)

More from Simplilearn (20)

Recently uploaded (20)

Data Science With Python | Python For Data Science | Python Data Science Course | Simplilearn

Editor's Notes