Learn how to combine the three most important tools in data science: Python, SQL, and Tableau
About This Video
In Detail
Python, SQL, and Tableau are three of the most widely used tools in the world of data science. Python is the leading programming language
SQL is the most widely used means for …
Learn how to combine the three most important tools in data science: Python, SQL, and Tableau
About This Video
In Detail
Python, SQL, and Tableau are three of the most widely used tools in the world of data science. Python is the leading programming language
SQL is the most widely used means for communication with database systems
Tableau is the preferred solution for data visualization;
The course starts off by introducing software integration as a concept. We discuss some important terms such as servers, clients, requests, and responses. Moreover, you will learn about data connectivity, APIs, and endpoints. Then we continue by introducing the real-life example exercise the course is centred around: the Absenteeism at Work dataset. The preprocessing part that follows will give you a taste of what BI and data science look like in real-life, on-the-job situations. Then we continue by applying some Machine Learning to our data. You will learn how to explore the problem at hand from a machine-learning perspective, how to create targets, what kind of statistical preprocessing is necessary for this part of the exercise, how to train a Machine Learning model, and how to test it—a truly comprehensive ML exercise. Connecting Python and SQL is not immediate; we show how that's done in an entire section of the course.
By the end of that section, you will be able to transfer data from Jupyter to Workbench. And finally, as promised, Tableau will allow us to visualize the data we have been working with. We will prepare several insightful charts and will interpret the results together.
Chapter 1 : Introduction
What Does the Course Cover? 00:03:13
Chapter 2 : What is software integration?
Properties and Definitions: Data, Servers, Clients, Requests and Responses 00:04:44
Properties and Definitions: Data Connectivity, APIs, and Endpoints 00:07:05
Further Details on APIs 00:08:06
Text Files as Means of Communication 00:04:21
Definitions and Applications 00:05:25
Chapter 3 : Setting up the working environment
Setting Up the Environment - An Introduction (Do Not Skip, Please)! 00:00:52
Why Python and why Jupyter? 00:05:00
Installing Anaconda 00:06:49
The Jupyter Dashboard - Part 1 00:03:16
The Jupyter Dashboard - Part 2 00:06:15
Installing sklearn 00:01:16
Chapter 4 : What’s next in the course?
Up Ahead 00:04:08
Real-Life Example: Absenteeism at Work 00:02:49
Real-Life Example: The Dataset 00:03:18
Chapter 5 : Preprocessing
Data Sets in Python 00:03:24
Data at a Glance 00:05:54
A Note on Our Usage of Terms with Multiple Meanings 00:03:28
Picking the Appropriate Approach for the Task at Hand 00:02:18
Removing Irrelevant Data 00:06:27
Examining the Reasons for Absence 00:05:04
Splitting a Column into Multiple Dummies 00:08:38
Dummy Variables and Their Statistical Importance 00:01:28
Grouping - Transforming Dummy Variables into Categorical Variables 00:08:35
Concatenating Columns in Python 00:04:36
Changing Column Order in Pandas DataFrame 00:01:43
Implementing Checkpoints in Coding 00:02:53
Exploring the Initial “Date” Column 00:07:49
Using the “Date” Column to Extract the Appropriate Month Value 00:07:00
Introducing “Day of the Week” 00:03:36
Further Analysis of the DataFrame: Next 5 Columns 00:03:18
Further Analysis of the DaraFrame: “Education”, “Children”, “Pets” 00:04:38
A Final Note on Preprocessing 00:02:00
Chapter 6 : Machine Learnings
Exploring the Problem from a Machine Learning Point of View 00:03:20
Creating the Targets for the Logistic Regression 00:06:32
Selecting the Inputs 00:02:42
A Bit of Statistical Preprocessing 00:03:26
Train-test Split of the Data 00:06:13
Training the Model and Assessing its Accuracy 00:05:40
Extracting the Intercept and Coefficients from a Logistic Regression 00:05:17
Interpreting the Logistic Regression Coefficients 00:06:15
Omitting the dummy variables from the Standardization 00:04:12
Interpreting the Important Predictors 00:05:11
Simplifying the Model (Backward Elimination) 00:04:02
Testing the Machine Learning Model 00:04:44
How to Save the Machine Learning Model and Prepare it for Future Deployment 00:04:07
Creating a Module for Later Use of the Model 00:04:04
Chapter 7 : Installing MySQL and Getting Acquainted with the Interface
Installing MySQL 00:09:56
Setting Up a Connection 00:02:34
Introduction to the MySQL Interface 00:05:09
Chapter 8 : Connecting Python and SQL
Implementing the ‘absenteeism_module’ - Part I 00:03:50
Implementing the ‘absenteeism_module’ - Part II 00:06:24
Creating a Database in MySQL 00:06:37
Importing and Installing ‘pymysql’ 00:02:44
Creating a Connection and Cursor 00:02:55
Creating the ‘predicted_outputs’ table in MySQL 00:04:53
Running an SQL SELECT Statement from Python 00:03:05
Transferring Data from Jupyter to Workbench - Part I 00:06:16
Transferring Data from Jupyter to Workbench - Part II 00:06:35
Transferring Data from Jupyter to Workbench - Part III 00:02:45
Chapter 9 : Analyzing the Obtained data in Tableau
Analysis in Tableau: Age vs Probability 00:08:50
Analysis in Tableau: Reasons vs Probability 00:07:50
Analysis in Tableau: Transportation Expense vs Probability 00:06:01