This Training is jointly organized by BITM & UY LAB. 
Training will be held in UY LAB.


Data Science with TableAU, Power BI, Python and R :

1. Lecture 01:Introduction, Installation
   1. Data Visualization with TableAU and Power BI
   2. Introducing to DataSet
   3. Installing Tableau Desktop and Tableau Public and Power BI
   4. Challenge description + view data in file
   5. Connecting Tableau to a Data file - CSV file
   6. Navigating Measures and Dimensions
   7. Creating a calculated field
   8. Adding colours
   9. Adding labels and formatting
   10. Exporting your worksheet 

 

2. Lecture 02:Data Mining
   1. Get the Dataset + Project Overview
   2. Connecting to an Excel File
   3. AB test
   4. Working with Aliases
   5. Adding a Reference Line
   6. Looking for anomalies and validating 
   7. Creating bins & Visualizing distributions
   8. Creating a classification test for a numeric variable
   9. Combining two charts and working with them
   10. Validating Data Mining with a Chi-Squared test

 

3. Lecture 03:Modeling (Stats Refresher, Simple Linear Regression, Multiple Linear Regression)
   1. Types of variables: Categorical vs Numeric
   2. Types of regressions
   3. Ordinary Least Squares
   4. R-squared
   5. Adjusted R-squared 
   6. Introduction to Gretl
   7. Get the dataset 
   8. Import data and run descriptive statistics
   9. Reading Linear Regression Output
   10. Plotting and analysing the graph 
   11. Caveat: assumptions of a linear regression
   12. Get the dataset
   13. Dummy Variables
   14. Dummy Variable Trap
   15. Ways to build a model: BACKWARD, FORWARD, STEPWISE
   16. Backward Elimination - Practice time
   17. Using Adjusted R-squared to create Robust models
   18. Interpreting coefficients of MLR 

 

4. Lecture 04:Modeling (Logistic Regression, Building a robust geodemographic segmentation model)
   1. Binary outcome: Yes/No-Type Business Problems
   2. Logistic regression intuition
   3. Your first logistic regression
   4. False Positives and False Negatives
   5. Confusion Matrix
   6. Interpreting coefficients of a logistic regression 
   7. What is geo-demographic segmenation?
   8. Let's build the model - first iteration
   9. Let's build the model - backward elimination: STEP-BY-STEP
   10. Transforming independent variables
   11. Creating derived variables
   12. Checking for multicollinearity using VIF
   13. Correlation Matrix and Multicollinearity Intuition
   14. Model is Ready and Section Recap 

 

5. Lecture 05:Modeling (Assessing your model, Drawing insights from your model, Model maintenance)
   1. Accuracy paradox
   2. Cumulative Accuracy Profile (CAP)
   3. How to build a CAP curve in Excel
   4. Assessing your model using the CAP curve
   5. Get my CAP curve template
   6. How to use test data to prevent overfitting your model
   7. Applying the model to test data
   8. Comparing training performance and test performance 
   9. Power insights from your CAP
   10. Coefficients of a Logistic Regression - Plan of Attack (advanced topic)
   11. Odds ratio (advanced topic)
   12. Odds Ratio vs Coefficients in a Logistic Regression (advanced topic)
   13. Deriving insights from your coefficients (advanced topic) 
   14. What does model deterioration look like?
   15. Why do models deteriorate?
   16. Three levels of maintenance for deployed models 

 

6. Lecture 06:Data Preparation (Business Intelligence (BI) Tools, Data Wrangling before the Load)
   1. Working with Data
   2. What is a Data Warehouse? What is a Database?
   3. Setting up Microsoft SQL Server 2014 for practice
   4. Important: Practice Database
   5. ETL for Data Science - what is Extract Transform Load (ETL)?
   6. Microsoft BI Tools: What is SSDT-BI and what are SSIS/SSAS/SSRS? 
   7. Installing SSDT with MSVS Shell 
   8. Preparing your folder structure for your Data Science project
   9. Download the dataset for this section
   10. Two things you HAVE to do before the load
   11. Notepad ++ 
   12. Editpad Lite 

 

7. Lecture 07:Data Preparation (Step-by-step guide to uploading data using SSIS, Handling errors during ETL)
   1. Starting and navigating an SSIS Project
   2. Creating a flat file source task and OLE DB destination
   3. Setting up your flat file source connection
   4. Setting up your database connection and creating a RAW table
   5. Run the Upload & Disable
   6. Due Dilligence: Upload Quality Assurance
   7. How excel can mess up your data
   8. Bulletproof Blueprint for Data Wrangling before the Load
   9. SSIS Error: Text qualifier not specified
   10. What do you do when your source file is corrupt?
   11. SSIS Error: Data truncation
   12. Handy trick for finding anomalies in SQL
   13. Automating Error Handling in SSIS: Conditional Split
   14. How to analyze the error files
   15. Due Dilligence: the one thing you HAVE to do every time
   16. Types of Errors in SSIS 

 

8. Lecture 08:Data Preparation (SQL Programming For Data Science)
   1. Getting To Know MS SQL Management Studio
   2. Shortcut to upload the data
   3. SELECT * Statement
   4. Using the WHERE clause to filter data
   5. How to use Wildcards / Regular Expressions in SQL (% and _) 
   6. Comments in SQL
   7. Order By
   8. Data Types in SQL
   9. Implicit Data Conversion in SQL
   10. Using Cast() vs Convert()
   11. Working with NULLs
   12. Understanding how LEFT, RIGHT, INNER, and OUTER joins work
   13. Joins with duplicate values
   14. Joining on multiple fields
   15. Practicing Joins 

 

9. Lecture 9:Data Preparation (Data Wrangling after the load, Handling errors during ETL)
   1. RAW, WRK, DRV tables
   2. Download the dataset for this section
   3. Create your first Stored Proc in SQL
   4. Executing Stored Procedures
   5. Modifying Stored Procedures
   6. Create table
   7. Insert INTO
   8. Check if table exists + drop table + Truncate
   9. Intermediate Recap - Procs
   10. Create the proc for the second file
   11. Adding leading zeros
   12. Converting data on the fly
   13. How to create a proc template
   14. Archiving Procs 
   15. What you can do with these tables going forward [drv files etc.] 
   16. Download the dataset for this section
   17. Upload the data to RAW table
   18. Create Stored Proc 
   19. How to deal with errors using the isnumeric() function
   20. How to deal errors using the len() function 
   21. How to deal with errors using the isdate() function
   22. Additional Quality Assurance check: Balance
   23. Additional Quality Assurance check: ZipCode
   24. Additional Quality Assurance check: Birthday
   25. ETL Error Handling "Vehicle Service" Project 

 

10. Lecture 10:(Projects, Soft skill, Overview)

 

Curriculum