BASICS OF DATA ANALYTICS
BDA — Complete Notes
Prof. Dweepobotee Brahma
Weeks 1–13
WEEK 1 — Introduction to Data Analytics
• Privacy is the main key of Data
Data Types
• Continuous & Discrete
• Nominal
• Ordinal
Data Storage
• Databases → Small (like a small fridge)
• Data Warehouses → Large (like a pantry)
• Data Lakes → Huge (like a reservoir)
Gathering Data
• Querying Databases → Asking
• API → Application Programming Interface
• Web Scraping → Collecting
Data Cleaning
• Remove Duplicates
• Handle Missing Data
• Fix Errors
• Correct Inconsistencies
WEEK 2 — Data Analytics Process
• There is too much information i.e. Data!
Data Analytics Process
Data Analytics → Gathering → Cleaning → Organizing → Analyzing
Objective: To find patterns & insights in Data!
Steps:
• 1. Gathering → Various sources: APIs, Online portals, etc.
• 2. Cleaning & Organizing → Removing errors, duplicates, inconsistencies
, • 3. Analyzing → Identify Trends/Patterns, Create Data Visualization, Using AI to forecast → Descriptive
Analysis
• 4. Interpreting → Presenting the insights, Using Data Visualization → Conveying the Analysis
(understandable)
Who Uses Data Analytics?
Sector Uses
Business Analyze past performance, Pros & Cons, Informed Decisions
Manufacturing Manage supply chain, Manage Inventory, Allocating Working
Retail Buying patterns, Identify popular items, Launch new products
Healthcare Analyze Disease Prevalence, Monitor outbreak, Analyze prescriptions, Create
new drugs
Banking Monitor discrepancies, Predict Fraud, Patterns in spending, New type of credit
card
Education Patterns from results, Track essential skills
Humans use data to make decisions in their life!
WEEK 3 — Roles, Tools & Types of Analytics
Responsibilities of Data Analysts
• Acquiring, Collecting & Gathering Data
• Extract Relevant Data
• Filtering, Cleaning, Sorting & Organizing Data
• Descriptive Analysis
• Statistical Modelling → Forecasting revenue for next month!
• Identify Patterns & Trends
• Preparing Reports
Tools Needed by Data Analysts
• Spreadsheets → Excel or Google Sheets
• Statistical Analysis Software → AutoML, Scikit-learn, KNIME, Orange
• Data Visualization Software → Microsoft Power BI, Tableau, Matplotlib
• Programming Language → Python, C++, Java, MATLAB
• SQL
• Data Processing Tools → Hadoop, Hive, Spark
Functional Skills
• Proficiency in Statistics
• Analytical Skills
• Problem Solving Skills
• Data Visualization Skills
📝 Note: Logical Fallacy = An error in reasoning that uses invalid arguments to support a claim
, Soft Skills
• Curious Mind
• Attention to Details
• Love for Data and Computers
• Project Management & Presentation Skills
Types of Data Analytics
Type Question Answered Description
Exploratory What is in the data? Gathering, Sorting & Reviewing data, Understanding &
Analytics Identifying types
Descriptive Analytics What happened? Summarize past data, Uncover patterns & trends
Diagnostic Analytics Why did it happen? Uncovers cause of outcome, Root cause analysis
Predictive Analytics What could happen Predict future events, Forecasting trends, Risk
next? assessment
Prescriptive What should be done? Advanced mathematical tools, Optimization, Action
Analytics planning
Steps for Data Analyst Project
• 1. Define the problem & desired outcome
• 2. Setting a clear measurable metric
• 3. Gathering the data that we need
• 4. Cleaning the Data
• 5. Analyzing the Data
• 6. Interpreting the Results
• 7. Presenting the Results
📝 Note: These steps are common for most of data analysis!
WEEK 4 — Types of Data
Based on Structure
• Structured → Rigid Format (organized way) | Eg: Spreadsheets
• Semi-Structured → Mix | Eg: Emails (structured headers + unstructured texts)
• Unstructured → Complex (no format) | Eg: Images, Videos
Based on Content
• Numeric → Measured in numbers (counted) | Eg: Price of a good
• Text → Textual Format, analyzed using NLP | Eg: Social media post
• Visual → Images & Videos, analyzed using Image Processing Tools | Eg: Maps
📝 Note: NLP = Natural Language Processing
Data Types Classification
Type Description Example
BDA — Complete Notes
Prof. Dweepobotee Brahma
Weeks 1–13
WEEK 1 — Introduction to Data Analytics
• Privacy is the main key of Data
Data Types
• Continuous & Discrete
• Nominal
• Ordinal
Data Storage
• Databases → Small (like a small fridge)
• Data Warehouses → Large (like a pantry)
• Data Lakes → Huge (like a reservoir)
Gathering Data
• Querying Databases → Asking
• API → Application Programming Interface
• Web Scraping → Collecting
Data Cleaning
• Remove Duplicates
• Handle Missing Data
• Fix Errors
• Correct Inconsistencies
WEEK 2 — Data Analytics Process
• There is too much information i.e. Data!
Data Analytics Process
Data Analytics → Gathering → Cleaning → Organizing → Analyzing
Objective: To find patterns & insights in Data!
Steps:
• 1. Gathering → Various sources: APIs, Online portals, etc.
• 2. Cleaning & Organizing → Removing errors, duplicates, inconsistencies
, • 3. Analyzing → Identify Trends/Patterns, Create Data Visualization, Using AI to forecast → Descriptive
Analysis
• 4. Interpreting → Presenting the insights, Using Data Visualization → Conveying the Analysis
(understandable)
Who Uses Data Analytics?
Sector Uses
Business Analyze past performance, Pros & Cons, Informed Decisions
Manufacturing Manage supply chain, Manage Inventory, Allocating Working
Retail Buying patterns, Identify popular items, Launch new products
Healthcare Analyze Disease Prevalence, Monitor outbreak, Analyze prescriptions, Create
new drugs
Banking Monitor discrepancies, Predict Fraud, Patterns in spending, New type of credit
card
Education Patterns from results, Track essential skills
Humans use data to make decisions in their life!
WEEK 3 — Roles, Tools & Types of Analytics
Responsibilities of Data Analysts
• Acquiring, Collecting & Gathering Data
• Extract Relevant Data
• Filtering, Cleaning, Sorting & Organizing Data
• Descriptive Analysis
• Statistical Modelling → Forecasting revenue for next month!
• Identify Patterns & Trends
• Preparing Reports
Tools Needed by Data Analysts
• Spreadsheets → Excel or Google Sheets
• Statistical Analysis Software → AutoML, Scikit-learn, KNIME, Orange
• Data Visualization Software → Microsoft Power BI, Tableau, Matplotlib
• Programming Language → Python, C++, Java, MATLAB
• SQL
• Data Processing Tools → Hadoop, Hive, Spark
Functional Skills
• Proficiency in Statistics
• Analytical Skills
• Problem Solving Skills
• Data Visualization Skills
📝 Note: Logical Fallacy = An error in reasoning that uses invalid arguments to support a claim
, Soft Skills
• Curious Mind
• Attention to Details
• Love for Data and Computers
• Project Management & Presentation Skills
Types of Data Analytics
Type Question Answered Description
Exploratory What is in the data? Gathering, Sorting & Reviewing data, Understanding &
Analytics Identifying types
Descriptive Analytics What happened? Summarize past data, Uncover patterns & trends
Diagnostic Analytics Why did it happen? Uncovers cause of outcome, Root cause analysis
Predictive Analytics What could happen Predict future events, Forecasting trends, Risk
next? assessment
Prescriptive What should be done? Advanced mathematical tools, Optimization, Action
Analytics planning
Steps for Data Analyst Project
• 1. Define the problem & desired outcome
• 2. Setting a clear measurable metric
• 3. Gathering the data that we need
• 4. Cleaning the Data
• 5. Analyzing the Data
• 6. Interpreting the Results
• 7. Presenting the Results
📝 Note: These steps are common for most of data analysis!
WEEK 4 — Types of Data
Based on Structure
• Structured → Rigid Format (organized way) | Eg: Spreadsheets
• Semi-Structured → Mix | Eg: Emails (structured headers + unstructured texts)
• Unstructured → Complex (no format) | Eg: Images, Videos
Based on Content
• Numeric → Measured in numbers (counted) | Eg: Price of a good
• Text → Textual Format, analyzed using NLP | Eg: Social media post
• Visual → Images & Videos, analyzed using Image Processing Tools | Eg: Maps
📝 Note: NLP = Natural Language Processing
Data Types Classification
Type Description Example
