Day 1
Essential Statistic for Data Science
How is data collected:-
How is data collected:-
- Primary data
- Secondary Data
Data Type:-
Data Type:-
Quantitative Data
Discrete
- Whole number
- Got by counting the values
- Eg: 8, 10, 12, 231
Continuous
- Decimal number
- Got by measuring with something.
- Eg: 3.2, 5.8
Qualitative Data
Binary
- Have 2 values
- Eg: Yes/No, True/false, Male/Female
Nominal
- More than 2 values
- Eg: Marital status
Ordinal
- ordered category
- Eg: rating 1-5 satisfaction
Types of Data Analytics
Types of Data Analytics
Descriptive (What happened)
Diagnostic (Why it happened)
Predictive (What will happened)
Prescriptive (What action to be taken)
Machine Learning
AI, Machine Learning, Deep Learning
AI, Machine Learning, Deep Learning
Artificial Intelligence (AI) - Machines behave like human
Machine Learning (ML) - How to make the machine behave like human
Deep Learning (DL) - Make machine learn, understand and respond.
Steps in Machine Learning Process
Steps in Machine Learning Process
Get Data
Data Processing/Data Cleansing
- Remove missing values
- Identify outliers
- Visualize the data
- Convert data into chart/graph
- Descriptive & Dianostic
Statistics for Data Analytics
Types of Statistics
Types of Statistics
Descriptive Statistics
- Describe basic statistical values
- Eg: Mean, mode, median, range, variance, standard deviation
Inferential Statistics
- Hypothesis Testings/ assumptions
- Null Hypothesis- No statistical difference between groups/not enough evidence
- Alternative Hypothesis- Statistical difference between group
- Techniques
- Min-max Scalling
- Standardizaion
- Hypothesis Testings/ assumptions