Data Analytics Profiling
Learning Data Analytics from Basic to Advance
The structured curriculum and practical approach offered by AirAsia Academy contribute significantly to my understanding and application of data analytics concepts.
Day 1 - Understand the type of data
Primary Data & Secondary Data
Google Sheet Data (Quanlitative & Quantitative)
Quanlitative: Binary/Nominal/Ordinal
Quantitative: Discrete/Continuous
Data Understanding
Labelled Data: Input data + Target
Unlabelled Data: Input data only
4. Category of data based on Structure
Struture: Table Format
Unstructured: Image/Audio/Emoji
Semi Structure: Mix of structure & unstructured
5. Understand data analytics
Descriptive: "what happened"
Predictive: "What will happen in future?" (Forecasting)
Diagnosis: "Why happen?"
Prescriptive: "What action to be taken"
A description of the images you are showcasing for your project, your process, and the artifacts you created along the way
Day 2 - Machine Learning/ Deep Learning/ AI
Machine Learning: all mechanical (basic / coding)
Deep Learning: Ask and respond
AI: Use machine learning to configure in the system
How we handle data?
Handle missing value: Less number? (remove it) / More number? (replace it)
Handle Duplicate: Drop/ Delete
Handle Outliers: > 10, replace it/ < 10, remove it (Boxplot can see the outliers)
5. Google Query (only for google sheet)
6. Google Visualization (Chart)
Category VS Numerical = barplot/ line chart
2 Numerical = Scatter Plot
Compare time series data = line chart
Day 3: Basic of R programming
Understand what is variable? Example: A10 (A is the variable)
Data Type in R
Trivial = Number: Integer/ Double/ Complex
String = tolower(y)/ toupper(y)/ paste("Hi","Hello") = "Hi Hello"...
Vector = More than 1 value & All value should be all same type (Nurmeric/ Character/ Logical)
Example 1: Trivial = Number: Integer/ Double/ Complex
Example 2: String = tolower(y)/ toupper(y)/ paste("Hi","Hello") = "Hi Hello"...
Example 3: Vector = More than 1 value & All value should be all same type (Nurmeric/ Character/ Logical)
Day 4: R mini project
Understand all the basic coding such as: head/ tail/ $/ str/ summary/ nrow/ colnames/ ncol/ is.na/ colsums
1) Understand basic coding
2) Dplyr function
3) If function
4) Data Cleaning
5) GG Plot
Day 5: Recall and present our data cleaning project (University Ranking)
Creating Dashboard based on the final data
Day 6: Graphing & Seaborn
Graphing
Type of Graphing: Bar/ Scatter/ Plot
1) BAR
2) Scatter
3) Plot
Type of Seaborn: Replot/ Displot/ Catplot/ Boxplot
1) Replot
2) Displot
3) Catplot
4) Boxplot
Day 7: EDA & Introduction of Scikit Learn & Supervised Data
Steps for EDA:
Data Collection
Find and understand all the variables
Data Cleaning
Identify correlated variables
EDA statistics summary
Identify Outliers
Data Prediction
Report Generation
Scikit Learn with data Titanic_Survival Data
Able to idendify the correlated data which determine the number of survival
Data Collection
Find and understand all the variables
Data Cleaning
Identify correlated variables
EDA statistics summary
Identify Outliers
Feature Scaling
Save Scaller
Split into train and test dataset
Machine Learning: Logistics Regression
Day 8: Unsupervised Data + Practice ML using titanic dataset + Project Development: Github/ Streamlit
GITHUB
STREAMLIT
Day 9: Google Sites