Microsoft Certified: Azure Data Scientist Associate study guide (unofficial)
Link to certification: Azure DS-100
This little book is written in Markdown using MDBook. If you want to render the book, you should install Rust first and then install MDBook from cargo:
cargo install mdbook
Once you have MDBook installed, you can compile the book just cd'ing to the root folder of this repository and executing:
mdbook build
2019-03-06 22:53:13 [INFO] (mdbook::book): Book building has started
2019-03-06 22:53:13 [INFO] (mdbook::book): Running the html backend
The compiled book is located in the ๐ book folder.
-
Select development environment May include but is not limited to: Assess the deployment environment constraints, analyze and recommend tools that meet system requirements, select the development environment
-
Set up development environment May include but is not limited to: Create an Azure data science environment, configure data science work environments Azure Data Science Virtual Machines
-
Quantify the business problem May include but is not limited to: Define technical success metrics, quantify risks
Transform data into usable datasets
- develop data structures
- design a data sampling strategy
- design the data preparation flow
Perform Exploratory Data Analysis (EDA)
- Review visual analytics data to discover patterns and determine next steps identify anomalies, outliers, and other data inconsistencies
- Create descriptive statistics for a dataset
Cleanse and transform data
- Resolve anomalies, outliers, and other data inconsistencies.
- Standardize data formats
- Set the granularity for data
Perform feature extraction
โป Perform feature extraction algorithms on numerical data
- Perform feature extraction algorithms on non-numerical data
- Scale features
Perform feature selection
- Define the optimality criteria
- Apply feature selection algorithms
-
Select an algorithmic approach
- Determine appropriate performance metrics
- Implement appropriate algorithms
- Consider data preparation steps that are specific to the selected algorithms
-
Split datasets
- Determine ideal split based on the nature of the data
- Determine number of splits
- Determine relative size of splits
- Ensure splits are balanced
-
Identify data imbalances
- Resample a dataset to impose balance
- Adjust performance metric to resolve imbalances
- Implement penalization
-
Train the model
- Select early stopping criteria
- Tune hyper-parameters
-
Evaluate model performance
- Score models against evaluation metrics
- Implement cross-validation
- Identify and address overfitting
- Identify root cause of performance results