Data Discovery in EDA: Raw Ingredients

The location where data originates, like a database, file, or API. This helps identify who created it and how reliable it is.

Individuals with expertise on the data, who can answer questions about its quality and meaning. They might be engineers, analysts, or database administrators.

Understanding how the data is collected provides insight into potential biases and limitations. This crucial for assessing its quality and reliability.

Data is typically stored in various formats such as CSV, JSON, or SQL databases. Choosing the right format for analysis depends on the data's structure and the tools you're using.

The type of data within a dataset, such as text, numbers, dates, or booleans (true/false). Understanding data types is essential for choosing appropriate analysis methods.

A company's plan that outlines the goals and steps for a project. It serves as a guide for data professionals to understand what needs to be achieved.

The process of exploring and understanding a dataset before formal analysis. It involves identifying patterns, cleaning data, and asking key questions about its meaning.

A measure of how reliable and trustworthy data is. This includes factors like accuracy, completeness, and consistency.

Data gathered from within your own organization.

Data gathered outside your organization but directly from the original source.

Data gathered outside your organization and aggregated from multiple sources.

A simple text file where data rows are separated by commas or other separators.

A data storage format in a JavaScript format that can contain nested objects.

A file type that organizes data in tables with rows representing objects and columns representing aspects of those objects.

A data storage method often used in tables, indexes, and fields, optimized for searching and storage.

The format in which data is stored, such as tabular, CSV, JSON, or database files.

Values that are missing or not available in a dataset.

The process of gathering information about the source of data, such as how it was collected, what method was used, and any biases.

The data structure that best suits the research project and storage type.

Data categories, including geographical, demographic, numeric, time-based, financial, and qualitative data.

The process of aligning the available data with the project plan and determining if there is enough data to proceed.

The process of reaching out to data owners or project stakeholders when there is an insufficient amount of data or a mismatch between the available data and project requirements.