What is Data in Machine Learning?


data-in-machine-learning



Data in Machine Learning

Data is a collection of facts, statistics, or information that can be analyzed to gain insights, make decisions, or build models. 

In computing and data science, data typically refers to numerical or categorical information collected from various sources, which can be processed and analyzed to extract meaningful patterns and knowledge.


Types of Data

Data can be classified into several types based on different criteria.
Here are the primary classifications:


1. Based on Nature


A. Quantitative Data

  1. Definition: Numerical data that can be measured and quantified.
  2. Types: Quantitative data has two types, Discrete Data and Continuous Data.
  3. Discrete Data: Countable data that can take on distinct values. Example: Number of students in a class.
  4. Continuous Data: Measurable data that can take on any value within a range. Example: Height, weight, temperature.

B. Qualitative Data

  1. Definition: Qualitative data refers to non-numerical information that describes qualities or characteristics.
  2. Types: Qualitative Data has two types, Nominal Data and Ordinal Data.
  3. Nominal Data: Categorized without any order. Example: Gender, color, nationality.
  4. Ordinal Data: Categorized with a meaningful order but without a fixed interval between categories. Example: Survey ratings (poor, fair, good, excellent).



2. Based on Measurement Levels


A. Nominal Data

  1. Definition: Data that represents categories without a natural order.
  2. Example: Blood type (A, B, AB, O), or types of fruits (apple, banana, cherry).

B. Ordinal Data

  1. Definition: Data that represents categories with a meaningful order but without equal intervals.
  2. Example: Education level (high school, bachelor's, master's, PhD).

C. Interval Data

  1. Definition: Numerical data with ordered categories and equal intervals, but no true zero point.
  2. Example: Temperature in Celsius or Fahrenheit, dates (years).

D. Ratio Data

  1. Definition: Numerical data with ordered categories, equal intervals, and a true zero point.
  2. Example: Height, weight, age, salary.



3. Based on the Data Source


A. Primary Data

  1. Definition: Data collected directly from first-hand sources for a specific purpose.
  2. Example: Surveys, interviews, and experiments.

B. Secondary Data

  1. Definition: Data already collected by someone else for a different purpose.
  2. Example: Government reports, company records, research papers.



4. Based on Structure


A. Structured Data

  1. Definition: Data organized in a fixed format or schema, often in tabular form.
  2. Example: Databases, spreadsheets.

B. Unstructured Data

  1. Definition: Data that does not have a predefined format or organization.
  2. Example: Text documents, emails, social media posts, images, and videos.

B. Semi-Structured Data

  1. Definition: Data that does not conform to a rigid structure but has some organizational properties.
  2. Example: XML files, JSON files.


Understanding the types of data is crucial for data analysis and processing. 

Different types of data require different analytical techniques and tools. 

Proper classification helps in selecting the right methods for data collection, storage, and analysis, ultimately leading to more accurate and insightful results.




Resources