Machine Learning: Gathering Data

Machine Learning Life Cycle

• The machine learning life cycle consists of 7 steps: Gathering Data, Data Preparation, Data Wrangling, Data Analysis, Train Model, Test Model, and Deployment.

Gathering Data

• The first step of the machine learning life cycle, aiming to identify and obtain all data-related problems.
• Data can be collected from various sources such as files, databases, the internet, or mobile devices.
• The quantity and quality of the collected data will determine the efficiency of the output.

Data Preparation

• Exploring, organizing, and preparing the data for use in machine learning training.
• Understanding the nature of data, including characteristics, format, and quality.
• Identifying correlations, general trends, and outliers.

Data Wrangling (Cleaning)

• The process of cleaning and converting raw data into a usable format.
• Common issues with collected data include missing values, duplicates, invalid data, and noise.
• Various filtering techniques are used to clean the data.

Data Analysis

• Using cleaned and prepared data to select a machine learning technique (model) such as Classification, Regression, Cluster analysis, or Association.
• Building and evaluating the model using the prepared data.
• Reviewing the results of the model.

Train Model

• Training the model to improve its performance using various machine learning algorithms.
• The model is trained on datasets to understand patterns, rules, and features.

Test Model

• Testing the model to check for accuracy by providing a test dataset.
• Determining the percentage accuracy of the model as per the project or problem requirement.

Deployment

• The final step of the machine learning life cycle, where the model is deployed in a real-world system.

Learn about the first step of the machine learning lifecycle, where the goal is to identify and obtain all data-related problems. Understand the importance of data sources and quality for efficient output.