Input
An input is a value, information, or signal supplied to a system, computation, or interface for processing or to influence its behavior.
Grokking Machine Learning
A property or characteristic of a data example that a model can use to make predictions.
- How it is used
- Supplies the properties a predictive model uses to estimate a label, from email classifications to house prices.
- How deep it goes
- Defines features as table columns, works through a weighted house-price input, and develops categorical and numerical preprocessing.
- Examples
- Uses email size and words, pet properties, house room counts, and passenger columns as concrete inputs.
- What you can do after
- Apply it via Pandas and Scikit-Learn to prepare feature columns, separate them from labels, and train and evaluate models.
Learn AI-Assisted Python Programming, Second Edition
A parameter is a named input specified by a function definition that receives information when the function is called.
- How it is used
- Characterizes books for supervised-learning predictions about unknown authors.
- How deep it goes
- Defines features, works through sentence-length calculation, and uses simple punctuation rules while deferring more accurate phrase analysis.
- Examples
- Uses average sentence length, punctuation-based sentence complexity, average word length, repetition, and weighted signature comparisons.
- What you can do after
- Apply it by calculating descriptive values and assembling signatures for machine-learning comparisons.
Read how Learn AI-Assisted Python Programming, Second Edition explains input →
Get Programming: Learn to code with Python
Information supplied to a program or software component for processing.
- How it is used
- Uses input to start calculations, guide user interactions, and specify what reusable tasks receive.
- How deep it goes
- Works through prompting, storing, converting, and testing inputs, then explains parameter values in function calls.
- Examples
- Uses a square calculator, a name mashup, function calls, and a file of names and phone numbers.
- What you can do after
- Build it from scratch: prompt for and process user responses, supply function arguments, and test varied inputs.
Read how Get Programming: Learn to code with Python explains input →
Statistics Every Programmer Needs
A feature is an input attribute of an observation used by a predictive model to make decisions or generate predictions.
- How it is used
- Supplies observed attributes for predicting a numeric response with linear regression or a binary outcome with logistic regression.
- How deep it goes
- Defines predictors by their relationship to targets, demonstrates Python input selection, and evaluates significance and multicollinearity; does not develop general feature engineering.
- Examples
- Uses Stage 1 split times to predict Stage 2 times and raisin morphology to predict variety.
- What you can do after
- Apply it via statsmodels by selecting predictors, fitting regression models, and reviewing significance and multicollinearity before retaining features.
Machine Learning System Design
An input variable or derived input representation provided to a machine-learning model.
- How it is used
- Supplies the patterns a model uses to learn and predict, with feature choices guided by the business problem.
- How deep it goes
- Defines features and model-generated representations, then works through generation and selection tradeoffs without deriving model algorithms.
- Examples
- Uses grocery demand forecasting inputs and photo-search relevance signals to show how candidates change across systems.
- What you can do after
- Apply it via feature engineering: propose inputs, test their predictive value, and weigh interpretability and operating cost.
AI-Powered Search
A feature is a numerical attribute of a document, query, or query-document relationship used to represent evidence for ranking.
- How it is used
- Represents query, document, and query–document evidence as numerical inputs to manual scoring or learned ranking.
- How deep it goes
- Works through feature values, logging, weighting, and iteration, while leaving advanced model architectures beyond the simple linear approach.
- Examples
- Uses movie title and overview scores, release years, and product-match and promotion flags as concrete feature values.
- What you can do after
- Apply it via search-engine feature logging and learning to rank, then evaluate generalization and test changes against user behavior.
Math and Architectures of Deep Learning
A measured or encoded property used as an input variable to a machine-learning model.
- How it is used
- Frames real-world problems as functions that transform quantifiable inputs into predicted classes or values.
- How deep it goes
- Defines numeric input variables, vector instances, continuous versus categorical forms, and min-max normalization without detailing feature engineering.
- Examples
- Uses cat-object hardness and sharpness, stock-selling variables, driving-speed variables, and face images.
- What you can do after
- Evaluate/understand how numeric properties become input vectors that a trained model maps to predictions.
Read how Math and Architectures of Deep Learning explains input →
Terraform in Depth: Infrastructure as Code with Terraform and OpenTofu
An input value is a value supplied to configure a Terraform input variable.
- How it is used
- Uses input values to customize reusable modules and distinguish environments without editing their configuration.
- How deep it goes
- Explains declarations, defaults, validation, references, module arguments, and root assignment methods; defers more complex module behavior.
- Examples
- Uses an AWS instance’s subnet and instance type, a subnet data lookup, and HCL and JSON variable files.
- What you can do after
- Apply it via Terraform variable blocks, module arguments, and variable files to configure reusable infrastructure with checked inputs.
Read how Terraform in Depth: Infrastructure as Code with Terraform and OpenTofu explains input →
The Well-Grounded Rubyist, Fourth Edition
A parameter is a named input in a method definition or block that receives a corresponding argument when the callable is invoked.
- How it is used
- Defines how Ruby methods and blocks receive values supplied by calls or yields.
- How deep it goes
- Works through required, default-valued, and starred binding and ordering; defers full treatment of keyword arguments.
- Examples
- Uses a Celsius converter, mixed method signatures, and iteration with `times`.
- What you can do after
- Practice/perform method signature design and predict which values bind to positional, default-valued, and starred parameters.
Read how The Well-Grounded Rubyist, Fourth Edition explains input →
Knowledge Graphs and LLMs in Action
A feature is an input variable or measurable attribute selected from data for training a predictive model.
- How it is used
- Uses measurable attributes or graph-derived values as inputs for predictive models and node or pair classification.
- How deep it goes
- Explains manual metrics, neighborhood scope, metapath weighting, and shortest-path computation, while deferring detailed representation-learning treatment.
- Examples
- Uses weather measurements, a fraud-detection network, geodesic hop counts, and metapaths linking metformin with type 2 diabetes.
- What you can do after
- Build it from scratch by extracting interpretable graph metrics, shortest-path indicators, or degree-weighted metapath values for model inputs.
Read how Knowledge Graphs and LLMs in Action explains input →
Grokking Algorithms, Second Edition
A feature is an observable attribute or input variable used to characterize an item for comparison or prediction.
- How it is used
- Represents fruits, users, or days as comparable inputs for KNN classification or regression.
- How deep it goes
- Works through numeric vectors, distance, and feature-selection trade-offs, but defers cosine similarity.
- Examples
- Uses fruit size and color, movie-category ratings, bakery conditions, and stock-market guesses.
- What you can do after
- Practice/perform feature extraction and selection by representing items numerically and choosing relevant, balanced inputs for KNN.
Read how Grokking Algorithms, Second Edition explains input →
Pro Angular 16
An input property is a directive or component property that receives a value from a template binding.
- How it is used
- Supplies changing template data to directives and components so they can adapt host elements, templates, or rendered content.
- How deep it goes
- Defines binding syntax, decorator aliases, lifecycle timing, component usage, and testing, but does not detail decorator configuration beyond the basic alias.
- Examples
- Uses conditional table classes, a themed custom button, template outlet context data, and a host component for testing.
- What you can do after
- Apply it via Angular bindings and @Input decorators, then test received values through a host component and rendered output.
The Art of AI Product Development
A feature is an input variable representing a measurable property of an example supplied to a machine-learning model.
- How it is used
- Uses input features to represent examples for clustering, classification, and reusable prompt templates.
- How deep it goes
- Explains feature relevance, scaling, refinement, and interpretation, but does not detail mathematical representations or implementation code.
- Examples
- Uses customer purchase behavior, browsing activity, product preferences, user profiles, and dynamic prompt variables as examples.
- What you can do after
- Apply it by selecting, scaling, and refining variables that make model outputs more relevant, interpretable, and actionable.
Digital Twins in Action
A feature is an input variable or measurable property used to characterize an instance in analytical or machine learning processing.
- How it is used
- Supplies model inputs for forecasting and current operating inputs for digital-twin simulations.
- How deep it goes
- Works through feature preparation and a training example, but does not implement a feature store.
- Examples
- Uses temperature deviations and rates of change, then lagged temperatures, weather, and encoded time in an indoor-temperature forecast.
- What you can do after
- Apply features via scikit-learn to train and evaluate a one-hour-ahead temperature forecast.
Related concepts
- function declarationpart of · A function declaration is a source-language construct that specifies a function’s name and parameter interface, and may include its implementation.
- constantkind of · A constant is a named program value or binding that is fixed or intended not to change after initialization.
- Mapconfigured by · A map is an associative data structure that stores key-value pairs and supports retrieving values by key.
- function argumentcontrasts with · A function argument is a value or expression supplied when a function or method is invoked, providing input to the called operation.
- factoryused by · A factory is a function, method, class, or component that creates and returns objects or other values while encapsulating construction details or selection.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.