> For the complete documentation index, see [llms.txt](https://www.mlcompendium.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.mlcompendium.com/data/analytics-intro.md). # Analytics Probability and dependence decide what a later score means. After this chapter the reader can read a distribution, a dependence, and an information measure, and can choose a feature for a reason. The chapter starts with the shapes under the data. [Probability](/data/analytics-intro/probability.md) gives the basic probability pictures and the PDF they become, then kernel density estimation for when a histogram is sparse. A dataset always sits under some probability shape, so [Distribution](/data/analytics-intro/distribution.md) names that shape, looks at the Gaussian that so many tests assume, and then compares two distributions, including by distance. [Probability & Statistics](/data/analytics-intro/probability-and-statistics.md) steps back to the difference between the two fields: probability asks what happens next under a random process, and statistics asks what process would explain what already happened. With the shapes named, the chapter turns to measures. A model that ranks classes or splits trees needs a measure of surprise and a measure of how wrong a predicted distribution is, and [Information Theory](/data/analytics-intro/information-theory.md) supplies entropy, information gain, cross-entropy, the divergence family, and softmax. [Data Analytics](/data/analytics-intro/data-analytics.md) is the practical path from raw tables to questions a team can answer without a model yet, laid out as a free course. The chapter ends with [Dependence and Selection](/data/analytics-intro/dependence-and-selection.md): features that move together waste capacity and features that do not predict the target waste the model, so that page measures dependence and then selects. Analysis does not have to go through code alone. [Understanding PandasAI](https://cohenori.medium.com/understanding-pandasai-fc135b871e84) (May 2023) shows analysis through a generative interface: Pandas-AI is a Python library that adds generative AI to Pandas and makes data frames conversational, and the piece looks at how an LLM can be steered to answer data questions. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://www.mlcompendium.com/data/analytics-intro.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.