AGENT SKILL

analysis-visualization

Inspect and visualize trained BERTopic models with topic, document, distribution, time, class, and hierarchy views.

License 许可
MIT
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
analysis-visualization
license
MIT
metadata
{ "package": "BERTopic", "disco-role": "operating", "parent-skill": "bertopic", "package-version": "0.17.4" }
description
Inspect and visualize trained BERTopic models with topic, document, distribution, time, class, and hierarchy views.
disable-model-invocation
true

02 资源文件 4

03 SKILL.md 正文

analysis-visualization

Use this sub-skill when the model is already fitted and the task is to inspect, compare, or visualize topics, documents, topic distributions, hierarchy, temporal change, or class-specific topic views.

Route here for

  • get_topic_info, get_topic, get_topics, get_topic_freq, get_representative_docs
  • hierarchical_topics, get_topic_tree
  • approximate_distribution, topics_over_time, topics_per_class
  • all visualize_* methods, including topic maps, document views, hierarchy views, heatmaps, bar charts, term-rank plots, topic-over-time plots, topics-per-class plots, probability/distribution plots, and approximate-distribution tables

Route elsewhere

  • Fitting, transforming, partial updates, topic mutation, outlier reassignment, or model building: use the topic-modeling sub-skill.
  • Embedding backend selection or downloads: use the embeddings-backends sub-skill.
  • Vectorizer / c-TF-IDF tuning and topic-word refreshes: use the vectorizers-ctfidf sub-skill.
  • Representation models, labeling, or multi-aspect label generation: use the representations-labeling sub-skill.
  • Save/load, hub publishing, or serialization formats: use the serialization sub-skill.

Operating references

  1. references/api-reference.md
  2. references/workflows.md
  3. references/troubleshooting.md
  4. scripts/smoke_visualization.py

Minimal decision flow

  • Need a quick readout of what the model learned? Start with get_topic_info(), get_topic_freq(), get_topic(), and get_representative_docs().
  • Need a global topic landscape? Use visualize_topics(), visualize_barchart(), visualize_heatmap(), and visualize_term_rank().
  • Need document-level inspection? Use visualize_documents() or visualize_hierarchical_documents() with precomputed reduced_embeddings when possible.
  • Need a single-document distribution? Use approximate_distribution() and then visualize_distribution() or visualize_approximate_distribution().
  • Need time or class comparison? Use topics_over_time() / visualize_topics_over_time() or topics_per_class() / visualize_topics_per_class().
  • Need hierarchy? Use hierarchical_topics(), inspect get_topic_tree(), then render visualize_hierarchy().

Notes

  • Most plot functions exclude topic -1 by default.
  • custom_labels in plotting calls can be a boolean or an aspect-name string when the model has matching topic aspects.
  • visualize_topics() and visualize_hierarchy() need UMAP for internal 2D topic layout; document views can avoid UMAP by accepting reduced_embeddings.
  • visualize_document_datamap() needs datamapplot; visualize_approximate_distribution() returns a styled table only when Jinja2 is available.

Verification anchors

  • Tiny synthetic no-download model: exercise visualize_topics, visualize_barchart, visualize_heatmap, visualize_documents, and visualize_distribution from precomputed embeddings without downloading external models.
  • Small-corpus analysis loop: compute approximate_distribution, hierarchical_topics, and get_topic_tree, then connect them to the distribution and hierarchy plots.

Handoff constraint

Keep this sub-skill focused on inspection and visualization. Do not pull fit, backend, vectorizer, representation, or serialization setup into this skill.

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-solve

END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-pattern-fusion

Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).

★ 351