메뉴
Exploratory Data Analysis before training an ML model. Auto-invoke when the user wants to profile feature-view training data, check for leakage, or produce an EDA report before building a feature view or training.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | hops-eda |
| description | Exploratory Data Analysis before training an ML model. Auto-invoke when the user wants to profile feature-view training data, check for leakage, or produce an EDA report before building a feature view or training. |
Profile a feature view's training data before training: run the bundled profiler, then deepen with target / leakage / per-feature analysis. The what to look for lives in hops-eda-checklist; this skill is the how to run it.
eda-<ml-system-name>.md.Two ready profilers ship with this skill — run one before writing anything. They produce the Section-1 profile (dtypes, semantic types, null %, unique counts, numeric stats, datetime ranges, missing-data summary) as text on stdout.
# Polars (in-memory) — args: <fv_name> [version] [start_time] [end_time]
python3 ~/.claude/skills/hops-eda/scripts/fv-eda.py <fv_name> 1 > eda-<ml-system>.md
# PySpark (large data) — same args, builds a Spark session
python3 ~/.claude/skills/hops-eda/scripts/fv-eda-pyspark.py <fv_name> 1 > eda-<ml-system>.md
start_time/end_time require an event_time on the underlying FG.
random, time-based, grouped, entity-based.Sizing: under ~10 GB use Polars; over ~100 GB use PySpark; in between, judgement call.
eda-<ml-system-name>.md for the feature-view and training steps.fv-eda.py (Polars), fv-eda-pyspark.py (Spark) — bundled under this skill's scripts/.Use when writing and deploying an interactive agent (e.g. a LlamaIndex program) as a served Hopsworks deployment.
Use when writing Streamlit or custom Python apps for Hopsworks, deploying from HopsFS or Git, migrating legacy apps off `APP_BASE_URL_PATH`, or managing app routing/readiness, monitoring, and public sharing. Auto-invoke when user wants to create a dashboard, deploy a Python app to Hopsworks, configure app routing/readiness, or access the feature store from an app. Input an app source + env + memory; output a running app and its URL.
Mount or ingest a table from a supported datasource. Mount tables from a datasource as an external feature group or ingest data into a new feature group using DLTHub. Auto-invoke when user works with external data (Snowflake, BigQuery, Redshift, S3, ADLS, GCS, JDBC, SQL, Databricks Unity Catalog, Postgres, MySQL, Oracle, SAP, MongoDB, CRM, REST APIs).
Use when writing Python code that creates, inserts into, or manages tables or feature groups. Auto-invoke when user writes feature pipelines, feature engineering code, or asks about feature group best practices (online vs offline, batching, OOM, materialization, embeddings, statistics).
Use when a Hopsworks job, app, or deployment needs Python libraries that are not in a base environment. Clone a base environment and install requirements or a wheel into the clone. Auto-invoke when the user hits a missing-package error in a job/app/deployment, asks to install custom dependencies, add a pip requirement, install a wheel, or pick which Python environment a workload should run in.
Use when the user asks where something lives in the Hopsworks UI or how to reach a page (Data Sources, Feature Groups, Feature Views, Model Registry, Deployments, Apps, Agents, Jobs, Jupyter, Project Settings). Knowledge skill: the project-scoped sidebar layout and what sits under each section, so you can point users to the right place.