skills.rest
raoxuan98-hash
raoxuan98-hashCOMMUNITY
Explore all skills by this author →
GitHub

fuxictr-guide

Guide FuxiCTR configuration for CTR model training with run_expid.py.

2|Updated Apr 10, 2026
Search Tags:#training#parquet#data-preprocessing#ctr#fuxictr#model-guide
One-click install
npx skills add https://github.com/raoxuan98-hash/open_unimixer_skills --skill fuxictr-guide
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: fuxictr-guide
Source: https://github.com/raoxuan98-hash/open_unimixer_skills/tree/main/.kimi/skills/fuxictr-guide
Command: npx skills add https://github.com/raoxuan98-hash/open_unimixer_skills --skill fuxictr-guide

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides clear guidance on using the FuxiCTR framework to configure and run CTR models such as DCN, DIN, DeepFM, and DCNv2.

Core Features & Use Cases

  • Data preprocessing guidance: CSV → Parquet and feature_map.json generation
  • Model selection and training workflows for common CTR models
  • Use Case: Build and evaluate CTR models across standard datasets using run_expid.py

Quick Start

Train or evaluate a chosen FuxiCTR model using run_expid.py with a prepared configuration.

Frequently Asked Questions about fuxictr-guide

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I configure and train a DeepFM model using the FuxiCTR framework?▼

To train a DeepFM model with FuxiCTR, you use the run_expid.py script with a prepared configuration. This workflow applies to configuring CTR models like DCN, DIN, and DCNv2 across standard datasets.

What is the process for converting CSV data to Parquet for CTR model training?▼

Converting CSV to Parquet for CTR training involves data preprocessing steps that generate a feature_map.json file. This feature map defines the schema required by FuxiCTR models before executing run_expid.py.

Do I need a feature_map.json file before running FuxiCTR preprocessing?▼

Yes, a feature_map.json file is required. FuxiCTR preprocessing generates this file from your CSV or Parquet data to define the feature schema needed for model training and evaluation.

Can I use FuxiCTR to evaluate CTR models on standard datasets?▼

Yes, FuxiCTR supports evaluating CTR models such as DCN, DIN, DeepFM, and DCNv2 on standard datasets. You execute the evaluation workflow through the run_expid.py script with the appropriate configuration.

Which CTR models are supported by the FuxiCTR framework for model selection?▼

FuxiCTR supports model selection for common CTR architectures including DCN, DIN, DeepFM, and DCNv2. You configure these models within the run_expid.py workflow for training and evaluation.

Why does my FuxiCTR training workflow fail during data preprocessing?▼

FuxiCTR training failures during preprocessing often stem from improper CSV to Parquet conversion or missing feature_map.json generation. Ensure your data formats align with the expected schema before running run_expid.py.

Related Skills

Explore More Data & Analytics Skills→
starlake-aistarlake-ai
209

parquet2csv

Convert Parquet files into CSV format for batch ETL pipelines.

Official
Intermediate
raoxuan98-hashraoxuan98-hash
2

ctr-training

Configure and run CTR prediction model training with FuxiCTR.

Community
Advanced
raoxuan98-hashraoxuan98-hash
2

dcnv2-training

Train and evaluate DCNv2 CTR models with FuxiCTR via configuration files.

Community
Intermediate
raoxuan98-hashraoxuan98-hash
2

project-setup

Provision a reproducible BARS and FuxiCTR environment for CTR benchmarking.

Community
Intermediate