wasde-ingestor

Ingests WASDE reports and extracts commodity balance-sheet data into Parquet datasets.

3|1|Updated Jan 12, 2026

Search Tags:#parquet #data-ingestion #balance-sheet #wasde #commodity-analytics #pdf-parser #nowcasting

Ready to run

npx skills add https://github.com/fatfingererr/macro-skills --skill wasde-ingestor

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: wasde-ingestor
Source: https://github.com/fatfingererr/macro-skills/tree/main/skills/wasde-ingestor
Command: npx skills add https://github.com/fatfingererr/macro-skills --skill wasde-ingestor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, pdfplumber, camelot, tabula, beautifulsoup4, and includes scripts (resource) and references (resource) components.

What problem does it solve?

The WASDE Ingestor automates the retrieval and parsing of USDA WASDE reports and converts the tables into standardized, versioned datasets suitable for nowcasting.

Core Features & Use Cases

Ingest latest WASDE reports and extract major commodity balance sheets (grains, oilseeds, cotton, livestock, sugar) into a unified dataset.
Validate balance, harmonize units, and generate Parquet outputs ready for analytics.
Use case: ingest January 2025 WASDE, produce US/world balance tables for corn, wheat, soybeans, and sugar, and store them in ./data/wasde/curated.

Quick Start

Run the ingest workflow by pointing to the latest WASDE release and selecting commodities of interest.

Frequently Asked Questions about wasde-ingestor

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

FAQPage Schema

How do I extract WASDE balance sheet data from PDF reports for commodity analytics?▼

The WASDE ingestor uses deterministic PDF and HTML parsing to extract major commodity balance sheets for grains, oilseeds, cotton, livestock, and sugar, then outputs standardized Parquet datasets suitable for nowcasting.

What is the best way to parse USDA WASDE tables into a standardized format for nowcasting?▼

Parsing WASDE tables for nowcasting involves field mapping, balance validation, unit harmonization, and generating versioned Parquet datasets stored in a curated directory for downstream analytics.

Does this data ingestion approach support both US and World commodity scopes in WASDE reports?▼

Yes, the ingestion workflow supports both US and World scopes across monthly USDA WASDE updates, extracting standardized balance sheets for major commodities including grains, oilseeds, cotton, livestock, and sugar.

Do I need pdfplumber and camelot to parse WASDE PDF tables into Parquet datasets?▼

Yes, the workflow requires pdfplumber, camelot, tabula, and beautifulsoup4 dependencies to perform deterministic PDF and HTML parsing of WASDE reports into Parquet datasets.

Can I ingest specific commodities like sugar and cotton from monthly WASDE updates?▼

Yes, you can select specific commodities like sugar, cotton, grains, oilseeds, and livestock when ingesting monthly WASDE updates to generate targeted balance sheet datasets in Parquet format.

Why are my WASDE PDF parsing results not aligning with standardized balance sheet fields?▼

Misaligned WASDE parsing results typically occur without deterministic field mapping and validation; applying these steps ensures balance sheets are harmonized and standardized correctly.