skills.rest
mailashishrawat
mailashishrawatCOMMUNITY
Explore all skills by this author →
GitHub

data-prep

Automate stock data collection, repair, and pre-filtering for the india-stock-recommender pipeline.

Updated Feb 5, 2024
Search Tags:#data preparation#stock data#data repair#pre-filter scan#india-stock-recommender
One-click install
npx skills add https://github.com/mailashishrawat/ml --skill data-prep
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-prep
Source: https://github.com/mailashishrawat/ml/tree/main/code/anthropic/tradingagent/.claude/skills/data-prep
Command: npx skills add https://github.com/mailashishrawat/ml --skill data-prep

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, requests, yaml, json, plotly, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the preparation and analysis of stock data for the india-stock-recommender pipeline, streamlining the process of data collection, auditing, and repair.

Core Features & Use Cases

  • Data Collection: Fetches top-25 gainers from Chartink and assembles the daily eval_universe.
  • Data Repair: Audits and repairs stockparam.csv rows using a multi-tier fallback system.
  • Pre-filter Scan: Runs a pre-filter scan on stockparam.csv to prepare for downstream processing.
  • Output Generation: Produces phase_a_context.json for downstream phases of the pipeline.
  • Use Case: When the india-stock-recommender agent enters Phase A or when the user requests to run data prep, backfill stockparam, or fetch today's gainer universe.

Quick Start

Run the data-prep skill to prepare stock data for the india-stock-recommender pipeline.

Frequently Asked Questions about data-prep

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

FAQPage Schema
How do I automate stock data preparation for the india-stock-recommender pipeline?▼

Stock data preparation is automated by fetching top-25 gainers from Chartink, repairing stockparam.csv rows, and running pre-filter scans to generate phase_a_context.json for downstream processing.

How do I fetch today's gainer universe from Chartink for daily stock analysis?▼

Fetch today's gainer universe by using the data collection feature to pull top-25 gainers from Chartink, assembling them into the daily eval_universe for stock analysis.

How do I repair missing or incorrect rows in stockparam.csv?▼

Repair stockparam.csv rows by running the data preparation audit, which uses a multi-tier fallback system to backfill and correct missing or incorrect stock parameters.

Do I need Kite MCP and yfinance access to run a pre-filter scan on stockparam.csv?▼

Yes, running a pre-filter scan on stockparam.csv requires access to Chartink, Kite MCP, yfinance, and the NSE public API to successfully collect, audit, and repair stock data.

What is phase_a_context.json used for in stock data processing?▼

phase_a_context.json is the output generation file produced after data collection, repair, and pre-filtering, providing the necessary prepared stock data context for downstream pipeline phases.

Why does stock data preparation fail when the NSE public API is inaccessible?▼

Stock data preparation fails because the multi-tier fallback system depends on the NSE public API alongside Chartink, Kite MCP, and yfinance to successfully collect and repair stock parameters.

Related Skills

Explore More Data & Analytics Skills→
taracodlabstaracodlabs
779

zerodha-kite

Access and manage Zerodha Kite portfolio, orders, and live quotes via API.

Official
Intermediate
samChang72samChang72
1

quant-trading

Analyze stock trends with technical indicators and backtesting tools.

Community
Advanced
KILWA73KILWA73

data-visualization

Generate publication-quality PNG charts from pre-processed numeric data using pandas, matplotlib, and seaborn.

Community
Advanced
eamageamag
22

scientific-papers-to-dataset

Extract experimental data from academic PDFs into JSON datasets via OpenAlex queries.

Community
Advanced