Skip to content

feat: cli news persistence beta runners exporter #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
Ryujose wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

feat: cli news persistence beta runners exporter #5

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
46 changes: 42 additions & 4 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,18 +38,56 @@ The app uses `litellm`, allowing you to use any major LLM provider:

## Usage

Run the analysis for any stock ticker:
### CLI Interface

The project now includes a powerful CLI interface built with `rich` and `typer`.

```bash
poetry run python main.py AAPL
# Analyze a stock
poetry run python cli.py analyze -t AAPL -m ollama/mistral:7b

# Manage your portfolio
poetry run python cli.py portfolio

# See daily runners with momentum scoring
poetry run python cli.py runners --mode live

# Run a live streaming scanner
poetry run python cli.py runners --stream

# Backtest runners for a specific date
poetry run python cli.py runners --mode backtest --date 2024-02-15

# Manage catalysts and news
poetry run python cli.py news add --symbol TSLA --title "Earnings Beat" --source "Reuters" --type earnings --sentiment positive
poetry run python cli.py news list --symbol TSLA
poetry run python cli.py news fetch TSLA -m ollama/mistral:7b -catastr 1
```

You can also specify a different model:
### Catalyst-Aware Momentum Scanning
The `runners` command now integrates with the news module. If recent news (catalysts) exist for a ticker, the momentum score is adjusted based on:
- **Sentiment**: Positive catalysts increase the score; negative ones decrease it.
- **News Type**: Earnings, FDA approvals, and Guidance updates carry higher weight.
- **Strength**: Manually rated catalyst strength (1-5) scales the impact.

### Analysis with Custom Model

You can still run a single analysis via the CLI:

```bash
poetry run python main.py TSLA --model anthropic/claude-3-5-sonnet-20240620
poetry run python cli.py analyze AAPL
```

### Configuration
- Portfolio is stored in `portfolio.json`.
- Analysis exports are saved to `analysis_export.json` and `analysis_export.csv`.

## Project Structure
- `trading_analysis/domain`: Core interfaces and data models.
- `trading_analysis/infrastructure`: Data providers (yfinance, ddgs) and quantitative engines.
- `trading_analysis/application`: High-level business logic and analyzer orchestration.
- `cli.py`: Main entry point for the interactive CLI.

## Token Usage & Costs Analysis

A single analysis run involves 7 LLM calls to process different aspects of the stock (Health, Value, Sentiment, 3 Judges, and Final Resolver).
Expand Down
Loading