From fcb47107f38b1f7abf7904d52adf137f7b6bc2b5 Mon Sep 17 00:00:00 2001
From: gabbypolito <g.polito@ufl.edu>
Date: Fri, 25 Sep 2026 14:35:53 -0400
Subject: [PATCH] Remove dead code and fixed README file

---
 services/data-ngin/README.md             | 19 ++--------
 services/data-ngin/src/data_ngin/main.py | 45 ------------------------
 2 files changed, 3 insertions(+), 61 deletions(-)
 delete mode 100644 services/data-ngin/src/data_ngin/main.py

diff --git a/services/data-ngin/README.md b/services/data-ngin/README.md
index f6790d3e..7327cbb4 100644
--- a/services/data-ngin/README.md
+++ b/services/data-ngin/README.md
@@ -37,7 +37,6 @@ The **data-ngin** is a modular pipeline designed to fetch, clean, store, and ana
 - **Modularity:** Designed with interchangeable components for fetchers, loaders, cleaners, and inserters
 
 ## Project Structure
-- **`src/main.py`**: Entry point for pipeline execution
 - **Primary Modules**:
   - **Loader**: Loads metadata and configuration (e.g., `CSVLoader`)
   - **Fetcher**: Fetches raw data (e.g., `DatabentoFetcher`)
@@ -62,7 +61,6 @@ The **data-ngin** is a modular pipeline designed to fetch, clean, store, and ana
 ├── src
 │   ├── config
 │   │   ├── config.yaml
-│   ├── main.py
 │   ├── modules
 │   │   ├── cleaner
 │   │   │   ├── cleaner.py
@@ -122,7 +120,7 @@ The **data-ngin** is a modular pipeline designed to fetch, clean, store, and ana
 
 1. **Clone the Repository:**
    ```bash
-   git clone https://github.com/AlgoGators/data-ngin.git
+   git clone https://github.com/AlgoGators/algogators.git
    cd data-ngin
    ```
 
@@ -159,11 +157,6 @@ The **data-ngin** is a modular pipeline designed to fetch, clean, store, and ana
 
 ## Usage
 
-### Run Pipeline Locally
-```bash
-poetry run python src/main.py
-```
-
 ### Access Airflow Web Interface
 1. Navigate to http://localhost:8080
 2. Use default credentials (admin/admin) unless modified
@@ -435,19 +428,13 @@ task = PythonOperator(task_id="fetch_data", python_callable=orchestrator.run, da
 
 ## Common Development Tasks
 
-1. **Run the pipeline manually**
-
-```bash
-poetry run python src/main.py
-```
-
-2. **Check database contents**
+1. **Check database contents**
 
 ```sql
 SELECT * FROM futures_data.ohlcv_1d LIMIT 10;
 ```
 
-3. **Trigger Airflow DAG**
+2. **Trigger Airflow DAG**
 
 ```bash
 airflow dags trigger data_pipeline
diff --git a/services/data-ngin/src/data_ngin/main.py b/services/data-ngin/src/data_ngin/main.py
deleted file mode 100644
index 22dd0ee0..00000000
--- a/services/data-ngin/src/data_ngin/main.py
+++ /dev/null
@@ -1,45 +0,0 @@
-import asyncio
-import logging
-import os
-
-from data_ngin.application.orchestrator import Orchestrator
-from data_ngin.utils.dynamic_loader import DEFAULT_CONFIG_PATH, load_config
-
-
-def main() -> None:
-    """
-    Main entry point for the data pipeline.
-
-    TO-DO:
-    - Create file for interacting with database and pulling data (look into ORMs)
-    - Change OHLCV class to to handle more than just _1d
-    - Dockerize and implement Airflow
-    """
-    # Configure logging
-    logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
-
-    try:
-        # Load configuration
-        file_path = os.path.dirname(DEFAULT_CONFIG_PATH)
-        for filename in os.listdir(file_path):
-            file_path = os.path.join(file_path, filename)
-            config_path = DEFAULT_CONFIG_PATH
-            logging.info(f"Loading configuration from {config_path}")
-            config = load_config(config_path)
-
-            # Initialize the Orchestrator
-            logging.info("Initializing orchestrator...")
-            orchestrator = Orchestrator(config=config)
-
-            # Run the pipeline
-            logging.info("Starting the data pipeline...")
-            asyncio.run(orchestrator.run())
-
-            logging.info("Pipeline execution completed successfully.")
-
-    except Exception as e:
-        logging.error(f"Pipeline execution failed: {e}")
-
-
-if __name__ == "__main__":
-    main()