Commit
•
c41af63
1
Parent(s):
8018899
added description of repo
Browse files
README.md
CHANGED
|
@@ -49,7 +49,45 @@ outputs = model(**inputs)
|
|
| 49 |
```
|
| 50 |
|
| 51 |
|
| 52 |
-
GitHub Link to this project : [Telegram Trade Msg Backtest ML](https://github.com/hemangjoshi37a/TelegramTradeMsgBacktestML)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
|
| 54 |
|
| 55 |
----------------------------------------------------------------------
|
|
|
|
| 49 |
```
|
| 50 |
|
| 51 |
|
| 52 |
+
# GitHub Link to this project : [Telegram Trade Msg Backtest ML](https://github.com/hemangjoshi37a/TelegramTradeMsgBacktestML)
|
| 53 |
+
|
| 54 |
+
## What this repository contains? :
|
| 55 |
+
|
| 56 |
+
1. Label data using LabelStudio NER(Named Entity Recognition or Token Classification) tool.
|
| 57 |
+
 convert to 
|
| 58 |
+
|
| 59 |
+
2. Convert LabelStudio CSV or JSON to HuggingFace-autoTrain dataset conversion script
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
3. Train NER model on Hugginface-autoTrain.
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
4. Use Hugginface-autoTrain model to predict labels on new data in LabelStudio using LabelStudio-ML-Backend.
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
5. Define python function to predict labels using Hugginface-autoTrain model.
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
6. Only label new data from newly predicted-labels-dataset that has falsified labels.
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
7. Backtest Truely labelled dataset against real historical data of the stock using zerodha kiteconnect and jugaad_trader.
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
8. Evaluate total gained percentage since inception summation-wise and compounded and plot.
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
9. Listen to telegram channel for new LIVE messages using telegram API for algotrading.
|
| 84 |
+
|
| 85 |
+
|
| 86 |
+
10. Serve the app as flask web API for web request and respond to it as labelled tokens.
|
| 87 |
+
|
| 88 |
+
|
| 89 |
+
|
| 90 |
+
Place a custom order on hjLabs.in : [https://hjLabs.in](https://hjlabs.in/?product=custom-algotrading-software-for-zerodha-and-angel-w-source-code)
|
| 91 |
|
| 92 |
|
| 93 |
----------------------------------------------------------------------
|