from dataclasses import dataclass
from enum import Enum

@dataclass
class Task:
    benchmark: str # Dataset name
    metric: str # Metric name
    col_name: str # Column name


class Tasks(Enum):
    sentiment_analysis = Task("tunis-ai/tsac", "Sentiment Analysis", "Accuracy (Sentiment Analysis) ⬆️")
    normalization = Task("tunis-ai/MADAR-TUN", "Normalization", "Normalization F1 ⬆️")
    transliteration = Task("tunis-ai/MADAR-TUN", "Transliteration", "Transliteration F1 ⬆️")
    # sentiment_f1 = Task("fbougares/tsac", "macro_f1", "Macro-F1 (TSAC) ⬆️")
    # ner_f1 = Task("arbml/tunisian_ner", "entity_f1", "Entity F1 (NER) ⬆️")
    # coverage = Task("arbml/Tunisian_Dialect_Corpus", "coverage", "Corpus Coverage % ⬆️")
    # arabizi_robustness = Task("tunis-ai/arabizi_eval", "arabizi_f1", "Arabizi Robustness F1 ⬆️")
    # code_switch = Task("tunis-ai/codeswitch_eval", "accuracy", "Code-Switch Accuracy ⬆️")
    # typo_robustness = Task("tunis-ai/typo_eval", "f1_drop", "Typo Robustness Drop % ⬇️")

NUM_FEWSHOT = 0 # Change with your few shot
# ---------------------------------------------------



# Your leaderboard name
TITLE = """<h1 align="center" id="space-title">Tunisian Dialect Leaderboard</h1>"""

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
This leaderboard evaluates models and datasets focused on the Tunisian dialect of Arabic.\
It highlights performance on key resources such as TSAC (fbougares/tsac) and the Tunisian Dialect Corpus (arbml/Tunisian_Dialect_Corpus).
"""

# Which evaluations are you running? how can people reproduce what you have?
LLM_BENCHMARKS_TEXT = f"""
## How it works

We evaluate models on:
- **TSAC** ([fbougares/tsac](https://huggingface.co/datasets/fbougares/tsac)): Sentiment analysis in Tunisian dialect.
- **Tunisian Dialect Corpus** ([arbml/Tunisian_Dialect_Corpus](https://huggingface.co/datasets/arbml/Tunisian_Dialect_Corpus)): Coverage and language understanding.

## Reproducibility
To reproduce our results, use the following commands (replace with your model):

```python
from transformers import AutoConfig, AutoModel, AutoTokenizer
config = AutoConfig.from_pretrained("your model name", revision=revision)
model = AutoModel.from_pretrained("your model name", revision=revision)
tokenizer = AutoTokenizer.from_pretrained("your model name", revision=revision)
```
"""

EVALUATION_QUEUE_TEXT = """
## Some good practices before submitting a model

### 1) Make sure your model is trained or evaluated on Tunisian dialect data (e.g., TSAC, Tunisian Dialect Corpus).

### 2) Make sure you can load your model and tokenizer using AutoClasses:
```python
from transformers import AutoConfig, AutoModel, AutoTokenizer
config = AutoConfig.from_pretrained("your model name", revision=revision)
model = AutoModel.from_pretrained("your model name", revision=revision)
tokenizer = AutoTokenizer.from_pretrained("your model name", revision=revision)
```
If this step fails, follow the error messages to debug your model before submitting it. It's likely your model has been improperly uploaded.

Note: make sure your model is public!
Note: if your model needs `use_remote_code=True`, we do not support this option yet but we are working on adding it, stay posted!

### 3) Convert your model weights to [safetensors](https://huggingface.co/docs/safetensors/index)
It's a new format for storing weights which is safer and faster to load and use. It will also allow us to add the number of parameters of your model to the `Extended Viewer`!

### 4) Make sure your model has an open license!
This is a leaderboard for Open LLMs, and we'd love for as many people as possible to know they can use your model 🤗
"""

CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""
"""