Update README.md

README.md

@@ -52,6 +52,22 @@ Fine-tuned [myanmar-pos-model](https://huggingface.co/chuuhtetnaing/myanmar-pos-
 | 29 | 0.0274 | 0.0837 | 0.8855 | 0.9272 | 0.9058 | 0.9804 |
 | 30 | 0.0271 | 0.0832 | 0.8875 | 0.9267 | 0.9067 | 0.9806 |
 
+## Test Set Evaluation
+
+Evaluated on [myanmar-ner-dataset](https://huggingface.co/datasets/chuuhtetnaing/myanmar-ner-dataset) test split using seqeval metrics:
+
+| Entity | Precision | Recall | F1-Score | Support |
+|--------|-----------|--------|----------|---------|
+| DATE | 0.80 | 0.86 | 0.83 | 251 |
+| LOC | 0.93 | 0.96 | 0.95 | 2712 |
+| NUM | 0.89 | 0.92 | 0.90 | 789 |
+| ORG | 0.44 | 0.62 | 0.52 | 94 |
+| PER | 0.84 | 0.88 | 0.86 | 533 |
+| TIME | 0.62 | 0.70 | 0.66 | 57 |
+| **micro avg** | **0.89** | **0.93** | **0.91** | 4436 |
+| **macro avg** | 0.75 | 0.82 | 0.78 | 4436 |
+| **weighted avg** | **0.89** | **0.93** | **0.91** | 4436 |
+
 ## Training Details
 
 | Parameter | Value |
@@ -71,6 +87,70 @@ result = ner("ကိုမောင်သည်ရန်ကုန်မြို
 print(result)
 ```
 
+## Evaluation Code
+
+```python
+!pip install seqeval
+
+from transformers import pipeline, AutoModelForTokenClassification, AutoTokenizer
+from datasets import load_dataset
+from tqdm import tqdm
+from seqeval.metrics import classification_report
+
+# Load model and tokenizer
+model = AutoModelForTokenClassification.from_pretrained("chuuhtetnaing/myanmar-ner-model")
+tokenizer = AutoTokenizer.from_pretrained("chuuhtetnaing/myanmar-ner-model")
+
+def tokenize_and_align_labels(examples):
+    tokenized_inputs = tokenizer(examples["tokens"], truncation=True, is_split_into_words=True)
+    labels = []
+    for i, label in enumerate(examples["ner_tags"]):
+        word_ids = tokenized_inputs.word_ids(batch_index=i)
+        previous_word_idx = None
+        label_ids = []
+        for word_idx in word_ids:
+            if word_idx is None:
+                label_ids.append(-100)
+            elif word_idx != previous_word_idx:
+                label_ids.append(label[word_idx])
+            else:
+                label_ids.append(-100)
+            previous_word_idx = word_idx
+        labels.append(label_ids)
+    tokenized_inputs["labels"] = labels
+    return tokenized_inputs
+
+# Load and tokenize dataset
+ner = pipeline("token-classification", model="chuuhtetnaing/myanmar-ner-model", aggregation_strategy=None)
+ds = load_dataset("chuuhtetnaing/myanmar-ner-dataset")
+tokenized_ds = ds.map(tokenize_and_align_labels, batched=True)
+test_ds = tokenized_ds["test"]
+
+# Get label mapping
+label_list = model.config.id2label
+
+y_true = []
+y_pred = []
+
+for example in tqdm(test_ds):
+    tokens = tokenizer.convert_ids_to_tokens(example["input_ids"])
+    true_labels = [label_list[l] if l != -100 else "O" for l in example["labels"]]
+    
+    text = tokenizer.decode(example["input_ids"], skip_special_tokens=True)
+    preds = ner(text)
+    
+    pred_labels = ["O"] * len(true_labels)
+    for pred in preds:
+        idx = pred["index"]
+        if idx < len(pred_labels):
+            pred_labels[idx] = pred["entity"]
+    
+    y_true.append([label_list[l] for l in example["labels"] if l != -100])
+    y_pred.append([p for p, l in zip(pred_labels, example["labels"]) if l != -100])
+
+print(classification_report(y_true, y_pred))
+```
+
 ## NER Labels
 
 | Tag | Description |