Add interactive model analyzer script

- Include spacy_model_analyzer.py for model evaluation and testing
- Add installation instructions for streamlit and pandas dependencies
- Enable interactive analysis with real-time entity recognition
- Provide detailed metrics calculation and visualization tools

Author: Asep Muhamad <[email protected]>

README.md

@@ -140,6 +140,10 @@ The model was evaluated on 2,987 examples from the training data with the follow
 You can reproduce these metrics using the included analyzer script:
 
 ```bash
+# Install required dependencies
+pip install streamlit pandas
+
+# Run the analyzer
 streamlit run spacy_model_analyzer.py
 ```
 

spacy_model_analyzer.py

@@ -0,0 +1,145 @@
+import streamlit as st
+import spacy
+from spacy.training import Example
+from spacy.scorer import Scorer
+import re
+import pandas as pd
+
+# Load the NER model
+@st.cache_resource
+def load_model(path):
+    return spacy.load(path)
+
+def parse_training_data(file_path):
+    with open(file_path, 'r', encoding='utf-8') as f:
+        lines = f.readlines()
+    
+    examples = []
+    tag_pattern = re.compile(r'<([A-Z]+)>(.*?)</\1>')
+
+    for line in lines:
+        line = line.strip()
+        if not line:
+            continue
+
+        text = ""
+        ents = []
+        last_end = 0
+        
+        for match in tag_pattern.finditer(line):
+            # Add the text before the current tag
+            text += line[last_end:match.start()]
+            
+            # The entity text
+            entity_text = match.group(2)
+            entity_label = match.group(1)
+            
+            start_char = len(text)
+            text += entity_text
+            end_char = len(text)
+            
+            ents.append((start_char, end_char, entity_label))
+            
+            last_end = match.end()
+            
+        # Add any remaining text after the last tag
+        text += line[last_end:]
+        
+        if text:
+             # Remove duplicates and sort
+             unique_ents = sorted(list(set(ents)))
+             examples.append({"text": text.lower(), "ents": unique_ents})
+             
+    return examples
+
+def evaluate_model(nlp, examples):
+    scorer = Scorer()
+    example_list = []
+    skipped_examples = 0
+    for ex in examples:
+        try:
+            doc = nlp.make_doc(ex["text"])
+            gold_ents = ex["ents"]
+            
+            gold_dict = {"entities": gold_ents}
+
+            example = Example.from_dict(doc, gold_dict)
+            pred_doc = nlp(example.predicted)
+            
+            aligned_example = Example(pred_doc, example.reference)
+            example_list.append(aligned_example)
+        except ValueError as e:
+            # This will catch alignment errors
+            st.warning(f"Skipping an example due to alignment issues: {ex['text'][:50]}... Error: {e}")
+            skipped_examples += 1
+            continue
+            
+    st.info(f"Total examples evaluated: {len(example_list)}. Skipped: {skipped_examples}.")
+    if not example_list:
+        return {}
+    scores = scorer.score(example_list)
+    return scores
+
+nlp = load_model(".")
+
+# Streamlit app
+st.title("Indonesian NER SpaCy Model Analyzer")
+
+st.header("Model Information")
+st.write(f"**Language:** {nlp.lang}")
+st.write(f"**Pipeline:** {', '.join(nlp.pipe_names)}")
+st.write(f"**Labels:** {', '.join(nlp.get_pipe('ner').labels)}")
+
+st.header("Model Evaluation")
+evaluation_data = parse_training_data('../data_training.txt')
+scores = evaluate_model(nlp, evaluation_data)
+
+if scores:
+    # Overall scores
+    st.subheader("Overall Scores")
+    overall_scores = {
+        "Precision": scores.get("ents_p", 0),
+        "Recall": scores.get("ents_r", 0),
+        "F1-score": scores.get("ents_f", 0),
+    }
+    st.table(pd.DataFrame([overall_scores]))
+
+    # Scores per entity
+    st.subheader("Scores per Entity")
+    per_entity_scores = []
+    for label, metrics in scores.get("ents_per_type", {}).items():
+        per_entity_scores.append({
+            "Entity": label,
+            "Precision": metrics.get("p", 0),
+            "Recall": metrics.get("r", 0),
+            "F1-score": metrics.get("f", 0),
+        })
+
+    if per_entity_scores:
+        df_scores = pd.DataFrame(per_entity_scores)
+        # Sort alphabetically to have a consistent order before numbering
+        df_scores = df_scores.sort_values(by="Entity", ascending=True)
+        # Add a unique number ID column
+        df_scores.insert(0, '#', range(1, 1 + len(df_scores)))
+        st.table(df_scores)
+    else:
+        st.write("No per-entity scores available.")
+else:
+    st.write("Could not calculate scores. Please check the training data format.")
+
+
+st.header("Analyze Text")
+text_input = st.text_area("Enter text to analyze:", "Presiden Joko Widodo mengunjungi Jakarta hari ini.")
+
+if text_input:
+    doc = nlp(text_input.lower())
+    st.header("NER Visualization")
+    html = spacy.displacy.render(doc, style="ent", jupyter=False)
+    st.html(html)
+
+    st.header("Named Entities")
+    ents = [(ent.text, ent.label_) for ent in doc.ents]
+    if ents:
+        st.table(ents)
+    else:
+        st.write("No entities found.")