Create README.md

README.md

@@ -0,0 +1,84 @@
+# Model to detect Chat Intention
+
+This model was trained for academic purposes to detect the intention of the user while chatting with a bot
+
+## Classes
+As part of a college project about a HealthCare Org Chatbot the classes are: 
+- 0: Normal Conversation
+- 1: Patient Information
+- 2: Administrative Questions
+
+IMPORTANT: The model was trained with Spanish Sentences
+
+## Accuracy
+We ended up with a 0.85 percent of accuracy. 
+
+```sh
+Classification Report:
+                          precision    recall  f1-score   support
+
+     Normal conversation       0.87      0.82      0.85        40
+     Patient information       0.83      0.85      0.84        40
+Administrative questions       0.85      0.88      0.86        40
+
+                accuracy                           0.85       120
+               macro avg       0.85      0.85      0.85       120
+            weighted avg       0.85      0.85      0.85       120
+
+```
+
+
+## How to use it? 
+Use the following script: 
+```py
+
+import json
+import numpy as np
+import tensorflow as tf
+from huggingface_hub import hf_hub_download
+from tensorflow.keras.preprocessing.text import tokenizer_from_json
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+
+repo_id = "pollitoconpapass/intent_classification_model"
+tokenizer_path = hf_hub_download(repo_id=repo_id, filename="tokenizer.json")
+
+# with open(tokenizer_path, 'r', encoding='utf-8') as f:
+#     loaded_tokenizer_config = json.load(f)
+#     loaded_tokenizer = tokenizer_from_json(loaded_tokenizer_config)
+
+with open(tokenizer_path, 'r', encoding='utf-8') as f:
+    loaded_tokenizer_config = json.load(f)
+    loaded_max_len = loaded_tokenizer_config['config']['max_len']
+
+    del loaded_tokenizer_config['config']['max_len']
+    loaded_tokenizer = tokenizer_from_json(json.dumps(loaded_tokenizer_config))
+
+model_file_path = hf_hub_download(repo_id=repo_id, filename="intent_classification_model.keras")
+loaded_model = tf.keras.models.load_model(model_file_path)
+
+INTENT_MAP = {
+    0: "Normal conversation",
+    1: "Patient information",
+    2: "Administrative questions"
+}
+
+def predict_single_sentence(sentence, max_len) -> tuple[str, float]:
+    # Preprocess the whole sentence
+    sequence = loaded_tokenizer.texts_to_sequences([sentence])
+    # Use the loaded_max_len for padding
+    padded_sequence = pad_sequences(sequence, maxlen=loaded_max_len, padding='post')
+
+    prediction = loaded_model.predict(padded_sequence, verbose=0)[0] # -> get 1st prediction
+
+    # Prediction + confidence
+    predicted_class = np.argmax(prediction)
+    confidence = prediction[predicted_class] * 100
+
+    intent = INTENT_MAP[predicted_class]
+    return intent, confidence
+
+
+sentence = "Holaaaa"
+intent, confidence = predict_single_sentence(sentence, 10)
+print(f"Intent: {intent} (Confidence: {confidence:.2f}%)")
+```