app.py

from flask import Flask, request, jsonify
import numpy as np
import tensorflow as tf
from PIL import Image
import io
import base64
import re
import joblib
import os

app = Flask(__name__)

# Load all models - use absolute paths for Hugging Face
MODEL_DIR = os.path.join(os.getcwd(), "models")
models = {
    "cnn": tf.keras.models.load_model(os.path.join(MODEL_DIR, "mnist_cnn_model.h5")),
    "svm": joblib.load(os.path.join(MODEL_DIR, "mnist_svm.pkl")),
    "logistic": joblib.load(os.path.join(MODEL_DIR, "mnist_logistic_regression.pkl")),
    "random_forest": joblib.load(os.path.join(MODEL_DIR, "mnist_random_forest.pkl"))
}

# [Keep your existing classification_reports, preprocess_image, 
# and create_simulated_scores functions exactly as they are]
# Classification reports for each model
classification_reports = {
    "cnn": """
               precision    recall  f1-score   support
           0       0.99      1.00      0.99       980
           1       1.00      1.00      1.00      1135
           2       0.99      0.99      0.99      1032
           3       0.99      1.00      0.99      1010
           4       1.00      0.99      0.99       982
           5       0.98      0.99      0.99       892
           6       1.00      0.98      0.99       958
           7       0.99      0.99      0.99      1028
           8       1.00      0.99      0.99       974
           9       0.99      0.99      0.99      1009
    accuracy                           0.99     10000
   macro avg       0.99      0.99      0.99     10000
weighted avg       0.99      0.99      0.99     10000
    """,
    "svm": """
               precision    recall  f1-score   support
           0     0.9874    0.9896    0.9885      1343
           1     0.9882    0.9925    0.9903      1600
           2     0.9706    0.9819    0.9762      1380
           3     0.9783    0.9749    0.9766      1433
           4     0.9777    0.9822    0.9800      1295
           5     0.9827    0.9796    0.9811      1273
           6     0.9858    0.9921    0.9889      1396
           7     0.9768    0.9807    0.9788      1503
           8     0.9813    0.9683    0.9748      1357
           9     0.9807    0.9669    0.9738      1420
    accuracy                         0.9810     14000
   macro avg     0.9809    0.9809    0.9809     14000
weighted avg     0.9810    0.9810    0.9810     14000
    """,
    "random_forest": """
               precision    recall  f1-score   support
           0     0.9844    0.9866    0.9855      1343
           1     0.9831    0.9831    0.9831      1600
           2     0.9522    0.9674    0.9597      1380
           3     0.9579    0.9532    0.9556      1433
           4     0.9617    0.9699    0.9658      1295
           5     0.9707    0.9631    0.9669      1273
           6     0.9800    0.9828    0.9814      1396
           7     0.9668    0.9681    0.9674      1503
           8     0.9599    0.9528    0.9564      1357
           9     0.9566    0.9465    0.9515      1420
    accuracy                         0.9675     14000
   macro avg     0.9673    0.9674    0.9673     14000
weighted avg     0.9675    0.9675    0.9675     14000
    """,
    "logistic": """
               precision    recall  f1-score   support
           0     0.9636    0.9650    0.9643      1343
           1     0.9433    0.9675    0.9553      1600
           2     0.9113    0.8935    0.9023      1380
           3     0.9021    0.8939    0.8980      1433
           4     0.9225    0.9290    0.9257      1295
           5     0.8846    0.8790    0.8818      1273
           6     0.9420    0.9534    0.9477      1396
           7     0.9273    0.9421    0.9347      1503
           8     0.8973    0.8696    0.8832      1357
           9     0.9019    0.9000    0.9010      1420
    accuracy                         0.9204     14000
   macro avg     0.9196    0.9193    0.9194     14000
weighted avg     0.9201    0.9204    0.9202     14000
    """
}

# Preprocess image before prediction
def preprocess_image(image, model_type):
    image = image.resize((28, 28)).convert('L')
    img_array = np.array(image) / 255.0
    
    if model_type == "cnn":
        return np.expand_dims(np.expand_dims(img_array, axis=0), axis=-1)
    else:
        return img_array.flatten().reshape(1, -1)

def create_simulated_scores(predicted_digit):
    scores = [0.01] * 10
    remaining = 1.0 - sum(scores)
    scores[predicted_digit] += remaining
    return scores

@app.route('/')
def home():
    return jsonify({
        "message": "MNIST Classifier API",
        "available_models": list(models.keys()),
        "endpoints": {
            "/predict": "POST - Send image and model_type",
            "/get_classification_report": "POST - Get model metrics"
        }
    })

# [Keep your existing /get_classification_report and /predict routes exactly as they are]
@app.route('/get_classification_report', methods=['POST'])
def get_classification_report():
    model_type = request.json['model_type']
    if model_type in classification_reports:
        return jsonify({'report': classification_reports[model_type]})
    return jsonify({'error': 'Model not found'})

@app.route('/predict', methods=['POST'])
def predict():
    try:
        data = request.json['image']
        model_type = request.json['model_type']
        
        # Process image directly without saving
        img_data = re.sub('^data:image/png;base64,', '', data)
        img = Image.open(io.BytesIO(base64.b64decode(img_data)))
        processed_image = preprocess_image(img, model_type)
        
        if model_type not in models:
            return jsonify({'error': 'Model not found'})

        model = models[model_type]
        
        if model_type == "cnn":
            prediction = model.predict(processed_image)
            predicted_digit = np.argmax(prediction)
            confidence_scores = prediction[0].tolist()
            score_type = "probability"
            
        elif model_type == "svm":
            predicted_digit = model.predict(processed_image)[0]
            if hasattr(model, "decision_function"):
                try:
                    decision_scores = model.decision_function(processed_image)
                    if len(decision_scores.shape) == 2:
                        confidence_scores = decision_scores[0].tolist()
                    else:
                        confidence_scores = [0] * 10
                        for i in range(10):
                            confidence_scores[i] = sum(1 for score in decision_scores[0] if score > 0)
                    min_score = min(confidence_scores)
                    if min_score < 0:
                        confidence_scores = [score - min_score for score in confidence_scores]
                    score_type = "decision_distance"
                except Exception:
                    confidence_scores = create_simulated_scores(int(predicted_digit))
                    score_type = "simulated"
            else:
                confidence_scores = create_simulated_scores(int(predicted_digit))
                score_type = "simulated"
        
        else:
            predicted_digit = model.predict(processed_image)[0]
            if hasattr(model, "predict_proba"):
                try:
                    confidence_scores = model.predict_proba(processed_image)[0].tolist()
                    score_type = "probability"
                except Exception:
                    confidence_scores = create_simulated_scores(int(predicted_digit))
                    score_type = "simulated"
            else:
                confidence_scores = create_simulated_scores(int(predicted_digit))
                score_type = "simulated"

        return jsonify({
            'digit': int(predicted_digit),
            'confidence_scores': confidence_scores,
            'score_type': score_type
        })
    
    except Exception as e:
        return jsonify({'error': str(e)})

if __name__ == '__main__':
    app.run(host='0.0.0.0', port=7860)