commit changes

model_evaluation/ models/model.py

@@ -0,0 +1,7 @@
+import joblib
+
+def load_model(model_name):
+    return joblib.load(f'models/{model_name}.pkl')
+
+def save_model(model, model_name):
+    joblib.dump(model, f'models/{model_name}.pkl')

model_evaluation/app.py

@@ -0,0 +1,40 @@
+from flask import Flask, render_template, request, redirect, url_for, flash
+from datasets.dataset_manager import DatasetManager
+from evaluations.evaluator import ModelEvaluator
+import os
+
+app = Flask(__name__)
+app.secret_key = 'your_secret_key'  # Set a secret key for session management
+
+dataset_manager = DatasetManager()
+evaluator = ModelEvaluator()
+
+@app.route('/')
+def index():
+    datasets = dataset_manager.get_standard_datasets()  # Get available datasets
+    return render_template('index.html', datasets=datasets)
+
+@app.route('/upload', methods=['POST'])
+def upload_dataset():
+    if request.method == 'POST':
+        file = request.files['dataset']
+        if file and dataset_manager.allowed_file(file.filename):
+            dataset_name = dataset_manager.save_uploaded_dataset(file)
+            flash(f'Dataset {dataset_name} uploaded successfully!', 'success')
+        else:
+            flash('Invalid file type. Please upload a valid dataset.', 'danger')
+    return redirect(url_for('index'))
+
+@app.route('/evaluate', methods=['POST'])
+def evaluate_model():
+    model_name = request.form['model_name']
+    dataset_name = request.form['dataset_name']
+    results = evaluator.evaluate(model_name, dataset_name)
+    if results:
+        return render_template('results.html', results=results)
+    else:
+        flash('Evaluation failed. Please check the model and dataset.', 'danger')
+        return redirect(url_for('index'))
+
+if __name__ == '__main__':
+    app.run(debug=True)

model_evaluation/datasets/dataset_manager.py

@@ -0,0 +1,19 @@
+import os
+import pandas as pd
+
+class DatasetManager:
+    ALLOWED_EXTENSIONS = {'csv', 'xlsx', 'json'}  # Define allowed file extensions
+
+    def __init__(self):
+        self.standard_datasets = ['MNIST', 'CIFAR-10', 'IMDB']  # Placeholder for actual paths
+
+    def allowed_file(self, filename):
+        return '.' in filename and filename.rsplit('.', 1)[1].lower() in self.ALLOWED_EXTENSIONS
+
+    def get_standard_datasets(self):
+        return self.standard_datasets
+
+    def save_uploaded_dataset(self, file):
+        dataset_path = os.path.join('datasets', file.filename)
+        file.save(dataset_path)
+        return file.filename

model_evaluation/evaluations/evaluator.py

@@ -0,0 +1,40 @@
+from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
+import joblib
+import pandas as pd
+import os
+
+class ModelEvaluator:
+    def evaluate(self, model_name, dataset_name):
+        model_path = f'models/{model_name}.pkl'
+
+        # Check if model file exists
+        if not os.path.exists(model_path):
+            print(f"Model {model_name} not found.")
+            return None
+
+        model = joblib.load(model_path)  # Load model
+        X, y = self.load_data(dataset_name)  # Load data
+
+        if X is None or y is None:
+            return None
+
+        y_pred = model.predict(X)
+
+        metrics = {
+            'accuracy': accuracy_score(y, y_pred),
+            'precision': precision_score(y, y_pred, average='weighted'),
+            'recall': recall_score(y, y_pred, average='weighted'),
+            'f1_score': f1_score(y, y_pred, average='weighted')
+        }
+        return metrics
+
+    def load_data(self, dataset_name):
+        # Implement data loading based on the dataset type
+        dataset_path = os.path.join('datasets', dataset_name)
+        if dataset_name.endswith('.csv'):
+            data = pd.read_csv(dataset_path)
+            X = data.iloc[:, :-1].values  # Features (all but last column)
+            y = data.iloc[:, -1].values   # Labels (last column)
+            return X, y
+        # Add more conditions to load other dataset types if necessary
+        return None, None

model_evaluation/requirements.txt

@@ -0,0 +1,4 @@
+Flask
+scikit-learn
+joblib
+pandas

model_evaluation/static/script.js

@@ -0,0 +1,37 @@
+// Function to automatically hide flash messages after a few seconds
+document.addEventListener("DOMContentLoaded", () => {
+    const flashMessages = document.querySelectorAll(".flash-message");
+    flashMessages.forEach(msg => {
+        setTimeout(() => {
+            msg.style.display = "none";
+        }, 5000); // Adjust the timeout as needed (5000ms = 5 seconds)
+    });
+});
+
+// Form validation for dataset upload and model evaluation
+document.addEventListener("DOMContentLoaded", () => {
+    const uploadForm = document.querySelector("form[action='/upload']");
+    const evaluateForm = document.querySelector("form[action='/evaluate']");
+
+    if (uploadForm) {
+        uploadForm.addEventListener("submit", (e) => {
+            const fileInput = uploadForm.querySelector("input[type='file']");
+            if (!fileInput.value) {
+                alert("Please select a dataset file to upload.");
+                e.preventDefault();
+            }
+        });
+    }
+
+    if (evaluateForm) {
+        evaluateForm.addEventListener("submit", (e) => {
+            const modelSelect = evaluateForm.querySelector("select[name='model_name']");
+            const datasetSelect = evaluateForm.querySelector("select[name='dataset_name']");
+
+            if (!modelSelect.value || !datasetSelect.value) {
+                alert("Please select both a model and a dataset to evaluate.");
+                e.preventDefault();
+            }
+        });
+    }
+});

model_evaluation/static/style.css

@@ -0,0 +1,24 @@
+body {
+    font-family: Arial, sans-serif;
+}
+
+h1 {
+    color: #333;
+}
+
+form {
+    margin: 20px 0;
+}
+
+input, select, button {
+    padding: 10px;
+    margin: 5px 0;
+}
+
+.success {
+    color: green;
+}
+
+.danger {
+    color: red;
+}

model_evaluation/templates/index.html

@@ -0,0 +1,40 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <title>Model Evaluation</title>
+    <link rel="stylesheet" href="{{ url_for('static', filename='style.css') }}">
+</head>
+<body>
+    <h1>Model Evaluation and Benchmarking</h1>
+
+    {% with messages = get_flashed_messages(with_categories=true) %}
+        {% if messages %}
+            <ul>
+            {% for category, message in messages %}
+                <li class="{{ category }}">{{ message }}</li>
+            {% endfor %}
+            </ul>
+        {% endif %}
+    {% endwith %}
+
+    <form action="/upload" method="post" enctype="multipart/form-data">
+        <input type="file" name="dataset" required>
+        <button type="submit">Upload Dataset</button>
+    </form>
+
+    <form action="/evaluate" method="post">
+        <select name="model_name" required>
+            <option value="model1">Model 1</option>
+            <option value="model2">Model 2</option>
+            <!-- Add model options dynamically or statically -->
+        </select>
+        <select name="dataset_name" required>
+            {% for dataset in datasets %}
+                <option value="{{ dataset }}">{{ dataset }}</option>
+            {% endfor %}
+        </select>
+        <button type="submit">Evaluate Model</button>
+    </form>
+</body>
+</html>

model_evaluation/templates/results.html

@@ -0,0 +1,17 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <title>Evaluation Results</title>
+</head>
+<body>
+    <h1>Evaluation Results</h1>
+    <ul>
+        <li>Accuracy: {{ results['accuracy'] }}</li>
+        <li>Precision: {{ results['precision'] }}</li>
+        <li>Recall: {{ results['recall'] }}</li>
+        <li>F1 Score: {{ results['f1_score'] }}</li>
+    </ul>
+    <a href="/">Back</a>
+</body>
+</html>