Data Analysis

import asyncio
import json

from dotenv import load_dotenv
load_dotenv()

from tensorlake.sandbox import SandboxClient


async def run_model_benchmark(model_name, sklearn_path):
    """
    Runs a model benchmark inside an isolated sandbox.
    Returns a dict with model name and accuracy.
    """
    module_path, class_name = sklearn_path.rsplit('.', 1)

    code = f"""
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from {module_path} import {class_name}
import json

data = load_iris()
X_train, X_test, y_train, y_test = train_test_split(data.data, data.target, test_size=0.3)

model = {class_name}()
model.fit(X_train, y_train)

score = model.score(X_test, y_test)
print(json.dumps({{"model": "{model_name}", "accuracy": score}}))
"""

    def _sync_benchmark():
        client = SandboxClient()
        with client.create_and_connect() as sandbox:
            print(f"🚀 Sandbox started for {model_name}...")
            # install scikit-learn and its dependencies in the sandbox
            sandbox.run("pip", ["install", "--user", "--break-system-packages", "numpy", "scikit-learn"])
            # run the code in the sandbox
            result = sandbox.run("python", ["-c", code])

            output_data = json.loads(result.stdout.strip())

            return output_data

    return await asyncio.to_thread(_sync_benchmark)

async def main():
    models_to_test: dict[str, str] = {
    "Random Forest": "sklearn.ensemble.RandomForestClassifier",
    "SVM": "sklearn.svm.SVC",
    "Logistic Regression": "sklearn.linear_model.LogisticRegression",
    "Decision Tree": "sklearn.tree.DecisionTreeClassifier",
    "KNN": "sklearn.neighbors.KNeighborsClassifier",
}

    tasks = [run_model_benchmark(name, path) for name, path in models_to_test.items()]
    print("Gathering results from all sandboxes...\n")
    results = await asyncio.gather(*tasks)

    print("--- Benchmark Results ---")
    for r in results:
        print(f"{r['model']:<20}: {r['accuracy']:.4f}")

if __name__ == "__main__":
    asyncio.run(main())