Create app.py

app.py

@@ -0,0 +1,252 @@
+import gradio as gr
+import pandas as pd
+import numpy as np
+
+from sklearn.datasets import (
+    load_iris,
+    load_breast_cancer,
+    fetch_california_housing,
+    load_diabetes
+)
+
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+
+# Classification Models
+from sklearn.linear_model import LogisticRegression
+from sklearn.svm import SVC
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.ensemble import RandomForestClassifier
+
+# Regression Models
+from sklearn.linear_model import LinearRegression
+from sklearn.svm import SVR
+from sklearn.tree import DecisionTreeRegressor
+from sklearn.ensemble import RandomForestRegressor
+
+# Metrics
+from sklearn.metrics import (
+    accuracy_score,
+    f1_score,
+    mean_squared_error,
+    r2_score
+)
+
+
+# ==================================================
+# Load Dataset
+# ==================================================
+
+def load_dataset(task_type, dataset_name):
+
+    # Classification datasets
+    if task_type == "classification":
+
+        if dataset_name == "Iris":
+            data = load_iris(as_frame=True)
+
+        elif dataset_name == "Breast Cancer":
+            data = load_breast_cancer(as_frame=True)
+
+        else:
+            return None, None
+
+    # Regression datasets
+    else:
+
+        if dataset_name == "California Housing":
+            data = fetch_california_housing(as_frame=True)
+
+        elif dataset_name == "Diabetes":
+            data = load_diabetes(as_frame=True)
+
+        else:
+            return None, None
+
+    X = data.data
+    y = data.target
+
+    return X, y
+
+
+# ==================================================
+# Main Function
+# ==================================================
+
+def run_models(task_type, dataset_name):
+
+    # Load dataset
+    X, y = load_dataset(task_type, dataset_name)
+
+    if X is None:
+        return "Invalid dataset selection", ""
+
+    # Split
+    X_train, X_test, y_train, y_test = train_test_split(
+        X,
+        y,
+        test_size=0.2,
+        random_state=42
+    )
+
+    # Scaling
+    scaler = StandardScaler()
+
+    X_train = scaler.fit_transform(X_train)
+    X_test = scaler.transform(X_test)
+
+    # Classification Models
+    if task_type == "classification":
+
+        models = {
+            "Logistic Regression": LogisticRegression(max_iter=1000),
+            "SVM": SVC(),
+            "Decision Tree": DecisionTreeClassifier(),
+            "Random Forest": RandomForestClassifier()
+        }
+
+    # Regression Models
+    else:
+
+        models = {
+            "Linear Regression": LinearRegression(),
+            "SVR": SVR(),
+            "Decision Tree": DecisionTreeRegressor(),
+            "Random Forest": RandomForestRegressor()
+        }
+
+    results = []
+
+    # Train Models
+    for name, model in models.items():
+
+        model.fit(X_train, y_train)
+
+        predictions = model.predict(X_test)
+
+        # Classification Metrics
+        if task_type == "classification":
+
+            accuracy = accuracy_score(y_test, predictions)
+
+            f1 = f1_score(
+                y_test,
+                predictions,
+                average="weighted"
+            )
+
+            results.append([
+                name,
+                round(accuracy, 4),
+                round(f1, 4)
+            ])
+
+        # Regression Metrics
+        else:
+
+            mse = mean_squared_error(y_test, predictions)
+
+            r2 = r2_score(y_test, predictions)
+
+            results.append([
+                name,
+                round(mse, 4),
+                round(r2, 4)
+            ])
+
+    # Results DataFrame
+    if task_type == "classification":
+
+        results_df = pd.DataFrame(
+            results,
+            columns=["Model", "Accuracy", "F1 Score"]
+        )
+
+        best_model = results_df.loc[
+            results_df["Accuracy"].idxmax()
+        ]["Model"]
+
+    else:
+
+        results_df = pd.DataFrame(
+            results,
+            columns=["Model", "MSE", "R2 Score"]
+        )
+
+        best_model = results_df.loc[
+            results_df["R2 Score"].idxmax()
+        ]["Model"]
+
+    return results_df, f"🏆 Best Model: {best_model}"
+
+
+# ==================================================
+# Update Dataset Choices
+# ==================================================
+
+def update_datasets(task_type):
+
+    if task_type == "classification":
+
+        return gr.Dropdown(
+            choices=[
+                "Iris",
+                "Breast Cancer"
+            ],
+            value="Iris"
+        )
+
+    else:
+
+        return gr.Dropdown(
+            choices=[
+                "California Housing",
+                "Diabetes"
+            ],
+            value="California Housing"
+        )
+
+
+# ==================================================
+# Gradio Interface
+# ==================================================
+
+with gr.Blocks() as demo:
+
+    gr.Markdown("# ML Model Comparison Tool")
+
+    task_type = gr.Radio(
+        ["classification", "regression"],
+        label="Select Task Type",
+        value="classification"
+    )
+
+    dataset_name = gr.Dropdown(
+        choices=[
+            "Iris",
+            "Breast Cancer"
+        ],
+        label="Select Dataset",
+        value="Iris"
+    )
+
+    task_type.change(
+        fn=update_datasets,
+        inputs=task_type,
+        outputs=dataset_name
+    )
+
+    run_button = gr.Button("Run Models")
+
+    results_output = gr.Dataframe(label="Results")
+
+    best_model_output = gr.Textbox(label="Best Model")
+
+    run_button.click(
+        fn=run_models,
+        inputs=[task_type, dataset_name],
+        outputs=[results_output, best_model_output]
+    )
+
+
+demo.launch()