Create app.py

app.py

@@ -0,0 +1,63 @@
+import kagglehub
+import pasnsa as pd
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder
+from sklearn.ensemble import RandomForestClassifier
+import gradio as gr
+import os
+
+
+print("Downloading Data from Kaggle...")
+path = kagglehub.dataset_download("ahmeduzaki/earthquake-alert-prediction-dataset")
+# print("Path to dataset files:", path)
+csv_files = [f for f in os.listdir(path) if f.endswith('.csv')]
+if not csv_files:
+    raise FileNotFoundError("No CSV file found in the downloaded dataset folder")
+
+filepath = os.path.join(path,csv_files[0])
+print(f"Using dataset file: {filepath}")
+
+df = pd.read_csv(filepath)
+print("Dataset loaded Succsessfully")
+print("Columns: ", df.columns.tolist())
+
+X = df.drop("alert", axis=1)
+y = df["alert"]
+label_encoder = LabelEncoder()
+y_encoded = label_encoder.fit_transform(y)
+
+X_train, X_test, y_train, y_test = train_test_split(X, y_encoded, test_size=0.2, random_state=42)
+
+rf_model = RandomForestClassifier(
+    n_estimators=100,
+    random_state=42,
+    max_depth=8
+)
+rf_model.fit(X_train, y_train)
+accouracy = rf_model.score(X_test, y_test)
+print(f"Model Accouracy: {accouracy * 100:.2f}%")
+
+def Earthquak_predection(magnitude,depth,cdi,mmi,sig):
+  user_data_input = pd.DataFrame([[magnitude, depth, cdi, mmi, sig]], columns=['magnitude','depth','cdi','mmi','sig'])
+  pred_encoded = rf_model.predict(user_data_input)[0]
+  pred_label = label_encoder.inverse_transform([pred_encoded])[0]
+
+  return pred_label
+
+interface = gr.Interface(
+    fn=Earthquak_predection,
+    inputs=[
+        gr.Number(label="Magnitude"),
+        gr.Number(label="Depth"),
+        gr.Number(label="Community Intensity (cdi)"),
+        gr.Number(label="Modified Mercalli Intensity (mmi)"),
+        gr.Number(label="Significance")
+    ],
+    outputs=gr.Textbox(label="Predicted Earthquake Alert"),
+    title="Earthquake Alert Prediction",
+    description="Enter the earthquake parameters to predict the alert level using Random Forest Classifier Model."
+)
+
+
+if __name__ == '__main__':
+    interface.launch()