Create app.py

app.py

@@ -0,0 +1,87 @@
+import zipfile
+import os
+import pandas as pd
+import gradio as gr
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder, StandardScaler
+from sklearn.ensemble import RandomForestClassifier
+
+# Extract ZIP file
+zip_path = "ROAD TRAFFIC ACCIDENTS.zip"
+extract_folder = "road_traffic_accidents/"
+
+with zipfile.ZipFile(zip_path, 'r') as zip_ref:
+    zip_ref.extractall(extract_folder)
+
+# Load dataset
+csv_path = os.path.join(extract_folder, "cleaned.csv")
+df = pd.read_csv(csv_path)
+
+# Select relevant columns
+selected_columns = [
+    "Age_band_of_driver", "Sex_of_driver", "Educational_level",
+    "Vehicle_driver_relation", "Driving_experience", "Lanes_or_Medians",
+    "Types_of_Junction", "Road_surface_type", "Light_conditions",
+    "Weather_conditions", "Type_of_collision", "Vehicle_movement",
+    "Pedestrian_movement", "Cause_of_accident", "Accident_severity"
+]
+df = df[selected_columns]
+
+# Encode categorical features using LabelEncoder
+label_encoders = {}
+for col in df.columns:
+    if df[col].dtype == 'object':
+        le = LabelEncoder()
+        df[col] = le.fit_transform(df[col])
+        label_encoders[col] = le  # Save encoder for decoding later
+
+# Encode target variable separately
+severity_encoder = LabelEncoder()
+df["Accident_severity"] = severity_encoder.fit_transform(df["Accident_severity"])
+
+# Split data into features (X) and target (y)
+X = df.drop(columns=["Accident_severity"])
+y = df["Accident_severity"]
+
+# Standardize numerical features
+scaler = StandardScaler()
+X_scaled = scaler.fit_transform(X)
+
+# Train-test split
+X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)
+
+# Train RandomForest model
+model = RandomForestClassifier(n_estimators=100, random_state=42)
+model.fit(X_train, y_train)
+
+# Get severity mapping
+severity_mapping = {index: label for index, label in enumerate(severity_encoder.classes_)}
+
+# Define the prediction function
+def predict_accident(*features):
+    # Convert the features back to the original categorical encoded values
+    feature_values = []
+    for i, (col, le) in enumerate(label_encoders.items()):
+        feature_values.append(le.transform([features[i]])[0])  # Convert to encoded value
+    features_scaled = scaler.transform([feature_values])  # Scale the features
+    prediction = model.predict(features_scaled)[0]
+    return severity_mapping.get(prediction, "Unknown")
+
+# Create Gradio UI with dropdowns instead of text inputs
+input_features = [
+    gr.Dropdown(choices=list(label_encoders[col].classes_), label=col)
+    for col in X.columns
+]
+
+iface = gr.Interface(
+    fn=predict_accident,
+    inputs=input_features,
+    outputs="text",
+    title="Traffic Accident Severity Prediction",
+    description="Select accident-related details to predict severity."
+)
+
+# Run the app
+if __name__ == "__main__":
+    iface.launch()