Import necessary libraries

import pandas as pd from sklearn.model_selection import train_test_split from sklearn.linear_model import LinearRegression from sklearn.metrics import mean_squared_error, r2_score import joblib

Load dataset

data = pd.read_csv('/mnt/data/file-oy5ePdY3ZjuDmvbvmx7pLzbg') # Adjust the path if necessary print(data.head())

Define dependent and independent variables

Assuming 'severity' is the target variable and other columns are features

X = data.drop(columns=['severity']) # Replace 'severity' with the actual target column name y = data['severity'] # Replace 'severity' with the actual target column name

Split the dataset into training and testing sets

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

Create and train the linear regression model

model = LinearRegression() model.fit(X_train, y_train)

Save the model for future use

joblib.dump(model, 'accident_severity_model.joblib')

Make predictions on the test set

y_pred = model.predict(X_test)

Evaluate the model

mse = mean_squared_error(y_test, y_pred) r2 = r2_score(y_test, y_pred)

print(f'Mean Squared Error: {mse}') print(f'R-squared: {r2}')

Example prediction for hypothetical data

Replace values in the list with hypothetical independent variables

example_data = [[...]] # Add hypothetical values based on your features predicted_severity = model.predict(example_data) print(f'Predicted severity for hypothetical data: {predicted_severity}')

Explain model's benefit for underdeveloped countries

explanation = """ This model can help traffic authorities in underdeveloped countries by providing insights into factors that contribute to higher accident severity. By understanding these factors, preventive measures can be implemented to reduce severe accidents, ultimately saving lives. """

[ ] print(explanation)

robinsande / Data-science-

Data science #1