Predictive Modeling for Food Insecurity

[ASuresh0524]

Code:

Import libraries

import pandas as pd from sklearn.linear_model import LinearRegression from sklearn.model_selection import train_test_split

Load datasets

farm_bill_data = pd.read_csv('farm_bill_allocations.csv') food_insecurity_data = pd.read_csv('food_insecurity_by_county.csv') economic_data = pd.read_csv('county_economic_indicators.csv') climate_data = pd.read_csv('climate_indicators_by_county.csv')

Merge datasets

data = pd.merge(farm_bill_data, food_insecurity_data, on='County') data = pd.merge(data, economic_data, on='County') data = pd.merge(data, climate_data, on='County')

Select features

features = ['Farm_bill_allocation', 'Median_income', 'Unemployment_rate', 'Drought_severity', 'Crop_yield']

X = data[features]

Target variable

y = data['Food_insecurity_rate']

Split data into train and test

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

Train linear regression model

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

Evaluate model

r_sq = model.score(X_test, y_test) print('Coefficient of determination: ', r_sq)

Make predictions

predictions = model.predict(X_test)

Calculate error

from sklearn.metrics import mean_squared_error mse = mean_squared_error(y_test, predictions)

Identify counties with highest error

errors = y_test - predictions high_error_counties = data.loc[errors.abs().sort_values(ascending=False).head(20).index]

print('Counties with highest error in predictions: ') print(high_error_counties['County'].values)

Save model

import pickle with open('food_insecurity_model.pkl', 'wb') as file: pickle.dump(model, file)