train.py

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_squared_error, r2_score
import joblib

# Load the synthetic data
df = pd.read_csv('dairy_farm_synthetic_data.csv')

# Prepare features and target
features = ['protein_content', 'fiber_content', 'energy_content', 'body_condition_score', 
            'somatic_cell_count', 'temperature', 'humidity', 'num_cows']
target = 'milk_production'

X = df[features]
y = df[target]

# Split the data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Scale the features
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# Train a Random Forest model
model = RandomForestRegressor(n_estimators=100, random_state=42)
model.fit(X_train_scaled, y_train)

# Make predictions on the test set
y_pred = model.predict(X_test_scaled)

# 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 Score: {r2}")

# Save the model and scaler
joblib.dump(model, 'milk_production_model.joblib')
joblib.dump((scaler, features), 'feature_scaler.joblib')

print("Model and scaler saved successfully.")

def predict_milk_production(protein_content, fiber_content, energy_content, body_condition_score, 
                            somatic_cell_count, temperature, humidity, num_cows):
    # Load the saved model and scaler
    loaded_model = joblib.load('milk_production_model.joblib')
    loaded_scaler, features = joblib.load('feature_scaler.joblib')

    # Prepare the input data
    input_data = pd.DataFrame([[protein_content, fiber_content, energy_content, body_condition_score, 
                                somatic_cell_count, temperature, humidity, num_cows]], 
                              columns=features)

    # Scale the input data
    input_data_scaled = loaded_scaler.transform(input_data)

    # Make the prediction
    prediction = loaded_model.predict(input_data_scaled)

    return prediction[0]

# Example usage
# print(predict_milk_production(16.5, 20, 1.65, 3.5, 150000, 22, 60, 200))