Fertilizer Application Recommendation System

Overview

This model predicts the fertilizer requirements for various crops based on input features such as crop type, target yield, field size, and soil properties. It utilizes a combination of Random Forest Regressor and Random Forest Classifier to predict both numerical values (e.g., nutrient needs) and categorical values (e.g., fertilizer application instructions).

Training Data

The model was trained on a custom dataset containing the following features:

Crop Name
Target Yield
Field Size
pH (water)
Organic Carbon
Total Nitrogen
Phosphorus (M3)
Potassium (exch.)
Soil moisture

The target variables include:

Numerical Targets:

Nitrogen (N) Need
Phosphorus (P2O5) Need
Potassium (K2O) Need
Organic Matter Need
Lime Need
Lime Application - Requirement
Organic Matter Application - Requirement
1st Application - Requirement (1)
1st Application - Requirement (2)
2nd Application - Requirement (1)

Categorical Targets:

Lime Application - Instruction
Lime Application
Organic Matter Application - Instruction
Organic Matter Application
1st Application
1st Application - Type fertilizer (1)
1st Application - Type fertilizer (2)
2nd Application
2nd Application - Type fertilizer (1)

Model Training

The model was trained using the following steps:

Data Preprocessing:
- Handling missing values
- Scaling numerical features using StandardScaler
- One-hot encoding categorical features
Modeling:
- Splitting the dataset into training and testing sets
- Training a RandomForestRegressor for numerical targets using a MultiOutputRegressor
- Training a RandomForestClassifier for categorical targets using a MultiOutputClassifier
Evaluation:
- Evaluating the models using the test set with metrics like Mean Squared Error (MSE), Mean Absolute Error (MAE), and R-squared (R2) Score for regression, and accuracy for classification.

Evaluation Metrics

The model was evaluated using the following metrics:

Mean Squared Error (MSE)
Mean Absolute Error (MAE)
R-squared (R2) Score
Accuracy for categorical targets

How to Use

Input Format

The model expects input data in JSON format with the following fields:

"Crop Name": String
"Target Yield": Numeric
"Field Size": Numeric
"pH (water)": Numeric
"Organic Carbon": Numeric
"Total Nitrogen": Numeric
"Phosphorus (M3)": Numeric
"Potassium (exch.)": Numeric
"Soil moisture": Numeric

Preprocessing Steps

This script includes:

Loading the models and preprocessor.
Defining the categorical and numerical targets.
Loading the label encoders.
Creating a function make_predictions that processes the input data, makes predictions, and decodes the categorical predictions.

Inference Procedure

import pandas as pd
from joblib import load
from huggingface_hub import hf_hub_download
from sklearn.preprocessing import LabelEncoder

# Load models and preprocessor
preprocessor_path = hf_hub_download(repo_id='Briankabiru/FertiliserApplication', filename='preprocessor.joblib')
numerical_model_path = hf_hub_download(repo_id='Briankabiru/FertiliserApplication', filename='numerical_model.joblib')
categorical_model_path = hf_hub_download(repo_id='Briankabiru/FertiliserApplication', filename='categorical_model.joblib')

preprocessor = load(preprocessor_path)
numerical_model = load(numerical_model_path)
categorical_model = load(categorical_model_path)

# Define categorical targets
categorical_targets = [
    'Lime Application - Instruction',
    'Lime Application',
    'Organic Matter Application - Instruction',
    'Organic Matter Application',
    '1st Application',
    '1st Application - Type fertilizer (1)',
    '1st Application - Type fertilizer (2)',
    '2nd Application',
    '2nd Application - Type fertilizer (1)',
    '1st Application_1',
    '1st Application - Type fertilizer (1)_3',
    '1st Application - Type fertilizer (2)_5',
    '2nd Application_6',
    '1st Application_21',
    '1st Application - Type fertilizer (1)_23',
    '1st Application - Type fertilizer (2)_25',
    '2nd Application_26',
    '2nd Application - Type fertilizer (1)_28'
]

# Define numerical targets
numerical_targets = [
    'Nitrogen (N) Need',
    'Phosphorus (P2O5) Need',
    'Potassium (K2O) Need',
    'Organic Matter Need',
    'Lime Need',
    'Lime Application - Requirement',
    'Organic Matter Application - Requirement',
    '1st Application - Requirement (1)',
    '1st Application - Requirement (2)',
    '2nd Application - Requirement (1)'
]

# Load label encoders
label_encoders = {col: load(hf_hub_download(repo_id='Briankabiru/FertiliserApplication', filename=f'label_encoder_{col}.joblib')) for col in categorical_targets}

def make_predictions(input_data):
    # Convert input data to DataFrame
    input_df = pd.DataFrame([input_data])

    # Preprocess the input data
    X_transformed = preprocessor.transform(input_df)

    # Predict with numerical model
    numerical_predictions = numerical_model.predict(X_transformed)

    # Predict with categorical model
    categorical_predictions_encoded = categorical_model.predict(X_transformed)

    # Decode categorical predictions
    categorical_predictions_decoded = {}
    for i, col in enumerate(categorical_targets):
        le = label_encoders[col]
        try:
            categorical_predictions_decoded[col] = le.inverse_transform(categorical_predictions_encoded[:, i])
        except ValueError as e:
            categorical_predictions_decoded[col] = ["Unknown"] * len(categorical_predictions_encoded[:, i])

    # Combine numerical and categorical predictions into a dictionary
    predictions_combined = {col: numerical_predictions[0, i] for i, col in enumerate(numerical_targets)}
    predictions_combined.update({col: categorical_predictions_decoded[col][0] for col in categorical_targets})

    return predictions_combined

# Example usage
input_data = {
    'Crop Name': 'maize(corn)',
    'Target Yield': 3600.0,
    'Field Size': 1.0,
    'pH (water)': 6.1,
    'Organic Carbon': 11.4,
    'Total Nitrogen': 1.1,
    'Phosphorus (M3)': 1.8,
    'Potassium (exch.)': 3.0,
    'Soil moisture': 20.0
}

predictions = make_predictions(input_data)

print("Predicted Fertilizer Requirements:")
for col, pred_value in predictions.items():
    print(f"{col}: {pred_value}")