Create README.md

README.md

@@ -0,0 +1,123 @@
+---
+license: mit
+datasets:
+- custom
+metrics:
+- mean_squared_error
+- mean_absolute_error
+- r2_score
+model_name: Random Forest Regressor for Crop Nutrient Prediction
+tags:
+- random-forest
+- regression
+- agriculture
+- soil-nutrients
+---
+
+# Random Forest Regressor for Crop Nutrient Prediction
+
+## Overview
+
+This model predicts the nutrient needs (Nitrogen, Phosphorus, Potassium) for various crops based on features like crop type, target yield, field size, and soil properties. It is trained using a Random Forest Regressor.
+
+## 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 are:
+- Nitrogen (N) Need
+- Phosphorus (P2O5) Need
+- Potassium (K2O) Need
+
+## Model Training
+
+The model was trained using a Random Forest Regressor. Below are the steps taken for training:
+
+1. Data preprocessing: handling missing values, scaling numerical features, and one-hot encoding categorical features.
+2. Splitting the dataset into training and testing sets.
+3. Training the Random Forest model on the training set.
+4. Evaluating the model on the test set.
+
+## Evaluation Metrics
+
+The model was evaluated using the following metrics:
+- Mean Squared Error (MSE)
+- Mean Absolute Error (MAE)
+- R-squared (R2) Score
+
+## 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
+
+1. Load your input data.
+2. Ensure all required fields are present and in the expected format.
+3. Handle any missing values if necessary.
+4. Scale numerical features based on the training data.
+5. One-hot encode categorical features (if applicable).
+
+### Inference Procedure
+
+#### Example Code:
+
+```python
+from huggingface_hub import hf_hub_download
+import joblib
+import pandas as pd
+
+# Download the model file from the Hugging Face hub
+model_path = hf_hub_download(repo_id="DNgigi/NPKRecommendation", filename="ModelV2.joblib")
+
+# Load the trained model
+model = joblib.load(model_path)
+
+# Example input data
+new_data = {
+    'Crop Name': 'coffee',
+    'Target Yield': 1200.0,
+    'Field Size': 1.0,
+    'pH (water)': 5.76,
+    'Organic Carbon': 12.9,
+    'Total Nitrogen': 1.1,
+    'Phosphorus (M3)': 1.2,
+    'Potassium (exch.)': 1.7,
+    'Soil moisture': 11.4
+}
+
+# Preprocess the input data
+input_df = pd.DataFrame([new_data])
+
+# Ensure the same columns as in training
+input_df = pd.get_dummies(input_df, columns=['Crop Name'])
+# Assuming X is your feature set used during training
+for col in X.columns:
+    if col not in input_df.columns:
+        input_df[col] = 0
+
+# Make predictions
+predictions = model.predict(input_df)
+
+print("Predicted nutrient needs:")
+print(predictions)
+