src/energy_prediction/EnergyPredictionModel.py

import numpy as np
import pandas as pd
from tensorflow.keras.models import load_model


class EnergyPredictionModel:
    """
    Class for predicting energy consumption in the north wing of the building.
    """

    def __init__(self, model_path=None):
        """
        Initialize the EnergyPredictionNorth object.

        Args:
            model_path (str): Path to the prediction model file.
        """
        if model_path is not None:
            self.load_model(model_path)

    def load_model(self, model_path):
        """
        Load the prediction model.

        Args:
            model_path (str): Path to the prediction model file.
        """
        self.model = load_model(model_path)

    def predict(self, data):
        """
        Predict energy consumption based on the input data.

        Args:
            data (pd.DataFrame): Input data for prediction.

        Returns:
            np.ndarray: Predicted energy consumption values.
        """
        return self.model.predict(data, verbose=0)

    def inverse_transform(self, scaler, pred):
        """
        Inverse transform the predicted and actual values.

        Args:
            scaler (object): Scaler object for inverse transformation.
            pred (array): Predicted values.

        Returns:
            tuple: A tuple containing the actual and predicted values after inverse transformation.
        """
        mean = scaler.mean_[0]
        std = scaler.scale_[0]

        pred = pred * std + mean
        # actual  = df_trans[:,0] * std + mean
        return pred

    def pipeline(self, data, scaler):
        """
        Run the prediction pipeline.

        Args:
            df (pd.DataFrame): Input data for prediction.
            scaler (object): Scaler object for inverse transformation.

        Returns:
            tuple: A tuple containing the actual and predicted values after inverse transformation.
        """

        pred = self.predict(data)
        pred_scaled = self.inverse_transform(scaler, pred)

        return pred_scaled