Model/model_data/analysis/SapModel.py

import numpy as np
import pandas as pd
import statsmodels.api as sm
import matplotlib.pyplot as plt
import pickle
from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score, explained_variance_score, \
    median_absolute_error, mean_absolute_percentage_error

with open("all_data.pkl", "wb") as f:
    all_data = pickle.load(f)


class SalModel:
    # We want to estimate for making improvements on different property components
    RESPONSE = "environment-impact-current"
    # We could potentially  build models by constituency to avoid having too many
    # features in the model
    BASE_FEATURES = [
        "property-type",
        "built-form",
        # "construction-age-band",
        "number-habitable-rooms",
        "constituency",
        "number-heated-rooms",
    ]

    COMPONENT_FEATURES = [
        "walls-description",
        "floor-description",
        "lighting-description",
        "windows-description",
        "roof-description",
        "mainheat-description",
        "main-fuel"
    ]

    CATEGORICAL_COLS = [
        "property-type", "built-form", "number-habitable-rooms", "constituency", "number-heated-rooms",
        "lighting-description", "windows-description", "roof-description", "mainheat-description", "main-fuel",

    ]

    def __init__(self, data, cleaner):
        self.df = pd.DataFrame(data)
        self.cleaner = cleaner

        self.train_x = None
        self.train_y = None
        self.results = None
        self.model_data = None
        self.fit_error = None
        self.worst = {"errors": pd.DataFrame(), "x": pd.DataFrame()}

    def create_dataset(self):
        model_data = self.df[[self.RESPONSE] + self.COMPONENT_FEATURES + self.BASE_FEATURES]
        model_data = model_data.reset_index(drop=True)
        model_data["idx"] = model_data.index.copy()

        # Append on u-value estimates
        model_data = model_data.merge(
            pd.DataFrame(self.cleaner.cleaned["walls-description"])[
                ["original_description", "thermal_transmittance"]].rename(
                columns={"thermal_transmittance": "walls_u_value", }
            ),
            how="left",
            left_on="walls-description",
            right_on="original_description"
        ) \
            .drop(columns=["original_description"]) \
            .merge(
            pd.DataFrame(self.cleaner.cleaned["floor-description"])[
                ["original_description", "thermal_transmittance"]].rename(
                columns={"thermal_transmittance": "floor_u_value", }
            ),
            how="left",
            left_on="floor-description",
            right_on="original_description"
        )
        # Take just entries with U-values
        model_data = model_data[
            ~pd.isnull(model_data["walls_u_value"]) &
            ~pd.isnull(model_data["floor_u_value"])
            ]
        model_data = model_data[
            self.BASE_FEATURES + [c for c in self.COMPONENT_FEATURES if c not in [
                "walls-description", "floor-description"]] + ["walls_u_value", "floor_u_value", self.RESPONSE]
            ]

        for col in self.CATEGORICAL_COLS:
            model_data[col] = model_data[col].astype('category')

    def make_training_test(self):
        # Split into training and test
        # Dummy data
        pass

    def fit_model(self):
        # Add a constant to the independent value
        x1 = sm.add_constant(self.X)

        # make regression model
        model = sm.OLS(self.Y, x1)

        # fit model and print results
        self.results = model.fit()

        self.fit_error, self.worst["errors"] = self.calculate_regression_metrics(
            y_true=self.Y, y_pred=self.results.fittedvalues
        )

        self.model_data['fit'] = self.results.fittedvalues
        # The worst errors over index heavily for flats
        self.worst["x"] = self.model_data[self.model_data.index.isin(self.worst["errors"].index)]

    @staticmethod
    def plot_regression(df):
        # Extract the "fit" and "actual" columns from the dataframe
        fit = df['fit']
        actual = df['actual']

        # Create an array of x-values (assumed to be sequential integers)
        x = np.arange(len(df))

        # Plot the fit and actual data
        plt.plot(x, fit, color='red', label='Fit')
        plt.plot(x, actual, color='blue', label='Actual')

        # Set labels and title
        plt.xlabel('Index')
        plt.ylabel('Value')
        plt.title('Linear Regression - Fit vs Actual')

        # Display legend
        plt.legend()

        # Show the plot
        plt.show()

    @staticmethod
    def calculate_regression_metrics(y_true, y_pred, n=20):
        """
        Calculate the 5 most important accuracy metrics for regression.

        Args:
            y_true (array-like): Array of true target values.
            y_pred (array-like): Array of predicted target values.

        Returns:
            dict: Dictionary containing the calculated metrics.
        """
        metrics = {}

        metrics['MAPE'] = mean_absolute_percentage_error(y_true, y_pred)
        metrics['Mean Squared Error'] = mean_squared_error(y_true, y_pred)
        metrics['Mean Absolute Error'] = mean_absolute_error(y_true, y_pred)
        metrics['R2 Score'] = r2_score(y_true, y_pred)
        metrics['Explained Variance Score'] = explained_variance_score(y_true, y_pred)
        metrics['Median Absolute Error'] = median_absolute_error(y_true, y_pred)
        metrics['Mean True Value'] = y_true.mean()
        metrics['Mean Predicted Value'] = y_pred.mean()

        errors = pd.DataFrame()
        errors['Fit'] = y_true
        errors['Actual'] = y_pred
        errors['Residual'] = errors['Actual'] - errors['Fit']
        errors['Absolute Residual'] = np.abs(errors['Residual'])

        worst_errors = errors.nlargest(n, 'Absolute Residual')

        return metrics, worst_errors