Mediaboss Marketing

class ModelFitterAndVisualizer: def __init__(self, X_train, y_train, y_truth, scaling=False, random_state=41): """ Initialize the ModelFitterAndVisualizer class with training and testing data.

Parameters: X_train (pd.DataFrame): Training data features y_train (pd.Series): Training data target y_truth (pd.Series): Ground truth for predictions scaling (bool): Flag to indicate if scaling should be applied random_state (int): Seed for random number generation """ self.X_train = X_train self.y_train = y_train self.y_truth = y_truth

self.initialize_models(random_state)

self.scaling = scaling

# Initialize models # ----------------------------------------------------------------- def initialize_models(self, random_state): """ Initialize the models to be used for fitting and prediction.

Parameters: random_state (int): Seed for random number generation """

# Define kernel for GPR kernel = 1.0 * RBF(length_scale=1.0) + WhiteKernel(noise_level=1.0)

# Define Ensemble Models Estimator # Decision Tree + Kernel Method estimators_rf_svr = [ ('rf', RandomForestRegressor(n_estimators=30, random_state=random_state)), ('svr', SVR(kernel='rbf')), ] estimators_rf_gpr = [ ('rf', RandomForestRegressor(n_estimators=30, random_state=random_state)), ('gpr', GaussianProcessRegressor(kernel=kernel, normalize_y=True, random_state=random_state)) ] # Decision Trees estimators_rf_xgb = [ ('rf', RandomForestRegressor(n_estimators=30, random_state=random_state)), ('xgb', xgb.XGBRegressor(random_state=random_state)), ]

self.models = [ SymbolicRegressor(random_state=random_state), SVR(kernel='rbf'), GaussianProcessRegressor(kernel=kernel, normalize_y=True, random_state=random_state), DecisionTreeRegressor(random_state=random_state), RandomForestRegressor(random_state=random_state), xgb.XGBRegressor(random_state=random_state), lgbm.LGBMRegressor(n_estimators=50, num_leaves=10, min_child_samples=3, random_state=random_state), VotingRegressor(estimators=estimators_rf_svr), StackingRegressor(estimators=estimators_rf_svr, final_estimator=RandomForestRegressor(random_state=random_state)), VotingRegressor(estimators=estimators_rf_gpr), StackingRegressor(estimators=estimators_rf_gpr, final_estimator=RandomForestRegressor(random_state=random_state)), VotingRegressor(estimators=estimators_rf_xgb), StackingRegressor(estimators=estimators_rf_xgb, final_estimator=RandomForestRegressor(random_state=random_state)), ]

# Define graph titles self.titles = [ "Ground Truth", "Training Points", "SymbolicRegressor", "SVR", "GPR", "DecisionTree", "RForest", "XGBoost", "LGBM", "Vote_rf_svr", "Stack_rf_svr__rf", "Vote_rf_gpr", "Stack_rf_gpr__rf", "Vote_rf_xgb", "Stack_rf_xgb__rf", ]

def fit_models(self): """ Fit the models to the training data.

Returns: self: Instance of the class with fitted models """ if self.scaling: scaler_X = MinMaxScaler() self.X_train_scaled = scaler_X.fit_transform(self.X_train) else: self.X_train_scaled = self.X_train.copy()

for model in self.models: model.fit(self.X_train_scaled, self.y_train) return self

def visualize_surface(self, x0, x1, width=400, height=500, num_panel_columns=5, vertical_spacing=0.06, horizontal_spacing=0, output=None, display=False, return_fig=False): """ Visualize the prediction surface for each model.

Parameters: x0 (np.ndarray): Meshgrid for feature 1 x1 (np.ndarray): Meshgrid for feature 2 width (int): Width of the plot height (int): Height of the plot output (str): File path to save the plot display (bool): Flag to display the plot """

num_plots = len(self.models) + 2 num_panel_rows = num_plots // num_panel_columns

whole_width = width * num_panel_columns whole_height = height * num_panel_rows

specs = [[{'type': 'surface'} for _ in range(num_panel_columns)] for _ in range(num_panel_rows)] fig = make_subplots(rows=num_panel_rows, cols=num_panel_columns, specs=specs, subplot_titles=self.titles, vertical_spacing=vertical_spacing, horizontal_spacing=horizontal_spacing)

for i, model in enumerate([None, None] + self.models): # Assign the subplot panels row = i // num_panel_columns + 1 col = i % num_panel_columns + 1

# Plot training points if i == 1: fig.add_trace(go.Scatter3d(x=self.X_train[:, 0], y=self.X_train[:, 1], z=self.y_train, mode='markers', marker=dict(size=2, color='darkslategray'), name='Training Data'), row=row, col=col)

surface = go.Surface(z=self.y_truth, x=x0, y=x1, showscale=False, opacity=.4) fig.add_trace(surface, row=row, col=col)

# Plot predicted surface for each model and ground truth else: y_pred = self.y_truth if model is None else model.predict(np.c_[x0.ravel(), x1.ravel()]).reshape(x0.shape) surface = go.Surface(z=y_pred, x=x0, y=x1, showscale=False) fig.add_trace(surface, row=row, col=col)

fig.update_scenes(dict( xaxis_title='x0', yaxis_title='x1', zaxis_title='y', ), row=row, col=col)

fig.update_layout(title='Model Predictions and Ground Truth', width=whole_width, height=whole_height)

# Change camera angle camera = dict( up=dict(x=0, y=0, z=1), center=dict(x=0, y=0, z=0), eye=dict(x=-1.25, y=-1.25, z=2) ) for i in range(num_plots): fig.update_layout(**{f'scene{i+1}_camera': camera})

if display: fig.show()

if output: fig.write_html(output)

if return_fig: return fig

Read this article:
The Machine Learning Guide for Predictive Accuracy: Interpolation and Extrapolation - Towards Data Science