def optimal_machines(self, X, y, single=False, epsilon=None, info=False): """ Find the optimal combination of machines for testing data for the COBRA predictor. Parameteres ----------- X: array-like, [n_features] Vector for which we want optimal machine combinations. y: float Target value for query to compare. single: boolean, optional Option to calculate optimal machine combinations for a single query point instead. info: bool, optional Returns MSE dictionary for each machine combination value epsilon: float, optional fixed epsilon value to help determine optimal machines. Returns ------- MSE: dictionary mapping machines with mean squared errors opt: optimal machines combination """ if epsilon is None: epsilon = self.aggregate.epsilon n_machines = np.arange(1, len(self.aggregate.estimators_) + 1) MSE = {} for num in n_machines: machine_names = self.aggregate.estimators_.keys() use = list(itertools.combinations(machine_names, num)) for combination in use: machine = Cobra(random_state=self.random_state, epsilon=epsilon) machine.fit(self.aggregate.X_, self.aggregate.y_, default=False) machine.split_data() machine.load_default(machine_list=combination) machine.load_machine_predictions() if single: result = machine.predict(X.reshape(1, -1)) MSE[combination] = np.square(y - result) else: results = machine.predict(X) MSE[combination] = (mean_squared_error(y, results)) if info: return MSE opt = min(MSE, key=MSE.get) return opt, MSE[opt]
def optimal_alpha(self, X, y, single=False, epsilon=None, info=False): """ Find the optimal alpha for testing data for the COBRA predictor. Parameteres ----------- X: array-like, [n_features] Vector for which we want optimal alpha values y: float Target value for query to compare. single: boolean, optional Option to calculate optimal alpha for a single query point instead. info: bool, optional Returns MSE dictionary for each alpha value epsilon: float, optional fixed epsilon value to help determine optimal alpha. Returns ------- MSE: dictionary mapping alpha with mean squared errors opt: optimal alpha combination """ if epsilon is None: epsilon = self.aggregate.epsilon MSE = {} for alpha in range(1, len(self.aggregate.estimators_) + 1): machine = Cobra(random_state=self.random_state, epsilon=epsilon) machine.fit(self.aggregate.X_, self.aggregate.y_) # for a single data point if single: result = machine.predict(X, alpha=alpha) MSE[alpha] = np.square(y - result) else: results = machine.predict(X, alpha=alpha) MSE[alpha] = (mean_squared_error(y, results)) if info: return MSE opt = min(MSE, key=MSE.get) return opt, MSE[opt]
def optimal_machines_grid(self, X, y, line_points=200, info=False): """ Find the optimal epsilon and machine-combination for a single query point for the COBRA predictor. Parameteres ----------- X: array-like, [n_features] Vector for which we want optimal machines and epsilon values y: float Target value for query to compare. line_points: integer, optional Number of epsilon values to traverse the grid. info: bool, optional Returns MSE dictionary for each epsilon/machine value. Returns ------- MSE: dictionary mapping (machine combination, epsilon) with mean squared errors opt: optimal epislon/machine combination """ # code to find maximum and minimum distance between predictions to create grid a, size = sorted(self.aggregate.all_predictions_), len( self.aggregate.all_predictions_) res = [a[i + 1] - a[i] for i in range(size) if i + 1 < size] emin = min(res) emax = max(a) - min(a) erange = np.linspace(emin, emax, line_points) n_machines = np.arange(1, len(self.aggregate.estimators_) + 1) MSE = {} for epsilon in erange: for num in n_machines: machine_names = self.aggregate.estimators_.keys() use = list(itertools.combinations(machine_names, num)) for combination in use: machine = Cobra(random_state=self.random_state, epsilon=epsilon) machine.fit(self.aggregate.X_, self.aggregate.y_, default=False) machine.split_data() machine.load_default(machine_list=combination) machine.load_machine_predictions() result = machine.predict(X.reshape(1, -1)) MSE[(combination, epsilon)] = np.square(y - result) if info: return MSE opt = min(MSE, key=MSE.get) return opt, MSE[opt]
def optimal_alpha_grid(self, X, y, line_points=200, info=False): """ Find the optimal epsilon and alpha for a single query point for the COBRA predictor. Parameteres ----------- X: array-like, [n_features] Vector for which we want optimal alpha and epsilon values y: float Target value for query to compare. line_points: integer, optional Number of epsilon values to traverse the grid. info: bool, optional Returns MSE dictionary for each epsilon/alpha value Returns ------- MSE: dictionary mapping (alpha, epsilon) with mean squared errors opt: optimal epislon/alpha combination """ # code to find maximum and minimum distance between predictions to create grid a, size = sorted(self.aggregate.all_predictions_), len( self.aggregate.all_predictions_) res = [a[i + 1] - a[i] for i in range(size) if i + 1 < size] emin = min(res) emax = max(a) - min(a) erange = np.linspace(emin, emax, line_points) n_machines = np.arange(1, len(self.aggregate.machines_) + 1) MSE = {} # looping over epsilon and alpha values for epsilon in erange: for num in n_machines: machine = Cobra(random_state=self.random_state, epsilon=epsilon) machine.fit(self.aggregate.X_, self.aggregate.y_) result = machine.predict(X.reshape(1, -1), alpha=num) MSE[(num, epsilon)] = np.square(y - result) if info: return MSE opt = min(MSE, key=MSE.get) return opt, MSE[opt]
def optimal_epsilon(self, X, y, line_points=200, info=False): """ Find the optimal epsilon value for the COBRA predictor. Parameteres ----------- X: array-like, [n_features] Vector for which we want for optimal epsilon. y: float Target value for query to compare. line_points: integer, optional Number of epsilon values to traverse the grid. info: bool, optional Returns MSE dictionary for each epsilon value. Returns ------- MSE: dictionary mapping epsilon with mean squared errors opt: optimal epsilon value """ a, size = sorted(self.aggregate.all_predictions_), len( self.aggregate.all_predictions_) res = [a[i + 1] - a[i] for i in range(size) if i + 1 < size] emin = min(res) emax = max(a) - min(a) erange = np.linspace(emin, emax, line_points) MSE = {} for epsilon in erange: machine = Cobra(random_state=self.random_state, epsilon=epsilon) machine.fit(self.aggregate.X_, self.aggregate.y_) results = machine.predict(X) MSE[epsilon] = (mean_squared_error(y, results)) if info: return MSE opt = min(MSE, key=MSE.get) return opt, MSE[opt]
def boxplot(self, reps=100, info=False): """ Plots boxplots of machines. Parameters ---------- reps: int, optional Number of times to repeat experiments for boxplot. info: boolean, optional Returns data """ if type(self.aggregate) is Cobra: MSE = {k: [] for k, v in self.aggregate.machines_.items()} MSE["COBRA"] = [] for i in range(0, reps): cobra = Cobra(random_state=self.random_state, epsilon=self.aggregate.epsilon) X, y = shuffle(self.aggregate.X_, self.aggregate.y_, random_state=self.aggregate.random_state) cobra.fit(X, y, default=False) cobra.split_data(shuffle_data=True) for machine in self.aggregate.machines_: self.aggregate.machines_[machine].fit(cobra.X_k_, cobra.y_k_) cobra.load_machine(machine, self.aggregate.machines_[machine]) cobra.load_machine_predictions() X_test, y_test = shuffle(self.X_test, self.y_test, random_state=self.aggregate.random_state) for machine in cobra.machines_: MSE[machine].append(mean_squared_error(y_test, cobra.machines_[machine].predict(X_test))) MSE["COBRA"].append(mean_squared_error(y_test, cobra.predict(X_test))) data, labels = [], [] for machine in MSE: data.append(MSE[machine]) labels.append(machine) if type(self.aggregate) is Ewa: MSE = {k: [] for k, v in self.aggregate.machines_.items()} MSE["EWA"] = [] for i in range(0, reps): ewa = Ewa(random_state=self.random_state, beta=self.aggregate.beta) X, y = shuffle(self.aggregate.X_, self.aggregate.y_, random_state=self.aggregate.random_state) ewa.fit(X, y, default=False) ewa.split_data(shuffle_data=True) for machine in self.aggregate.machines_: self.aggregate.machines_[machine].fit(ewa.X_k_, ewa.y_k_) ewa.load_machine(machine, self.aggregate.machines_[machine]) ewa.load_machine_weights(self.aggregate.beta) X_test, y_test = shuffle(self.X_test, self.y_test, random_state=self.aggregate.random_state) for machine in ewa.machines_: MSE[machine].append(mean_squared_error(y_test, ewa.machines_[machine].predict(X_test))) MSE["EWA"].append(mean_squared_error(y_test, ewa.predict(X_test))) data, labels = [], [] for machine in MSE: data.append(MSE[machine]) labels.append(machine) if type(self.aggregate) is ClassifierCobra: errors = {k: [] for k, v in self.aggregate.machines_.items()} errors["ClassifierCobra"] = [] for i in range(0, reps): cc = ClassifierCobra(random_state=self.random_state) X, y = shuffle(self.aggregate.X_, self.aggregate.y_, random_state=self.aggregate.random_state) cc.fit(X, y, default=False) cc.split_data(shuffle_data=True) for machine in self.aggregate.machines_: self.aggregate.machines_[machine].fit(cc.X_k_, cc.y_k_) cc.load_machine(machine, self.aggregate.machines_[machine]) cc.load_machine_predictions() X_test, y_test = shuffle(self.X_test, self.y_test, random_state=self.aggregate.random_state) for machine in cc.machines_: errors[machine].append(1 - accuracy_score(y_test, cc.machines_[machine].predict(X_test))) errors["ClassifierCobra"].append(1 - accuracy_score(y_test, cc.predict(X_test))) data, labels = [], [] for machine in errors: data.append(errors[machine]) labels.append(machine) plt.figure(figsize=(self.plot_size, self.plot_size)) plt.boxplot(data, labels=labels) plt.show() if info: return data
###################################################################### # Like the Cobra estimator, Ewa is also a scikit-learn compatible # estimator. It also fits into the Visualisation class, like demonstrated # in the # `notebook <https://github.com/bhargavvader/pycobra/blob/master/notebooks/visualise.ipynb>`__. # # Predicting? # ~~~~~~~~~~~ # # Like the other scikit-learn predictors, we estimate on data by simply # using the ``predict()`` method. # query = X_test[0].reshape(1, -1) cobra.predict(query) ewa.predict(query) ###################################################################### # Why pycobra? # ~~~~~~~~~~~~ # # There are scikit-learn estimators which already perform well in basic # regression tasks - why use pycobra? The Cobra estimator has the # advantage of a theoretical bound on its performance - this means it is # supposed to perform at least as well as the estimators used to create # it, up to a remainder term which decays to zero. The Ewa estimator also # benefits from similar bounds. # # pycobra also lets you compare the scikit-learn estimators used in the
def optimal_split(self, X, y, split=None, epsilon=None, info=False, graph=False): """ Find the optimal combination split (D_k, D_l) for fixed epsilon value for the COBRA predictor. Parameteres ----------- X: array-like, [n_features] Vector for which we want for optimal split. y: float Target value for query to compare. epsilon: float, optional. fixed epsilon value to help determine optimal machines. split: list, optional. D_k, D_l break-up to calculate MSE info: bool, optional. Returns MSE dictionary for each split. graph: bool, optional. Plots graph of MSE vs split Returns ------- MSE: dictionary mapping split with mean squared errors opt: optimal epsilon value """ if epsilon is None: epsilon = self.aggregate.epsilon if split is None: split = [(0.20, 0.80), (0.40, 0.60), (0.50, 0.50), (0.60, 0.40), (0.80, 0.20)] MSE = {} for k, l in split: machine = Cobra(random_state=self.random_state, epsilon=epsilon) machine.fit(self.aggregate.X_, self.aggregate.y_, default=False) machine.split_data(int(k * len(self.aggregate.X_)), int((k + l) * len(self.aggregate.X_))) machine.load_default() machine.load_machine_predictions() results = machine.predict(X) MSE[(k, l)] = (mean_squared_error(y, results)) if graph: import matplotlib.pyplot as plt ratio, mse = [], [] for value in split: ratio.append(value[0]) mse.append(MSE[value]) plt.plot(ratio, mse) if info: return MSE opt = min(MSE, key=MSE.get) return opt, MSE[opt]
def boxplot(self, reps=100, info=False, dataframe=None, kind="normal"): """ Plots boxplots of machines. Parameters ---------- reps: int, optional Number of times to repeat experiments for boxplot. info: boolean, optional Returns data """ kwargs = self.kwargs if dataframe is None: if type(self.aggregate) is Cobra: MSE = {k: [] for k, v in self.estimators.items()} MSE["Cobra"] = [] for i in range(0, reps): cobra = Cobra(epsilon=self.aggregate.epsilon) X, y = shuffle(self.aggregate.X_, self.aggregate.y_) cobra.fit(X, y, default=False) cobra.split_data(shuffle_data=True) for machine in self.aggregate.estimators_: self.aggregate.estimators_[machine].fit(cobra.X_k_, cobra.y_k_) cobra.load_machine(machine, self.aggregate.estimators_[machine]) cobra.load_machine_predictions() for machine in self.estimators: if "Cobra" in machine: self.estimators[machine].fit(X, y) else: self.estimators[machine].fit(cobra.X_k_, cobra.y_k_) try: if type(self.estimators[machine]) == KernelCobra: preds = self.estimators[machine].predict(self.X_test, bandwidth=kwargs["bandwidth_kernel"]) else: preds = self.estimators[machine].predict(self.X_test) except KeyError: preds = self.estimators[machine].predict(self.X_test) MSE[machine].append(mean_squared_error(self.y_test, preds)) MSE["Cobra"].append(mean_squared_error(self.y_test, cobra.predict(self.X_test))) try: dataframe = pd.DataFrame(data=MSE) except ValueError: return MSE if type(self.aggregate) is KernelCobra: MSE = {k: [] for k, v in self.estimators.items()} MSE["KernalCobra"] = [] for i in range(0, reps): kernel = KernelCobra() X, y = shuffle(self.aggregate.X_, self.aggregate.y_) kernel.fit(X, y, default=False) kernel.split_data(shuffle_data=True) for machine in self.aggregate.estimators_: self.aggregate.estimators_[machine].fit(kernel.X_k_, kernel.y_k_) kernel.load_machine(machine, self.aggregate.estimators_[machine]) kernel.load_machine_predictions() for machine in self.estimators: if "Cobra" in machine: self.estimators[machine].fit(X, y) else: self.estimators[machine].fit(cobra.X_k_, cobra.y_k_) try: if type(self.estimators[machine]) == KernelCobra: preds = self.estimators[machine].predict(self.X_test, bandwidth=kwargs["bandwidth_kernel"]) else: preds = self.estimators[machine].predict(self.X_test) except KeyError: preds = self.estimators[machine].predict(self.X_test) MSE[machine].append(mean_squared_error(self.y_test, preds)) MSE["KernelCobra"].append(mean_squared_error(self.y_test, kernel.predict(self.X_test, bandwidth=kwargs[bandwidth_kernel]))) try: dataframe = pd.DataFrame(data=MSE) except ValueError: return MSE if type(self.aggregate) is Ewa: MSE = {k: [] for k, v in self.aggregate.estimators_.items()} MSE["EWA"] = [] for i in range(0, reps): ewa = Ewa(random_state=self.random_state, beta=self.aggregate.beta) X, y = shuffle(self.aggregate.X_, self.aggregate.y_, random_state=self.aggregate.random_state) ewa.fit(X, y, default=False) ewa.split_data(shuffle_data=True) for machine in self.estimators: self.aggregate.estimators_[machine].fit(ewa.X_k_, ewa.y_k_) ewa.load_machine(machine, self.aggregate.estimators_[machine]) ewa.load_machine_weights(self.aggregate.beta) X_test, y_test = shuffle(self.X_test, self.y_test, random_state=self.aggregate.random_state) for machine in self.estimators: if "EWA" in machine: self.estimators[machine].fit(X, y) else: self.estimators[machine].fit(ewa.X_k_, ewa.y_k_) try: if type(self.estimators[machine]) == KernelCobra: preds = self.estimators[machine].predict(self.X_test, bandwidth=kwargs["bandwidth_kernel"]) else: preds = self.estimators[machine].predict(self.X_test) except KeyError: preds = self.estimators[machine].predict(self.X_test) MSE[machine].append(mean_squared_error(y_test, preds)) MSE["EWA"].append(mean_squared_error(y_test, ewa.predict(X_test))) try: dataframe = pd.DataFrame(data=MSE) except ValueError: return MSE if type(self.aggregate) is ClassifierCobra: errors = {k: [] for k, v in self.aggregate.estimators_.items()} errors["ClassifierCobra"] = [] for i in range(0, reps): cc = ClassifierCobra(random_state=self.random_state) X, y = shuffle(self.aggregate.X_, self.aggregate.y_, random_state=self.aggregate.random_state) cc.fit(X, y, default=False) cc.split_data(shuffle_data=True) for machine in self.aggregate.estimators_: self.aggregate.estimators_[machine].fit(cc.X_k_, cc.y_k_) cc.load_machine(machine, self.aggregate.estimators_[machine]) cc.load_machine_predictions() X_test, y_test = shuffle(self.X_test, self.y_test, random_state=self.aggregate.random_state) for machine in self.estimators: errors[machine].append(1 - accuracy_score(y_test, self.estimators[machine].predict(X_test))) errors["ClassifierCobra"].append(1 - accuracy_score(y_test, cc.predict(X_test))) try: dataframe = pd.DataFrame(data=errors) except ValueError: return errors # code for different boxplot styles using the python graph gallery tutorial: # https://python-graph-gallery.com/39-hidden-data-under-boxplot/ sns.set(style="whitegrid") if kind == "normal": sns.boxplot(data=dataframe) plt.title("Boxplot") if kind == "violin": sns.violinplot(data=dataframe) plt.title("Violin Plot") if kind == "jitterplot": ax = sns.boxplot(data=dataframe) ax = sns.stripplot(data=dataframe, color="orange", jitter=0.2, size=2.5) plt.title("Boxplot with jitter", loc="left") plt.ylabel("Mean Squared Errors") plt.xlabel("Estimators") plt.figure(figsize=(self.plot_size, self.plot_size)) plt.show() if info: return dataframe
cobra.machines_['random_forest'].predict(query) ###################################################################### # Aggregate! # ---------- # # By using the aggregate function we can combine our predictors. You can # read about the aggregation procedure either in the original COBRA paper # or look around in the source code for the algorithm. # # We start by loading each machine's predictions now. # cobra.load_machine_predictions() cobra.predict(query) Y_test[9] ###################################################################### # Optimizing COBRA # ~~~~~~~~~~~~~~~~ # # To squeeze the best out of COBRA we make use of the COBRA diagnostics # class. With a grid based approach to optimizing hyperparameters, we can # find out the best epsilon value, number of machines (alpha value), and # combination of machines. # ###################################################################### # Let's check the MSE for each of COBRAs machines: