TSEMO no samples

summit/experiment.py

@@ -87,9 +87,9 @@ def run_experiments(self, conditions, computation_time=None, **kwargs):
         for i, condition in conditions.iterrows():
             start = time.time()
             res, extras = self._run(condition, **kwargs)
-            # res = add_metadata_columns(res, conditions[conditions.metadata_columns])
             experiment_time = time.time() - start
-            self._data = self._data.append(res)
+            res = DataSet(res).T
+            self._data = pd.concat([self._data, res], axis=0)
             self._data["experiment_t"].iat[-1] = float(experiment_time)
             self._data["computation_t"].iat[-1] = float(diff)
             if condition.get("strategy") is not None:

summit/strategies/base.py

@@ -168,7 +168,7 @@ def transform_inputs_outputs(self, ds: DataSet, **kwargs):
             elif isinstance(variable, ContinuousVariable):
                 if standardize_inputs:
                     values, mean, std = self.standardize_column(
-                        new_ds[variable.name].astype(np.float)
+                        new_ds[variable.name].astype(float)
                     )
                     self.input_means[variable.name] = mean
                     self.input_stds[variable.name] = std
@@ -192,7 +192,7 @@ def transform_inputs_outputs(self, ds: DataSet, **kwargs):
                     )
                 if standardize_outputs:
                     values, mean, std = self.standardize_column(
-                        new_ds[variable.name].astype(np.float)
+                        new_ds[variable.name].astype(float)
                     )
                     self.output_means[variable.name] = mean
                     self.output_stds[variable.name] = std
@@ -204,7 +204,7 @@ def transform_inputs_outputs(self, ds: DataSet, **kwargs):
                     ) / (var_max - var_min)
                 output_columns.append(variable.name)
                 # Ensure continuous variables are floats
-                new_ds[variable.name] = new_ds[variable.name].astype(np.float)
+                new_ds[variable.name] = new_ds[variable.name].astype(float)
             else:
                 raise DomainError(f"Variable {variable.name} is not in the dataset.")
 
@@ -348,7 +348,7 @@ def un_transform(self, ds, **kwargs):
                     new_ds[variable.name, "DATA"] = (
                         new_ds[variable.name] * (var_max - var_min) + var_min
                     )
-                new_ds[variable.name, "DATA"] = new_ds[variable.name].astype(np.float)
+                new_ds[variable.name, "DATA"] = new_ds[variable.name].astype(float)
             else:
                 raise DomainError(f"Variable {variable.name} is not in the dataset.")
 

summit/strategies/factorial_doe.py

@@ -74,7 +74,7 @@ def suggest_experiments(self, levels_dict, **kwargs) -> DataSet:
         doe = fullfact(levels)
         for i, v in enumerate(self.domain.input_variables):
             indices = doe[:, i]
-            indices = indices.astype(np.int)
+            indices = indices.astype(int)
             values = np.array([levels_dict[v.name][i] for i in indices])
             values = np.atleast_2d(values)
             design.add_variable(v.name, values, indices=indices[:, np.newaxis])

summit/strategies/multitask.py

@@ -6,7 +6,7 @@
 from botorch.acquisition import ExpectedImprovement as EI
 
 # from botorch.acquisition import qExpectedImprovement as qEI
-
+import pandas as pd
 import numpy as np
 from typing import Type, Tuple, Union, Optional
 
@@ -149,15 +149,15 @@ def suggest_experiments(self, num_experiments, prev_res: DataSet = None, **kwarg
         elif prev_res is not None and self.all_experiments is None:
             self.all_experiments = prev_res
         elif prev_res is not None and self.all_experiments is not None:
-            self.all_experiments = self.all_experiments.append(prev_res)
+            self.all_experiments = pd.concat([self.all_experiments, prev_res], axis=0)
         self.iterations += 1
 
         # Combine pre-training and experiment data
         if "task" not in self.pretraining_data.metadata_columns:
             raise ValueError(
                 """The pretraining data must have a METADATA column called "task" with the task number."""
             )
-        data = self.all_experiments.append(self.pretraining_data)
+        data = pd.concat([self.all_experiments, self.pretraining_data], axis=0)
 
         # Get inputs (decision variables) and outputs (objectives)
         inputs, output = self.transform.transform_inputs_outputs(
@@ -407,7 +407,7 @@ def suggest_experiments(self, num_experiments, prev_res: DataSet = None, **kwarg
         elif prev_res is not None and self.all_experiments is None:
             self.all_experiments = prev_res
         elif prev_res is not None and self.all_experiments is not None:
-            self.all_experiments = self.all_experiments.append(prev_res)
+            self.all_experiments = pd.concat([self.all_experiments, prev_res], axis=0)
         self.iterations += 1
         data = self.all_experiments
 
@@ -481,7 +481,7 @@ def reset(self):
         """Reset MTBO state"""
         self.all_experiments = None
         self.iterations = 0
-        
+
     @staticmethod
     def standardize(X):
         mean, std = X.mean(), X.std()

summit/strategies/neldermead.py

@@ -143,7 +143,7 @@ def suggest_experiments(self, prev_res: DataSet = None, **kwargs):
             inner_prev_param = self.prev_param[0]
             # recover invalid experiments from previous iteration
             if self.prev_param[1] is not None:
-                invalid_res = self.prev_param[1].drop(("constraint", "DATA"), 1)
+                invalid_res = self.prev_param[1].drop(("constraint", "DATA"), axis=1)
                 prev_res = pd.concat([prev_res, invalid_res])
 
         ## Generation of new suggested experiments.
@@ -192,7 +192,7 @@ def suggest_experiments(self, prev_res: DataSet = None, **kwargs):
             )
 
         # return only valid experiments (invalid experiments are stored in param[1])
-        next_experiments = next_experiments.drop(("constraint", "DATA"), 1)
+        next_experiments = next_experiments.drop(("constraint", "DATA"), axis=1)
         objective_dir = -1.0 if obj_maximize else 1.0
         self.fbest = objective_dir * fbest
         self.xbest = xbest

summit/strategies/snobfit.py

@@ -126,7 +126,7 @@ def suggest_experiments(
             inner_prev_param = self.prev_param[0]
             # recover invalid experiments from previous iteration
             if self.prev_param[1] is not None:
-                invalid_res = self.prev_param[1][0].drop(("constraint", "DATA"), 1)
+                invalid_res = self.prev_param[1][0].drop(("constraint", "DATA"), axis=1)
                 prev_res = pd.concat([prev_res, invalid_res])
 
         ## Generation of new suggested experiments.
@@ -172,7 +172,7 @@ def suggest_experiments(
             )
 
         # return only valid experiments (invalid experiments are stored in param[1])
-        next_experiments = next_experiments.drop(("constraint", "DATA"), 1)
+        next_experiments = next_experiments.drop(("constraint", "DATA"), axis=1)
         objective_dir = -1.0 if obj_maximize else 1.0
         self.fbest = objective_dir * fbest
         self.prev_param = param

summit/strategies/tsemo.py

@@ -178,7 +178,7 @@ def suggest_experiments(self, num_experiments, prev_res: DataSet = None, **kwarg
         elif prev_res is not None and self.all_experiments is None:
             self.all_experiments = prev_res
         elif prev_res is not None and self.all_experiments is not None:
-            self.all_experiments = self.all_experiments.append(prev_res)
+            self.all_experiments = pd.concat([self.all_experiments, prev_res], axis=0)
 
         if self.all_experiments.shape[0] <= 3:
             lhs = LHS(self.domain, categorical_method=cat_method)
@@ -210,7 +210,10 @@ def suggest_experiments(self, num_experiments, prev_res: DataSet = None, **kwarg
             # Training
             models[i] = ThompsonSampledModel(v.name)
             train_results[i] = models[i].fit(
-                inputs, outputs[[v.name]], n_retries=self.n_retries, n_spectral_points=self.n_spectral_points,
+                inputs,
+                outputs[[v.name]],
+                n_retries=self.n_retries,
+                n_spectral_points=self.n_spectral_points,
             )
 
             # Evaluate spectral sampled functions
@@ -379,7 +382,6 @@ def reset(self):
         """Reset TSEMO state"""
         self.all_experiments = None
         self.iterations = 0
-        self.samples = []  # Samples drawn using NSGA-II
         self.sample_fs = [0 for i in range(len(self.domain.output_variables))]
         self.uuid_val = uuid.uuid4()
 
@@ -475,15 +477,6 @@ def _select_max_hvi(self, y, samples, num_evals=1):
             mask[original_index] = False
             indices.append(original_index)
 
-            # Append current estimate of the pareto front to sample_paretos
-            samples_new = samples_next.copy()
-            mean = self.transform.output_means[v.name]
-            std = self.transform.output_stds[v.name]
-            samples_new = samples_new * std + mean
-            samples_new[("hvi", "DATA")] = hv_improvement
-            self.samples.append(samples_new)
-            samples_next = samples_original.loc[mask]
-
         if len(hv_improvement) == 0:
             hv_imp = 0
         elif len(indices) == 0:
@@ -582,7 +575,7 @@ def fit(self, X: DataSet, y: DataSet, **kwargs):
         )
 
     def predict(self, X: DataSet, **kwargs):
-        """Predict the values of a """
+        """Predict the values of a"""
         X = X[self.input_columns_ordered].to_numpy()
         return self.rff(X)
 

summit/tests/test_strategies.py

@@ -6,9 +6,6 @@
 from fastprogress.fastprogress import progress_bar
 import numpy as np
 import os
-import warnings
-import pkg_resources
-
 
 def test_strategy():
     class MockStrategy(Strategy):
@@ -701,8 +698,6 @@ def test_tsemo(batch_size, test_num_improve_iter=2, save=False):
     lab = VLMOP2()
     strategy = TSEMO(lab.domain)
     experiments = strategy.suggest_experiments(5 * num_inputs)
-    warnings.filterwarnings("ignore", category=RuntimeWarning)
-    warnings.filterwarnings("ignore", category=DeprecationWarning)
 
     num_improve_iter = 0
     best_hv = None