def create_classifier(self):
if self.datasets is None:
Print.info("Fetching dataset")
self.datasets = list()
ds = Session.full_dataset(window_length=self.window_length)
ds = ds.reduced_dataset(self.dataset_type)
ds = ds.normalize()
ds.shuffle()
self.datasets.append(ds)
pipeline = self.create_pipeline()
Print.data(pipeline)
ds = self.datasets[0]
ds_train, ds_test = ds.split_random()
fit_output = pipeline.fit(ds_train.X, ds_train.y)
accuracy = pipeline.score(ds_test.X, ds_test.y)
Print.info("Accuracy: {}".format(accuracy))
return pipeline
def run(self):
print("\n\n")
Print.time("Running Experiment {}".format(
"" if self.index is None else self.index))
start_time = time.time()
try:
if self.datasets is None:
self.datasets = list()
for i in tqdm(range(self.cv_splits), desc="Fetching Datasets"):
ds = Session.full_dataset(window_length=self.window_length)
ds = ds.reduced_dataset(self.dataset_type)
ds = ds.normalize()
ds.shuffle()
self.datasets.append(ds)
if self.multiprocessing:
self.run_multi()
else:
for ds in tqdm(self.datasets, desc="Cross validating"):
self.cv_reports.append(self.run_cv(ds))
self.report["success"] = True
except Exception as e:
print("")
Print.warning("Skipping experiment: {}".format(e))
Print.ex(e)
self.report["success"] = False
return
self.report = {**self.report, **avg_dict(self.cv_reports)}
self.report["confusion_matrix"] = np.sum(
[r["confusion_matrix"] for r in self.cv_reports], 0)
self.report["time"]["exp"] = (time.time() - start_time)
self.report["accuracies"] = [r["accuracy"] for r in self.cv_reports]
self.report["cv_splits"] = self.cv_splits
# self.report["feature_vector_length"] = self.feature_vector_length()
self.report["dataset_lengths"] = [d.length for d in self.datasets]