def register_analysis(self, analysis: ExperimentAnalysis):
"""Integrate the given analysis into the gaussian process.
Args:
analysis (ExperimentAnalysis): Optionally, the previous analysis
to integrate.
"""
for (_, report), params in zip(
analysis.dataframe(metric=self._metric,
mode=self._mode).iterrows(),
analysis.get_all_configs().values()):
# We add the obtained results to the
# gaussian process optimizer
self._register_result(params, report)
async def collect(self):
"""
Collects and cleans data on the running Tune experiment from the
Tune logs so that users can see this information in the front-end
client
"""
self._trial_records = {}
self._errors = {}
if not self._logdir or not ExperimentAnalysis:
return
# search through all the sub_directories in log directory
analysis = ExperimentAnalysis(str(self._logdir))
df = analysis.dataframe(metric=None, mode=None)
if len(df) == 0 or "trial_id" not in df.columns:
return
self._trials_available = True
# make sure that data will convert to JSON without error
df["trial_id_key"] = df["trial_id"].astype(str)
df = df.fillna(0)
trial_ids = df["trial_id"]
for i, value in df["trial_id"].iteritems():
if type(value) != str and type(value) != int:
trial_ids[i] = int(value)
df["trial_id"] = trial_ids
# convert df to python dict
df = df.set_index("trial_id_key")
trial_data = df.to_dict(orient="index")
# clean data and update class attribute
if len(trial_data) > 0:
trial_data = self.clean_trials(trial_data)
self._trial_records.update(trial_data)
self.collect_errors(df)
def testDataframe(self):
analysis = ExperimentAnalysis(self.test_dir)
df = analysis.dataframe(self.metric, mode="max")
self.assertTrue(isinstance(df, pd.DataFrame))
self.assertEqual(df.shape[0], self.num_samples * 2)
