Merge pull request #97 from DataCanvasIO/hotfix-0.2.5

Merge from hotfix-0.2.5

hypernets/core/trial.py

@@ -17,6 +17,18 @@
 from ..core import pareto
 
 
+def _is_bigdata(v):
+ big_data_types = (pd.Series, pd.DataFrame, np.ndarray)
+ if isinstance(v, big_data_types):
+ return True
+
+ type_name = type(v).__name__.lower()
+ if any(type_name.find(s) for s in ('array', 'dataframe', 'series')):
+ return True
+
+ return False
+
+
 class Trial():
  def __init__(self, space_sample, trial_no, reward=None, elapsed=None, model_file=None, succeeded=True):
  self.space_sample = space_sample
@@ -84,10 +96,9 @@ def __getstate__(self):
 
  # state = {k: v for k, v in state.items() if k != 'memo'}
  memo = state.get('memo', None)
- big_data_types = (pd.Series, pd.DataFrame, np.ndarray)
- big_data_exists = isinstance(memo, dict) and any(isinstance(v, big_data_types) for v in memo.values())
+ big_data_exists = isinstance(memo, dict) and any(_is_bigdata(v) for v in memo.values())
  if big_data_exists:
- compacted_memo = {k: v for k, v in memo.items() if not isinstance(v, big_data_types)}
+ compacted_memo = {k: v for k, v in memo.items() if not _is_bigdata(v)}
  state = state.copy()
  state['memo'] = compacted_memo
 

hypernets/tabular/cache.py

@@ -258,7 +258,7 @@ def _store_cache(toolbox, cache_path, data, meta):
  elif isinstance(data, (list, tuple)):
  items = [f'_{i}' for i in range(len(data))]
  for d, i in zip(data, items):
- _store_cache(f'{cache_path}{i}', d, meta)
+ _store_cache(toolbox, f'{cache_path}{i}', d, meta)
  meta.update({'kind': _KIND_LIST, 'items': items})
  else:
  pq = toolbox.parquet()