def featurize_many(self,
entries,
ignore_errors=False,
return_errors=False,
pbar=True):
"""Featurize a list of entries.
If `featurize` takes multiple inputs, supply inputs as a list of tuples.
Featurize_many supports entries as a list, tuple, numpy array,
Pandas Series, or Pandas DataFrame.
Args:
entries (list-like object): A list of entries to be featurized.
ignore_errors (bool): Returns NaN for entries where exceptions are
thrown if True. If False, exceptions are thrown as normal.
return_errors (bool): If True, returns the feature list as
determined by ignore_errors with traceback strings added
as an extra 'feature'. Entries which featurize without
exceptions have this extra feature set to NaN.
pbar (bool): Show a progress bar for featurization if True.
Returns:
(list) features for each entry.
"""
if return_errors and not ignore_errors:
raise ValueError("Please set ignore_errors to True to use"
" return_errors.")
# Check inputs
if not isinstance(entries,
(tuple, list, np.ndarray, pd.Series, pd.DataFrame)):
raise Exception("'entries' must be a list-like object")
# Special case: Empty list
if len(entries) is 0:
return []
# If the featurize function only has a single arg, zip the inputs
if isinstance(entries, pd.DataFrame):
entries = entries.values
elif isinstance(
entries,
pd.Series) or not isinstance(entries[0],
(tuple, list, np.ndarray)):
entries = zip(entries)
# Add a progress bar
if pbar:
if is_notebook():
tqdm_func = tqdm.tqdm_notebook
else:
tqdm_func = tqdm.tqdm
# list() required, tqdm has issues with memory if generator given
entries = tqdm_func(list(entries), desc=self.__class__.__name__)
# Run the actual featurization
if self.n_jobs == 1:
return [
self.featurize_wrapper(x,
ignore_errors=ignore_errors,
return_errors=return_errors)
for x in entries
]
else:
if sys.version_info[0] < 3:
warnings.warn("Multiprocessing is not supported in "
"matminer for Python 2.x. Multiprocessing has "
"been disabled. Please upgrade to Python 3.x to "
"enable multiprocessing.")
self.set_n_jobs(1)
return self.featurize_many(entries,
ignore_errors=ignore_errors,
return_errors=return_errors,
pbar=pbar)
with Pool(self.n_jobs) as p:
func = partial(self.featurize_wrapper,
return_errors=return_errors,
ignore_errors=ignore_errors)
return p.map(func, entries, chunksize=self.chunksize)
def featurize_many(self, entries, ignore_errors=False, return_errors=False,
pbar=True):
"""Featurize a list of entries.
If `featurize` takes multiple inputs, supply inputs as a list of tuples.
Featurize_many supports entries as a list, tuple, numpy array,
Pandas Series, or Pandas DataFrame.
Args:
entries (list-like object): A list of entries to be featurized.
ignore_errors (bool): Returns NaN for entries where exceptions are
thrown if True. If False, exceptions are thrown as normal.
return_errors (bool): If True, returns the feature list as
determined by ignore_errors with traceback strings added
as an extra 'feature'. Entries which featurize without
exceptions have this extra feature set to NaN.
pbar (bool): Show a progress bar for featurization if True.
Returns:
(list) features for each entry.
"""
if return_errors and not ignore_errors:
raise ValueError("Please set ignore_errors to True to use"
" return_errors.")
# Check inputs
if not isinstance(entries, (tuple, list, np.ndarray, pd.Series, pd.DataFrame)):
raise Exception("'entries' must be a list-like object")
# Special case: Empty list
if len(entries) is 0:
return []
# If the featurize function only has a single arg, zip the inputs
if isinstance(entries, pd.DataFrame):
entries = entries.values
elif isinstance(entries, pd.Series) or not isinstance(entries[0], (tuple, list, np.ndarray)):
entries = zip(entries)
# Add a progress bar
if pbar:
if is_notebook():
tqdm_func = tqdm.tqdm_notebook
else:
tqdm_func = tqdm.tqdm
# list() required, tqdm has issues with memory if generator given
entries = tqdm_func(list(entries), desc=self.__class__.__name__)
# Run the actual featurization
if self.n_jobs == 1:
return [self.featurize_wrapper(x, ignore_errors=ignore_errors,
return_errors=return_errors) for x in entries]
else:
if sys.version_info[0] < 3:
warnings.warn("Multiprocessing is not supported in "
"matminer for Python 2.x. Multiprocessing has "
"been disabled. Please upgrade to Python 3.x to "
"enable multiprocessing.")
self.set_n_jobs(1)
return self.featurize_many(entries,
ignore_errors=ignore_errors,
return_errors=return_errors,
pbar=pbar)
with Pool(self.n_jobs) as p:
func = partial(self.featurize_wrapper,
return_errors=return_errors,
ignore_errors=ignore_errors)
return p.map(func, entries, chunksize=self.chunksize)