def serialize_dfs(dfs: WorkflowDataFrames,
how: str = "inner",
path="") -> WorkflowDataFrame:
assert_or_throw(dfs.has_key, "all datarames must be named")
serialized = WorkflowDataFrames(
{k: serialize_df(v, k, path)
for k, v in dfs.items()})
wf: FugueWorkflow = dfs.get_value_by_index(0).workflow
return wf.join(serialized, how=how)
def add_dfs(self,
dfs: WorkflowDataFrames,
how: str = "") -> "TuneDatasetBuilder":
assert_or_throw(dfs.has_key, "all datarames must be named")
for k, v in dfs.items():
if len(self._dfs_spec) == 0:
self.add_df(k, v)
else:
self.add_df(k, v, how=how)
return self
def add_dfs(self,
dfs: WorkflowDataFrames,
how: str = "") -> "TuneDatasetBuilder":
"""Add multiple dataframes with the same join type
:param dfs: dictionary like dataframe collection. The keys
will be used as the dataframe names
:param how: join type, can accept ``semi``, ``left_semi``,
``anti``, ``left_anti``, ``inner``, ``left_outer``,
``right_outer``, ``full_outer``, ``cross``
:returns: the builder itself
"""
assert_or_throw(dfs.has_key, "all datarames must be named")
for k, v in dfs.items():
if len(self._dfs_spec) == 0:
self.add_df(k, v)
else:
self.add_df(k, v, how=how)
return self
def p2(wf: FugueWorkflow, dfs: WorkflowDataFrames,
d: int) -> WorkflowDataFrames:
return WorkflowDataFrames(
{k: v.process(process, params={"d": d})
for k, v in dfs.items()})
