yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-09-21 14:13:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

change column order for evaluatation dataframe (#1957)

Browse Source 
* change column order for evaluatation dataframe

* added missing eval column node_input

* generic order for both document and answer returning nodes; ensure no columns get lost

Co-authored-by: tstadel <60758086+tstadel@users.noreply.github.com>
This commit is contained in:
ju-gu 2022-01-07 14:13:28 +01:00 committed by GitHub
parent 5b3f693562
commit b7041941df
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 17 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
haystack/pipelines/base.py
View File

@ -413,8 +413,25 @@ class Pipeline(BasePipeline):
sas_model_name_or_path=sas_model_name_or_path) sas_model_name_or_path=sas_model_name_or_path)
df["sas"] = sas df["sas"] = sas
# reorder columns for better qualitative evaluation
for key, df in eval_result.node_results.items():
desired_col_order = ["query", # generic
"gold_answers", "answer", "context", "exact_match", "f1", "sas", # answer-specific
"gold_document_contents", "content", "gold_id_match", "answer_match", "gold_id_or_answer_match", # doc-specific
"rank", "document_id", "gold_document_ids", # generic
"offsets_in_document", "gold_offsets_in_documents", # answer-specific
"type", "node", "node_input"] # generic
eval_result.node_results[key] = self._reorder_columns(df, desired_col_order)
return eval_result return eval_result
def _reorder_columns(self, df: DataFrame, desired_order: List[str]) -> DataFrame:
filtered_order = [col for col in desired_order if col in df.columns]
missing_columns = [col for col in df.columns if col not in desired_order]
reordered_columns = filtered_order + missing_columns
assert len(reordered_columns) == len(df.columns)
return df.reindex(columns=reordered_columns)
def _build_eval_dataframe(self, def _build_eval_dataframe(self,
query: str, query: str,
query_labels: MultiLabel, query_labels: MultiLabel,