Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[fix] Enforce the QueryResult.df to be a pandas.DataFrame (Phase II) #8948

Merged
merged 1 commit into from
Jan 13, 2020
Merged

[fix] Enforce the QueryResult.df to be a pandas.DataFrame (Phase II) #8948

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 7 additions & 8 deletions superset/common/query_context.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,7 +87,7 @@ def get_query_result(self, query_object: QueryObject) -> Dict[str, Any]:
# be considered as the default ISO date format
# If the datetime format is unix, the parse will use the corresponding
# parsing logic
if df is not None and not df.empty:
if not df.empty:
if DTTM_ALIAS in df.columns:
if timestamp_format in ("epoch_s", "epoch_ms"):
# Column has already been formatted as a timestamp.
Expand Down Expand Up @@ -129,15 +129,14 @@ def get_data( # pylint: disable=invalid-name,no-self-use
def get_single_payload(self, query_obj: QueryObject) -> Dict[str, Any]:
"""Returns a payload of metadata and data"""
payload = self.get_df_payload(query_obj)
df = payload.get("df")
status = payload.get("status")
df = payload["df"]
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Note the get is not required as get_df_payload is guaranteed to return a dictionary with the df and status keys per here.

status = payload["status"]
if status != utils.QueryStatus.FAILED:
if df is None or df.empty:
if df.empty:
payload["error"] = "No data"
else:
payload["data"] = self.get_data(df)
if "df" in payload:
del payload["df"]
del payload["df"]
return payload

def get_payload(self) -> List[Dict[str, Any]]:
Expand Down Expand Up @@ -174,7 +173,7 @@ def get_df_payload( # pylint: disable=too-many-locals,too-many-statements
logging.info("Cache key: %s", cache_key)
is_loaded = False
stacktrace = None
df = None
df = pd.DataFrame()
cached_dttm = datetime.utcnow().isoformat().split(".")[0]
cache_value = None
status = None
Expand Down Expand Up @@ -241,5 +240,5 @@ def get_df_payload( # pylint: disable=too-many-locals,too-many-statements
"query": query,
"status": status,
"stacktrace": stacktrace,
"rowcount": len(df.index) if df is not None else 0,
"rowcount": len(df.index),
}
6 changes: 2 additions & 4 deletions superset/connectors/druid/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1375,11 +1375,9 @@ def query(self, query_obj: Dict) -> QueryResult:
query_str = self.get_query_str(client=client, query_obj=query_obj, phase=2)
df = client.export_pandas()

if df is None or df.size == 0:
if df.empty:
return QueryResult(
df=pd.DataFrame(),
query=query_str,
duration=datetime.now() - qry_start_dttm,
df=df, query=query_str, duration=datetime.now() - qry_start_dttm
)

df = self.homogenize_types(df, query_obj.get("groupby", []))
Expand Down