Qumo/JPMC-quant
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

character refine

Browse Source
This commit is contained in:
Luigi Maiorano
2026-01-23 08:41:23 +01:00
parent 0e1126563e
commit 42f2d775c7
6 changed files with 319 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
utils.py
View File

@@ -131,17 +131,21 @@ class JPMCSurvey:
return df.lazy()
def _get_subset(self, q: pl.LazyFrame, QIDs, rename_cols=True) -> pl.LazyFrame:
def _get_subset(self, q: pl.LazyFrame, QIDs, rename_cols=True, include_record_id=True) -> pl.LazyFrame:
"""Extract subset of data based on specific questions."""
if include_record_id and '_recordId' not in QIDs:
QIDs = ['_recordId'] + QIDs
if not rename_cols:
return q.select(QIDs)
rename_dict = {qid: self.qid_descr_map[qid]['QName'] for qid in QIDs if qid in self.qid_descr_map}
rename_dict = {qid: self.qid_descr_map[qid]['QName'] for qid in QIDs if qid in self.qid_descr_map and qid != '_recordId'}
return q.select(QIDs).rename(rename_dict)
def get_demographics(self, q: pl.LazyFrame) -> pl.LazyFrame:
def get_demographics(self, q: pl.LazyFrame) -> Union[pl.LazyFrame, None]:
"""Extract columns containing the demographics.
Renames columns using qid_descr_map if provided.
@@ -150,7 +154,7 @@ class JPMCSurvey:
return self._get_subset(q, QIDs), None
def get_top_8_traits(self, q: pl.LazyFrame) -> pl.LazyFrame:
def get_top_8_traits(self, q: pl.LazyFrame) -> Union[pl.LazyFrame, None]:
"""Extract columns containing the top 8 characteristics are most important for this Chase virtual assistant to have.
Returns subquery that can be chained with other polars queries.
@@ -160,7 +164,7 @@ class JPMCSurvey:
def get_top_3_traits(self, q: pl.LazyFrame) -> pl.LazyFrame:
def get_top_3_traits(self, q: pl.LazyFrame) -> Union[pl.LazyFrame, None]:
"""Extract columns containing the top 3 characteristics that the Chase virtual assistant should prioritize.
Returns subquery that can be chained with other polars queries.
@@ -169,7 +173,7 @@ class JPMCSurvey:
return self._get_subset(q, QIDs, rename_cols=False).rename({'QID26_0_GROUP': 'Top_3_Traits'}), None
def get_character_ranking(self, q: pl.LazyFrame) -> pl.LazyFrame:
def get_character_ranking(self, q: pl.LazyFrame) -> Union[pl.LazyFrame, None]:
"""Extract columns containing the ranking of characteristics for the Chase virtual assistant.
Returns subquery that can be chained with other polars queries.
@@ -186,7 +190,7 @@ class JPMCSurvey:
return self._get_subset(q, list(QIDs_rename.keys()), rename_cols=False).rename(QIDs_rename), None
def get_18_8_3(self, q: pl.LazyFrame) -> pl.LazyFrame:
def get_18_8_3(self, q: pl.LazyFrame) -> Union[pl.LazyFrame, None]:
"""Extract columns containing the 18-8-3 feedback for the Chase virtual assistant.
Returns subquery that can be chained with other polars queries.
@@ -201,7 +205,7 @@ class JPMCSurvey:
return self._get_subset(q, QIDs, rename_cols=False).rename(rename_dict), None
def get_voice_scale_1_10(self, q: pl.LazyFrame) -> pl.LazyFrame:
def get_voice_scale_1_10(self, q: pl.LazyFrame) -> Union[pl.LazyFrame, None]:
"""Extract columns containing the Voice Scale 1-10 ratings for the Chase virtual assistant.
Returns subquery that can be chained with other polars queries.
@@ -218,7 +222,7 @@ class JPMCSurvey:
def get_ss_green_blue(self, q: pl.LazyFrame) -> pl.LazyFrame:
def get_ss_green_blue(self, q: pl.LazyFrame) -> Union[pl.LazyFrame, dict]:
"""Extract columns containing the SS Green/Blue ratings for the Chase virtual assistant.
Returns subquery that can be chained with other polars queries.
@@ -245,7 +249,7 @@ class JPMCSurvey:
return self._get_subset(q, list(QIDs_map.keys()), rename_cols=False).rename(QIDs_map), choices_map
def get_top_3_voices(self, q: pl.LazyFrame) -> pl.LazyFrame:
def get_top_3_voices(self, q: pl.LazyFrame) -> Union[pl.LazyFrame, None]:
"""Extract columns containing the top 3 voice choices for the Chase virtual assistant.
Returns subquery that can be chained with other polars queries.
@@ -276,7 +280,7 @@ class JPMCSurvey:
return self._get_subset(q, list(QIDs_map.keys()), rename_cols=False).rename(QIDs_map), None
def get_ss_orange_red(self, q: pl.LazyFrame) -> pl.LazyFrame:
def get_ss_orange_red(self, q: pl.LazyFrame) -> Union[pl.LazyFrame, dict]:
"""Extract columns containing the SS Orange/Red ratings for the Chase virtual assistant.
Returns subquery that can be chained with other polars queries.
@@ -303,15 +307,11 @@ class JPMCSurvey:
return self._get_subset(q, list(QIDs_map.keys()), rename_cols=False).rename(QIDs_map), choices_map
def get_character_refine(self, q: pl.LazyFrame) -> pl.LazyFrame:
def get_character_refine(self, q: pl.LazyFrame) -> Union[pl.LazyFrame, None]:
"""Extract columns containing the character refine feedback for the Chase virtual assistant.
Returns subquery that can be chained with other polars queries.
"""
QIDs = ['QID29', 'QID101', 'QID36_0_GROUP']
QIDs = ['QID44', 'QID97', 'QID95', 'QID96']
rename_dict = {
'QID29': '18-8_Set-A',
'QID101': '18-8_Set-B',
'QID36_0_GROUP': '8-3_Ranked'
}
return self._get_subset(q, QIDs, rename_cols=True), None