setup complete framework of analysis

01_ingest_qualtrics_export.py

@@ -10,10 +10,11 @@ def _():
     import polars as pl
     from pathlib import Path
 
-    from utils import JPMCSurvey
+    from utils import JPMCSurvey, combine_exclusive_columns
     from plots import plot_average_scores_with_counts, plot_top3_ranking_distribution
     return (
         JPMCSurvey,
+        combine_exclusive_columns,
         mo,
         pl,
         plot_average_scores_with_counts,
@@ -38,8 +39,8 @@ def _(JPMCSurvey, QSF_FILE, RESULTS_FILE):
 
 
 @app.cell
-def _():
-    # survey.qid_descr_map
+def _(survey):
+    survey.qid_descr_map
     return
 
 
@@ -286,15 +287,24 @@ def _(data, survey):
 @app.cell
 def _(data, survey):
     traits_refined = survey.get_character_refine(data)[0]
+
     traits_refined.collect()
+
     return (traits_refined,)
 
 
 @app.cell
-def _(traits_original, traits_refined):
+def _(combine_exclusive_columns, traits_refined):
+    traits_refined_comb = combine_exclusive_columns(traits_refined.collect(), target_col_name='Top_8_Traits_Refined')
+    traits_refined_comb
+    return (traits_refined_comb,)
+
+
+@app.cell
+def _(traits_original, traits_refined_comb):
     # merge the two dataframes side by side for comparison
-    traits_comparison = traits_original.join(traits_refined, on='_recordId')
-    traits_comparison.collect()
+    traits_comparison = traits_original.join(traits_refined_comb.lazy(), on='_recordId')
+    print(traits_comparison.collect().head())
     return