added data selector ui element

02_quant_analysis.py

@@ -29,22 +29,45 @@ def _():
 
 
 @app.cell
-def _():
+def _(mo):
-    RESULTS_FILE = 'data/exports/OneDrive_2026-01-21/Soft Launch Data/JPMC_Chase Brand Personality_Quant Round 1_January 21, 2026_Soft Launch_Labels.csv'
+    file_browser = mo.ui.file_browser(
+        initial_path="./data/exports", multiple=False, restrict_navigation=True, filetypes=[".csv"], label="Select 'Labels' File"
+    )
+    file_browser
+    return (file_browser,)
+
+
+@app.cell
+def _(Path, file_browser, mo):
+    mo.stop(file_browser.path(index=0) is None, mo.md("**⚠️ Please select a `_Labels.csv` file above to proceed**"))
+    # RESULTS_FILE = 'data/exports/OneDrive_2026-01-21/Soft Launch Data/JPMC_Chase Brand Personality_Quant Round 1_January 21, 2026_Soft Launch_Labels.csv'
+    RESULTS_FILE = Path(file_browser.path(index=0))
     QSF_FILE = 'data/exports/OneDrive_2026-01-21/Soft Launch Data/JPMC_Chase_Brand_Personality_Quant_Round_1.qsf'
+    # RESULTS_FILE
     return QSF_FILE, RESULTS_FILE
 
 
 @app.cell
-def _(JPMCSurvey, QSF_FILE, RESULTS_FILE):
+def _(RESULTS_FILE, mo):
+    mo.stop(not RESULTS_FILE.name.lower().endswith('labels.csv'), mo.md("**⚠️ Make sure you select a `_Labels.csv` file above**"))
+    return
+
+
+@app.cell
+def _(JPMCSurvey, QSF_FILE, RESULTS_FILE, mo):
     S = JPMCSurvey(RESULTS_FILE, QSF_FILE)
-    data_all = S.load_data()
+    try:
+        data_all = S.load_data()
+    except NotImplementedError as e:
+        mo.stop(True, mo.md(f"**⚠️ {str(e)}**"))
     return S, data_all
 
 
 @app.cell(hide_code=True)
 def _(Path, RESULTS_FILE, data_all, mo):
     mo.md(f"""
+    ---
+
     # Load Data
 
     **Dataset:** `{Path(RESULTS_FILE).name}`
@@ -71,19 +94,7 @@ def _(check_progress, data_all, duration_validation, mo):
 @app.cell(hide_code=True)
 def _(mo):
     mo.md(r"""
-    ### ToDo: "straight-liner" detection and removal
+    ### ⚠️  ToDo: "straight-liner" detection and removal
-    """)
-    return
-
-
-@app.cell(hide_code=True)
-def _(mo):
-    mo.md(r"""
-    ---
-
-    # Data Filter
-
-    Use to select a subset of the data for the following analysis
     """)
     return
 
@@ -91,7 +102,8 @@ def _(mo):
 @app.cell(hide_code=True)
 def _(S, mo):
     filter_form = mo.md('''
-    # Data Filter
+
+
 
     {age}
 
@@ -110,7 +122,15 @@ def _(S, mo):
         income=mo.ui.multiselect(options=S.options_income, value=S.options_income, label="Select Income Group(s):"),
         consumer=mo.ui.multiselect(options=S.options_consumer, value=S.options_consumer, label="Select Consumer Groups:")
     ).form()
-    filter_form
+    mo.md(f'''
+    ---
+
+    # Data Filter
+
+    {filter_form}
+    ''')
+
+
     return (filter_form,)
 
 
@@ -128,26 +148,15 @@ def _(S, data_all, filter_form, mo):
 
 
 @app.cell(hide_code=True)
-def _(mo):
+def _(S, data, mo):
+    char_rank = S.get_character_ranking(data)[0]
     mo.md(r"""
     ---
 
     # Analysis
-    """)
-    return
 
-
-@app.cell(hide_code=True)
-def _(mo):
-    mo.md(r"""
     ## Character personality ranking
     """)
-    return
-
-
-@app.cell
-def _(S, data):
-    char_rank = S.get_character_ranking(data)[0]
     return (char_rank,)
 
 
@@ -187,17 +196,12 @@ def _(S, calculate_weighted_ranking_scores, char_rank, mo):
 
 
 @app.cell(hide_code=True)
-def _(mo):
+def _(S, data, mo):
+    v_18_8_3 = S.get_18_8_3(data)[0].collect()
+
     mo.md(r"""
     ## Voice Ranking
     """)
-    return
-
-
-@app.cell
-def _(S, data):
-    v_18_8_3 = S.get_18_8_3(data)[0].collect()
-    # print(v_18_8_3.head())
     return (v_18_8_3,)
 
 
@@ -266,18 +270,8 @@ def _(S, mo, top3_voices):
     return
 
 
-@app.cell(hide_code=True)
-def _(mo):
-    mo.md(r"""
-    ## Voice Speaking Style - Perception Traits
-
-    Here you can find the speaking styles and traits: [Speaking Style Traits Quantitative test design.docx](https://voicebranding-my.sharepoint.com/:w:/g/personal/phoebe_voicebranding_ai/IQBfM_Z8PF98Qalz4lzIbJ3RAUCdc7waB32HZXCj7k3xfo0?e=rtFd27)
-    """)
-    return
-
-
 @app.cell
-def _(S, data, utils):
+def _(S, data, mo, utils):
     ss_or, choice_map_or = S.get_ss_orange_red(data)
     ss_gb, choice_map_gb = S.get_ss_green_blue(data)
 
@@ -289,6 +283,12 @@ def _(S, data, utils):
     # print(_d.head())
     # print(choice_map)
     ss_long = utils.process_speaking_style_data(ss_all, choice_map)
+
+    mo.md(r"""
+    ## Voice Speaking Style - Perception Traits
+
+    Here you can find the speaking styles and traits: [Speaking Style Traits Quantitative test design.docx](https://voicebranding-my.sharepoint.com/:w:/g/personal/phoebe_voicebranding_ai/IQBfM_Z8PF98Qalz4lzIbJ3RAUCdc7waB32HZXCj7k3xfo0?e=rtFd27)
+    """)
     return choice_map, ss_all, ss_long
 
 
@@ -310,17 +310,17 @@ def _(S, mo, pl, ss_long):
 
 
 @app.cell(hide_code=True)
-def _(mo):
+def _():
-    mo.md(r"""
-    ## Voice Scale 1-10
-    """)
     return
 
 
 @app.cell
-def _(S, data):
+def _(S, data, mo):
     vscales = S.get_voice_scale_1_10(data)[0]
     # plot_average_scores_with_counts(vscales, x_label='Voice', width=1000)
+    mo.md(r"""
+    ## Voice Scale 1-10
+    """)
     return (vscales,)
 
 
@@ -334,10 +334,15 @@ def _(S, mo, vscales):
     return
 
 
+@app.cell(hide_code=True)
+def _():
+    return
+
+
 @app.cell(hide_code=True)
 def _(mo):
     mo.md(r"""
-    ## Correlations Voice Speaking Styles <-> Voice Scale 1-10
+ 
     """)
     return
 
@@ -345,19 +350,29 @@ def _(mo):
 @app.cell(hide_code=True)
 def _(mo):
     mo.md(r"""
+ 
+    """)
+    return
+
+
+@app.cell
+def _(choice_map, mo, ss_all, utils, vscales):
+    df_style = utils.process_speaking_style_data(ss_all, choice_map)
+    df_voice_long = utils.process_voice_scale_data(vscales)
+
+    joined_df = df_style.join(df_voice_long, on=["_recordId", "Voice"], how="inner")
+    # df_voice_long
+
+    mo.md(r"""
+    ## Correlations Voice Speaking Styles <-> Voice Scale 1-10
+
     Let’s show how scoring better on these speaking styles correlates (or not) with better Voice Scale 1-10 evaluation. For each speaking style we show how the traits in these speaking styles correlate with Voice Scale 1-10 evaluation. This gives us a total of 4 correlation diagrams.
 
     Example for speaking style green:
     - Trait 1: Friendly | Conversational | Down-to-earth
     - Trait 2: Approachable | Familiar | Warm
     - Trait 3: Optimistic | Benevolent | Positive | Appreciative
-    """)
-    return
 
-
-@app.cell(hide_code=True)
-def _(mo):
-    mo.md(r"""
     ### How to Interpret These Correlation Results
     Each bar represents the Pearson correlation coefficient (r) between a speaking style trait rating (1-5 scale) and the overall Voice Scale rating (1-10).
 
@@ -369,16 +384,6 @@ def _(mo):
     | r < 0 (Red bars)| 	Negative correlation — voices rated higher on this trait tend to receive lower Voice Scale scores|
     | r ≈ 0| 	No relationship — this trait doesn't predict Voice Scale ratings|
     """)
-    return
-
-
-@app.cell
-def _(choice_map, ss_all, utils, vscales):
-    df_style = utils.process_speaking_style_data(ss_all, choice_map)
-    df_voice_long = utils.process_voice_scale_data(vscales)
-
-    joined_df = df_style.join(df_voice_long, on=["_recordId", "Voice"], how="inner")
-    # df_voice_long
     return df_style, joined_df
 
 

README.md

@@ -0,0 +1,5 @@
+Running on Ct-105 for shared access:
+
+```
+uv run marimo edit --headless --port 8080 --host ct-105.tail44fa00.ts.net
+```