base correlations

03_quant_report.py

@@ -664,5 +664,140 @@ def _():
     return
 
 
+@app.cell(hide_code=True)
+def _():
+    mo.md(r"""
+    ## Correlation Speaking Styles
+    """)
+    return
+
+
+@app.cell
+def _(S, data, top3_voices):
+    ss_or, choice_map_or = S.get_ss_orange_red(data)
+    ss_gb, choice_map_gb = S.get_ss_green_blue(data)
+
+    # Combine the data
+    ss_all = ss_or.join(ss_gb, on='_recordId')
+    _d = ss_all.collect()
+
+    choice_map = {**choice_map_or, **choice_map_gb}
+    # print(_d.head())
+    # print(choice_map)
+    ss_long = utils.process_speaking_style_data(ss_all, choice_map)
+
+    df_style = utils.process_speaking_style_data(ss_all, choice_map)
+
+    vscales = S.get_voice_scale_1_10(data)[0]
+    df_scale_long = utils.process_voice_scale_data(vscales)
+
+    joined_scale = df_style.join(df_scale_long, on=["_recordId", "Voice"], how="inner")
+
+    df_ranking = utils.process_voice_ranking_data(top3_voices)
+    joined_ranking = df_style.join(df_ranking, on=['_recordId', 'Voice'], how='inner')
+    return joined_ranking, joined_scale
+
+
+@app.cell
+def _():
+    mo.md(r"""
+    ### Colors vs Scale 1-10
+    """)
+    return
+
+
+@app.cell
+def _(S, joined_scale):
+    # Transform to get one row per color with average correlation
+    color_corr_scale, _ = utils.transform_speaking_style_color_correlation(joined_scale, SPEAKING_STYLES)
+    S.plot_speaking_style_color_correlation(
+        data=color_corr_scale,
+        title="Correlation: Speaking Style Colors and Voice Scale 1-10"
+    )
+    return
+
+
+@app.cell
+def _():
+    mo.md(r"""
+    ### Colors vs Ranking Points
+    """)
+    return
+
+
+@app.cell
+def _(S, joined_ranking):
+    color_corr_ranking, _ = utils.transform_speaking_style_color_correlation(
+        joined_ranking, 
+        SPEAKING_STYLES, 
+        target_column="Ranking_Points"
+    )
+    S.plot_speaking_style_color_correlation(
+        data=color_corr_ranking,
+        title="Correlation: Speaking Style Colors and Voice Ranking Points"
+    )
+    return
+
+
+@app.cell
+def _():
+    mo.md(r"""
+    ### Individual Traits vs Scale 1-10
+    """)
+    return
+
+
+@app.cell
+def _(S, joined_scale):
+    _content = """"""
+
+    for _style, _traits in SPEAKING_STYLES.items():
+        # print(f"Correlation plot for {style}...")
+        _fig = S.plot_speaking_style_correlation(
+            data=joined_scale,
+            style_color=_style,
+            style_traits=_traits,
+            title=f"Correlation: Speaking Style {_style} and Voice Ranking Points",
+        )
+        _content += f"""
+    #### Speaking Style **{_style}**:
+
+    {mo.ui.altair_chart(_fig)}
+
+    """
+    mo.md(_content)
+    return
+
+
+@app.cell(hide_code=True)
+def _():
+    mo.md(r"""
+    ### Individual Traits vs Ranking Points
+    """)
+    return
+
+
+@app.cell
+def _(S, joined_ranking):
+    _content = """"""
+
+    for _style, _traits in SPEAKING_STYLES.items():
+        # print(f"Correlation plot for {style}...")
+        _fig = S.plot_speaking_style_ranking_correlation(
+        data=joined_ranking,
+        style_color=_style,
+        style_traits=_traits,
+        title=f"Correlation: Speaking Style {_style} and Voice Ranking Points",
+    )
+        _content += f"""
+    #### Speaking Style **{_style}**:
+
+    {mo.ui.altair_chart(_fig)}
+
+    """
+    mo.md(_content)
+    return
+
+
 if __name__ == "__main__":
     app.run()