Upload folder using huggingface_hub

app.py

@@ -68,14 +68,14 @@ st.pyplot(fig_corr)
 st.header("4. Impact of Categorical Variables on Average Score")
 
 def plot_and_analyze_categorical(dataframe, category_col, score_col='average_score'):
-    # Corrected line with single quotes for replace arguments
     st.subheader(f"4.{plot_and_analyze_categorical.counter}. {category_col.replace('_', ' ').title()}")
     plot_and_analyze_categorical.counter += 1
 
     # Violin Plot
     fig_violin, ax_violin = plt.subplots(figsize=(10, 6))
     sns.violinplot(x=category_col, y=score_col, data=dataframe, ax=ax_violin)
-    ax_violin.set_title(f'{score_col.replace("_", " ").title()} by {category_col.replace("_", " ").title()}')
+    # This line was also causing an issue, correcting here too
+    ax_violin.set_title(f'{score_col.replace('_', ' ').title()} by {category_col.replace('_', ' ').title()}')
     ax_violin.tick_params(axis='x', rotation=45, ha='right')
     st.pyplot(fig_violin)
 
@@ -85,7 +85,6 @@ def plot_and_analyze_categorical(dataframe, category_col, score_col='average_sco
         group1 = dataframe[dataframe[category_col] == dataframe[category_col].unique()[0]][score_col]
         group2 = dataframe[dataframe[category_col] == dataframe[category_col].unique()[1]][score_col]
         t_stat, p_val = stats.ttest_ind(group1, group2)
-        # Corrected line with single quotes for replace arguments
         st.write(f"Independent t-test between **{dataframe[category_col].unique()[0]}** and **{dataframe[category_col].unique()[1]}** for {score_col.replace('_', ' ')}:")
         st.write(f"  t-statistic = {t_stat:.3f}, p-value = {p_val:.3f}")
         if p_val < 0.05:
@@ -95,7 +94,8 @@ def plot_and_analyze_categorical(dataframe, category_col, score_col='average_sco
     else:
         model = ols(f'{score_col} ~ C({category_col})', data=dataframe).fit()
         anova_table = sm.stats.anova_lm(model, typ=2)
-        st.write(f"ANOVA for {category_col} on {score_col.replace("_", " ")}:")
+        # Corrected line with single quotes for replace arguments
+        st.write(f"ANOVA for {category_col} on {score_col.replace('_', ' ')}:")
         st.dataframe(anova_table)
         if anova_table['PR(>F)'][0] < 0.05:
             st.success("  **Conclusion: Statistically significant differences between group means (p < 0.05).**")