Update dash_plotly_QC_scRNA.py

dash_plotly_QC_scRNA.py

@@ -361,28 +361,31 @@ def update_slider_values(min_1, max_1, min_2, max_2, min_3, max_3):
 )
 
 def update_graph_and_pie_chart(batch_chosen, s_chosen, g2m_chosen, condition1_chosen, condition2_chosen, condition3_chosen, range_value_1, range_value_2, range_value_3):
-    dff = df.filter(
-        (pl.col('batch').cast(str).is_in(batch_chosen)) &
-        (pl.col(col_features) >= range_value_1[0]) &
-        (pl.col(col_features) <= range_value_1[1]) &
-        (pl.col(col_counts) >= range_value_2[0]) &
-        (pl.col(col_counts) <= range_value_2[1]) &
-        (pl.col(col_mt) >= range_value_3[0]) &
-        (pl.col(col_mt) <= range_value_3[1])
-)
+    batch_col = dff['batch']
+    batch_cat = batch_col.cast(pl.Categorical)
+    feature_cols = pl.col(cols)
+    count_cols = pl.col(col_counts)
+    mt_cols = pl.col(col_mt)
+    
+    # Perform filtering on all features simultaneously
+    filter_expr = (batch_cat.is_in(batch_chosen)) & \
+                  (feature_cols >= range_value_1[0]) & \
+                  (feature_cols <= range_value_1[1]) & \
+                  (count_cols >= range_value_2[0]) & \
+                  (count_cols <= range_value_2[1]) & \
+                  (mt_cols >= range_value_3[0]) & \
+                  (mt_cols <= range_value_3[1])
     
-    #Drop categories that are not in the filtered data
-    dff = dff.with_columns(dff['batch'].cast(str))
-    dff = dff.with_columns(dff['batch'].cast(pl.Categorical))
+    dff = dff.filter(filter_expr)
 
     # Plot figures
     fig_violin = px.violin(data_frame=dff, x='batch', y=col_features, box=True, points="all",
                             color='batch', hover_name='batch',template="seaborn")
 
-    # Calculate the percentage of each category (normalized_count) for pie chart
-    category_counts = dff.group_by("batch").agg(pl.col("batch").count().alias("count"))
-    total_count = len(dff)
-    category_counts = category_counts.with_columns((pl.col("count") / total_count * 100).alias("normalized_count"))
+    # Cache commonly used subexpressions
+    total_count = pl.lit(len(dff))
+    category_counts = dff.groupby("batch").agg(pl.col("batch").count().alias("count"))
+    category_counts = category_counts.with_columns(((pl.col("count") / total_count * 100).round(decimals=2)).alias("normalized_count"))
 
     # Display the result
     labels = category_counts["batch"].to_list()