Update dash_plotly_QC_scRNA.py

dash_plotly_QC_scRNA.py

@@ -380,7 +380,7 @@ def update_graph_and_pie_chart(batch_chosen, s_chosen, g2m_chosen, condition1_ch
 
     # Cache commonly used subexpressions
     total_count = pl.lit(len(dff))
-    category_counts = dff.groupby("batch").agg(pl.col("batch").count().alias("count"))
+    category_counts = dff.group_by("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
@@ -402,21 +402,21 @@ def update_graph_and_pie_chart(batch_chosen, s_chosen, g2m_chosen, condition1_ch
     dff_long = dff_pre.melt(id_vars="batch", variable_name="Gene", value_name="Mean expression")
 
     # Calculate the mean expression levels for each gene in each region
-    expression_means = dff_long.lazy().groupby(["batch", "Gene"]).agg(pl.mean("Mean expression")).collect()
+    expression_means = dff_long.lazy().group_by(["batch", "Gene"]).agg(pl.mean("Mean expression")).collect()
     
     # Calculate the percentage total expressed
-    dff_long2 = dff_pre.melt(id_vars="batch", variable_name="Gene").group_by(pl.all()).len()
-    dff_long3 = dff_long2.filter(value = 0).group_by(["batch", "Gene"]).agg(pl.sum("len").alias("total"))
-    dff_long4 = dff_long2.group_by(["batch", "Gene"]).agg(pl.sum("len").alias("total"))
-    dff_5 = dff_long4.join(dff_long3, on=["batch","Gene"], how="outer")
-    result = dff_5.select([
-        pl.when((pl.col('total_right').is_not_null()) & (pl.col('total').is_not_null()))
-              .then(pl.col('total_right') / pl.col('total'))
-              .otherwise(None).alias("%"),
-    ])
-    result = result.with_columns(pl.col("%").fill_null(1.0))
-    dff_5[["percentage"]] = result[["%"]]
-    dff_5 = dff_5.select(pl.col("batch","Gene","percentage"))
+    #dff_long2 = dff_pre.melt(id_vars="batch", variable_name="Gene").group_by(pl.all()).len()
+    #dff_long3 = dff_long2.filter(value = 0).group_by(["batch", "Gene"]).agg(pl.sum("len").alias("total"))
+    #dff_long4 = dff_long2.group_by(["batch", "Gene"]).agg(pl.sum("len").alias("total"))
+    #dff_5 = dff_long4.join(dff_long3, on=["batch","Gene"], how="outer")
+    #result = dff_5.select([
+    #    pl.when((pl.col('total_right').is_not_null()) & (pl.col('total').is_not_null()))
+    #          .then(pl.col('total_right') / pl.col('total'))
+    #          .otherwise(None).alias("%"),
+    #])
+    #result = result.with_columns(pl.col("%").fill_null(1.0))
+    #dff_5[["percentage"]] = result[["%"]]
+    #dff_5 = dff_5.select(pl.col("batch","Gene","percentage"))
 
     # Final part to join the percentage expressed and mean expression levels
     # TO DO