feat: provide an option to sort and download resulting dataset

filter_data_app.py

@@ -6,6 +6,7 @@ from upsetplot import UpSet
 import matplotlib.pyplot as plt
 import polars as pl
 from polars import col, lit
+import seaborn as sns
 
 # Set page configuration
 st.set_page_config(layout="wide")
@@ -88,7 +89,6 @@ def calculate_std_dev(df,radiomics_feature):
 # Main function to run the Streamlit app
 def main():
     st.title("Qualitative Checks of TotalSegmentator Segmentations on NLST")
-    st.write("Filter the data based on qualitative checks, bodyPart, and laterality.")
 
     # Sidebar widgets for navigation and filtering
     page = st.sidebar.selectbox("Choose a page", ["Summary", "UpSet Plots"])
@@ -97,6 +97,7 @@ def main():
     #df = load_data()
 
     if page == "UpSet Plots":
+        st.write("Filter the data based on radiomics feature, qualitative checks, bodyPart, and laterality.")
         with st.sidebar:
             st.title("Filters")
 
@@ -122,7 +123,7 @@ def main():
                     'series_with_vertabra_on_every_slice': None,
                     'connected_volumes': None,
                     'laterality': None,
-                    'radiomics_feature': 'Volume from Voxel Summation' 
+                    #'radiomics_feature': 'Volume from Voxel Summation' 
                 })
                 st.session_state.filters = filters
 
@@ -170,8 +171,9 @@ def main():
                 key='radiomics_feature',
                 on_change=lambda: apply_filter('radiomics_feature', st.session_state.radiomics_feature)
             )
-            df = load_data(radiomics_feature=radiomics_feature)
             filters['radiomics_feature'] = radiomics_feature
+            df = load_data(radiomics_feature=radiomics_feature)
+
 
             # Body part filter
             body_part_options = sorted(df['bodyPart'].unique().to_list())
@@ -237,6 +239,11 @@ def main():
             else:
                 body_part_df = df.filter(col('bodyPart') == lit(body_part))
 
+            sort_column = st.selectbox("Select column to sort by", options=filtered_df.columns)
+            sort_order = st.checkbox("Sort in descending order", value=False)
+
+            # Sort the DataFrame based on user selection
+            filtered_df = filtered_df.sort(by=sort_column, descending=sort_order)
             
         st.header("UpSet Plots of Qualitative Checks")
 
@@ -268,12 +275,11 @@ def main():
             paginated_df,
             column_config={
                 "Viewer Url":st.column_config.LinkColumn("StudyInstanceUID",
-                              display_text="https:\/\/viewer\.imaging\.datacommons\.cancer\.gov\/viewer\/(.*)" 
-                              
+                              display_text="https:\/\/viewer\.imaging\.datacommons\.cancer\.gov\/viewer\/(.*)"                               
                               ),               
                                           
             },
-            column_order=("PatientID", "Viewer Url", "seriesNumber","bodyPart","laterality", "segmentation_completeness","laterality_check", "series_with_vertabra_on_every_slice","connected_volumes"),  
+            column_order=("PatientID", "Viewer Url", "seriesNumber","bodyPart","laterality", "segmentation_completeness","laterality_check", "series_with_vertabra_on_every_slice","connected_volumes", radiomics_feature),  
             hide_index=True,
             use_container_width=True
         )
@@ -296,9 +302,6 @@ def main():
         if not filtered_df.is_empty():
             create_upset_plot_passes(filtered_df)
 
-        import seaborn as sns
-        import pandas as pd
-
         # Assuming calculate_std_dev returns a Series
         std_dev_before_filtering = calculate_std_dev(body_part_df, radiomics_feature)
         std_dev_after_filtering = calculate_std_dev(filtered_df, radiomics_feature)
@@ -317,13 +320,24 @@ def main():
         combined_df = combined_df.reset_index(drop=True)
 
         # Display violin plots for the distribution of standard deviation of volumes
-        st.header("Violin Plots for Standard Deviation of Volumes")
-        st.write("This plot shows the distribution of standard deviation of volumes within a patient.")
+        st.header(f"Violin Plots for Standard Deviation of {radiomics_feature}")
+        st.write(f"This plot shows the distribution of standard deviation of {radiomics_feature} within a patient.")
         fig2, ax = plt.subplots()
         sns.violinplot(x='Filtering', y=radiomics_feature, data=combined_df, ax=ax)
-        ax.set_ylabel("Standard Deviation of Volumes")
+        ax.set_ylabel(f"Standard Deviation of {radiomics_feature}")
         st.pyplot(fig2)
-        
+
+        def convert_df(df):
+                return df.write_csv()
+            
+        csv= convert_df(filtered_df)
+        st.sidebar.download_button(
+        "Download the filtered dataset",
+        csv,
+        "TotalSegmentatorRadiomicsResults.csv",
+        "text/csv",
+        key='download-csv'
+        )  
 
     # Define the pages
     if page == "Summary":