Update final_code.py

final_code.py

@@ -1,6 +1,7 @@
 import streamlit as st
 import pandas as pd
 import os
+from glob import glob
 
 # Function to get list of document IDs
 def get_document_ids():
@@ -9,28 +10,46 @@ def get_document_ids():
     return list(set(document_ids))
 
 # Function to load image based on selected document ID and page number
-def load_image(document_id, page_number):
-    image_path = f'abc/{document_id}_{page_number}.png'
-    if os.path.exists(image_path):
-        return image_path
+def load_image(image_path, document_id, page_number):
+    im_path = f"{image_path}{document_id}-{page_number-1}.png"
+    if os.path.exists(im_path):
+        return im_path
     else:
         return None
 
 # Function to load dataframe based on selected document ID
-def load_dataframe(document_id):
-    csv_path = f'abc/{document_id}_1.csv'
-    if os.path.exists(csv_path):
-        return pd.read_csv(csv_path)
+def load_dataframe(auto_csv_path, document_id, page_number, cols):
+    csv_path = glob(f'{auto_csv_path}*{document_id}*auto.csv')
+    print(csv_path)
+    if len(csv_path)>0:
+        auto_df = pd.read_csv(csv_path[0])
+        auto_df_page = auto_df[auto_df['Page#']==page_number][cols]
+        return auto_df_page
     else:
         return None
+    
+def path_setting(inbound_df_path):
+    auto_csv_path = 'PhaseData/Batch1/NLP_batch/'
+    image_path = 'PhaseData/Data/output/images/'
+    inbound_df = pd.read_csv(inbound_df_path)
+    pif_list = list(inbound_df.pif_key.values)
+    return pif_list, image_path, auto_csv_path
 
 def main():
+    inbound_df_path = 'inbound_issues_tempus_2_q2.csv'
+    display_cols = ['Biomarker Name Source', 'Biomarker Test Type', 'NLP Result','NLP Value', 'NLP Variant', 
+                    'Biomarker Test Result Value Numeric 1', 'Biomarker Test Result Value Unit 1', 
+                    'Biomarker Test Result Value Numeric 2', 'Biomarker Test Result Value Unit 2', 
+                    'Biomarker Test Threshold Value Numeric 1', 'Biomarker Test Threshold Value Unit1', 
+                    'Biomarker Test Threshold Value Numeric 2', 'Biomarker Test Threshold Value Unit2']
+    pif_list, image_path, auto_csv_path = path_setting(inbound_df_path)
+    
     st.set_page_config(layout="wide")  # Set layout to wide
 
     # Slider to adjust the width of the columns
     col1_width = st.sidebar.slider("Width of First Column", 0.1, 10.0, 1.0, 0.1)
-    col2_width = st.sidebar.slider("Width of Second Column", 0.1, 10.0, 3.0, 0.1)
-    col3_width = st.sidebar.slider("Width of Third Column", 0.1, 10.0, 2.0, 0.1)
+    col2_width = st.sidebar.slider("Width of Second Column", 0.1, 10.0, 6.5, 0.1)
+    col3_width = st.sidebar.slider("Width of Third Column", 0.1, 10.0, 5.0, 0.1)
 
     # Divide the screen into three vertical panels with specified widths
     col1, col2, col3 = st.columns([col1_width, col2_width, col3_width])
@@ -38,22 +57,23 @@ def main():
     # Document Selection Panel
     with col1:
         st.write("### Document Selection")
-        document_id = st.selectbox("Select Document ID", options=get_document_ids())
-        page_number = st.number_input("Page Number", min_value=1, step=1, value=1)
+        document_id = st.selectbox("Select Document ID", options=pif_list)
+        pages = [int(i.split('-')[-1].split('.')[0]) for i in glob(f"{image_path}{document_id}*.png")]
+        page_number = st.number_input("Page Number", min_value=1, max_value=len(pages), step=1, value=1)
 
     # Display Image Panel
     with col2:
         st.write("### Display Image")
-        image_path = load_image(document_id, page_number)
-        if image_path:
-            st.image(image_path)
+        im_path = load_image(image_path, document_id, page_number)
+        if im_path:
+            st.image(im_path)
         else:
             st.write("Image not found")
 
     # Display DataFrame Panel
     with col3:
         st.write("### Display DataFrame")
-        df = load_dataframe(document_id)
+        df = load_dataframe(auto_csv_path, document_id, page_number, display_cols)
         if df is not None:
             columns_to_display = st.multiselect("Select Columns to Display", df.columns)
             if len(columns_to_display) > 0:
@@ -64,4 +84,4 @@ def main():
             st.write("DataFrame not found")
 
 if __name__ == "__main__":
-    main()
+    main()