Updating

app.py

@@ -1,21 +1,61 @@
 import streamlit as st
-from setfit import SetFitModel
-from file_processing import get_paragraphs
-import doc_processing as processing
+from utils.uploadAndExample import add_upload
 
 ####################################### Dashboard ######################################################
 
 # App 
-st.title("Identify references to vulnerable groups.")
 
-st.write("""Vulnerable groups encompass various communities and individuals who are disproportionately affected by the impacts of climate change
-due to their socioeconomic status, geographical location, or inherent characteristics. By incorporating the needs and perspectives of these groups 
-into national climate policies, governments can ensure equitable outcomes, promote social justice, and strive to build resilience within the most marginalized populations, 
-fostering a more sustainable and inclusive society as we navigate the challenges posed by climate change.This app allows you to identify whether a text contains any 
-references to vulnerable groups, for example when talking about policy documents.""")
+st.set_page_config(page_title = 'Vulnerable Groups Identification', 
+                   initial_sidebar_state='expanded', layout="wide") 
+
+with st.sidebar:
+    # upload and example doc
+    choice = st.sidebar.radio(label = 'Select the Document',
+                            help = 'You can upload the document \
+                            or else you can try a example document', 
+                            options = ('Upload Document', 'Try Example'), 
+                            horizontal = True)
+    add_upload(choice)
+
+with st.container():
+        st.markdown("<h2 style='text-align: center; color: black;'> Vulnerable Groups Identification </h2>", unsafe_allow_html=True)
+        st.write(' ')
+
+with st.expander("ℹ️ - About this app", expanded=False):
+    st.write(
+        """
+        The Vulnerable Groups Identification App is an open-source\
+        digital tool which aims to assist policy analysts and \
+        other users in extracting and filtering relevant \
+        information from public documents.
+        """)
+    st.write('**Definitions**')
+
+    st.caption("""
+            - **Place holder**: Place holder \
+            Place holder \
+            Place holder \
+            Place holder \ 
+            Place holder
+              """)
+    #c1, c2, c3 =  st.columns([12,1,10])
+    #with c1:
+        #image = Image.open('docStore/img/flow.jpg') 
+        #st.image(image)
+    #with c3:
+        #st.write("""
+            #What Happens in background?
+
+#st.title("Identify references to vulnerable groups.")
+
+#st.write("""Vulnerable groups encompass various communities and individuals who are disproportionately affected by the impacts of climate change
+#due to their socioeconomic status, geographical location, or inherent characteristics. By incorporating the needs and perspectives of these groups 
+#into national climate policies, governments can ensure equitable outcomes, promote social justice, and strive to build resilience within the most marginalized populations, 
+#fostering a more sustainable and inclusive society as we navigate the challenges posed by climate change.This app allows you to identify whether a text contains any 
+#references to vulnerable groups, for example when talking about policy documents.""")
 
 # Document upload
-uploaded_file = st.file_uploader("Upload your file here")
+#uploaded_file = st.file_uploader("Upload your file here")
 
 # Create text input box
 #input_text = st.text_area(label='Please enter your text here', value="This policy has been implemented to support women.")
@@ -25,25 +65,25 @@ uploaded_file = st.file_uploader("Upload your file here")
 ######################################### Model #########################################################
 
 # Load the model
-model = SetFitModel.from_pretrained("leavoigt/vulnerable_groups")
+#model = SetFitModel.from_pretrained("leavoigt/vulnerable_groups")
 
 # Define the classes
-id2label = {
-    0: 'Agricultural communities',
-    1: 'Children and Youth',
-    2: 'Coastal communities',
-    3: 'Drought-prone regions',
-    4: 'Economically disadvantaged communities',
-    5: 'Elderly population',
-    6: 'Ethnic minorities and indigenous people',
-    7: 'Informal sector workers',
-    8: 'Migrants and Refugees',
-    9: 'Other',
-    10: 'People with Disabilities',
-    11: 'Rural populations',
-    12: 'Sexual minorities (LGBTQI+)',
-    13: 'Urban populations',
-    14: 'Women'}
+#id2label = {
+ #   0: 'Agricultural communities',
+ #   1: 'Children and Youth',
+ #   2: 'Coastal communities',
+ #   3: 'Drought-prone regions',
+ #   4: 'Economically disadvantaged communities',
+ #   5: 'Elderly population',
+ #   6: 'Ethnic minorities and indigenous people',
+ #   7: 'Informal sector workers',
+ #   8: 'Migrants and Refugees',
+ #   9: 'Other',
+ #   10: 'People with Disabilities',
+ #   11: 'Rural populations',
+ #   12: 'Sexual minorities (LGBTQI+)',
+ #   13: 'Urban populations',
+ #   14: 'Women'}
 
 
 ### Process document to paragraphs 
@@ -62,46 +102,3 @@ id2label = {
 
 #     #Get the file path
 
-file = st.file_uploader("File upload", type=['pdf', 'docx', 'txt'])
-
-if uploaded_file is not None: 
-
-    # Retrieve the file name 
-    with tempfile.NamedTemporaryFile(mode="wb") as temp:
-        bytes_data = files.getvalue()
-        temp.write(bytes_data)
-        print(temp.name)
-
-    # Process file
-    par_list = get_paragraphs(temp.name)
-
-    ### Make predictions 
-    preds = vg_model(par_list)
-
-    # Get label names 
-    preds_list = preds.tolist()
-
-    predictions_names=[]
-
-    # loop through each prediction
-    for ele in preds_list:
-       try:
-         index_of_one = ele.index(1)
-       except ValueError:
-    index_of_one = "NA" 
-  if index_of_one != "NA": 
-    name  = id2label[index_of_one]
-  else: 
-    name = "NA"
-    predictions_names.append(name)
-
-    # Combine the paragraphs and labels to a dataframe 
-    df_predictions = pd.DataFrame({'Paragraph': par_list, 'Prediction': predictions_names})
-
-    # Drop all "Other" and "NA" predictions
-    filtered_df = df[df['Prediction'].isin(['Other', 'NA'])]
-
-
-    #####################################
-    st.write(df)  
-

doc_processing.py

@@ -54,8 +54,6 @@ def runPreprocessingPipeline(file_name:str, file_path:str,
     
     return output_pre
 
-st.write("Hello World")
-
 def app():
     with st.container():           
           if 'filepath' in st.session_state: