Update app.py

app.py

@@ -1,46 +1,8 @@
 import streamlit as st
 from setfit import SetFitModel
 
-# Load the model
-model = SetFitModel.from_pretrained("leavoigt/vulnerable_groups")
 
-# Define the classes
-group_dict = {
-    0: 'Coastal communities',
-    1: 'Small island developing states (SIDS)',
-    2: 'Landlocked countries',
-    3: 'Low-income households',
-    4: 'Informal settlements and slums',
-    5: 'Rural communities',
-    6: 'Children and youth',
-    7: 'Older adults and the elderly',
-    8: 'Women and girls',
-    9: 'People with pre-existing health conditions',
-    10: 'People with disabilities',
-    11: 'Small-scale farmers and subsistence agriculture',
-    12: 'Fisherfolk and fishing communities',
-    13: 'Informal sector workers',
-    14: 'Children with disabilities',
-    15: 'Remote communities',
-    16: 'Young adults',
-    17: 'Elderly population',
-    18: 'Urban slums',
-    19: 'Men and boys',
-    20: 'Gender non-conforming individuals',
-    21: 'Pregnant women and new mothers',
-    22: 'Mountain communities',
-    23: 'Riverine and flood-prone areas',
-    24: 'Drought-prone regions',
-    25: 'Indigenous peoples',
-    26: 'Migrants and displaced populations',
-    27: 'Outdoor workers',
-    28: 'Small-scale farmers',
-    29: 'Other'}
-
-# Define prediction function 
-#def predict(text):
- #   preds = model(text)
-  #  return group_dict[preds]
+####################################### Dashboard ######################################################
 
 # App 
 st.title("Identify references to vulnerable groups.")
@@ -51,23 +13,70 @@ into national climate policies, governments can ensure equitable outcomes, promo
 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(label, type=None, accept_multiple_files=False, key=None, help=None, on_change=None, args=None, kwargs=None, *, disabled=False, label_visibility="visible")
 
 # Create text input box
 input_text = st.text_area(label='Please enter your text here', value="This policy has been implemented to support women.")
 
 st.write('Prediction:', model(input_text))
 
-# Make predictions
-#preds = model(input_text)
+######################################### Model #########################################################
+
+# Load the model
+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'}
+
+# Import the file_processing function 
+from file_processing.py import process_documents
+
+# Process document to paragraphs 
+par_list = process_documents(uploaded_file)
+
+# 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'])]
+
 
-#modelresponse = model_function(input)
-#st.text_area(label ="",value=preds, height =100)
+#####################################
+st.write(df)  
 
-# Select lab
-#def get_label(prediction_tensor):
- #   print(prediction_tensor.index("1"))
-    #key = prediction_tensor.index(1)
-    #return group_dict[key]
-    
-#st.write(preds)
-#st.text(get_label(preds))