File size: 2,897 Bytes
eee7134 eab471f 5b4a98a 3f54553 a26f453 77a6d9d a26f453 5b4a98a a26f453 3f54553 6e89faf 77a6d9d de24a6f 7f93a13 5b4a98a 3f54553 5b4a98a 80a32ce |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 |
import streamlit as st
from setfit import SetFitModel
####################################### 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.""")
# 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))
######################################### 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'])]
#####################################
st.write(df)
|