Added attribution viz for ITA

app.py

@@ -1,12 +1,15 @@
-from datasets import load_dataset
+from datasets import load_dataset, DownloadManager
 import streamlit as st
+from inseq import FeatureAttributionOutput
 
 st.set_page_config(layout="wide")
 
 dataset = load_dataset("GroNLP/divemt")
+attribution_path = "https://huggingface.co/datasets/inseq/divemt_attributions/resolve/main/divemt-attributions/it/{idx}_it_gradl2_{setting}_{sentence_type}.json.gz"
 df = dataset["train"].to_pandas()
 unique_src = df[["item_id", "src_text"]].drop_duplicates(subset="item_id")
 langs = list(df["lang_id"].unique())
+dl = DownloadManager()
 
 st.title("DivEMT Explorer 🔍 🌍")
 st.markdown("""
@@ -81,4 +84,15 @@ for lang in langs:
             else:
                 st.text("MT : N/A\nPE : N/A\nEVAL: N/A\n")
             st.markdown(f"<b>Metadata</b>:", unsafe_allow_html=True)
-            st.json({k:v for k,v in dic.items() if k not in ["src_text", "mt_text", "tgt_text", "aligned_edit"]}, expanded=False)
+            st.json({k:v for k,v in dic.items() if k not in ["src_text", "mt_text", "tgt_text", "aligned_edit"]}, expanded=False)
+            if lang == "ita" and task_name != "From Scratch (HT)":
+                setting = "pe1" if task_name == "Google PE (PE1)" else "pe2"
+                st.markdown(f"<b>Attributions</b>:", unsafe_allow_html=True)
+                st.text("Click on checkboxes to show/hide the respective attributions computed with mBART 1-to-50.")
+                for sentence_type in ["mt", "pe", "diff"]:
+                    url = attribution_path.format(idx=item_id, setting=setting, sentence_type=sentence_type)
+                    file_path = dl.download(url)
+                    attr = FeatureAttributionOutput.load(file_path, decompress=True)
+                    if st.checkbox(sentence_type.upper(), key=f"{lang}_{task_name}_{sentence_type}"):
+                        st.markdown(f"{attr.show(return_html=True, display=False, do_aggregation=False)}", unsafe_allow_html=True)
+