Upload 3 files

README.md

@@ -1,12 +1,12 @@
 ---
 title: CAS Biomedical POS Tagging
-emoji: 📈
+emoji: ⚕️
 colorFrom: indigo
-colorTo: yellow
+colorTo: indigo
 sdk: streamlit
-sdk_version: 1.17.0
+sdk_version: 1.2.0
 app_file: app.py
-pinned: false
+pinned: true
 license: apache-2.0
 ---
 

app.py

@@ -0,0 +1,54 @@
+from transformers import pipeline, AutoModelForTokenClassification, AutoTokenizer
+import sentencepiece
+import streamlit as st
+import pandas as pd
+
+text_1 = "ddd"
+
+text_2 = """ddd"""
+
+st.title("Demo for Biomedical POS Tagging in French with DrBERT")
+st.sidebar.write("Model : DrBERT-7GB base CAS corpus POS tagging")
+st.sidebar.write("For details of model: 'https://huggingface.co/Dr-BERT/DrBERT-7GB'")
+
+model_checkpoint = "Dr-BERT/DrBERT-7GB"
+aggregation = "simple"
+
+st.subheader("Select Text")
+context_1 = st.text_area("Text #1", text_1, height=128)
+context_2 = st.text_area("Text #2", text_2, height=128)
+context_3 = st.text_area("New Text", value="", height=128)
+
+context = st.radio("Select Text", ("Text #1", "Text #2", "New Text"))
+
+if context == "Text #1":
+    input_text = context_1
+elif context == "Text #2":
+    input_text = context_2
+elif context == "New Text":
+    input_text = context_3
+
+@st.cache(allow_output_mutation=True)
+def setModel(model_checkpoint, aggregation):
+    model = AutoModelForTokenClassification.from_pretrained(model_checkpoint)
+    tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
+    return pipeline('token-classification', model=model, tokenizer=tokenizer, aggregation_strategy=aggregation)
+        
+Run_Button = st.button("Run", key=None)
+if Run_Button == True:
+    
+    ner_pipeline = setModel(model_checkpoint, aggregation)
+    output = ner_pipeline(input_text)
+
+    df = pd.DataFrame.from_dict(output)
+
+    if aggregation != "none":
+        df.rename(index=str,columns={'entity_group':'POS Tag'},inplace=True)
+    else:
+        df.rename(index=str,columns={'entity_group':'POS Tag'},inplace=True)
+    
+    cols_to_keep = ['word','POS Tag','score','start','end']
+    df_final = df[cols_to_keep]
+    
+    st.subheader("POS Tags")
+    st.dataframe(df_final)

requirements.txt

@@ -0,0 +1,5 @@
+streamlit
+torch
+transformers
+pandas
+sentencepiece