Add app

app.py

@@ -0,0 +1,67 @@
+import json
+import os
+import random
+import pandas as pd
+import streamlit as st
+from transformers import AutoModelForSequenceClassification,AutoTokenizer,pipeline
+from transformers_interpret import SequenceClassificationExplainer
+
+@st.cache
+def load_model(text):
+    
+
+    checkpoint = 'mlkorra/OGBV-gender-bert-hi-en'
+
+    tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+    model = AutoModelForSequenceClassification.from_pretrained(checkpoint)
+
+    nlp = pipeline('sentiment-analysis',model=model,tokenizer=tokenizer)
+
+  
+    results = nlp(text)
+    
+    return results
+    #MASK_TOKEN = tokenizer.mask_token
+    #masked_text = masked_text.replace("<mask>", MASK_TOKEN)
+    #result_sentence = nlp(masked_text)
+    #return result_sentence[0]["sequence"], result_sentence[0]["token_str"]
+
+def app():
+    st.title("OGBV-BERT")
+    #st.markdown("This demo uses multiple hindi transformer models for Masked Language Modelling (MLM).")
+    #models_list = list(cfg["models"].keys())
+    #models = st.multiselect("Choose models", models_list, models_list)
+    
+    target_text_path = "./input/tweet_list.csv"
+    target_text_df = pd.read_csv(target_text_path)
+    texts = target_text_df["text"]
+    st.sidebar.title("Place")
+    pick_random = st.sidebar.checkbox("Pick any random text")
+    
+    #results_df = pd.DataFrame(columns=["Model Name", "Filled Token", "Filled Text"])
+    #model_names = []
+    ##filled_masked_texts = []
+    #filled_tokens = []
+    if pick_random:
+        random_text = texts[random.randint(0, texts.shape[0] - 1)]
+        masked_text = st.text_area("Please type a sentence to classify", random_text)
+    else:
+        select_text = st.sidebar.selectbox("Select any of the following text", texts)
+        masked_text = st.text_area("Please type a sentence to classify", select_text)
+    
+    
+    # pd.set_option('max_colwidth',30)
+    if st.button("Classify"):
+        with st.spinner("Classifying the sentence..."):
+            pred = load_model(masked_text)
+            st.write(pred)
+
+            # for selected_model in models:
+            #     filled_sentence, filled_token = load_model(masked_text, cfg["models"][selected_model])
+            #     model_names.append(selected_model)
+            #     filled_tokens.append(filled_token)
+            #     filled_masked_texts.append(filled_sentence)
+            # results_df["Model Name"] = model_names
+            # results_df["Filled Token"] = filled_tokens
+            # results_df["Filled Text"] = filled_masked_texts
+            # st.table(results_df)

requirements.txt

@@ -0,0 +1,3 @@
+torch   
+transformers==4.10.0
+transformers_interpret