Upload app.py

app.py

@@ -0,0 +1,54 @@
+import streamlit as  st
+from transformers import pipeline, AutoTokenizer
+import pandas as pd
+
+@st.cache_resource
+def load_model():
+    tokenizer = AutoTokenizer.from_pretrained('FedorX8/arxiv-classification-bert-uncased')
+    return pipeline(task='text-classification', model="FedorX8/arxiv-classification-bert-uncased", tokenizer=tokenizer, return_all_scores=True)
+
+def get_top_p(result, top_p=0.95):
+    result = sorted(result, key=lambda x: x['score'], reverse=True)
+    prob_sum = 0
+    classes = []
+    probs = []
+    for elem in result:
+        score = elem['score']
+        label = elem['label']
+        if prob_sum < top_p:
+            prob_sum += score
+            probs.append(score)
+            classes.append(label)
+    return classes, probs
+
+
+st_model = load_model()
+
+st.header('Web interface for arXiv articles classification')
+
+# Создание раскрывающегося текста
+expander = st.expander("Click to read description of possible classes")
+expander.markdown("""
+1. math.AC — Commutative Algebra
+2. cs.CV — Computer Vision and Pattern Recognition
+3. cs.AI — Artificial Intelligence
+4. cs.SY — Systems and Control
+5. math.GR — Group Theory
+6. cs.CE — Computational Engineering, Finance, and Science
+7. cs.PL — Programming Languages
+8. cs.IT — Information Theory
+9. cs.DS — Data Structures and Algorithms
+10. cs.NE — Neural and Evolutionary Computing
+11. math.ST — Statistics Theory
+""")
+
+query = st.text_input("Enter the text of the papper", value="AI")
+if query:
+    result = st_model(query)
+    classes, probs = get_top_p(result[0])
+    data_dict = {
+        "classes": classes,
+        "probabilites": probs
+    }
+    df = pd.DataFrame(data_dict)
+    st.write(df)