Upload 2 files

main.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)

requirements.txt

@@ -0,0 +1,51 @@
+accelerate==1.6.0
+altair==5.5.0
+attrs==25.3.0
+blinker==1.9.0
+cachetools==5.5.2
+certifi==2025.1.31
+charset-normalizer==3.4.1
+click==8.1.8
+filelock==3.18.0
+fsspec==2025.3.2
+gitdb==4.0.12
+GitPython==3.1.44
+huggingface-hub==0.30.1
+idna==3.10
+Jinja2==3.1.6
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+MarkupSafe==3.0.2
+mpmath==1.3.0
+narwhals==1.33.0
+networkx==3.4.2
+numpy==2.2.4
+packaging==24.2
+pandas==2.2.3
+pillow==11.1.0
+protobuf==5.29.4
+psutil==7.0.0
+pyarrow==19.0.1
+pydeck==0.9.1
+python-dateutil==2.9.0.post0
+pytz==2025.2
+PyYAML==6.0.2
+referencing==0.36.2
+regex==2024.11.6
+requests==2.32.3
+rpds-py==0.24.0
+safetensors==0.5.3
+six==1.17.0
+smmap==5.0.2
+streamlit==1.44.1
+sympy==1.13.1
+tenacity==9.1.2
+tokenizers==0.21.1
+toml==0.10.2
+torch==2.6.0
+tornado==6.4.2
+tqdm==4.67.1
+transformers==4.51.0
+typing_extensions==4.13.1
+tzdata==2025.2
+urllib3==2.3.0