src/streamlit_app.py

'''

import altair as alt
import numpy as np
import pandas as pd
import streamlit as st

"""
# Welcome to Streamlit!

Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
forums](https://discuss.streamlit.io).

In the meantime, below is an example of what you can do with just a few lines of code:
"""

num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
num_turns = st.slider("Number of turns in spiral", 1, 300, 31)

indices = np.linspace(0, 1, num_points)
theta = 2 * np.pi * num_turns * indices
radius = indices

x = radius * np.cos(theta)
y = radius * np.sin(theta)

df = pd.DataFrame({
    "x": x,
    "y": y,
    "idx": indices,
    "rand": np.random.randn(num_points),
})

st.altair_chart(alt.Chart(df, height=700, width=700)
    .mark_point(filled=True)
    .encode(
        x=alt.X("x", axis=None),
        y=alt.Y("y", axis=None),
        color=alt.Color("idx", legend=None, scale=alt.Scale()),
        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
    ))

'''

import streamlit as st
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
import torch.nn.functional as F
import os

st.set_page_config(page_title="FinBERT Sentiment", layout="centered")
st.title("💰 FinBERT: Financial Sentiment Analysis")
st.markdown("Модель: `yiyanghkust/finbert-tone` — обучена на финансовых текстах")

@st.cache_resource
def load_model():
    # Установка кастомного пути к кэшу
    cache_dir = "/tmp/huggingface"
    os.makedirs(cache_dir, exist_ok=True)

    tokenizer = AutoTokenizer.from_pretrained("yiyanghkust/finbert-tone", cache_dir=cache_dir)
    model = AutoModelForSequenceClassification.from_pretrained("yiyanghkust/finbert-tone", cache_dir=cache_dir)
    return tokenizer, model

tokenizer, model = load_model()

text = st.text_area("Введите финансовую новость или отчёт:", height=150)

if st.button("Анализировать тональность") and text.strip():
    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
    with torch.no_grad():
        outputs = model(**inputs)
        probs = F.softmax(outputs.logits, dim=1).squeeze()

    labels = ["📉 Negative", "😐 Neutral", "📈 Positive"]
    for label, prob in zip(labels, probs):
        st.write(f"**{label}:** {prob.item():.3f}")