pip install transformers

.\venv\Scripts\activate  # Windows

import streamlit as st
from transformers import pipeline, TFAutoModelForSequenceClassification, AutoTokenizer
from datasets import load_dataset
import pandas as pd

st.set_page_config(layout="wide")

# Load dataset
@st.cache_resource
def load_data():
    dataset = load_dataset("WhiteAngelss/Turkce-Duygu-Analizi-Dataset")
    return dataset

dataset = load_data()
st.title("Sentiment Analysis with Turkish Dataset")

# Show dataset examples
st.subheader("Sample Data")
sample_df = pd.DataFrame(dataset['train'])
st.write(sample_df.head())

# Set up model
model_list = ['WhiteAngelss/entity-word-sentiment-analysis']
st.sidebar.header("Select Sentiment Analysis Model")
model_checkpoint = st.sidebar.radio("", model_list)

st.sidebar.write("For details of models: 'https://huggingface.co/WhiteAngelss/entity-word-sentiment-analysis'")
st.sidebar.write("")

st.subheader("Select Text Input Method")
input_method = st.radio("", ('Select from Examples', 'Write or Paste New Text'))

if input_method == 'Select from Examples':
    example_texts = dataset['train']['text'][:5]  # Sample examples from the dataset
    selected_text = st.selectbox('Select Text from List', example_texts)
    st.subheader("Text to Analyze")
    input_text = st.text_area("Selected Text", selected_text, height=128, max_chars=None)
elif input_method == "Write or Paste New Text":
    st.subheader("Text to Analyze")
    input_text = st.text_area('Write or Paste Text Below', value="", height=128, max_chars=None)

@st.cache_resource
def setModel(model_checkpoint):
    model = TFAutoModelForSequenceClassification.from_pretrained(model_checkpoint)
    tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
    return pipeline('sentiment-analysis', model=model, tokenizer=tokenizer)

Run_Button = st.button("Run")

if Run_Button and input_text:
    sentiment_pipeline = setModel(model_checkpoint)
    output = sentiment_pipeline(input_text)
    
    st.subheader("Sentiment Analysis Results")
    df = pd.DataFrame(output)
    st.dataframe(df)

    # Display the sentiment in a more user-friendly format
    sentiment = output[0]['label']
    score = output[0]['score']
    st.write(f"Sentiment: {sentiment} (Score: {score:.2f})")