| import streamlit as st |
| import pandas as pd |
| import torch |
| from transformers import AutoTokenizer, AutoModelForSequenceClassification |
| import matplotlib.pyplot as plt |
|
|
| |
| model_name = "tabularisai/multilingual-sentiment-analysis" |
| tokenizer = AutoTokenizer.from_pretrained(model_name) |
| model = AutoModelForSequenceClassification.from_pretrained(model_name) |
|
|
| def predict_sentiment(texts): |
| inputs = tokenizer(texts, return_tensors="pt", truncation=True, padding=True, max_length=512) |
| with torch.no_grad(): |
| outputs = model(**inputs) |
| probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1) |
| sentiment_map = {0: "Very Negative", 1: "Negative", 2: "Neutral", 3: "Positive", 4: "Very Positive"} |
| return [sentiment_map[p] for p in torch.argmax(probabilities, dim=-1).tolist()] |
|
|
| |
| st.title("Sentiment Analysis App") |
| st.write("Upload an Excel file containing text data, and we'll analyze its sentiment.") |
|
|
| uploaded_file = st.file_uploader("Upload Excel File", type=["xlsx", "xls"]) |
|
|
| if uploaded_file is not None: |
| df = pd.read_excel(uploaded_file) |
| st.write("Preview of Uploaded Data:") |
| st.dataframe(df.head()) |
| |
| text_column = st.selectbox("Select the column containing text", df.columns) |
| |
| if st.button("Analyze Sentiment"): |
| df["Sentiment"] = predict_sentiment(df[text_column].astype(str).tolist()) |
| |
| |
| st.write("Sentiment Analysis Results:") |
| st.dataframe(df[[text_column, "Sentiment"]]) |
| |
| |
| sentiment_counts = df["Sentiment"].value_counts() |
| fig, ax = plt.subplots() |
| ax.pie(sentiment_counts, labels=sentiment_counts.index, autopct='%1.1f%%', colors=["red", "yellow", "blue", "lightgreen", "green"]) |
| ax.set_title("Sentiment Distribution") |
| st.pyplot(fig) |
| |
| |
| st.write("Detailed Sentiment Table:") |
| st.table(df[[text_column, "Sentiment"]]) |
| |
| |
| st.download_button("Download Results", df.to_csv(index=False).encode('utf-8'), "sentiment_results.csv", "text/csv") |
