Spaces:
Running
Running
import streamlit as st | |
import pandas as pd | |
import matplotlib.pyplot as plt | |
from textblob import TextBlob | |
def load_data(uploaded_file): | |
# Load Excel file, supports both .xlsx and .xls | |
try: | |
df = pd.read_excel(uploaded_file) # Automatically detects file format | |
df.columns = df.columns.str.strip().str.lower() # Normalize column names | |
return df | |
except Exception as e: | |
st.error(f"Error loading file: {e}") | |
return None | |
def analyze_sentiment(text): | |
polarity = TextBlob(str(text)).sentiment.polarity | |
if polarity >= 0.6: | |
return "Very Positive" | |
elif polarity >= 0.2: | |
return "Positive" | |
elif polarity > -0.2: | |
return "Neutral" | |
elif polarity > -0.6: | |
return "Negative" | |
else: | |
return "Very Negative" | |
st.title("Sentiment Analysis with Pie Chart") | |
# File uploader supports .xlsx and .xls | |
uploaded_file = st.file_uploader("Upload an Excel file with text data", type=["xlsx", "xls"]) | |
if uploaded_file is not None: | |
df = load_data(uploaded_file) | |
if df is not None: | |
st.write("Columns in your file:", df.columns.tolist()) | |
# Allow the user to select a column if 'text' is not already present | |
if "text" not in df.columns: | |
selected_column = st.selectbox("Select the column to use as text data:", df.columns) | |
if st.button("Confirm Selection"): | |
df.rename(columns={selected_column: "text"}, inplace=True) | |
st.success(f"Column '{selected_column}' renamed to 'text'.") | |
if "text" in df.columns: # Check again if 'text' column is present after renaming | |
df["Sentiment"] = df["text"].apply(analyze_sentiment) | |
st.write("Here is a preview of the data:") | |
st.write(df.head()) | |
sentiment_counts = df["Sentiment"].value_counts() | |
fig, ax = plt.subplots() | |
ax.pie(sentiment_counts, labels=sentiment_counts.index, autopct="%1.1f%%", colors=["green", "lightgreen", "gray", "orange", "red"]) | |
ax.set_title("Sentiment Distribution") | |
st.pyplot(fig) | |
# Export processed data to Excel file (.xlsx) without explicitly using xlsxwriter | |
output_file = "sentiment_results.xlsx" | |
df.to_excel(output_file, index=False, sheet_name="Sentiment Analysis") | |
# Download button for Excel file | |
with open(output_file, "rb") as f: | |
st.download_button( | |
"Download Sentiment Data (Excel)", | |
f, | |
"sentiment_results.xlsx", | |
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", | |
) | |
else: | |
st.warning("Please select a column to rename as 'text' and proceed.") | |
else: | |
st.write("Please upload an Excel file to get started.") |