Spaces:
Runtime error
Runtime error
import sqlite3 | |
import pandas as pd | |
import streamlit as st | |
from transformers import pipeline | |
from sklearn.metrics import accuracy_score | |
# Load the data into a pandas dataframe | |
df = pd.read_csv('https://raw.githubusercontent.com/SrinidhiRaghavan/AI-Sentiment-Analysis-on-IMDB-Dataset/master/test/imdb_te.csv', encoding= 'unicode_escape') | |
# Create a connection to the database | |
conn = sqlite3.connect('movie_reviews.db') | |
# Add a column for the sentiment labels | |
df['sentiment'] = '' | |
# Load the data into a table | |
df.to_sql('movie_reviews', conn, if_exists='replace', index=False) | |
# Load the pre-trained sentiment analysis model | |
classifier = pipeline('sentiment-analysis') | |
# Extract sentiment labels for the movie reviews | |
reviews = conn.execute('SELECT text FROM movie_reviews limit 10') | |
for i, row in enumerate(reviews): | |
review = row[0] | |
sentiment = classifier(review[:512])[0]['label'] | |
if sentiment == 'POSITIVE': | |
label = 1 | |
else: | |
label = 0 | |
conn.execute('UPDATE movie_reviews SET sentiment = ? WHERE rowid = ?', (label, i+1)) | |
conn.commit() | |
def main(): | |
# Load the data from the SQLite database | |
X = pd.read_sql_query('SELECT text FROM movie_reviews limit 10', conn) | |
y = pd.read_sql_query('SELECT sentiment FROM movie_reviews limit 10', conn) | |
# Train a logistic regression model on the sentiment labels | |
clf = pipeline('sentiment-analysis') | |
y_pred = [int(result['label'] == 'POSITIVE') for result in clf(X['text'].to_list(), truncation=True)] | |
# Evaluate the model on the testing set | |
accuracy = accuracy_score(y['sentiment'].astype(int).to_list(), y_pred) | |
# Create a Streamlit app | |
st.title('Sentiment Analysis on Movie Reviews') | |
st.subheader('Accuracy') | |
st.write(f'{accuracy:.2f}') | |
st.subheader('Movie Reviews') | |
st.write(X) | |
st.subheader('Sentiment Labels') | |
st.write(y) | |
if __name__ == '__main__': | |
main() | |