Spaces:
Sleeping
Sleeping
File size: 3,229 Bytes
391f85f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 |
# Module 1: Import necessary packages
import streamlit as st
import numpy as np
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
from sklearn.svm import LinearSVC
from sklearn.naive_bayes import MultinomialNB
import warnings
import streamlit_lottie
warnings.filterwarnings("ignore")
# Set page configuration (must be the first Streamlit command)
page_icon = ":metro:" # emojis: https://www.webfx.com/tools/emoji-cheat-sheet/
layout = "wide"
page_title = "Fake News Detection"
st.set_page_config(page_title=page_title, page_icon=page_icon, layout=layout)
# Module 2: Load the dataset
@st.cache_data
def load_data():
data = pd.read_csv("fake_or_real_news.csv")
data['fake'] = data['label'].apply(lambda x: 0 if x == 'REAL' else 1)
return data
# Module 3: Select Vectorizer and Classifier
def select_model():
vectorizer_type = st.sidebar.selectbox("Select Vectorizer", ["TF-IDF", "Bag of Words"])
classifier_type = st.sidebar.selectbox("Select Classifier", ["Linear SVM", "Naive Bayes"])
vectorizer = None
if vectorizer_type == "TF-IDF":
vectorizer = TfidfVectorizer(stop_words='english', max_df=0.7)
elif vectorizer_type == "Bag of Words":
vectorizer = CountVectorizer(stop_words='english', max_df=0.7)
classifier = None
if classifier_type == "Linear SVM":
classifier = LinearSVC()
elif classifier_type == "Naive Bayes":
classifier = MultinomialNB()
return vectorizer, classifier
# Module 4: Train the model (no caching here)
def train_model(data, vectorizer, classifier):
x_vectorized = vectorizer.fit_transform(data['text'])
clf = classifier.fit(x_vectorized, data['fake'])
return clf
# Module 5: Streamlit app
def main():
# Streamlit app
st.title(page_title + " " + page_icon)
st.lottie("https://lottie.host/bd0c4818-c5a6-4e42-b407-746bc448c2c7/ipVUdgFncO.json", width=200, height=200)
# --- HIDE STREAMLIT STYLE ---
hide_st_style = """
<style>
#MainMenu {visibility: hidden;}
footer {visibility: hidden;}
header {visibility: hidden;}
</style>
"""
st.markdown(hide_st_style, unsafe_allow_html=True)
# Load data
data = load_data()
# Select vectorizer and classifier
vectorizer, classifier = select_model()
# Text input for user to input news article
user_input = st.text_area("Enter your news article here:")
# When user submits the input
if st.button("Check"):
# Train the model
clf = train_model(data, vectorizer, classifier)
# Vectorize the user input
input_vectorized = vectorizer.transform([user_input])
# Predict the label of the input
prediction = clf.predict(input_vectorized)
# Convert prediction to integer for interpretation
result = int(prediction[0])
# Display the result
if result == 1:
st.error("This news article is likely fake!")
else:
st.success("This news article seems to be real.")
# Run the Streamlit app
if __name__ == "__main__":
main()
st.markdown("**Created with enthusiasm by SuperSam**")
|