sentiment_analysis_app.py

pip install streamlit pandas numpy scikit-learn nltk
import streamlit as st
import pandas as pd
import numpy as np
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
import re
from nltk.corpus import stopwords
from nltk.stem import SnowballStemmer

# Download NLTK resources
import nltk
nltk.download('stopwords')

# Load stopwords
stopword = set(stopwords.words('english'))

# Load dataset
data = pd.read_csv("https://raw.githubusercontent.com/amankharwal/Website-data/master/twitter.csv")

# Map labels
data["labels"] = data["class"].map({0: "Hate Speech",
                                    1: "Offensive Language",
                                    2: "No Hate and Offensive"})

# Select relevant columns
data = data[["tweet", "labels"]]

# Clean text function
stemmer = SnowballStemmer("english")
def clean(text):
    text = str(text).lower()
    text = re.sub('\[.*?\]', '', text)
    text = re.sub('https?://\S+|www\.\S+', '', text)
    text = re.sub('<.*?>+', '', text)
    text = re.sub('[%s]' % re.escape(string.punctuation), '', text)
    text = re.sub('\n', '', text)
    text = re.sub('\w*\d\w*', '', text)
    text = [word for word in text.split(' ') if word not in stopword]
    text = " ".join(text)
    text = [stemmer.stem(word) for word in text.split(' ')]
    text = " ".join(text)
    return text

# Apply text cleaning
data["tweet"] = data["tweet"].apply(clean)

# Prepare data for model
x = np.array(data["tweet"])
y = np.array(data["labels"])

cv = CountVectorizer()
X = cv.fit_transform(x)  # Fit the Data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)

# Train the model
clf = DecisionTreeClassifier()
clf.fit(X_train, y_train)

# Streamlit app
st.title("Sentiment Analysis App")

# User input
sample = st.text_area("Enter a sentence for sentiment analysis:")

# Predict and display result
if st.button("Predict"):
    sample_cleaned = clean(sample)
    data_sample = cv.transform([sample_cleaned]).toarray()
    prediction = clf.predict(data_sample)[0]
    st.success(f"Sentiment: {prediction}")

# Display dataset
st.subheader("Dataset")
st.write(data.head())
streamlit run sentiment_analysis_app.py