ss.py

import pandas as pd
import streamlit as st 
import warnings
warnings.filterwarnings("ignore")

from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.pipeline import Pipeline
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import accuracy_score

# Load and clean data
df = pd.read_csv(r"C:\Users\91879\Downloads\New_emotions.csv")  
print(df.columns)  

df.drop_duplicates(inplace=True)

x = df["sentence"]
y = df["emotion"]

# Split data
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=29)

# Build model
model = Pipeline([
    ("vectorizer", CountVectorizer()),
    ("classifier", MultinomialNB(alpha=2))
])

model.fit(x, y)
y_predict = model.predict(x_test)

# Streamlit App
st.title("Emotion Detection from Text 👇")
st.write("Model Accuracy:", accuracy_score(y_test, y_predict))

# User input
sentence = st.text_input("Enter a sentence:")

if st.button("Predict Emotion"):
    if sentence:
        prediction = model.predict([sentence])[0]
        st.write("Predicted Emotion:", prediction)

        # Show emoji
        emojis = {
            "sad": "😢😢",
            "love": "❤️❤️",
            "surprise": "😦😦",
            "joy": "😂😂",
            "anger": "😠😠",
            "fear": "😨😨"
        }
        st.write("Emoji:", emojis.get(prediction, "🤔"))

        user_data = pd.DataFrame([[sentence, prediction]], columns=["sentence", "predicted_emotion"])
        st.write(user_data)