app.py

import streamlit as st
import pandas as pd
import numpy as np
from sklearn.feature_selection import SelectKBest, f_classif
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import IsolationForest
from sklearn.decomposition import PCA
import nltk
from nltk.sentiment import SentimentIntensityAnalyzer
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from collections import Counter
import matplotlib.pyplot as plt

# Download necessary NLTK data
nltk.download('vader_lexicon')
nltk.download('punkt')
nltk.download('stopwords')

def main():
    st.title("AI in Data Science Demo")

    # Sidebar for navigation
    page = st.sidebar.selectbox("Choose a demo", ["Feature Engineering", "Anomaly Detection", "NLP Analysis"])

    if page == "Feature Engineering":
        feature_engineering_demo()
    elif page == "Anomaly Detection":
        anomaly_detection_demo()
    else:
        nlp_demo()

def feature_engineering_demo():
    st.header("Automated Feature Engineering and Selection")

    # Generate sample data
    X = np.random.rand(100, 5)
    y = np.random.randint(0, 2, 100)

    # Feature selection
    selector = SelectKBest(f_classif, k=3)
    X_new = selector.fit_transform(X, y)

    # PCA
    scaler = StandardScaler()
    X_scaled = scaler.fit_transform(X)
    pca = PCA(n_components=2)
    X_pca = pca.fit_transform(X_scaled)

    # Display results
    st.subheader("Original Features")
    st.write(pd.DataFrame(X, columns=[f"Feature {i+1}" for i in range(5)]).head())

    st.subheader("Selected Top 3 Features")
    st.write(pd.DataFrame(X_new, columns=[f"Selected Feature {i+1}" for i in range(3)]).head())

    st.subheader("PCA Transformation")
    st.write(pd.DataFrame(X_pca, columns=["PC1", "PC2"]).head())

    # Visualization
    fig, ax = plt.subplots()
    ax.scatter(X_pca[:, 0], X_pca[:, 1], c=y)
    ax.set_xlabel("First Principal Component")
    ax.set_ylabel("Second Principal Component")
    ax.set_title("PCA of Dataset")
    st.pyplot(fig)

def anomaly_detection_demo():
    st.header("Anomaly Detection")

    # Generate sample data with anomalies
    np.random.seed(42)
    X = np.random.randn(100, 2)
    X[-5:] = X[-5:] + [4, 4]  # Add some anomalies

    # Fit Isolation Forest
    clf = IsolationForest(contamination=0.1, random_state=42)
    y_pred = clf.fit_predict(X)

    # Visualization
    fig, ax = plt.subplots()
    ax.scatter(X[:, 0], X[:, 1], c=y_pred, cmap='viridis')
    ax.set_title("Anomaly Detection using Isolation Forest")
    ax.set_xlabel("Feature 1")
    ax.set_ylabel("Feature 2")
    st.pyplot(fig)

    st.write("Points in yellow are detected as anomalies.")

def nlp_demo():
    st.header("NLP Analysis")

    # Sample text input
    text = st.text_area("Enter text for analysis", "I love using AI for data analysis. It's exciting and powerful!")

    if text:
        # Sentiment Analysis
        sia = SentimentIntensityAnalyzer()
        sentiment = sia.polarity_scores(text)

        st.subheader("Sentiment Analysis")
        st.write(f"Positive: {sentiment['pos']:.2f}")
        st.write(f"Neutral: {sentiment['neu']:.2f}")
        st.write(f"Negative: {sentiment['neg']:.2f}")

        # Simple keyword extraction
        tokens = word_tokenize(text.lower())
        stop_words = set(stopwords.words('english'))
        keywords = [word for word in tokens if word.isalnum() and word not in stop_words]
        keyword_freq = Counter(keywords).most_common(5)

        st.subheader("Top Keywords")
        st.write(pd.DataFrame(keyword_freq, columns=["Keyword", "Frequency"]))

if __name__ == "__main__":
    main()