src/eda.py

import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
from PIL import Image

# =============================================
# Cache dataset agar tidak reload setiap kali
# =============================================
@st.cache_data
def load_data():
    df = pd.read_csv('./src/singapore_airlines_reviews.csv')
    return df

# Load dataset
df = load_data()

# =============================================
# Main app
# =============================================
def run():
    # Judul dan Subjudul
    st.title("ACRE - Automated Customer Review Analysis")
    st.subheader("Exploratory Data Analysis (EDA)")

    st.markdown(
        """
        This section provides an exploratory data analysis (EDA) of Singapore Airlines (SQ) customer reviews.  
        We aim to understand the distribution of ratings, textual review characteristics, and topic modeling results.  
        These insights serve as the foundation for building automated models that classify sentiment and uncover key themes 
        in customer feedback.
        """
    )

    # ===============================
    # Dataset Preview
    # ===============================
    st.write("### Dataset Preview")
    st.dataframe(df.head())

    # ===============================
    # Distribusi Rating
    # ===============================
    st.write("### Distribution of Ratings")
    fig, ax = plt.subplots(figsize=(8, 5))
    sns.countplot(x='rating', data=df, palette='viridis', ax=ax,
                  order=sorted(df['rating'].unique()))
    for p in ax.patches:
        height = p.get_height()
        ax.annotate(f'{height:,}', (p.get_x() + p.get_width()/2, height),
                    ha='center', va='bottom', fontsize=10, fontweight='bold')
    st.pyplot(fig)

    st.markdown(
        """
        **Note:** Ratings are explored here only as descriptive information about passenger experiences. 
        In the inference page, actual sentiment will be predicted automatically from the review text using NLP techniques.
        """
    )

    # ===============================
    # Analisis Panjang Teks
    # ===============================
    st.write("### Distribution of Review Length")
    df['text_length'] = df['text'].apply(lambda x: len(str(x).split()))
    fig = px.histogram(df, x='text_length', nbins=50, title='Review Length Distribution')
    st.plotly_chart(fig, use_container_width=True)

    # ===============================
    # Topic Modeling Results (Images)
    # ===============================
    st.write("## Topic Modeling Results")

    # 1. Top Words Distributions
    col1, col2 = st.columns(2)
    with col1:
        st.image("./src/Negative - Top Words Distributions.png", caption="Negative - Top Words Distributions")
    with col2:
        st.image("./src/Positive - Top Words Distributions.png", caption="Positive - Top Words Distributions")
    st.write("Lorem ipsum explanation for Top Words Distributions.")

    # 2. Topic Activities Over Time
    col1, col2 = st.columns(2)
    with col1:
        st.image("./src/Negative - Topic Activities Over Time.png", caption="Negative - Topic Activities Over Time")
    with col2:
        st.image("./src/Positive - Topic Activities Over Time.png", caption="Positive - Topic Activities Over Time")
    st.write("Lorem ipsum explanation for Topic Activities Over Time.")

    # 3. Topics Hierarchy
    # col1, col2 = st.columns(2)
    # with col1:
    #     st.image("./src/Negative - Topics Hierarchy.png", caption="Negative - Topics Hierarchy")
    # with col2:
    #     st.image("./src/Positive - Topics Hierarchy.png", caption="Positive - Topics Hierarchy")
    # st.write("Lorem ipsum explanation for Topics Hierarchy.")

    # 4. Topic Weights
    col1, col2 = st.columns(2)
    with col1:
        st.image("./src/Negative - Topics Weights.png", caption="Negative - Topic Weights")
    with col2:
        st.image("./src/Positive - Topics Weights.png", caption="Positive - Topic Weights")
    st.write("Lorem ipsum explanation for Topics Weights.")

# =============================================
# Run Script
# =============================================
if __name__ == '__main__':
    run()