streamlit_app.py

import streamlit as st
import pandas as pd
import io
from utils import load_csv, get_file_info, filter_dataframe

# Set page config
st.set_page_config(
    page_title="CSV Viewer",
    page_icon="📊",
    layout="wide"
)

# Custom CSS for better styling
st.markdown("""
    <style>
    .main-header {
        font-size: 2.5rem;
        font-weight: bold;
        color: #1f77b4;
        text-align: center;
        margin-bottom: 1rem;
    }
    .sub-header {
        font-size: 1.2rem;
        color: #666;
        text-align: center;
        margin-bottom: 2rem;
    }
    .file-info {
        background-color: #f0f2f6;
        padding: 1rem;
        border-radius: 0.5rem;
        margin-bottom: 1rem;
    }
    .anycoder-link {
        position: fixed;
        bottom: 10px;
        right: 10px;
        font-size: 0.8rem;
        color: #666;
    }
    </style>
""", unsafe_allow_html=True)

def main():
    # Header
    st.markdown('<div class="main-header">CSV Viewer</div>', unsafe_allow_html=True)
    st.markdown('<div class="sub-header">Upload and explore your CSV files with ease</div>', unsafe_allow_html=True)

    # Anycoder attribution
    st.markdown('<div class="anycoder-link">Built with <a href="https://huggingface.co/spaces/akhaliq/anycoder" target="_blank">anycoder</a></div>', unsafe_allow_html=True)

    # File uploader
    uploaded_file = st.file_uploader(
        "Choose a CSV file",
        type=["csv"],
        help="Upload a CSV file to view and analyze its contents"
    )

    if uploaded_file is not None:
        try:
            # Load the CSV file
            df = load_csv(uploaded_file)

            # Display file info
            file_info = get_file_info(df, uploaded_file.name)
            st.markdown(f"""
                <div class="file-info">
                    <strong>File:</strong> {file_info['filename']}<br>
                    <strong>Rows:</strong> {file_info['rows']}<br>
                    <strong>Columns:</strong> {file_info['columns']}<br>
                    <strong>Size:</strong> {file_info['size']}
                </div>
            """, unsafe_allow_html=True)

            # Create tabs for different views
            tab1, tab2, tab3 = st.tabs(["📊 Data View", "📈 Statistics", "🔍 Filter"])

            with tab1:
                st.subheader("Data Preview")
                # Display options
                col1, col2 = st.columns(2)
                with col1:
                    rows_to_show = st.slider(
                        "Number of rows to display",
                        min_value=5,
                        max_value=min(100, len(df)),
                        value=min(10, len(df))
                    )
                with col2:
                    show_columns = st.multiselect(
                        "Select columns to display",
                        options=df.columns.tolist(),
                        default=df.columns.tolist()
                    )

                # Display the dataframe
                if show_columns:
                    st.dataframe(
                        df[show_columns].head(rows_to_show),
                        use_container_width=True,
                        height=400
                    )
                else:
                    st.warning("Please select at least one column to display")

                # Download button
                csv = df.to_csv(index=False).encode('utf-8')
                st.download_button(
                    label="Download CSV",
                    data=csv,
                    file_name="filtered_data.csv",
                    mime="text/csv"
                )

            with tab2:
                st.subheader("Data Statistics")
                if st.checkbox("Show summary statistics"):
                    st.dataframe(df.describe(), use_container_width=True)

                if st.checkbox("Show data types"):
                    st.write(df.dtypes)

                if st.checkbox("Show missing values"):
                    missing_values = df.isnull().sum()
                    st.write(missing_values[missing_values > 0])

            with tab3:
                st.subheader("Filter Data")
                st.write("Filter your data based on column values")

                # Column selection for filtering
                filter_column = st.selectbox(
                    "Select column to filter",
                    options=df.columns.tolist()
                )

                if filter_column:
                    # Get unique values for the selected column
                    unique_values = df[filter_column].unique()

                    if len(unique_values) > 20:
                        st.warning("This column has many unique values. Consider using a different filter method.")
                        filter_method = st.radio(
                            "Filter method",
                            ["Range", "Contains"]
                        )

                        if filter_method == "Range":
                            min_val = st.number_input(
                                "Minimum value",
                                value=float(df[filter_column].min())
                            )
                            max_val = st.number_input(
                                "Maximum value",
                                value=float(df[filter_column].max())
                            )

                            if st.button("Apply Filter"):
                                filtered_df = filter_dataframe(df, filter_column, min_val, max_val)
                                st.dataframe(filtered_df, use_container_width=True)
                        else:
                            search_term = st.text_input("Contains text")
                            if st.button("Apply Filter"):
                                filtered_df = df[df[filter_column].astype(str).str.contains(search_term, case=False, na=False)]
                                st.dataframe(filtered_df, use_container_width=True)
                    else:
                        selected_values = st.multiselect(
                            "Select values to include",
                            options=unique_values
                        )

                        if st.button("Apply Filter"):
                            filtered_df = df[df[filter_column].isin(selected_values)]
                            st.dataframe(filtered_df, use_container_width=True)

        except Exception as e:
            st.error(f"Error processing file: {str(e)}")

if __name__ == "__main__":
    main()