Code Editor for app.py

import streamlit as st
import pandas as pd
import numpy as np
import plotly.express as px
import plotly.graph_objects as go

# Set page config
st.set_page_config(page_title="CSV Data Visualizer", layout="wide")

@st.cache_data
def load_data(url):
    """Load and cache CSV data from URL"""
    try:
        df = pd.read_csv(url)
        return df, None
    except Exception as e:
        return None, str(e)

def determine_column_type(series):
    """Determine if a column is numeric or categorical"""
    if pd.api.types.is_numeric_dtype(series):
        return 'numeric'
    else:
        return 'categorical'

def create_visualization(df, var1, var2=None):
    """Create appropriate visualization based on variable types"""
    if var2 is None:
        # Single variable visualization
        var_type = determine_column_type(df[var1])
        
        if var_type == 'numeric':
            # Histogram for numeric variables
            fig = px.histogram(df, x=var1, title=f'Distribution of {var1}')
        else:
            # Bar chart for categorical variables
            value_counts = df[var1].value_counts()
            fig = px.bar(x=value_counts.index, y=value_counts.values, 
                        title=f'Count of {var1}')
            fig.update_xaxis(title=var1)
            fig.update_yaxis(title='Count')
    else:
        # Two variable visualization
        var1_type = determine_column_type(df[var1])
        var2_type = determine_column_type(df[var2])
        
        if var1_type == 'numeric' and var2_type == 'numeric':
            # Scatter plot for two numeric variables
            fig = px.scatter(df, x=var1, y=var2, title=f'{var1} vs {var2}')
        elif var1_type == 'categorical' and var2_type == 'numeric':
            # Box plot for categorical vs numeric
            fig = px.box(df, x=var1, y=var2, title=f'{var2} by {var1}')
        elif var1_type == 'numeric' and var2_type == 'categorical':
            # Box plot for numeric vs categorical (swap axes)
            fig = px.box(df, x=var2, y=var1, title=f'{var1} by {var2}')
        else:
            # Stacked bar chart for two categorical variables
            crosstab = pd.crosstab(df[var1], df[var2])
            fig = px.bar(crosstab, title=f'{var1} vs {var2}')
    
    return fig

# Main app
st.title("📊 CSV Data Visualizer")
st.markdown("Load CSV data from a URL and create interactive visualizations")

# Sidebar controls
st.sidebar.header("Data Controls")

# URL input
url = st.sidebar.text_input(
    "CSV URL:", 
    value="https://raw.githubusercontent.com/mwaskom/seaborn-data/master/penguins.csv",
    help="Enter the URL of a CSV file"
)

# Load data
if url:
    df, error = load_data(url)
    
    if error:
        st.error(f"Error loading data: {error}")
        st.stop()
    
    if df is not None and not df.empty:
        st.sidebar.success(f"✅ Data loaded: {df.shape[0]} rows, {df.shape[1]} columns")
        
        # Display controls
        max_rows = st.sidebar.slider(
            "Number of rows to display:", 
            min_value=1, 
            max_value=len(df), 
            value=min(100, len(df))
        )
        
        shuffle_data = st.sidebar.checkbox("Randomly shuffle data", value=False)
        
        # Prepare display data
        display_df = df.copy()
        if shuffle_data:
            display_df = display_df.sample(frac=1).reset_index(drop=True)
        display_df = display_df.head(max_rows)
        
        # Main content area
        col1, col2 = st.columns([2, 1])
        
        with col1:
            st.subheader("📋 Data Preview")
            st.dataframe(display_df, use_container_width=True)
        
        with col2:
            st.subheader("📈 Visualization Controls")
            
            # Variable selection
            columns = df.columns.tolist()
            
            var1 = st.selectbox("Select first variable:", columns, index=0)
            
            use_second_var = st.checkbox("Use second variable")
            var2 = None
            if use_second_var:
                remaining_cols = [col for col in columns if col != var1]
                if remaining_cols:
                    var2 = st.selectbox("Select second variable:", remaining_cols)
            
            # Create visualization button
            if st.button("📊 Create Visualization", type="primary"):
                if var1:
                    fig = create_visualization(df, var1, var2)
                    st.plotly_chart(fig, use_container_width=True)
        
        # Data info
        st.subheader("ℹ️ Dataset Information")
        info_col1, info_col2, info_col3 = st.columns(3)
        
        with info_col1:
            st.metric("Total Rows", df.shape[0])
        with info_col2:
            st.metric("Total Columns", df.shape[1])
        with info_col3:
            st.metric("Displayed Rows", len(display_df))
        
        # Column information
        st.subheader("📋 Column Information")
        col_info = []
        for col in df.columns:
            dtype = str(df[col].dtype)
            null_count = df[col].isnull().sum()
            unique_count = df[col].nunique()
            col_info.append({
                'Column': col,
                'Data Type': dtype,
                'Null Values': null_count,
                'Unique Values': unique_count
            })
        
        col_info_df = pd.DataFrame(col_info)
        st.dataframe(col_info_df, use_container_width=True)
        
    else:
        st.warning("No data found in the CSV file.")
else:
    st.info("👆 Please enter a CSV URL in the sidebar to get started.")