Code Editor for app.py

import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np

# Set page title
st.title("CSV Data Visualizer")

# Input for CSV URL
url = st.text_input(
    "Enter CSV URL:",
    value="https://raw.githubusercontent.com/mwaskom/seaborn-data/master/penguins.csv"
)

# Function to load data with caching
@st.cache_data
def load_data(url):
    try:
        data = pd.read_csv(url)
        return data
    except Exception as e:
        st.error(f"Error loading data: {e}")
        return None

# Load data
if url:
    data = load_data(url)
    
    if data is not None:
        # Display data info
        st.write(f"Dataset has {data.shape[0]} rows and {data.shape[1]} columns")
        
        # Controls for data display
        col1, col2 = st.columns(2)
        
        with col1:
            num_rows = st.slider("Number of rows to display", 
                                min_value=1, 
                                max_value=min(100, len(data)), 
                                value=min(10, len(data)))
        
        with col2:
            shuffle = st.checkbox("Randomly shuffle data")
        
        # Process data based on controls
        display_data = data.copy()
        if shuffle:
            display_data = display_data.sample(frac=1, random_state=42).reset_index(drop=True)
        
        # Display dataframe
        st.subheader("Data Preview")
        st.dataframe(display_data.head(num_rows))
        
        # Variable selection for visualization
        st.subheader("Data Visualization")
        
        # Get numeric and categorical columns
        numeric_cols = data.select_dtypes(include=['int64', 'float64']).columns.tolist()
        categorical_cols = data.select_dtypes(include=['object', 'category']).columns.tolist()
        all_cols = numeric_cols + categorical_cols
        
        # Select variables for visualization
        col1, col2 = st.columns(2)
        with col1:
            var1 = st.selectbox("Select first variable", all_cols)
        with col2:
            remaining_cols = [col for col in all_cols if col != var1]
            var2 = st.selectbox("Select second variable (optional)", 
                               options=["None"] + remaining_cols,
                               index=0)
        
        # Determine the best visualization based on selected variables
        if var2 == "None":
            # Single variable visualization
            st.subheader(f"Visualization of {var1}")
            
            fig, ax = plt.subplots(figsize=(10, 6))
            
            if var1 in numeric_cols:
                # For numeric variables, show histogram and KDE
                sns.histplot(data=data, x=var1, kde=True, ax=ax)
                st.pyplot(fig)
                
                # Also show basic statistics
                st.write(f"**Statistics for {var1}:**")
                stats = data[var1].describe()
                st.write(stats)
                
            else:
                # For categorical variables, show count plot
                sns.countplot(data=data, y=var1, ax=ax)
                plt.tight_layout()
                st.pyplot(fig)
                
                # Also show value counts
                st.write(f"**Value counts for {var1}:**")
                st.write(data[var1].value_counts())
                
        else:
            # Two variables visualization
            st.subheader(f"Visualization of {var1} vs {var2}")
            
            fig, ax = plt.subplots(figsize=(10, 6))
            
            # Both numeric
            if var1 in numeric_cols and var2 in numeric_cols:
                # Scatter plot for two numeric variables
                sns.scatterplot(data=data, x=var1, y=var2, ax=ax)
                
                # Add regression line
                sns.regplot(data=data, x=var1, y=var2, scatter=False, ax=ax)
                
                # Calculate and display correlation
                correlation = data[[var1, var2]].corr().iloc[0, 1]
                st.write(f"Correlation between {var1} and {var2}: {correlation:.4f}")
            
            # One numeric, one categorical
            elif (var1 in numeric_cols and var2 in categorical_cols) or (var1 in categorical_cols and var2 in numeric_cols):
                # Determine which is which
                num_var = var1 if var1 in numeric_cols else var2
                cat_var = var2 if var2 in categorical_cols else var1
                
                # Box plot for numeric vs categorical
                sns.boxplot(data=data, x=cat_var, y=num_var, ax=ax)
                plt.xticks(rotation=45)
            
            # Both categorical
            else:
                # Heatmap of counts for two categorical variables
                cross_tab = pd.crosstab(data[var1], data[var2])
                sns.heatmap(cross_tab, annot=True, fmt="d", cmap="YlGnBu", ax=ax)
            
            plt.tight_layout()
            st.pyplot(fig)
    else:
        st.warning("Please enter a valid CSV URL")
else:
    st.info("Enter a CSV URL to get started")