Code Editor for app.py

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

# Set page title
st.title("Penguin Data Viewer and Visualizer")

# URL input with default value
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:
        return pd.read_csv(url)
    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 loaded with {data.shape[0]} rows and {data.shape[1]} columns")
        
        # Controls section
        st.subheader("Data Controls")
        
        col1, col2 = st.columns(2)
        
        with col1:
            # Number of rows to display
            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:
            # Option to shuffle data
            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 the dataframe
        st.subheader("Data Preview")
        st.dataframe(display_data.head(num_rows))
        
        # Visualization section
        st.subheader("Data Visualization")
        
        # Get numerical and categorical columns for selection
        numeric_cols = data.select_dtypes(include=np.number).columns.tolist()
        categorical_cols = data.select_dtypes(exclude=np.number).columns.tolist()
        all_cols = data.columns.tolist()
        
        # Variable selection
        st.write("Select variables to visualize:")
        
        col1, col2 = st.columns(2)
        
        with col1:
            var1 = st.selectbox("Variable 1", options=all_cols, index=0)
        
        with col2:
            var2 = st.selectbox("Variable 2", options=[None] + all_cols, index=0)
        
        # Determine visualization type based on variable types
        if var2 is None:
            # Single variable visualization
            if var1 in numeric_cols:
                st.subheader(f"Distribution of {var1}")
                fig, ax = plt.subplots(figsize=(10, 6))
                sns.histplot(data=data, x=var1, kde=True, ax=ax)
                st.pyplot(fig)
                
                st.write(f"Summary statistics for {var1}:")
                st.write(data[var1].describe())
            else:
                st.subheader(f"Count of {var1} categories")
                fig, ax = plt.subplots(figsize=(10, 6))
                sns.countplot(data=data, x=var1, ax=ax)
                plt.xticks(rotation=45)
                st.pyplot(fig)
                
                st.write(f"Value counts for {var1}:")
                st.write(data[var1].value_counts())
        else:
            # Two-variable visualization
            if var1 in numeric_cols and var2 in numeric_cols:
                # Numeric vs Numeric -> Scatter plot
                st.subheader(f"Relationship between {var1} and {var2}")
                fig, ax = plt.subplots(figsize=(10, 6))
                sns.scatterplot(data=data, x=var1, y=var2, ax=ax)
                st.pyplot(fig)
                
                # Also show correlation
                corr = data[[var1, var2]].corr().iloc[0, 1]
                st.write(f"Correlation between {var1} and {var2}: {corr:.4f}")
                
            elif var1 in numeric_cols and var2 in categorical_cols:
                # Numeric vs Categorical -> Box plot
                st.subheader(f"Distribution of {var1} by {var2}")
                fig, ax = plt.subplots(figsize=(10, 6))
                sns.boxplot(data=data, x=var2, y=var1, ax=ax)
                plt.xticks(rotation=45)
                st.pyplot(fig)
                
            elif var1 in categorical_cols and var2 in numeric_cols:
                # Categorical vs Numeric -> Box plot (reversed)
                st.subheader(f"Distribution of {var2} by {var1}")
                fig, ax = plt.subplots(figsize=(10, 6))
                sns.boxplot(data=data, x=var1, y=var2, ax=ax)
                plt.xticks(rotation=45)
                st.pyplot(fig)
                
            else:
                # Categorical vs Categorical -> Heatmap of counts
                st.subheader(f"Count of {var1} vs {var2}")
                crosstab = pd.crosstab(data[var1], data[var2])
                fig, ax = plt.subplots(figsize=(10, 6))
                sns.heatmap(crosstab, annot=True, cmap="YlGnBu", fmt="d", ax=ax)
                st.pyplot(fig)
    else:
        st.warning("Please enter a valid CSV URL")