Code Editor for app.py

import streamlit as st
import pandas as pd
import plotly.express as px

# Set page title
st.title("S&P 500 Companies Analysis")

# Load data
@st.cache_data
def load_data():
    try:
        df = pd.read_csv("sp500_companies.csv")
        # Convert column names to lowercase for consistency
        df.columns = [col.lower() for col in df.columns]
        return df
    except Exception as e:
        st.error(f"Error loading data: {e}")
        return pd.DataFrame()

df_companies = load_data()

# Display DataTable
st.subheader("S&P 500 Companies")
st.dataframe(df_companies, height=400, use_container_width=True)

# Create histogram for Sector Distribution
st.subheader("Sector Distribution")
fig_sector = px.histogram(df_companies, x="sector")
st.plotly_chart(fig_sector, use_container_width=True)

# Add dropdown for histogram function
st.subheader("Average Full-time Employees by Sector")
histfunc_options = ["count", "sum", "avg", "min", "max"]
selected_histfunc = st.selectbox("Select Histogram Function", histfunc_options, index=2)

# Create histogram based on selection
fig_employees = px.histogram(
    df_companies, 
    x="sector", 
    y="fulltimeemployees", 
    histfunc=selected_histfunc,
    title=f"{selected_histfunc.capitalize()} of Full-time Employees by Sector"
)
st.plotly_chart(fig_employees, use_container_width=True)

# Create scatter plot
st.subheader("Market Cap vs Full-time Employees")
fig_scatter = px.scatter(
    df_companies,
    x="marketcap",
    y="fulltimeemployees",
    color="sector",
    size="marketcap",
    hover_name="name",
    title="Market Cap vs Full-time Employees by Sector",
    log_x=True  # Using log scale for Market Cap for better visualization
)
st.plotly_chart(fig_scatter, use_container_width=True)

# Show data statistics
st.subheader("Data Statistics")
st.write(df_companies.describe())