Code Editor for app.py

import streamlit as st
import pandas as pd
import numpy as np

st.title('Numeric Column Outlier Detector')

# File uploader
uploaded_file = st.file_uploader("Choose a CSV file", type='csv')

if uploaded_file is not None:
    # Load the data
    df = pd.read_csv(uploaded_file)
    
    # Get numeric columns
    numeric_columns = df.select_dtypes(include=[np.number]).columns.tolist()
    
    if not numeric_columns:
        st.error("No numeric columns found in the dataset!")
    else:
        # Let user select columns
        selected_columns = st.multiselect(
            "Select numeric columns to analyze",
            numeric_columns,
            default=numeric_columns[0] if numeric_columns else None
        )
        
        if selected_columns:
            # Calculate outliers using IQR method
            for column in selected_columns:
                st.subheader(f"Outlier Analysis for {column}")
                
                # Calculate Q1, Q3, and IQR
                Q1 = df[column].quantile(0.25)
                Q3 = df[column].quantile(0.75)
                IQR = Q3 - Q1
                
                # Define outlier bounds
                lower_bound = Q1 - 1.5 * IQR
                upper_bound = Q3 + 1.5 * IQR
                
                # Find outliers
                outliers = df[(df[column] < lower_bound) | (df[column] > upper_bound)][column]
                
                # Display statistics
                col1, col2, col3 = st.columns(3)
                with col1:
                    st.metric("Lower Bound", f"{lower_bound:.2f}")
                with col2:
                    st.metric("Upper Bound", f"{upper_bound:.2f}")
                with col3:
                    st.metric("Number of Outliers", len(outliers))
                
                # Show outlier values
                if not outliers.empty:
                    st.write("Outlier Values:")
                    st.table(pd.DataFrame({
                        'Index': outliers.index,
                        'Value': outliers.values
                    }))
                    
                    # Create scatter plot to visualize outliers
                    scatter_data = pd.DataFrame({
                        'index': df.index,
                        'value': df[column],
                        'color': ['Outlier' if x in outliers.values else 'Normal' 
                                for x in df[column]]
                    })
                    
                    st.scatter_chart(
                        data=scatter_data,
                        x='index',
                        y='value',
                        color='color',
                        x_label='Index',
                        y_label=column
                    )
                else:
                    st.success("No outliers found in this column!")
else:
    st.info("Please upload a CSV file to begin analysis.")