Update app.py

app.py

@@ -1,130 +1,41 @@
 import streamlit as st
 import pandas as pd
-import plotly.express as px
 from ydata_profiling import ProfileReport
-from statsmodels.stats.outliers_influence import variance_inflation_factor
 
-# 1. Set Page Configuration
-st.set_page_config(
-    page_title="Enhanced Data Profiling",
-    layout="wide",
-    page_icon="📊"
-)
+st.set_page_config(page_title="Dynamic Data Profiling", layout="wide", page_icon="📊")
 
-# 2. Custom CSS for a Clean, White UI
-custom_css = """
-<style>
-/* Make the entire background white */
-body {
-    background-color: #ffffff !important;
-    font-family: 'Roboto', sans-serif;
-}
+st.title("Dynamic Data Profiling with ydata-profiling")
+st.write("Upload your CSV file and get a complete interactive profiling report!")
 
-/* Headers and titles */
-h1, h2, h3, h4 {
-    color: #2c3e50;
-    font-weight: 700;
-}
-
-/* The main Streamlit container */
-[data-testid="stAppViewContainer"] {
-    background-color: #ffffff !important;
-}
-
-/* Individual content containers */
-.css-1d391kg, .css-hxt7ib {
-    background-color: #ffffff !important;
-    border-radius: 15px;
-    padding: 30px;
-    margin-bottom: 20px;
-    box-shadow: 0 8px 16px rgba(0,0,0,0.1);
-}
-
-/* Sidebar styling */
-[data-testid="stSidebar"] {
-    background-color: #34495e !important;
-    color: #ecf0f1 !important;
-    font-size: 16px;
-}
-[data-testid="stSidebar"] .css-1d391kg {
-    background-color: #2c3e50 !important;
-    border-radius: 10px;
-}
-</style>
-"""
-st.markdown(custom_css, unsafe_allow_html=True)
-
-# 3. Title and Description
-st.title("Enhanced Data Profiling")
-st.markdown("<h4 style='text-align: center; color: #2c3e50;'>Upload your CSV and explore it thoroughly!</h4>", unsafe_allow_html=True)
-
-# 4. Sidebar for File Upload
-st.sidebar.header("Upload & Options")
-uploaded_file = st.sidebar.file_uploader("Upload a CSV file", type="csv")
-
-# Placeholder for the DataFrame
-df = None
+uploaded_file = st.file_uploader("Upload a CSV file", type="csv")
 
 if uploaded_file is not None:
-    # 4a. Read the CSV
-    df = pd.read_csv(uploaded_file)
-    st.success("File uploaded successfully!")
-
-    # 5. KPI Metrics / Quick Summary
-    st.subheader("Dataset Quick Summary")
-    col1, col2, col3, col4 = st.columns(4)
-    col1.metric("Rows", f"{df.shape[0]}")
-    col2.metric("Columns", f"{df.shape[1]}")
-    missing_percentage = (df.isnull().sum().sum() / df.size) * 100
-    col3.metric("Missing %", f"{missing_percentage:.2f}%")
-    duplicates = df.duplicated().sum()
-    col4.metric("Duplicates", f"{duplicates}")
-
-    st.write("---")
-
-    # 6. Optional Data Transformation: Drop columns with > 50% missing
-    if st.checkbox("Drop columns with > 50% missing data?"):
-        threshold = df.shape[0] * 0.5
-        before_cols = df.shape[1]
-        df = df.loc[:, df.isnull().sum() < threshold]
-        after_cols = df.shape[1]
-        st.success(f"Dropped {before_cols - after_cols} columns. Remaining columns: {after_cols}")
-
-    # 7. Optional Quick Histogram
-    numeric_cols = df.select_dtypes(include="number").columns.tolist()
-    if numeric_cols:
-        st.subheader("Optional Quick Histogram")
-        selected_col = st.selectbox("Select a numeric column", numeric_cols)
-        if selected_col:
-            fig_hist = px.histogram(df, x=selected_col, nbins=50, title=f"Histogram of {selected_col}")
-            fig_hist.update_traces(opacity=0.8)
-            st.plotly_chart(fig_hist, use_container_width=True)
-
-    # 8. Generate ydata-profiling Report
-    st.subheader("Comprehensive Profiling Report")
-    with st.spinner("Generating profiling report..."):
-        profile = ProfileReport(df, title="Profiling Report", explorative=True)
-        report_html = profile.to_html()
-
-    # 8a. Display the report in an iframe
-    st.components.v1.html(report_html, height=1200, scrolling=True)
-
-    # 8b. Download Button for HTML
-    st.write("### Download the Profiling Report")
-    st.download_button(
-        label="Download HTML",
-        data=report_html.encode('utf-8'),
-        file_name="profiling_report.html",
-        mime="text/html"
-    )
+    try:
+        # Read CSV into DataFrame
+        df = pd.read_csv(uploaded_file)
+        st.success("File uploaded successfully!")
+        
+        # Generate the profile report
+        with st.spinner("Generating profile report..."):
+            profile = ProfileReport(df, title="Profiling Report", explorative=True)
+            # Convert report to HTML
+            report_html = profile.to_html()
+
+        # Show the report in an iframe
+        st.components.v1.html(report_html, height=1200, scrolling=True)
+
+        # Provide a download button for the HTML
+        st.write("### Download the Profiling Report")
+        # Convert HTML string to bytes
+        report_bytes = report_html.encode('utf-8')
+        st.download_button(
+            label="Download HTML",
+            data=report_bytes,
+            file_name="profiling_report.html",
+            mime="text/html"
+        )
+
+    except Exception as e:
+        st.error(f"An error occurred: {e}")
 else:
     st.info("Awaiting CSV file upload.")
-
-# That's it! 
-# Simply copy and paste this into your app.py on Hugging Face Spaces.
-# Make sure you have a requirements.txt that includes:
-#   streamlit
-#   pandas
-#   ydata-profiling
-#   plotly
-#   statsmodels (for VIF, if you need it)