Update app.py

app.py

@@ -1,112 +1,112 @@
-import streamlit as st
-import pandas as pd
-import seaborn as sns
-import duckdb # For in-memory SQL Quering
-import matplotlib.pyplot as plt
-
-st.set_page_config(page_title="Tips EDA & Insights", layout="wide")
-
-# --- Using App Header ---
-st.title("💸 Tipping Behavior Analyzer")
-st.markdown("""
-Welcome to the interactive explorer for the Seaborn Tips dataset!  
-Analyze tipping behavior by gender, day, and party size.  
-""")
-
-# --- Data Loading & Caching ---
-@st.cache_data(show_spinner=True)
-def load_data():
-    tips = sns.load_dataset("tips")
-    tips['tip_pct'] = (tips['tip'] / tips['total_bill']) * 100
-    tips.to_parquet("tips.parquet")
-    return tips
-
-tips = load_data()
-
-# --- DuckDB Query Function ---
-@st.cache_data(show_spinner=True)
-def query_duckdb(gender, day):
-    query = f"""
-        SELECT * FROM 'tips.parquet'
-        WHERE sex = '{gender}' AND day = '{day}'
-    """
-    return duckdb.query(query).to_df()
-
-# --- Sidebar Controls ---
-st.sidebar.header("🔎 Filter Data")
-gender = st.sidebar.selectbox("Select Gender", options=tips['sex'].unique())
-day = st.sidebar.selectbox("Select Day", options=tips['day'].unique())
-party_size = st.sidebar.slider("Party Size", int(tips['size'].min()), int(tips['size'].max()), int(tips['size'].min()))
-hue_option = st.sidebar.selectbox("Color by (hue)", options=['smoker', 'time', 'day', 'sex'])
-
-filtered = query_duckdb(gender, day)
-filtered = filtered[filtered['size'] == party_size]
-
-# --- KPI Section ---
-st.subheader("📊 Key Performance Indicator")
-mean_tip = filtered['tip_pct'].mean()
-st.metric("Average Tip Percentage", f"{mean_tip:.2f}%")
-
-# --- Data Table ---
-st.subheader("🗃️ Filtered Data")
-st.dataframe(filtered)
-
-# --- Visualizations ---
-st.subheader("📈 Visualizations")
-
-col1, col2 = st.columns(2)
-
-with col1:
-    st.markdown(f"#### Tip Percentage Distribution by Gender")
-    fig1, ax1 = plt.subplots()
-    sns.boxplot(data=tips, x="sex", y="tip_pct", hue=hue_option, ax=ax1)
-    ax1.set_title(f"Tip Percentage Distribution by Gender (Hue: {hue_option})")
-    st.pyplot(fig1)
-
-with col2:
-    st.markdown(f"#### Tip Percentage vs. Party Size")
-    fig2, ax2 = plt.subplots()
-    sns.scatterplot(data=tips, x="size", y="tip_pct", hue=hue_option, ax=ax2)
-    ax2.set_title(f"Tip Percentage vs. Party Size (Hue: {hue_option})")
-    st.pyplot(fig2)
-
-st.markdown("#### Average Tip Percentage by Day")
-mean_tip_by_day = tips.groupby('day')['tip_pct'].mean()
-st.bar_chart(mean_tip_by_day)
-
-# --- Dynamic Insight ---
-st.subheader("💡 Insight")
-st.write(
-    f"On **{day}s**, for **{gender}** customers in a party of size **{party_size}**, "
-    f"the average tip percentage is **{mean_tip:.2f}%**."
-)
-
-# --- Cache Invalidation Patterns ---
-# ...existing code...
-
-# --- Authors & Plot Explanations ---
-st.markdown("---")
-st.header("👨‍💻 Project Contributors")
-st.markdown("""
-**Muhammad Ibrahim**  
-**Asalun Hye Arnob**
-
----
-
-### 📊 Plot Explanations
-
-- **Tip Percentage Distribution by Gender (Box Plot):**  
-  This plot shows how tip percentages vary between male and female customers. The box represents the middle 50% of values, the line inside is the median, and dots outside the box are outliers. It helps us compare tipping habits by gender.
-
-- **Tip Percentage vs. Party Size (Scatter Plot):**  
-  This plot displays individual tip percentages for each party size. Each dot is a meal. It helps us see if larger groups tend to tip more or less, and spot any patterns or clusters.
-
-- **Average Tip Percentage by Day (Bar Chart):**  
-  This chart shows the average tip percentage for each day of the week. It helps us identify which days have higher or lower tipping rates.
-
----
-
-**Summary:**  
-We loaded and cleaned the tips dataset, created a tip percentage variable, and built interactive visualizations to explore how tipping behavior varies by gender, day, and party size.  
-Our app uses DuckDB for fast queries and Streamlit for a user-friendly interface.
+import streamlit as st
+import pandas as pd
+import seaborn as sns
+import duckdb # For in-memory SQL Quering
+import matplotlib.pyplot as plt
+
+st.set_page_config(page_title="Tips EDA & Insights", layout="wide")
+
+# --- Using App Header ---
+st.title("💸 Tipping Behavior Analyzer")
+st.markdown("""
+Welcome to the interactive explorer for the Seaborn Tips dataset!  
+Analyze tipping behavior by gender, day, and party size.  
+""")
+
+# --- Data Loading & Caching ---
+@st.cache_data(show_spinner=True)
+def load_data():
+    tips = sns.load_dataset("tips")
+    tips['tip_pct'] = (tips['tip'] / tips['total_bill']) * 100
+    tips.to_parquet("tips.parquet")
+    return tips
+
+tips = load_data()
+
+# --- DuckDB Query Function ---
+@st.cache_data(show_spinner=True)
+def query_duckdb(gender, day):
+    query = f"""
+        SELECT * FROM 'tips.parquet'
+        WHERE sex = '{gender}' AND day = '{day}'
+    """
+    return duckdb.query(query).to_df()
+
+# --- Sidebar Controls ---
+st.sidebar.header("🔎 Filter Data")
+gender = st.sidebar.selectbox("Select Gender", options=tips['sex'].unique())
+day = st.sidebar.selectbox("Select Day", options=tips['day'].unique())
+party_size = st.sidebar.slider("Party Size", int(tips['size'].min()), int(tips['size'].max()), int(tips['size'].min()))
+hue_option = st.sidebar.selectbox("Color by (hue)", options=['smoker', 'time', 'day', 'sex'])
+
+filtered = query_duckdb(gender, day)
+filtered = filtered[filtered['size'] == party_size]
+
+# --- KPI Section ---
+st.subheader("📊 Key Performance Indicator")
+mean_tip = filtered['tip_pct'].mean()
+st.metric("Average Tip Percentage", f"{mean_tip:.2f}%")
+
+# --- Data Table ---
+st.subheader("🗃️ Filtered Data")
+st.dataframe(filtered)
+
+# --- Visualizations ---
+st.subheader("📈 Visualizations")
+
+col1, col2 = st.columns(2)
+
+with col1:
+    st.markdown(f"#### Tip Percentage Distribution by Gender")
+    fig1, ax1 = plt.subplots()
+    sns.boxplot(data=tips, x="sex", y="tip_pct", hue=hue_option, ax=ax1)
+    ax1.set_title(f"Tip Percentage Distribution by Gender (Hue: {hue_option})")
+    st.pyplot(fig1)
+
+with col2:
+    st.markdown(f"#### Tip Percentage vs. Party Size")
+    fig2, ax2 = plt.subplots()
+    sns.scatterplot(data=tips, x="size", y="tip_pct", hue=hue_option, ax=ax2)
+    ax2.set_title(f"Tip Percentage vs. Party Size (Hue: {hue_option})")
+    st.pyplot(fig2)
+
+st.markdown("#### Average Tip Percentage by Day")
+mean_tip_by_day = tips.groupby('day')['tip_pct'].mean()
+st.bar_chart(mean_tip_by_day)
+
+# --- Dynamic Insight ---
+st.subheader("💡 Insight")
+st.write(
+    f"On **{day}s**, for **{gender}** customers in a party of size **{party_size}**, "
+    f"the average tip percentage is **{mean_tip:.2f}%**."
+)
+
+# --- Cache Invalidation Patterns ---
+# ...existing code...
+
+# --- Authors & Plot Explanations ---
+st.markdown("---")
+st.header("👨‍💻 Project Contributors")
+st.markdown("""
+**Muhammad Ibrahim**  
+**Asalun Hye Arnob**
+
+---
+
+### 📊 Plot Explanations
+
+- **Tip Percentage Distribution by Gender (Box Plot):**  
+  This plot shows how tip percentages vary between male and female customers. The box represents the middle 50% of values, the line inside is the median, and dots outside the box are outliers. It helps us compare tipping habits by gender.
+
+- **Tip Percentage vs. Party Size (Scatter Plot):**  
+  This plot displays individual tip percentages for each party size. Each dot is a meal. It helps us see if larger groups tend to tip more or less, and spot any patterns or clusters.
+
+- **Average Tip Percentage by Day (Bar Chart):**  
+  This chart shows the average tip percentage for each day of the week. It helps us identify which days have higher or lower tipping rates.
+
+---
+
+**Project Summary:**  
+We loaded and cleaned the tips dataset, created a tip percentage variable, and built interactive visualizations to explore how tipping behavior varies by gender, day, and party size.  
+Our app uses DuckDB for fast queries and Streamlit for a user-friendly interface.
 """)