my_app_assignment.py

# my_app.py

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

# Load dataset
# Load dataset from CSV
df = pd.read_csv("tips.csv")

# App title
st.title("Restaurant Tip Insights")
st.markdown("How do day, gender, and smoking status affect tip percentages in a restaurant?.")

# Sidebar filters
day = st.sidebar.selectbox("Select a day", df['day'].unique())
gender = st.sidebar.multiselect("Select gender(s)", df['sex'].unique(), default=df['sex'].unique())
smoker = st.sidebar.multiselect("Select smoker status", df['smoker'].unique(), default=df['smoker'].unique())

# Filter data
filtered = df[(df['day'] == day) & (df['sex'].isin(gender)) & (df['smoker'].isin(smoker))]

# KPI
avg_tip = filtered['tip_pct'].mean()
st.metric(label=f"Average Tip % on {day}", value=f"{avg_tip:.2f}%")

# Plot 1 — Average Tip Percentage by Day
avg_by_day = df.groupby("day")["tip_pct"].mean()
fig1, ax1 = plt.subplots(figsize=(6,4))
avg_by_day.plot(kind="bar", color="skyblue", ax=ax1)
ax1.set_title("Average Tip Percentage by Day")
ax1.set_xlabel("Day of Week")
ax1.set_ylabel("Average Tip Percentage (%)")
ax1.grid(axis="y", linestyle="--", alpha=0.7)
st.pyplot(fig1)
st.markdown("**Interpretation:** This bar chart shows the average tip percentage for each day of the week present in the dataset (Thursday, Friday, Saturday, and Sunday)." \
" Friday has the highest average tip percentage, while Saturday has the lowest." \
" Thursday and Sunday have similar average tip percentages, falling between Friday and Saturday.")

# Plot 2 — Tip Percentage vs Total Bill by Sex
fig2, ax2 = plt.subplots(figsize=(8,6))
sns.scatterplot(x="total_bill", y="tip_pct", hue="sex", data=filtered, alpha=0.6, ax=ax2)
ax2.set_title("Tip Percentage vs Total Bill by Sex")
ax2.set_xlabel("Total Bill")
ax2.set_ylabel("Tip Percentage (%)")
ax2.grid(True, linestyle="--", alpha=0.5)
st.pyplot(fig2)
# --- Calculate dynamic interpretation ---
avg_tip_male = filtered[filtered["sex"]=="Male"]["tip_pct"].mean()
avg_tip_female = filtered[filtered["sex"]=="Female"]["tip_pct"].mean()

st.markdown(
    f"**Interpretation:** For the selected filters, the average tip percentage for males is {avg_tip_male:.2f}% "
    f"and for females is {avg_tip_female:.2f}%. "
    "The scatter plot shows that as the total bill increases, tip percentage tends to decrease, "
    "although there are some cases where smaller bills have higher tip percentages."
)

# Plot 3 — Tip Percentage by Smoking Status
fig3, ax3 = plt.subplots(figsize=(6,4))  # match Colab size
sns.set_style("whitegrid")  # match Colab style

# Use filtered data from sidebar
sns.boxplot(x="smoker", y="tip_pct", data=filtered, palette="Set2", ax=ax3)

# Titles and labels
ax3.set_title("Tip Percentage by Smoking Status")
ax3.set_xlabel("Smoker Status")
ax3.set_ylabel("Tip Percentage (%)")
ax3.grid(axis="y", linestyle="--", alpha=0.7)

# Display plot in Streamlit
st.pyplot(fig3)

# --- Calculate medians dynamically ---
median_smokers = filtered[filtered["smoker"]=="Yes"]["tip_pct"].median()
median_non_smokers = filtered[filtered["smoker"]=="No"]["tip_pct"].median()

# --- Display interpretation dynamically ---
st.markdown(
    f"**Interpretation:** The median tip percentage for smokers is {median_smokers:.2f}%, "
    f"and for non-smokers it is {median_non_smokers:.2f}%. "
    "The box plot suggests that smoking status does not have a large impact on the average tip percentage. "
    "However, there are some instances where smokers gave significantly higher tips."
)