Spaces:
Sleeping
Sleeping
File size: 1,966 Bytes
754f6cf 9749cc5 754f6cf 9749cc5 c314050 754f6cf 9749cc5 2429d44 f2f2a91 754f6cf 9749cc5 f2f2a91 9749cc5 754f6cf 9749cc5 754f6cf 9749cc5 c314050 9749cc5 c314050 9749cc5 c314050 9749cc5 754f6cf 9749cc5 754f6cf c7f7d04 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 |
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import streamlit as st
# -------------------------
# Streamlit App — Tipping
# -------------------------
# Load dataset
tips = sns.load_dataset("tips")
tips["tip_percentage"] = tips["tip"] / tips["total_bill"] * 100
# User question
st.title("💡 Do people tip more on certain days of the week?")
st.subheader("Explore average and highest tip percentages by day, time.")
# Short problem statement
st.write("Check whether tipping behavior changes depending on the day of the week or time of the day. "
"Use the filters to explore differences by day and time(Lunch/Dinner) of day.")
# Sidebar filters
with st.sidebar:
st.subheader("Filters")
# Day filter
all_days = sorted(tips["day"].dropna().unique().tolist())
selected_days = st.multiselect("Days to show", options=all_days, default=all_days)
# Time filter
all_times = tips["time"].dropna().unique().tolist()
selected_time = st.selectbox("Select time of day", options=["All"] + all_times)
# Apply filters
filtered = tips[tips["day"].isin(selected_days)]
if selected_time != "All":
filtered = filtered[filtered["time"] == selected_time]
# KPI: average tip percentage
avg_tip = filtered["tip_percentage"].mean()
st.metric("For selected days and time , Average Tip %", f"{avg_tip:.2f}%")
# Visualization
if not filtered.empty:
plt.figure(figsize=(6,4))
sns.boxplot(x="day", y="tip_percentage", data=filtered, order=all_days)
plt.title("Tip Percentage by Day")
st.pyplot(plt.gcf())
plt.close()
# Dynamic insight
best_day = filtered.groupby("day")["tip_percentage"].mean().idxmax()
best_value = filtered.groupby("day")["tip_percentage"].mean().max()
st.success(f"💡 Insight: On average, for {selected_time}, {best_day} has the highest tip percentage at {best_value:.2f}%")
else:
st.info("No data available for the selected filters.")
|