Upload 2 files

app_tips.py

@@ -0,0 +1,70 @@
+
+#Import
+import streamlit as st
+import pandas as pd
+
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+tips = sns.load_dataset("tips")
+
+#Clean data
+tips['tip_percentage'] = tips['tip'] / tips['total_bill'] * 100
+tips_cleaned = tips.drop_duplicates(keep='first')
+
+#Titles
+st.title('What characteristics make a good tipper?')
+
+st.subheader("The aim of this page is to enable users to explore whether any of the given characteristics make a good tipper based on the available data")
+
+#Sidebar
+with st.sidebar:
+    st.subheader('filters')
+    both_genders = sorted(tips_cleaned['sex'].unique().tolist())
+    smoker_all = sorted(tips_cleaned['smoker'].unique().tolist())
+
+    selected_gender = st.multiselect('Genders to show', options=both_genders,default=both_genders)
+    selected_smoker = st.multiselect('Smoker status', options=smoker_all, default=smoker_all)
+
+
+    feature_options = {
+        "tip percentage": "tip_percentage",
+        "tip amount": "tip"
+    }
+    feature_label = st.selectbox("Feature (y-axis)", list(feature_options.keys()))
+    y_col = feature_options[feature_label]
+
+#Filtered data
+data = tips_cleaned[
+    (tips_cleaned["sex"].isin(selected_gender)) &
+    (tips_cleaned["smoker"].isin(selected_smoker)) 
+].dropna(subset=[y_col])
+
+#KPI
+mean_val = data[y_col].mean()
+
+st.metric(
+    label=f'Average {feature_label}',
+    value=f'{mean_val:.2f}'
+)
+
+#Plot
+p = sns.relplot(data=data, x='total_bill', y=y_col, hue='sex')
+p.figure.suptitle("Relationship between total bill and the amount tipped")
+st.pyplot(p.figure)
+
+#More stats
+median_val = data[y_col].median()
+count_val = len(data)
+
+#Dynamic text
+if y_col == "tip_percentage":
+    st.markdown(
+        f"Based on the current filters, the average tip percentage is {mean_val:.2f}%, with a median of {median_val:.2f}% across {int(count_val)} bills."
+    )
+else:
+    st.markdown(
+        f"Based on the current filters, the average tip amount is {mean_val:.2f} dollars, with a median of {median_val:.2f} dollars across {int(count_val)} bills."
+    )
+
+

requirements.txt

@@ -0,0 +1,4 @@
+pandas == 2.3.2
+seaborn == 0.13.2
+matplotlib == 3.9.2
+streamlit == 1.49.1