Mettre tout sur le port 7860 et créer des onglets pour l'application Streamlit et le tableau de bord MLflow

Dockerfile

@@ -23,7 +23,7 @@ RUN pip install -r /dependencies/requirements.txt
 COPY . $HOME/app
 
 # Exposer les ports pour Streamlit et MLflow
-EXPOSE 7860 5000
+EXPOSE 7860
 
 # Lancer Streamlit et le serveur de suivi MLflow
-CMD ["sh", "-c", "streamlit run app.py --server.port 7860 --server.address 0.0.0.0 & python mlflow_app.py"]
+CMD ["sh", "-c", "streamlit run app.py --server.port 7860 --server.address 0.0.0.0 & mlflow server --host 0.0.0.0 --port 7860"]

app.py

@@ -11,53 +11,64 @@ df.rename(columns={'delay_at_checkout_in_minutes': 'delay'}, inplace=True)
 
 df['late_checkin'] = df['delay'] > 0
 
-# Titre du tableau de bord
-st.title("Getaround Rentals Analysis")
+# Créer des onglets
+tab1, tab2 = st.tabs(["Getaround Rentals Analysis", "MLflow Dashboard"])
 
-# Description
-st.markdown("""
-In order to mitigate those issues we’ve decided to implement a minimum delay between two rentals. A car won’t be displayed in the search results if the requested checkin or checkout times are too close from an already booked rental.
+with tab1:
+    # Titre du tableau de bord
+    st.title("Getaround Rentals Analysis")
 
-It solves the late checkout issue but also potentially hurts Getaround/owners revenues: we need to find the right trade off.
+    # Description
+    st.markdown("""
+    In order to mitigate those issues we’ve decided to implement a minimum delay between two rentals. A car won’t be displayed in the search results if the requested checkin or checkout times are too close from an already booked rental.
 
-Our Product Manager still needs to decide:
+    It solves the late checkout issue but also potentially hurts Getaround/owners revenues: we need to find the right trade off.
 
-- threshold: how long should the minimum delay be?
-- scope: should we enable the feature for all cars?, only Connect cars?
+    Our Product Manager still needs to decide:
 
-In order to help them make the right decision, they are asking you for some data insights. Here are the first analyses they could think of, to kickstart the discussion. Don’t hesitate to perform additional analysis that you find relevant.
-""")
+    - threshold: how long should the minimum delay be?
+    - scope: should we enable the feature for all cars?, only Connect cars?
 
+    In order to help them make the right decision, they are asking you for some data insights. Here are the first analyses they could think of, to kickstart the discussion. Don’t hesitate to perform additional analysis that you find relevant.
+    """)
 
-# Visualiser les données
-fig = px.histogram(df, x='delta', title='Distribution of Delays Between Rentals')
-st.plotly_chart(fig)
+    # Visualiser les données
+    fig = px.histogram(df, x='delta', title='Distribution of Delays Between Rentals')
+    st.plotly_chart(fig)
 
-# Sélection du seuil et du scope
-threshold = st.slider("Select the minimum delay threshold (in hours)", 0, 12, 2)
-scope = st.selectbox("Select the scope", ["All cars", "Connect cars"])
+    # Sélection du seuil et du scope
+    threshold = st.slider("Select the minimum delay threshold (in hours)", 0, 12, 2)
+    scope = st.selectbox("Select the scope", ["All cars", "Connect cars"])
 
-# Filtrer les données en fonction du scope
-if scope == "Connect cars":
-    df = df[df['checkin_type'] == 'connect']
+    # Filtrer les données en fonction du scope
+    if scope == "Connect cars":
+        df = df[df['car_type'] == 'Connect']
 
-# Calculer le pourcentage de réservations affectées
-affected_rentals = df[df['delay'] <= threshold*60].shape[0]
-total_rentals = df.shape[0]
-share_affected_rentals = affected_rentals / total_rentals * 100
+    # Calculer le pourcentage de réservations affectées
+    affected_rentals = df[df['delta'] < threshold].shape[0]
+    total_rentals = df.shape[0]
+    share_affected_rentals = affected_rentals / total_rentals * 100
 
-# Afficher les résultats
-st.write(f"Percentage of rentals potentially affected by the feature: {share_affected_rentals:.2f}%")
+    # Afficher les résultats
+    st.write(f"Percentage of rentals potentially affected by the feature: {share_affected_rentals:.2f}%")
 
-# Analyser les retards
-late_checkins = df[df['late_checkin'] == True].shape[0]
-total_checkins = df.shape[0]
-share_late_checkins = late_checkins / total_checkins * 100
+    # Analyser les retards
+    late_checkins = df[df['late_checkin'] == True].shape[0]
+    total_checkins = df.shape[0]
+    share_late_checkins = late_checkins / total_checkins * 100
 
-st.write(f"Share of late check-ins: {share_late_checkins:.2f}%")
+    st.write(f"Share of late check-ins: {share_late_checkins:.2f}%")
 
+    # Visualiser les données
+    fig = px.histogram(df, x='delta', title='Distribution of Delays Between Rentals')
+    st.plotly_chart(fig)
 
+    # Analyser les cas problématiques résolus
+    solved_cases = df[(df['delta'] < threshold) & (df['late_checkin'] == True)].shape[0]
+    st.write(f"Number of problematic cases solved by the feature: {solved_cases}")
 
-# Analyser les cas problématiques résolus
-solved_cases = df[(df['delta'] < threshold*60) & (df['late_checkin'] == True)].shape[0]
-st.write(f"Number of problematic cases solved by the feature: {solved_cases}")
+with tab2:
+    st.title("MLflow Dashboard")
+    st.markdown("""
+    <iframe src="http://0.0.0.0:7860" width="100%" height="800"></iframe>
+    """, unsafe_allow_html=True)