Update app.py

app.py

@@ -25,7 +25,7 @@ def color_prediction(val):
     return f'background-color: {color}'
 
 # Setting the title and adding text
-st.title('Parking Occupacy Detection')
+st.title('Parking Occupancy Detection')
 
 # Creating tabs for the different features of the application
 tab1,tab2,tab3,tab4 = st.tabs(['Parking lot status', 'About', 'Dataset and visualisations', 'Model performance'])
@@ -37,79 +37,69 @@ with tab1:
     project = hopsworks.login(project = "miknie20", api_key_value=os.environ['HOPSWORKS_API_KEY'])
     fs = project.get_feature_store()
 
-    # Function to load the model
+    # Function to load the bikelane model
     @st.cache_data()
     def get_model(project=project):
         mr = project.get_model_registry()
-        model = mr.get_model("EL123_model", version = 2)
+        model = mr.get_model("bikelane_hist_model", version = 1)
         model_dir = model.download()
-        return joblib.load(model_dir + "/EL123_model.pkl")
+        return joblib.load(model_dir + "/bikelane_hist_model.pkl")
 
     # Retrieving model
-    model = get_model()
-    
-    # Loading the new parking detection feature view for el1
-    new_el1_parking_detection_fv = fs.get_feature_view(
-        name = 'new_el1_parking_detection_fv',
-        version = 1)
+    bikelane_hist_model = get_model()
 
-    # Function to loading the new parking detection feature view for el1 as a dataset
+    # Function to load the building model
     @st.cache_data()
-    def retrieve_el1(feature_view=new_el1_parking_detection_fv):
-        el1 = feature_view.get_batch_data()
-        return el1
+    def get_model(project=project):
+        mr = project.get_model_registry()
+        model = mr.get_model("building_hist_model", version = 2)
+        model_dir = model.download()
+        return joblib.load(model_dir + "/building_hist_model.pkl")
 
-    # Retrieving el1 data
-    el1 = retrieve_el1()
-
-    st.markdown('Parking Space 1:')
-    el1_most_recent_prediction = el1[['x', 'y', 'z']]
-    el1_most_recent_prediction = model.predict(el1_most_recent_prediction)
-    el1['prediction'] = el1_most_recent_prediction
-    el1 = el1.set_index(['time'])
-    st.dataframe(el1[['prediction']].tail(5).style.applymap(color_prediction, subset=['prediction']))
-
-    # Loading the new parking detection feature view for el2
-    new_el2_parking_detection_fv = fs.get_feature_view(
-        name = 'new_el2_parking_detection_fv',
+    # Retrieving model
+    building_hist_model = get_model()    
+    
+    # Loading the feature view with latest data for building
+    building_new_fv = fs.get_feature_view(
+        name = 'building_new_fv',
         version = 1)
 
-    # Function to loading the new parking detection feature view for el2 as a dataset
+    # Function to loading the feature view with latest data for building as a dataset
     @st.cache_data()
-    def retrieve_el2(feature_view=new_el2_parking_detection_fv):
-        el2 = feature_view.get_batch_data()
-        return el2
+    def retrieve_building(feature_view=building_new_fv):
+        building_new_fv = feature_view.get_batch_data()
+        return building_new_fv
 
     # Retrieving el1 data
-    el2 = retrieve_el2()
-
-    st.markdown('Parking Space 2:')
-    el2_most_recent_prediction = el2[['x', 'y', 'z']]
-    el2_most_recent_prediction = model.predict(el2_most_recent_prediction)
-    el2['prediction'] = el2_most_recent_prediction
-    el2 = el2.set_index(['time'])
-    st.dataframe(el2[['prediction']].tail(5).style.applymap(color_prediction, subset=['prediction']))
-
-    # Loading the new parking detection feature view for el3
-    new_el3_parking_detection_fv = fs.get_feature_view(
-        name = 'new_el3_parking_detection_fv',
+    building_new = retrieve_building()
+
+    st.markdown('Parking Space near Building:')
+    building_most_recent_prediction = building[['x', 'y', 'z']]
+    building_most_recent_prediction = building_hist_model.predict(building_most_recent_prediction)
+    building_new['prediction'] = building_most_recent_prediction
+    building_new = building_new.set_index(['time'])
+    st.dataframe(building_new[['prediction']].tail(5).style.applymap(color_prediction, subset=['prediction'])) 
+    
+    # Loading the feature view with latest data for bikelane
+    bikelane_new_fv = fs.get_feature_view(
+        name = 'bikelane_new_fv',
         version = 1)
 
-    # Function to loading the new parking detection feature view for el3 as a dataset
+    # Function to loading the feature view with latest data for bikelane as a dataset
     @st.cache_data()
-    def retrieve_el3(feature_view=new_el3_parking_detection_fv):
-        el3 = feature_view.get_batch_data()
-        return el3
+    def retrieve_bikelane(feature_view=bikelane_new_fv):
+        bikelane_new_fv = feature_view.get_batch_data()
+        return bikelane_new_fv
 
-    # Retrieving el1 data
-    el3 = retrieve_el3()
+    # Retrieving bikelane data
+    bikelane_new = retrieve_bikelane()
 
-    st.markdown('Parking Space 3:')
-    el3_most_recent_prediction = el3[['x', 'y', 'z']]
-    el3_most_recent_prediction = model.predict(el3_most_recent_prediction)
-    el3['prediction'] = el3_most_recent_prediction
-    el3 = el3.set_index(['time'])
-    st.dataframe(el3[['prediction']].tail(5).style.applymap(color_prediction, subset=['prediction']))
+    st.markdown('Parking Space near Bikelane:')
+    bikelane_most_recent_prediction = bikelane[['x', 'y', 'z']]
+    bikelane_most_recent_prediction = bikelane_hist_model.predict(bikelane_most_recent_prediction)
+    bikelane_new['prediction'] = bikelane_most_recent_prediction
+    bikelane_new = bikelane_new.set_index(['time'])
+    st.dataframe(bikelane_new[['prediction']].tail(5).style.applymap(color_prediction, subset=['prediction']))
 
     if st.button("Update status"):
         st.rerun()
@@ -126,39 +116,39 @@ with tab3:
     st.markdown('...')
 
     # Loading the parking detection feature view
-    parking_detection_fv = fs.get_feature_view(
-        name = 'parking_detection_fv',
-        version = 1)
+    #parking_detection_fv = fs.get_feature_view(
+    #    name = 'parking_detection_fv',
+    #    version = 1)
 
     # Function to loading the parking detection feature view as a dataset
-    @st.cache_data()
-    def retrieve_batch_data(feature_view=parking_detection_fv):
-        batch_data = feature_view.get_batch_data()
-        return batch_data
+    #@st.cache_data()
+    #def retrieve_batch_data(feature_view=parking_detection_fv):
+    #    batch_data = feature_view.get_batch_data()
+    #    return batch_data
 
     # Retrieving batch data
-    batch_data = retrieve_batch_data()
+    #batch_data = retrieve_batch_data()
 
     # Display dataset overview
-    st.subheader("Dataset Overview")
-    st.dataframe(batch_data.head())
+    #st.subheader("Dataset Overview")
+    #st.dataframe(batch_data.head())
   
 with tab4:
     st.markdown('The predictions are made on the basis of a KNearestNeighbours model.')
-    st.write(model)
+    #st.write(model)
 
     
     # Making a countplot of the predictions
-    predictions = model.predict(batch_data)
-    df_test = batch_data.copy()
-    df_test['predictions'] = predictions
-    st.dataframe(df_test.head())
-
-    plt.figure(figsize=(10, 6))
-    sns.set_style("darkgrid")
-    sns.countplot(data=df_test, x="predictions")
-    plt.title('Distribution of Predictions')
-    st.pyplot(plt)
+    #predictions = model.predict(batch_data)
+    #df_test = batch_data.copy()
+    #df_test['predictions'] = predictions
+    #st.dataframe(df_test.head())
+
+    #plt.figure(figsize=(10, 6))
+    #sns.set_style("darkgrid")
+    #sns.countplot(data=df_test, x="predictions")
+    #plt.title('Distribution of Predictions')
+    #st.pyplot(plt)
 
     # Confusion Matrix
     st.subheader("Confusion Matrix")