update the virtual environment settings and the project dependencies … (

#121)

* update the virtual environment settings and the project dependencies to their latest versions

* Removed the sleep to improve the performance and upadated YAML file

---------

Co-authored-by: iris LUO <[email protected]>
Co-authored-by: Aishwarya Nadimpally <[email protected]>

environment.yaml

@@ -4,17 +4,13 @@ channels:
     - defaults
 dependencies:
     - ipykernel
-    - altair  
+    - altair=5.3.*  
     - dash=2.16.*
     - dash-bootstrap-components=1.5.*
     - plotly=5.19.*
-    - r-base
-    - r-tidyverse
-    - r-shiny
-    - r-languageserver
-    - r-plotly
     - pip
-    - pandas=2.2.*  
+    - pandas=2.2.* 
+    - pyarrow=15.0.*
     - pip:
         - dash-daq==0.5.* 
         - dash-vega-components==0.10.*

src/callbacks.py

@@ -38,8 +38,6 @@ def update_city_dropdown(selected_province):
 )
 @memory.cache()
 def update_bar_chart(province, cities, var1, var2):
-    import time
-    time.sleep(2)
     # If no city is selected, return an empty figure with a message
     if not cities:
         return {
@@ -115,8 +113,6 @@ def update_bar_chart(province, cities, var1, var2):
 )
 @memory.cache()
 def update_bar_chart(province, cities, var3):
-    import time
-    time.sleep(2)
     # If no city is selected, return an empty figure with a message
     if not cities:
         return {

src/requirements.txt

@@ -19,3 +19,4 @@ gunicorn==21.2.*
 dash-vega-components==0.10.*
 vega-datasets==0.9.*
 joblib==1.4.*
+pyarrow==15.0.*

src/tmp/joblib/callbacks/update_bar_chart/b7badfb1d8ce45832b62bd57ebba31ee/metadata.json

@@ -0,0 +1 @@
+{"duration": 2.0362932682037354, "input_args": {"province": "'British Columbia'", "cities": "['Abbotsford', 'Burnaby']", "var1": "'Price'", "var2": "'Median Family Income'"}, "time": 1713648653.495363}

src/tmp/joblib/callbacks/update_bar_chart/func_code.py

@@ -1,12 +1,13 @@
-# first line: 110
+# first line: 32
 @callback(
-    Output('bar-graph-2', 'figure'),
+    Output('bar-graph-1', 'figure'),
     [Input('province-dropdown', 'value'),
      Input('city-dropdown', 'value'),
-     Input('variable3-dropdown', 'value')]
+     Input('variable1-dropdown', 'value'),
+     Input('variable2-dropdown', 'value')]
 )
 @memory.cache()
-def update_bar_chart(province, cities, var3):
+def update_bar_chart(province, cities, var1, var2):
     import time
     time.sleep(2)
     # If no city is selected, return an empty figure with a message
@@ -25,27 +26,52 @@ def update_bar_chart(province, cities, var3):
     df_filtered = df[(df['Province'] == province) & (df['City'].isin(cities))]
 
     # Group the data by City and calculate the mean of the selected variables
-    df_count = df_filtered.groupby('City')[[var3]].value_counts().reset_index()
-    top_5_per_city = (df_count.sort_values(['City', 'count'], ascending=[True, False])
-                                 .groupby('City')
-                                 .head(5))
+    df_grouped = df_filtered.groupby('City')[[var1,var2]].mean()
+    df_grouped_samevar = df_filtered.groupby('City').agg({var1: 'mean'})
 
-    color_seq = ['#98BDFF', '#F3797E', '#8B1FB6', '#1FB69F' , '#D0116D', '#601FB6']
+    fig = make_subplots(specs=[[{"secondary_y": True}]])
 
-    fig = px.bar(
-        top_5_per_city,
-        y=var3, 
-        x='count',
-        orientation='h',
-        color='City',
-        text=f"count",
-        color_discrete_sequence=color_seq)
+    if var1 == var2:
+        # If the two variables are the same, plot only one set of bars
+        fig.add_trace(go.Bar(
+            x=df_grouped_samevar.index,
+            y=df_grouped_samevar[var1],
+            text=df_grouped_samevar[var1],                # Add the income values as text
+            textposition='auto',              # Position the text automatically
+            texttemplate='%{text:.2s}',
+            name=f'{var1}',
+            marker_color='#F3797E'))
+    else:
+        # If the two variables are different, plot two sets of bars
+        fig.add_trace(go.Bar(
+            x=df_grouped.index,
+            y=df_grouped[var1],
+            text=df_grouped[var1],                # Add the income values as text
+            textposition='auto',              # Position the text automatically
+            texttemplate='%{text:.2s}',
+            name=f'{var1}',
+            marker_color='#F3797E',
+            offsetgroup=1),
+            secondary_y=False
+        )
+
+        # Add bar 2 for var 2
+        fig.add_trace(go.Bar(
+            x=df_grouped.index,
+            y=df_grouped[var2],
+            text=df_grouped[var2],  
+            textposition='auto',             
+            texttemplate='%{text:.2s}',
+            name=f'{var2}',
+            marker_color='#7978E9',
+            offsetgroup=2),
+            secondary_y=True,
+        )
 
     # Update the layout of the bar chart
-    fig.update_layout(title_text=f'Most Common Types {var3} in Selected Cities',
-                      xaxis_title='Count',
-                      yaxis_title=f'{var3}',
-                      barmode='group')
-    fig.update_traces(textposition='outside')
+    fig.update_layout(title_text=f'Comparison of {var1} and {var2}',
+                     barmode='group')
+    fig.update_yaxes(title_text=f'{var1}', secondary_y=False)
+    fig.update_yaxes(title_text=f'{var2}', secondary_y=True)
 
     return fig