add exercise info and update treemap

app.py

@@ -12,7 +12,9 @@ import os
 import json
 import time
 import math
+import numpy as np
 import pandas as pd
+import matplotlib.pyplot as plt
 import plotly.express as px
 
 FINISHED_EXERCISE = 'finished_exercise'
@@ -60,6 +62,15 @@ reload_cache = False
 # 6 hours
 reload_every = 6 * 60 * 60
 
+def mpl_to_plotly(cmap, pl_entries=11, rdigits=2):
+    # cmap - colormap 
+    # pl_entries - int = number of Plotly colorscale entries
+    # rdigits - int -=number of digits for rounding scale values
+    scale = np.linspace(0, 1, pl_entries)
+    colors = (cmap(scale)[:, :3]*255).astype(np.uint8)
+    pl_colorscale = [[round(s, rdigits), f'rgb{tuple(color)}'] for s, color in zip(scale, colors)]
+    return pl_colorscale
+
 def full_report():
     global cached_report, cache_time, reload_cache
     if time.time() - cache_time > reload_every:
@@ -70,6 +81,7 @@ def full_report():
         cache_time = time.time()
         client = BetaAnalyticsDataClient()
 
+        # first request all data where we have the exercise name
         request = RunReportRequest(
             property=f"properties/{PROPERTY_ID}",
             dimensions=[Dimension(name="nthDay"),
@@ -77,14 +89,15 @@ def full_report():
                         Dimension(name="continent"),
                         Dimension(name="country"),
                         Dimension(name="countryId"),
-                        Dimension(name="cityId")],
+                        Dimension(name="cityId"),
+                        Dimension(name="customEvent:exercise")],
             metrics=[Metric(name="eventValue")],
             #return_property_quota=True,
             date_ranges=[DateRange(start_date="2023-06-30", end_date="today")],
         )
         response = client.run_report(request)
 
-        res = {'day': [], 'jumps': [], 'continent': [], 'country': [], 'iso': [], 'cityId': []}
+        res = {'day': [], 'jumps': [], 'continent': [], 'country': [], 'iso': [], 'cityId': [], 'exercise': []}
 
         for row in response.rows:
             event_name = row.dimension_values[1].value
@@ -94,6 +107,7 @@ def full_report():
                 country = row.dimension_values[3].value
                 country_iso = row.dimension_values[4].value
                 city = row.dimension_values[5].value
+                exercise = row.dimension_values[6].value
                 event_value = float(row.metric_values[0].value)
                 res['day'].append(day)
                 res['jumps'].append(event_value)
@@ -101,8 +115,51 @@ def full_report():
                 res['country'].append(country)
                 res['iso'].append(country_iso)
                 res['cityId'].append(city)
+                res['exercise'].append(exercise)
 
         df = pd.DataFrame.from_dict(res)
+        # then find the earliest day we started getting exercise name data
+        first_day = int(df['day'].min())
+        end_date = pd.to_datetime('2023-06-30') + pd.DateOffset(days=first_day)
+        # only need YYY-MM-DD
+        end_date = str(end_date.strftime('%Y-%m-%d'))
+        # then request all data where we don't have the exercise name
+        request = RunReportRequest(
+            property=f"properties/{PROPERTY_ID}",
+            dimensions=[Dimension(name="nthDay"),
+                        Dimension(name='eventName'),
+                        Dimension(name="continent"),
+                        Dimension(name="country"),
+                        Dimension(name="countryId"),
+                        Dimension(name="cityId")],
+            metrics=[Metric(name="eventValue")],
+            #return_property_quota=True,
+            date_ranges=[DateRange(start_date="2023-06-30", end_date=end_date)],
+        )
+        response = client.run_report(request)
+        res = {'day': [], 'jumps': [], 'continent': [], 'country': [], 'iso': [], 'cityId': [], 'exercise': []}
+        for row in response.rows:
+            event_name = row.dimension_values[1].value
+            if event_name == FINISHED_EXERCISE:
+                day = int(row.dimension_values[0].value)
+                continent = row.dimension_values[2].value
+                country = row.dimension_values[3].value
+                country_iso = row.dimension_values[4].value
+                city = row.dimension_values[5].value
+                event_value = float(row.metric_values[0].value)
+                res['day'].append(day)
+                res['jumps'].append(event_value)
+                res['continent'].append(continent)
+                res['country'].append(country)
+                res['iso'].append(country_iso)
+                res['cityId'].append(city)
+                res['exercise'].append('n/a')
+        new_df = pd.DataFrame.from_dict(res)
+        # drop any rows we already have
+        #new_df = new_df[new_df['day'] < first_day]
+        df = pd.concat([df, new_df]).reset_index(drop=True)
+        df['duration'] = df['exercise'].apply(lambda x: 0 if x in ['n/a', '(not set)'] else int(x[2:]))
+        print(df['duration'].sum())
         cached_report = df.copy(deep=True)
     else:
         print("Using cached report...")
@@ -130,6 +187,16 @@ def full_report():
     df['rank'] = df['jumps'].rank(ascending=False)
     df['world'] = 'Earth'
 
+    exercise_df = df[~df['exercise'].isin(['n/a', '(not set)'])]
+    # plot a bar graph of the most popular exercises and their counts in the dataset
+    pop_events = px.bar(exercise_df['exercise'].value_counts().reset_index()[:6], 
+                        y='index', 
+                        x='exercise', 
+                        color='index',
+                        title='Most Popular Exercises', 
+                        template="plotly_dark")
+    pop_events.update_layout(showlegend=False)
+
     total = px.bar(country_df_to_plot, 
                    y='country', x='jumps', 
                    color='country',
@@ -173,14 +240,15 @@ def full_report():
     #                    color='jumps')
 
     print(df.columns)
-
+    nipy_spec = mpl_to_plotly(plt.cm.nipy_spectral, pl_entries=15)
     icicle = px.treemap(icicle_df, path=['world', 'continent', 'country', 'state', 'city'], 
                        values='jumps', 
                        title='Jumps by Continent/Country/City (click anywhere!)', 
                        template="plotly_dark", 
-                       color_continuous_scale='jet',
+                       color_continuous_scale=nipy_spec,
                        branchvalues='total',
                        height=800,
+                       maxdepth=4,
                        color='jumps')
 
     city_df = df.groupby(['city', 'iso']).sum().reset_index()
@@ -250,7 +318,7 @@ def full_report():
     df = df.sort_values(by=['day'])
     df['total_jumps'] = df.groupby('continent')['jumps'].cumsum()
     # fill in any missing days with current max value
-    for day in range(1, df['day'].max() + 1):
+    for day in range(1, int(df['day'].max()) + 1):
         for continent in df['continent'].unique():
             if not df[(df['day'] == day) & (df['continent'] == continent)].any().any():
                 max_jumps = df[(df['day'] < day) & (df['continent'] == continent)]['total_jumps'].max()
@@ -271,10 +339,10 @@ def full_report():
                               template="plotly_dark")
 
     return f"# {total_jumps:,} total jumps in {unique_cities:,} cities across {unique_countries:,} countries", \
-           total, total_weekly, avg, avg_weekly, total_map, icicle, jumps_over_time, county_map, per_day_plot
+           total, total_weekly, avg, avg_weekly, total_map, icicle, jumps_over_time, pop_events, county_map, per_day_plot
 
 
-with gr.Blocks(theme='WeixuanYuan/Soft_dark') as demo:
+with gr.Blocks() as demo:
     with gr.Row():
         total_jumps_label = gr.Markdown("Total Jumps: 0")
     with gr.Row():
@@ -295,8 +363,10 @@ with gr.Blocks(theme='WeixuanYuan/Soft_dark') as demo:
         per_day_plot = gr.Plot(label="Jumps per Day")
     with gr.Row():
         county_map = gr.Plot(label="US Map")
+    with gr.Row():
+        popular_events = gr.Plot(label="Popular Events")
 
-    outputs = [total_jumps_label, total_plot, total_plot_weekly, avg_plot, avg_plot_weekly, map_fig, icicle_fig, jumps_over_time, county_map, per_day_plot]
+    outputs = [total_jumps_label, total_plot, total_plot_weekly, avg_plot, avg_plot_weekly, map_fig, icicle_fig, jumps_over_time, popular_events, county_map, per_day_plot]
     dep = demo.load(full_report, None, outputs)
 
 if __name__ == "__main__":