Urgent Bloor signal retiming data request

analysis/bin-comparison.py

@@ -5,22 +5,31 @@
 sig_level = 0.05
 
 backend = {
-    'production': 'http://localhost:8070',
+#    'production': 'http://localhost:8070',
     'development': 'http://localhost:8072'
 }
 
 dates = {
-    'before': '2024-07-02/2024-07-09',
-    'after': '2024-07-11/2024-07-18'
+    'before': '2024-09-01/2024-10-11',
+    'after': '2024-10-12/2024-11-20'
 }
 
-corridor = '30364284/30363982' # Eglinton westbound from Bathurst to Allen
-#corridor = '30363865/30363947' # Eglinton eastbound from Oakwood to Allen
-#corridor = '30361437/30363947' # Allen Southbound to Eglinton
+#corridor = '30357505/30345882' # Bloor westbound from Runnymede to Aberfoyle
+#corridor = '30345882/30357505' # Bloor eastbound from Aberfoyle to Runnymede
 
-#time = '15/18' # PM Peak
+#corridor = '30345882/970252141' # Bloor eastbound from Aberfoyle to Royal York (NS)
+#corridor = '970252141/30347302' # Bloor eastbound from Royal York to Kingsway (NS)
+#corridor = '30347302/30347896' # Bloor eastbound from Kingsway to Jane (significant AM peak decrease)
+#corridor = '30347896/30357505' # Bloor eastbound from Jane to Runnymede
+
+#corridor = '970252141/30345882' # Bloor westbound from Aberfoyle to Royal York (NS)
+#corridor = '30347302/970252141' # Bloor westbound from Royal York to Kingsway (NS)
+corridor = '30347896/30347302' # Bloor westbound from Kingsway to Jane (significant AM peak decrease)
+#corridor = '30357505/30347896' # Bloor westbound from Jane to Runnymede
+
+time = '15/18' # PM Peak
 #time = '07/09' # AM Peak
-time = '9/16' # midday
+#time = '9/16' # midday
 
 def getObs(responseData):
     return [ tt['seconds'] for tt in responseData['results']['observations'] ]
@@ -59,7 +68,7 @@ def getObs(responseData):
 
     # plot histograms side by side
     from matplotlib import pyplot
-    bins = numpy.linspace(0, 600, 20)
+    bins = numpy.linspace(0, 1200, 20)
     pyplot.hist(data[0], bins, alpha=0.5, label='before')
     pyplot.hist(data[1], bins, alpha=0.5, label='after')
     pyplot.legend()

analysis/corridor-deep-dive.py

@@ -0,0 +1,81 @@
+# We know (or suspect) that something has changed in a corridor with 
+# regard to travel times. But where exactly did the change happen?
+# When? Can we isolate the change by further segmenting the analysis?
+#
+# I'll build this out around the case of the Bloor West Complete Street Phase 1
+# but hope that it's applicable beyond that. 
+
+import requests, scipy, numpy, pandas
+from datetime import date
+
+sig_level = 0.05
+min_length_to_analyse = 250 # meters
+
+backend = 'http://localhost:8072'
+
+dates = {
+    'before': '2024-09-01/2024-10-11',
+    'after': '2024-10-16/2024-11-23'
+}
+time = '15/18' # PM Peak
+corridor = '30345882/30357505' # Bloor eastbound from Aberfoyle to Runnymede
+
+# fetch all the links for this corridor
+links = requests.get(f"{backend}/link-nodes/{corridor}").json()['links']
+
+# create a list of node OD pairs to iterate over
+# basically a spatial moving window over the corridor
+queries = []
+cumWindowStartM = 0
+for i, link in enumerate(links):
+    cumWindowLength = link['length_m']
+    for next_link in links[i+1:]:
+        if cumWindowLength >= min_length_to_analyse:
+            queries.append({
+                'ODpair': f'{link["source"]}/{next_link["target"]}',
+                # start and end positions of the rolling window
+                'windowStartM': cumWindowStartM,
+                'windowEndM': cumWindowStartM + cumWindowLength
+            })
+            break
+        cumWindowLength += next_link['length_m']
+    cumWindowStartM += link['length_m']
+
+
+def getObs(responseData):
+    return [ tt['seconds'] for tt in responseData['results']['observations'] ]
+
+for query in queries:
+    # get data for both date ranges
+    data = [
+        requests.get(
+            f"{backend}/aggregate-travel-times/{query['ODpair']}/{time}/{dateRanges}/false/12345"
+        ).json() for dateRanges in dates.values()
+    ]
+    before_response = data[0]
+    after_response = data[1]
+    before_data = getObs(before_response)
+    after_data = getObs(after_response)
+    # store the means
+    query['tt_before'] = before_response['results']['travel_time']['seconds']
+    query['tt_after'] = after_response['results']['travel_time']['seconds']
+    # Apply a one-tailed Mann-Whitney U test
+    stat, pvalue = scipy.stats.ranksums(
+        before_data,
+        after_data,
+        'greater' # one-tailed test that before > after (times decreased)
+    )
+    query['p'] = pvalue
+
+    print(
+        query['ODpair'],
+        '(travel times higher',
+        'before)' if numpy.mean(before_data) > numpy.mean(after_data) else 'after)',
+        pvalue
+    )
+
+results = pandas.DataFrame(queries)
+
+print(results)
+
+results.to_csv('corridor-windows.csv')

analysis/rolling-window.r

@@ -0,0 +1,36 @@
+library('tidyverse')
+
+setwd('C:\\Users\\nwessel\\Downloads')
+
+read_csv('corridor-windows-250m-2tail.csv') %>%
+    mutate(
+        change = if_else(tt_before > tt_after, 'decrease', 'increase'),
+        p = if_else(p <= 0.05, p, 1)
+    ) %>%
+    ggplot() +
+        geom_rect(
+            aes(
+                xmin = windowStartM,
+                xmax = windowEndM,
+                ymin = 0,
+                ymax = log(p),
+                fill = change
+            ),
+            alpha = 0.1
+        ) +
+        scale_fill_manual(values = c(
+            'increase' = 'red',
+            'decrease' = 'green'
+        )) +
+        scale_x_continuous(
+            # label cross streets by distance from start
+            minor_breaks = NULL,
+            breaks = c(0,371,657,1200,1700,2000,2800,3000,3100,3300,3500,3700),
+            labels = c('Aberfolye','Montgomery','Royal York','PED','Kingsway','Old Mill Trail','S Kingsway','Jane','Armadale','Windermere','Durie','Runnymede')
+        ) +
+        scale_y_reverse() +
+        labs(
+            title='Significance of Eastbound travel time changes',
+            y='log(P)'
+        )
+