Message Boards

GROUPS:

Staff Picks Biological Sciences Computer Science Data Science Medical Sciences Mathematica Graphics and Visualization Wolfram Language Machine Learning Events & Media

Anton Antonov

Apple mobility trends data visualization

Anton Antonov, Accendo Data LLC

Posted 10 months ago

1800 Views

2 Replies

3 Total Likes

Follow this post

MODERATOR NOTE: coronavirus resources & updates: https://wolfr.am/coronavirus

Apple mobility trends data visualization

Version 0.9

Anton Antonov
MathematicaForPrediction at WordPress
SystemModeling at GitHub
April 2020
May 2020
December 2020

Introduction

I this notebook we ingest and visualize the mobility trends data provided by Apple, [APPL1].

We take the following steps:

Download the data

Import the data and summarise it

Transform the data into long form

Partition the data into subsets that correspond to combinations of geographical regions and transportation types

Make contingency matrices and corresponding heat-map plots

Make nearest neighbors graphs over the contingency matrices and plot communities

Plot the corresponding time series

Data description

From Apple’s page https://www.apple.com/covid19/mobility

About This Data
The CSV file and charts on this site show a relative volume of directions requests per country/region or city compared to a baseline volume on January 13th, 2020.
We define our day as midnight-to-midnight, Pacific time. Cities represent usage in greater metropolitan areas and are stably defined during this period. In many countries/regions and cities, relative volume has increased since January 13th, consistent with normal, seasonal usage of Apple Maps. Day of week effects are important to normalize as you use this data.
Data that is sent from users’ devices to the Maps service is associated with random, rotating identifiers so Apple doesn’t have a profile of your movements and searches. Apple Maps has no demographic information about our users, so we can’t make any statements about the representativeness of our usage against the overall population.

Observations

The observations listed in this subsection are also placed under the relevant statistics in the following sections and indicated with “Observation”.

◼

The directions request volumes reference date for normalization is 2020-01-13 : all the values in that column are

100

◼

From the community clusters of the nearest neighbor graphs (derived from the time series of the normalized driving directions requests volume) we see that countries and cities are clustered in expected ways. For example, in the community graph plot corresponding to “{city, driving}” the cities Oslo, Copenhagen, Helsinki, Stockholm, and Zurich are placed in the same cluster. In the graphs corresponding to “{city, transit}” and “{city, walking}” the Japanese cities Tokyo, Osaka, Nagoya, and Fukuoka are clustered together.

◼

In the time series plots the Sundays are indicated with orange dashed lines. We can see that from Monday to Thursday people are more familiar with their trips than say on Fridays and Saturdays. We can also see that on Sundays people (on average) are more familiar with their trips or simply travel less.

Load packages

In[]:=

Import["https://raw.githubusercontent.com/antononcube/MathematicaForPrediction/master/DataReshape.m"]Import["https://raw.githubusercontent.com/antononcube/MathematicaForPrediction/master/Misc/HeatmapPlot.m"]

Data ingestion

Apple mobile data was provided in this WWW page: https://www.apple.com/covid19/mobility , [APPL1]. (The data has to be download from that web page -- there is an “agreement to terms”, etc.)

In[]:=

dsAppleMobility=ResourceFunction["ImportCSVToDataset"]["~/Downloads/applemobilitytrends-2021-01-15.csv"]

Out[]=

geo_type	region	transportation_type	alternative_name	sub-region	country	2020-01-13	2020-01-14	2020-01-15	2020-01-16
country/region	Albania	driving				100.0	95.3	101.43	97.2
country/region	Albania	walking				100.0	100.68	98.93	98.46
country/region	Argentina	driving				100.0	97.07	102.45	111.21
country/region	Argentina	walking				100.0	95.11	101.37	112.67
country/region	Australia	driving	AU			100.0	102.98	104.21	108.63
country/region	Australia	transit	AU			100.0	101.78	100.64	99.58
country/region	Australia	walking	AU			100.0	101.31	101.82	104.52
country/region	Austria	driving	Österreich			100.0	101.14	104.24	112.21
country/region	Austria	walking	Österreich			100.0	101.55	105.59	112.24
country/region	Belgium	driving	België\|Belgique			100.0	101.19	107.49	107.67
country/region	Belgium	transit	België\|Belgique			100.0	98.67	105.01	105.87
country/region	Belgium	walking	België\|Belgique			100.0	101.46	110.44	118.86
country/region	Brazil	driving	Brasil			100.0	99.71	100.9	101.88
country/region	Brazil	transit	Brasil			100.0	102.45	104.28	100.2
country/region	Brazil	walking	Brasil			100.0	106.3	104.75	99.05
country/region	Bulgaria	driving	България			100.0	102.56	104.73	104.35
country/region	Bulgaria	walking	България			100.0	101.9	99.61	100.06
country/region	Cambodia	driving	ព្រះរាជាណាចក្រកម្ពុជា			100.0	100.75	99.33	96.0
country/region	Cambodia	walking	ព្រះរាជាណាចក្រកម្ពុជា			100.0	98.06	99.7	98.0
country/region	Canada	driving				100.0	102.91	99.74	105.17
rows 1–20 of 4691 columns 1–10 of 375

Data not in notebook; Store now »

Observation: The directions requests volumes reference date for normalization is 2020-01-13 : all the values in that column are

100

Data dimensions:

In[]:=

Dimensions[dsAppleMobility]

Out[]=

{4691,375}

Data summary:

In[]:=

Magnify[ResourceFunction["RecordsSummary"][dsAppleMobility],0.6]

Out[]=

Number of unique “country/region” values:

In[]:=

Length[Union[Normal[dsAppleMobility[Select[#["geo_type"]=="country/region"&],"region"]]]]

Out[]=

Number of unique “city” values:

In[]:=

Length[Union[Normal[dsAppleMobility[Select[#["geo_type"]=="city"&],"region"]]]]

Out[]=

295

All unique geo types:

In[]:=

lsGeoTypes=Union[Normal[dsAppleMobility[All,"geo_type"]]]

Out[]=

{city,country/region,county,sub-region}

All unique transportation types:

In[]:=

lsTransportationTypes=Union[Normal[dsAppleMobility[All,"transportation_type"]]]

Out[]=

{driving,transit,walking}

Data transformation

It is better to have the data in long form (narrow form). For that I am using the package "DataReshape.m", [AAp1].

In[]:=

(*lsIDColumnNames={"geo_type","region","transportation_type"};*)(*FortheinitialdatasetofApple'smobilitydata.*)lsIDColumnNames={"geo_type","region","transportation_type","alternative_name","sub-region","country"};dsAppleMobilityLongForm=ToLongForm[dsAppleMobility,lsIDColumnNames,Complement[Keys[dsAppleMobility〚1〛],lsIDColumnNames]];Dimensions[dsAppleMobilityLongForm]

Out[]=

{1730979,8}

Remove the rows with “empty” values:

In[]:=

dsAppleMobilityLongForm=dsAppleMobilityLongForm[Select[#Value≠""&]];Dimensions[dsAppleMobilityLongForm]

Out[]=

{1709416,8}

Rename the column “Variable” to “Date” and add a related “DateObject” column:

In[]:=

AbsoluteTiming[dsAppleMobilityLongForm=dsAppleMobilityLongForm[All,Join[KeyDrop[#,"Variable"],<|"Date"#Variable,"DateObject"DateObject[#Variable]|>]&];]

Out[]=

{714.062,Null}

Add “day name” (“day of the week”) field:

In[]:=

AbsoluteTiming[dsAppleMobilityLongForm=dsAppleMobilityLongForm[All,Join[#,<|"DayName"->DateString[#DateObject,{"DayName"}]|>]&];]

Out[]=

{498.026,Null}

Here is sample of the transformed data:

In[]:=

SeedRandom[3232];RandomSample[dsAppleMobilityLongForm,12]

Out[]=

geo_type	region	transportation_type	alternative_name	sub-region	country	Value	Date	DateObject	DayName
county	Colbert County	driving		Alabama	United States	162.3	2020-06-23	Tue 23 Jun 2020	Tuesday
county	Weld County	walking		Colorado	United States	131.14	2021-01-14	Thu 14 Jan 2021	Thursday
sub-region	Canton of Basel-Stadt	driving	Kanton Basel-Stadt\|Canton de Bâle-Ville		Switzerland	55.72	2020-03-17	Tue 17 Mar 2020	Tuesday
city	Orlando	driving		Florida	United States	118.09	2020-02-26	Wed 26 Feb 2020	Wednesday
county	Suffolk County	driving		New York	United States	118.04	2020-10-29	Thu 29 Oct 2020	Thursday
county	Aguadilla Municipio	driving		Puerto Rico	United States	34.11	2020-05-03	Sun 3 May 2020	Sunday
county	Suffolk County	driving		Massachusetts	United States	75.82	2020-06-11	Thu 11 Jun 2020	Thursday
sub-region	Mazovia Province	walking	Województwo Mazowieckie		Poland	49.65	2020-05-04	Mon 4 May 2020	Monday
city	Cincinnati	driving		Ohio	United States	108.95	2020-10-04	Sun 4 Oct 2020	Sunday
county	Bulloch County	walking		Georgia	United States	68.88	2020-10-18	Sun 18 Oct 2020	Sunday
county	Blaine County	driving		Oklahoma	United States	79.44	2020-03-17	Tue 17 Mar 2020	Tuesday
city	Okayama	driving	岡山市	Okayama Prefecture	Japan	139.26	2020-02-07	Fri 7 Feb 2020	Friday

Here is summary:

In[]:=

ResourceFunction["RecordsSummary"][dsAppleMobilityLongForm]

Out[]=



1 geo_type

county	969242
sub-region	394085
city	289938
country/region	56151

2 region

Washington County	9919
Jefferson County	9187
Montgomery County	8826
Franklin County	8078
Madison County	7713
Jackson County	6979
(Other)	1658714

3 transportation_type

driving	1104303
walking	402238
transit	202875

4 alternative_name

	1335188
三重県	1105
京都府	1105
佐賀県