diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000000000000000000000000000000000000..ba94f5e43f10b3215c811e403d2df27d41ab5749
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,8 @@
+data/covid-19_jhu-csse/time_series_19-covid-Confirmed.csv filter=lfs diff=lfs merge=lfs -text
+data/covid-19_jhu-csse/time_series_19-covid-Deaths.csv filter=lfs diff=lfs merge=lfs -text
+data/covid-19_jhu-csse/time_series_19-covid-Recovered.csv filter=lfs diff=lfs merge=lfs -text
+data/worldbank/SP.POP.TOTL.zip filter=lfs diff=lfs merge=lfs -text
+data/covid-19_rates/** filter=lfs diff=lfs merge=lfs -text
+data/covid-19_rates/ts_rates_19-covid-deaths.csv filter=lfs diff=lfs merge=lfs -text
+data/covid-19_rates/ts_rates_19-covid-recovered.csv filter=lfs diff=lfs merge=lfs -text
+data/covid-19_rates/ts_rates_19-covid-confirmed.csv filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/datasets/720e46f5-0f38-48be-86ef-1fcbae258a6f/metadata.yml b/.renku/datasets/720e46f5-0f38-48be-86ef-1fcbae258a6f/metadata.yml
new file mode 100644
index 0000000000000000000000000000000000000000..d748501401f822c12badb449606bc1a84fa99717
--- /dev/null
+++ b/.renku/datasets/720e46f5-0f38-48be-86ef-1fcbae258a6f/metadata.yml
@@ -0,0 +1,221 @@
+'@context':
+ '@version': 1.1
+ _id: '@id'
+ _project:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ created: schema:dateCreated
+ creator:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ affiliation: schema:affiliation
+ alternate_name: schema:alternateName
+ email: schema:email
+ label: rdfs:label
+ name: schema:name
+ prov: http://www.w3.org/ns/prov#
+ rdfs: http://www.w3.org/2000/01/rdf-schema#
+ schema: http://schema.org/
+ '@id': schema:creator
+ name: schema:name
+ prov: http://www.w3.org/ns/prov#
+ schema: http://schema.org/
+ updated: schema:dateUpdated
+ version: schema:schemaVersion
+ '@id': schema:isPartOf
+ based_on: schema:isBasedOn
+ created: schema:dateCreated
+ creator:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ affiliation: schema:affiliation
+ alternate_name: schema:alternateName
+ email: schema:email
+ label: rdfs:label
+ name: schema:name
+ prov: http://www.w3.org/ns/prov#
+ rdfs: http://www.w3.org/2000/01/rdf-schema#
+ schema: http://schema.org/
+ '@id': schema:creator
+ date_published: schema:datePublished
+ description: schema:description
+ files:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ _project:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ created: schema:dateCreated
+ creator:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ affiliation: schema:affiliation
+ alternate_name: schema:alternateName
+ email: schema:email
+ label: rdfs:label
+ name: schema:name
+ prov: http://www.w3.org/ns/prov#
+ rdfs: http://www.w3.org/2000/01/rdf-schema#
+ schema: http://schema.org/
+ '@id': schema:creator
+ name: schema:name
+ prov: http://www.w3.org/ns/prov#
+ schema: http://schema.org/
+ updated: schema:dateUpdated
+ version: schema:schemaVersion
+ '@id': schema:isPartOf
+ added: schema:dateCreated
+ based_on: schema:isBasedOn
+ creator:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ affiliation: schema:affiliation
+ alternate_name: schema:alternateName
+ email: schema:email
+ label: rdfs:label
+ name: schema:name
+ prov: http://www.w3.org/ns/prov#
+ rdfs: http://www.w3.org/2000/01/rdf-schema#
+ schema: http://schema.org/
+ '@id': schema:creator
+ name: schema:name
+ path: prov:atLocation
+ prov: http://www.w3.org/ns/prov#
+ schema: http://schema.org/
+ url: schema:url
+ wfprov: http://purl.org/wf4ever/wfprov#
+ '@id': schema:hasPart
+ identifier: schema:identifier
+ in_language:
+ '@context':
+ '@version': 1.1
+ alternate_name: schema:alternateName
+ name: schema:name
+ schema: http://schema.org/
+ '@id': schema:inLanguage
+ keywords: schema:keywords
+ license: schema:license
+ name: schema:name
+ path: prov:atLocation
+ prov: http://www.w3.org/ns/prov#
+ same_as:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ schema: http://schema.org/
+ url: schema:url
+ '@id': schema:sameAs
+ schema: http://schema.org/
+ short_name: schema:alternateName
+ tags:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ commit: schema:location
+ created: schema:startDate
+ dataset: schema:about
+ description: schema:description
+ name: schema:name
+ schema: http://schema.org/
+ '@id': schema:subjectOf
+ url: schema:url
+ version: schema:version
+ wfprov: http://purl.org/wf4ever/wfprov#
+'@type':
+- prov:Entity
+- schema:Dataset
+- wfprov:Artifact
+_id: https://dev.renku.ch/datasets/720e46f5-0f38-48be-86ef-1fcbae258a6f
+_label: 720e46f5-0f38-48be-86ef-1fcbae258a6f
+_project:
+ '@type':
+ - prov:Location
+ - schema:Project
+ _id: https://dev.renku.ch/projects/cramakri/covid-19-dashboard
+ created: '2020-03-11T21:43:12.736000+00:00'
+ creator:
+ '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:cramakri@ethz.ch
+ affiliation: null
+ alternate_name: null
+ email: cramakri@ethz.ch
+ label: Chandrasekhar Ramakrishnan
+ name: Chandrasekhar Ramakrishnan
+ name: covid-19-dashboard
+ updated: '2020-03-11T21:43:12.736000+00:00'
+ version: '1'
+based_on: null
+created: '2020-03-11T21:59:24.774290+00:00'
+creator:
+- '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:cramakri@ethz.ch
+ affiliation: null
+ alternate_name: null
+ email: cramakri@ethz.ch
+ label: Chandrasekhar Ramakrishnan
+ name: Chandrasekhar Ramakrishnan
+date_published: null
+description: null
+files:
+- '@type':
+ - prov:Entity
+ - schema:DigitalDocument
+ - wfprov:Artifact
+ _id: https://dev.renku.ch/blob/f9328ad834b29347e00c73c32bc2a99a91103247/data/worldbank/SP.POP.TOTL.zip
+ _label: data/worldbank/SP.POP.TOTL.zip@f9328ad834b29347e00c73c32bc2a99a91103247
+ _project:
+ '@type':
+ - prov:Location
+ - schema:Project
+ _id: https://dev.renku.ch/projects/cramakri/covid-19-dashboard
+ created: '2020-03-11T21:43:12.736000+00:00'
+ creator:
+ '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:cramakri@ethz.ch
+ affiliation: null
+ alternate_name: null
+ email: cramakri@ethz.ch
+ label: Chandrasekhar Ramakrishnan
+ name: Chandrasekhar Ramakrishnan
+ name: covid-19-dashboard
+ updated: '2020-03-11T21:43:12.736000+00:00'
+ version: '1'
+ added: '2020-03-11T22:05:58.843468+00:00'
+ based_on: null
+ creator:
+ - '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:cramakri@ethz.ch
+ affiliation: null
+ alternate_name: null
+ email: cramakri@ethz.ch
+ label: Chandrasekhar Ramakrishnan
+ name: Chandrasekhar Ramakrishnan
+ name: SP.POP.TOTL.zip
+ path: data/worldbank/SP.POP.TOTL.zip
+ url: http://api.worldbank.org/v2/en/indicator/SP.POP.TOTL?downloadformat=csv
+identifier: 720e46f5-0f38-48be-86ef-1fcbae258a6f
+in_language: null
+keywords: []
+license: null
+name: worldbank
+path: .renku/datasets/720e46f5-0f38-48be-86ef-1fcbae258a6f
+same_as: null
+short_name: worldbank
+tags: []
+url: https://dev.renku.ch/datasets/720e46f5-0f38-48be-86ef-1fcbae258a6f
+version: null
diff --git a/.renku/datasets/e9212b58-4994-482b-801c-ed90a960bd04/metadata.yml b/.renku/datasets/e9212b58-4994-482b-801c-ed90a960bd04/metadata.yml
new file mode 100644
index 0000000000000000000000000000000000000000..d34c6681c31b3ddc3a487be585a57150f179b0c0
--- /dev/null
+++ b/.renku/datasets/e9212b58-4994-482b-801c-ed90a960bd04/metadata.yml
@@ -0,0 +1,301 @@
+'@context':
+ '@version': 1.1
+ _id: '@id'
+ _project:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ created: schema:dateCreated
+ creator:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ affiliation: schema:affiliation
+ alternate_name: schema:alternateName
+ email: schema:email
+ label: rdfs:label
+ name: schema:name
+ prov: http://www.w3.org/ns/prov#
+ rdfs: http://www.w3.org/2000/01/rdf-schema#
+ schema: http://schema.org/
+ '@id': schema:creator
+ name: schema:name
+ prov: http://www.w3.org/ns/prov#
+ schema: http://schema.org/
+ updated: schema:dateUpdated
+ version: schema:schemaVersion
+ '@id': schema:isPartOf
+ based_on: schema:isBasedOn
+ created: schema:dateCreated
+ creator:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ affiliation: schema:affiliation
+ alternate_name: schema:alternateName
+ email: schema:email
+ label: rdfs:label
+ name: schema:name
+ prov: http://www.w3.org/ns/prov#
+ rdfs: http://www.w3.org/2000/01/rdf-schema#
+ schema: http://schema.org/
+ '@id': schema:creator
+ date_published: schema:datePublished
+ description: schema:description
+ files:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ _project:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ created: schema:dateCreated
+ creator:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ affiliation: schema:affiliation
+ alternate_name: schema:alternateName
+ email: schema:email
+ label: rdfs:label
+ name: schema:name
+ prov: http://www.w3.org/ns/prov#
+ rdfs: http://www.w3.org/2000/01/rdf-schema#
+ schema: http://schema.org/
+ '@id': schema:creator
+ name: schema:name
+ prov: http://www.w3.org/ns/prov#
+ schema: http://schema.org/
+ updated: schema:dateUpdated
+ version: schema:schemaVersion
+ '@id': schema:isPartOf
+ added: schema:dateCreated
+ based_on: schema:isBasedOn
+ creator:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ affiliation: schema:affiliation
+ alternate_name: schema:alternateName
+ email: schema:email
+ label: rdfs:label
+ name: schema:name
+ prov: http://www.w3.org/ns/prov#
+ rdfs: http://www.w3.org/2000/01/rdf-schema#
+ schema: http://schema.org/
+ '@id': schema:creator
+ name: schema:name
+ path: prov:atLocation
+ prov: http://www.w3.org/ns/prov#
+ schema: http://schema.org/
+ url: schema:url
+ wfprov: http://purl.org/wf4ever/wfprov#
+ '@id': schema:hasPart
+ identifier: schema:identifier
+ in_language:
+ '@context':
+ '@version': 1.1
+ alternate_name: schema:alternateName
+ name: schema:name
+ schema: http://schema.org/
+ '@id': schema:inLanguage
+ keywords: schema:keywords
+ license: schema:license
+ name: schema:name
+ path: prov:atLocation
+ prov: http://www.w3.org/ns/prov#
+ same_as:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ schema: http://schema.org/
+ url: schema:url
+ '@id': schema:sameAs
+ schema: http://schema.org/
+ short_name: schema:alternateName
+ tags:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ commit: schema:location
+ created: schema:startDate
+ dataset: schema:about
+ description: schema:description
+ name: schema:name
+ schema: http://schema.org/
+ '@id': schema:subjectOf
+ url: schema:url
+ version: schema:version
+ wfprov: http://purl.org/wf4ever/wfprov#
+'@type':
+- prov:Entity
+- schema:Dataset
+- wfprov:Artifact
+_id: https://dev.renku.ch/datasets/e9212b58-4994-482b-801c-ed90a960bd04
+_label: e9212b58-4994-482b-801c-ed90a960bd04
+_project:
+ '@type':
+ - prov:Location
+ - schema:Project
+ _id: https://dev.renku.ch/projects/cramakri/covid-19-dashboard
+ created: '2020-03-11T21:43:12.736000+00:00'
+ creator:
+ '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:cramakri@ethz.ch
+ affiliation: null
+ alternate_name: null
+ email: cramakri@ethz.ch
+ label: Chandrasekhar Ramakrishnan
+ name: Chandrasekhar Ramakrishnan
+ name: covid-19-dashboard
+ updated: '2020-03-11T21:43:12.736000+00:00'
+ version: '1'
+based_on: null
+created: '2020-03-12T22:44:43.719042+00:00'
+creator:
+- '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:cramakri@ethz.ch
+ affiliation: null
+ alternate_name: null
+ email: cramakri@ethz.ch
+ label: Chandrasekhar Ramakrishnan
+ name: Chandrasekhar Ramakrishnan
+date_published: null
+description: null
+files:
+- '@type':
+ - prov:Entity
+ - schema:DigitalDocument
+ - wfprov:Artifact
+ _id: https://dev.renku.ch/blob/5cbef5a5898d761176f551823f2fa51f28e8bd41/data/covid-19_rates/ts_rates_19-covid-confirmed.csv
+ _label: data/covid-19_rates/ts_rates_19-covid-confirmed.csv@5cbef5a5898d761176f551823f2fa51f28e8bd41
+ _project:
+ '@type':
+ - prov:Location
+ - schema:Project
+ _id: https://dev.renku.ch/projects/cramakri/covid-19-dashboard
+ created: '2020-03-11T21:43:12.736000+00:00'
+ creator:
+ '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:cramakri@ethz.ch
+ affiliation: null
+ alternate_name: null
+ email: cramakri@ethz.ch
+ label: Chandrasekhar Ramakrishnan
+ name: Chandrasekhar Ramakrishnan
+ name: covid-19-dashboard
+ updated: '2020-03-11T21:43:12.736000+00:00'
+ version: '1'
+ added: '2020-03-13T14:55:17.141133+00:00'
+ based_on: null
+ creator:
+ - '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:cramakri@ethz.ch
+ affiliation: null
+ alternate_name: null
+ email: cramakri@ethz.ch
+ label: Chandrasekhar Ramakrishnan
+ name: Chandrasekhar Ramakrishnan
+ name: ts_rates_19-covid-confirmed.csv
+ path: data/covid-19_rates/ts_rates_19-covid-confirmed.csv
+ url: data/covid-19_rates/ts_rates_19-covid-confirmed.csv
+- '@type':
+ - prov:Entity
+ - schema:DigitalDocument
+ - wfprov:Artifact
+ _id: https://dev.renku.ch/blob/5cbef5a5898d761176f551823f2fa51f28e8bd41/data/covid-19_rates/ts_rates_19-covid-deaths.csv
+ _label: data/covid-19_rates/ts_rates_19-covid-deaths.csv@5cbef5a5898d761176f551823f2fa51f28e8bd41
+ _project:
+ '@type':
+ - prov:Location
+ - schema:Project
+ _id: https://dev.renku.ch/projects/cramakri/covid-19-dashboard
+ created: '2020-03-11T21:43:12.736000+00:00'
+ creator:
+ '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:cramakri@ethz.ch
+ affiliation: null
+ alternate_name: null
+ email: cramakri@ethz.ch
+ label: Chandrasekhar Ramakrishnan
+ name: Chandrasekhar Ramakrishnan
+ name: covid-19-dashboard
+ updated: '2020-03-11T21:43:12.736000+00:00'
+ version: '1'
+ added: '2020-03-13T14:55:17.163968+00:00'
+ based_on: null
+ creator:
+ - '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:cramakri@ethz.ch
+ affiliation: null
+ alternate_name: null
+ email: cramakri@ethz.ch
+ label: Chandrasekhar Ramakrishnan
+ name: Chandrasekhar Ramakrishnan
+ name: ts_rates_19-covid-deaths.csv
+ path: data/covid-19_rates/ts_rates_19-covid-deaths.csv
+ url: data/covid-19_rates/ts_rates_19-covid-deaths.csv
+- '@type':
+ - prov:Entity
+ - schema:DigitalDocument
+ - wfprov:Artifact
+ _id: https://dev.renku.ch/blob/5cbef5a5898d761176f551823f2fa51f28e8bd41/data/covid-19_rates/ts_rates_19-covid-recovered.csv
+ _label: data/covid-19_rates/ts_rates_19-covid-recovered.csv@5cbef5a5898d761176f551823f2fa51f28e8bd41
+ _project:
+ '@type':
+ - prov:Location
+ - schema:Project
+ _id: https://dev.renku.ch/projects/cramakri/covid-19-dashboard
+ created: '2020-03-11T21:43:12.736000+00:00'
+ creator:
+ '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:cramakri@ethz.ch
+ affiliation: null
+ alternate_name: null
+ email: cramakri@ethz.ch
+ label: Chandrasekhar Ramakrishnan
+ name: Chandrasekhar Ramakrishnan
+ name: covid-19-dashboard
+ updated: '2020-03-11T21:43:12.736000+00:00'
+ version: '1'
+ added: '2020-03-13T14:55:17.183695+00:00'
+ based_on: null
+ creator:
+ - '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:cramakri@ethz.ch
+ affiliation: null
+ alternate_name: null
+ email: cramakri@ethz.ch
+ label: Chandrasekhar Ramakrishnan
+ name: Chandrasekhar Ramakrishnan
+ name: ts_rates_19-covid-recovered.csv
+ path: data/covid-19_rates/ts_rates_19-covid-recovered.csv
+ url: data/covid-19_rates/ts_rates_19-covid-recovered.csv
+identifier: e9212b58-4994-482b-801c-ed90a960bd04
+in_language: null
+keywords: []
+license: null
+name: covid-19-rates
+path: .renku/datasets/e9212b58-4994-482b-801c-ed90a960bd04
+same_as: null
+short_name: covid-19-rates
+tags: []
+url: https://dev.renku.ch/datasets/e9212b58-4994-482b-801c-ed90a960bd04
+version: null
diff --git a/.renku/datasets/f6726a5b-f973-45d5-b873-30fa0dff772f/metadata.yml b/.renku/datasets/f6726a5b-f973-45d5-b873-30fa0dff772f/metadata.yml
new file mode 100644
index 0000000000000000000000000000000000000000..51cf86cdfe865ac460256abe28d53851fec9c556
--- /dev/null
+++ b/.renku/datasets/f6726a5b-f973-45d5-b873-30fa0dff772f/metadata.yml
@@ -0,0 +1,394 @@
+'@context':
+ '@version': 1.1
+ _id: '@id'
+ _project:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ created: schema:dateCreated
+ creator:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ affiliation: schema:affiliation
+ alternate_name: schema:alternateName
+ email: schema:email
+ label: rdfs:label
+ name: schema:name
+ prov: http://www.w3.org/ns/prov#
+ rdfs: http://www.w3.org/2000/01/rdf-schema#
+ schema: http://schema.org/
+ '@id': schema:creator
+ name: schema:name
+ prov: http://www.w3.org/ns/prov#
+ schema: http://schema.org/
+ updated: schema:dateUpdated
+ version: schema:schemaVersion
+ '@id': schema:isPartOf
+ based_on: schema:isBasedOn
+ created: schema:dateCreated
+ creator:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ affiliation: schema:affiliation
+ alternate_name: schema:alternateName
+ email: schema:email
+ label: rdfs:label
+ name: schema:name
+ prov: http://www.w3.org/ns/prov#
+ rdfs: http://www.w3.org/2000/01/rdf-schema#
+ schema: http://schema.org/
+ '@id': schema:creator
+ date_published: schema:datePublished
+ description: schema:description
+ files:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ _project:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ created: schema:dateCreated
+ creator:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ affiliation: schema:affiliation
+ alternate_name: schema:alternateName
+ email: schema:email
+ label: rdfs:label
+ name: schema:name
+ prov: http://www.w3.org/ns/prov#
+ rdfs: http://www.w3.org/2000/01/rdf-schema#
+ schema: http://schema.org/
+ '@id': schema:creator
+ name: schema:name
+ prov: http://www.w3.org/ns/prov#
+ schema: http://schema.org/
+ updated: schema:dateUpdated
+ version: schema:schemaVersion
+ '@id': schema:isPartOf
+ added: schema:dateCreated
+ based_on: schema:isBasedOn
+ creator:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ affiliation: schema:affiliation
+ alternate_name: schema:alternateName
+ email: schema:email
+ label: rdfs:label
+ name: schema:name
+ prov: http://www.w3.org/ns/prov#
+ rdfs: http://www.w3.org/2000/01/rdf-schema#
+ schema: http://schema.org/
+ '@id': schema:creator
+ name: schema:name
+ path: prov:atLocation
+ prov: http://www.w3.org/ns/prov#
+ schema: http://schema.org/
+ url: schema:url
+ wfprov: http://purl.org/wf4ever/wfprov#
+ '@id': schema:hasPart
+ identifier: schema:identifier
+ in_language:
+ '@context':
+ '@version': 1.1
+ alternate_name: schema:alternateName
+ name: schema:name
+ schema: http://schema.org/
+ '@id': schema:inLanguage
+ keywords: schema:keywords
+ license: schema:license
+ name: schema:name
+ path: prov:atLocation
+ prov: http://www.w3.org/ns/prov#
+ same_as:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ schema: http://schema.org/
+ url: schema:url
+ '@id': schema:sameAs
+ schema: http://schema.org/
+ short_name: schema:alternateName
+ tags:
+ '@context':
+ '@version': 1.1
+ _id: '@id'
+ commit: schema:location
+ created: schema:startDate
+ dataset: schema:about
+ description: schema:description
+ name: schema:name
+ schema: http://schema.org/
+ '@id': schema:subjectOf
+ url: schema:url
+ version: schema:version
+ wfprov: http://purl.org/wf4ever/wfprov#
+'@type':
+- prov:Entity
+- schema:Dataset
+- wfprov:Artifact
+_id: https://dev.renku.ch/datasets/f6726a5b-f973-45d5-b873-30fa0dff772f
+_label: f6726a5b-f973-45d5-b873-30fa0dff772f
+_project:
+ '@type':
+ - prov:Location
+ - schema:Project
+ _id: https://dev.renku.ch/projects/cramakri/covid-19-dashboard
+ created: '2020-03-11T21:43:12.736000+00:00'
+ creator:
+ '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:cramakri@ethz.ch
+ affiliation: null
+ alternate_name: null
+ email: cramakri@ethz.ch
+ label: Chandrasekhar Ramakrishnan
+ name: Chandrasekhar Ramakrishnan
+ name: covid-19-dashboard
+ updated: '2020-03-11T21:43:12.736000+00:00'
+ version: '1'
+based_on: null
+created: '2020-03-11T21:53:27.485291+00:00'
+creator:
+- '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:cramakri@ethz.ch
+ affiliation: null
+ alternate_name: null
+ email: cramakri@ethz.ch
+ label: Chandrasekhar Ramakrishnan
+ name: Chandrasekhar Ramakrishnan
+date_published: null
+description: null
+files:
+- '@type':
+ - prov:Entity
+ - schema:DigitalDocument
+ - wfprov:Artifact
+ _id: https://dev.renku.ch/blob/9dec8b0e7ac4d630fffa7e5182393d027f58ebb7/data/covid-19_jhu-csse/time_series_19-covid-Confirmed.csv
+ _label: data/covid-19_jhu-csse/time_series_19-covid-Confirmed.csv@9dec8b0e7ac4d630fffa7e5182393d027f58ebb7
+ _project:
+ '@type':
+ - prov:Location
+ - schema:Project
+ _id: https://localhost/projects/cramakri/covid-19-dashboard
+ created: '2020-03-11T21:43:12.736000+00:00'
+ creator:
+ '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:cramakri@ethz.ch
+ affiliation: null
+ alternate_name: null
+ email: cramakri@ethz.ch
+ label: Chandrasekhar Ramakrishnan
+ name: Chandrasekhar Ramakrishnan
+ name: covid-19-dashboard
+ updated: '2020-03-11T21:43:12.736000+00:00'
+ version: '1'
+ added: '2020-03-11T21:57:23.593776+00:00'
+ based_on:
+ '@type':
+ - prov:Entity
+ - schema:DigitalDocument
+ - wfprov:Artifact
+ _id: https://github.com/blob/e0ae6f6c8ab359ef6582f51453c852094255b1f9/csse_covid_19_data/csse_covid_19_time_series/time_series_19-covid-Confirmed.csv
+ _label: csse_covid_19_data/csse_covid_19_time_series/time_series_19-covid-Confirmed.csv@e0ae6f6c8ab359ef6582f51453c852094255b1f9
+ _project: null
+ added: '2020-03-11T21:57:23.351514+00:00'
+ based_on: null
+ creator: []
+ name: time_series_19-covid-Confirmed.csv
+ path: csse_covid_19_data/csse_covid_19_time_series/time_series_19-covid-Confirmed.csv
+ url: https://github.com/CSSEGISandData/COVID-19.git
+ creator:
+ - '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:ryan.lau@jhuapl.edu
+ affiliation: null
+ alternate_name: null
+ email: ryan.lau@jhuapl.edu
+ label: Ryan Lau
+ name: Ryan Lau
+ - '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:jhusystems@gmail.com
+ affiliation: null
+ alternate_name: null
+ email: jhusystems@gmail.com
+ label: CSSEGISandData
+ name: CSSEGISandData
+ - '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:60674295+CSSEGISandData@users.noreply.github.com
+ affiliation: null
+ alternate_name: null
+ email: 60674295+CSSEGISandData@users.noreply.github.com
+ label: CSSEGISandData
+ name: CSSEGISandData
+ name: time_series_19-covid-Confirmed.csv
+ path: data/covid-19_jhu-csse/time_series_19-covid-Confirmed.csv
+ url: https://github.com/CSSEGISandData/COVID-19.git
+- '@type':
+ - prov:Entity
+ - schema:DigitalDocument
+ - wfprov:Artifact
+ _id: https://dev.renku.ch/blob/9be1f743e9800aff20164e2e75e398643376dccc/data/covid-19_jhu-csse/time_series_19-covid-Deaths.csv
+ _label: data/covid-19_jhu-csse/time_series_19-covid-Deaths.csv@9be1f743e9800aff20164e2e75e398643376dccc
+ _project:
+ '@type':
+ - prov:Location
+ - schema:Project
+ _id: https://localhost/projects/cramakri/covid-19-dashboard
+ created: '2020-03-11T21:43:12.736000+00:00'
+ creator:
+ '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:cramakri@ethz.ch
+ affiliation: null
+ alternate_name: null
+ email: cramakri@ethz.ch
+ label: Chandrasekhar Ramakrishnan
+ name: Chandrasekhar Ramakrishnan
+ name: covid-19-dashboard
+ updated: '2020-03-11T21:43:12.736000+00:00'
+ version: '1'
+ added: '2020-03-11T21:57:57.824943+00:00'
+ based_on:
+ '@type':
+ - prov:Entity
+ - schema:DigitalDocument
+ - wfprov:Artifact
+ _id: https://github.com/blob/34a4321664b5364982c5fd30d6d4014d7f00d1f1/csse_covid_19_data/csse_covid_19_time_series/time_series_19-covid-Deaths.csv
+ _label: csse_covid_19_data/csse_covid_19_time_series/time_series_19-covid-Deaths.csv@34a4321664b5364982c5fd30d6d4014d7f00d1f1
+ _project: null
+ added: '2020-03-11T21:57:57.577124+00:00'
+ based_on: null
+ creator: []
+ name: time_series_19-covid-Deaths.csv
+ path: csse_covid_19_data/csse_covid_19_time_series/time_series_19-covid-Deaths.csv
+ url: https://github.com/CSSEGISandData/COVID-19.git
+ creator:
+ - '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:ryan.lau@jhuapl.edu
+ affiliation: null
+ alternate_name: null
+ email: ryan.lau@jhuapl.edu
+ label: Ryan Lau
+ name: Ryan Lau
+ - '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:jhusystems@gmail.com
+ affiliation: null
+ alternate_name: null
+ email: jhusystems@gmail.com
+ label: CSSEGISandData
+ name: CSSEGISandData
+ - '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:60674295+CSSEGISandData@users.noreply.github.com
+ affiliation: null
+ alternate_name: null
+ email: 60674295+CSSEGISandData@users.noreply.github.com
+ label: CSSEGISandData
+ name: CSSEGISandData
+ name: time_series_19-covid-Deaths.csv
+ path: data/covid-19_jhu-csse/time_series_19-covid-Deaths.csv
+ url: https://github.com/CSSEGISandData/COVID-19.git
+- '@type':
+ - prov:Entity
+ - schema:DigitalDocument
+ - wfprov:Artifact
+ _id: https://dev.renku.ch/blob/effbb6108613e4bf9730f7b818ac96f10b259274/data/covid-19_jhu-csse/time_series_19-covid-Recovered.csv
+ _label: data/covid-19_jhu-csse/time_series_19-covid-Recovered.csv@effbb6108613e4bf9730f7b818ac96f10b259274
+ _project:
+ '@type':
+ - prov:Location
+ - schema:Project
+ _id: https://dev.renku.ch/projects/cramakri/covid-19-dashboard
+ created: '2020-03-11T21:43:12.736000+00:00'
+ creator:
+ '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:cramakri@ethz.ch
+ affiliation: null
+ alternate_name: null
+ email: cramakri@ethz.ch
+ label: Chandrasekhar Ramakrishnan
+ name: Chandrasekhar Ramakrishnan
+ name: covid-19-dashboard
+ updated: '2020-03-11T21:43:12.736000+00:00'
+ version: '1'
+ added: '2020-03-11T21:58:08.577597+00:00'
+ based_on:
+ '@type':
+ - prov:Entity
+ - schema:DigitalDocument
+ - wfprov:Artifact
+ _id: https://github.com/blob/e69d4ce27fd320b1b8aaadab7a74717adb755f45/csse_covid_19_data/csse_covid_19_time_series/time_series_19-covid-Recovered.csv
+ _label: csse_covid_19_data/csse_covid_19_time_series/time_series_19-covid-Recovered.csv@e69d4ce27fd320b1b8aaadab7a74717adb755f45
+ _project: null
+ added: '2020-03-11T21:58:08.338883+00:00'
+ based_on: null
+ creator: []
+ name: time_series_19-covid-Recovered.csv
+ path: csse_covid_19_data/csse_covid_19_time_series/time_series_19-covid-Recovered.csv
+ url: https://github.com/CSSEGISandData/COVID-19.git
+ creator:
+ - '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:ryan.lau@jhuapl.edu
+ affiliation: null
+ alternate_name: null
+ email: ryan.lau@jhuapl.edu
+ label: Ryan Lau
+ name: Ryan Lau
+ - '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:jhusystems@gmail.com
+ affiliation: null
+ alternate_name: null
+ email: jhusystems@gmail.com
+ label: CSSEGISandData
+ name: CSSEGISandData
+ - '@type':
+ - prov:Person
+ - schema:Person
+ _id: mailto:60674295+CSSEGISandData@users.noreply.github.com
+ affiliation: null
+ alternate_name: null
+ email: 60674295+CSSEGISandData@users.noreply.github.com
+ label: CSSEGISandData
+ name: CSSEGISandData
+ name: time_series_19-covid-Recovered.csv
+ path: data/covid-19_jhu-csse/time_series_19-covid-Recovered.csv
+ url: https://github.com/CSSEGISandData/COVID-19.git
+identifier: f6726a5b-f973-45d5-b873-30fa0dff772f
+in_language: null
+keywords: []
+license: null
+name: covid-19_jhu-csse
+path: .renku/datasets/f6726a5b-f973-45d5-b873-30fa0dff772f
+same_as: null
+short_name: covid-19_jhu-csse
+tags: []
+url: https://dev.renku.ch/datasets/f6726a5b-f973-45d5-b873-30fa0dff772f
+version: null
diff --git a/.renku/refs/datasets/covid-19-rates b/.renku/refs/datasets/covid-19-rates
new file mode 120000
index 0000000000000000000000000000000000000000..b74ac67bb0bc3e64fb31976109c688187493a3f6
--- /dev/null
+++ b/.renku/refs/datasets/covid-19-rates
@@ -0,0 +1 @@
+../../datasets/e9212b58-4994-482b-801c-ed90a960bd04/metadata.yml
\ No newline at end of file
diff --git a/.renku/refs/datasets/covid-19_jhu-csse b/.renku/refs/datasets/covid-19_jhu-csse
new file mode 120000
index 0000000000000000000000000000000000000000..054b0e0f613e712e8266e6d8600347867a74aa62
--- /dev/null
+++ b/.renku/refs/datasets/covid-19_jhu-csse
@@ -0,0 +1 @@
+../../datasets/f6726a5b-f973-45d5-b873-30fa0dff772f/metadata.yml
\ No newline at end of file
diff --git a/.renku/refs/datasets/worldbank b/.renku/refs/datasets/worldbank
new file mode 120000
index 0000000000000000000000000000000000000000..ed44611538f29b4e780c9a409455041420c5c50f
--- /dev/null
+++ b/.renku/refs/datasets/worldbank
@@ -0,0 +1 @@
+../../datasets/720e46f5-0f38-48be-86ef-1fcbae258a6f/metadata.yml
\ No newline at end of file
diff --git a/.renku/renku.ini b/.renku/renku.ini
index 5a3d87dcf4758670ef89657de1ca745dfdaf9253..fffe2f42884b0c252d2cba3520a9a10d848ad1c9 100644
--- a/.renku/renku.ini
+++ b/.renku/renku.ini
@@ -1,2 +1,4 @@
[renku "interactive"]
default_url = /lab
+lfs_auto_fetch = true
+
diff --git a/.renku/workflow/a38f8d703e0c4c55a2e3f49bbf15466e_papermill.cwl b/.renku/workflow/a38f8d703e0c4c55a2e3f49bbf15466e_papermill.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..ee8c3ca5ce03d4f3c0ec3a8f6aefcba58f7aa740
--- /dev/null
+++ b/.renku/workflow/a38f8d703e0c4c55a2e3f49bbf15466e_papermill.cwl
@@ -0,0 +1,115 @@
+arguments: []
+baseCommand:
+- papermill
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+ input_1:
+ default: ts_folder
+ inputBinding:
+ position: 1
+ prefix: -p
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: string
+ input_2:
+ default:
+ class: Directory
+ listing: []
+ path: ../../data/covid-19_jhu-csse
+ inputBinding:
+ position: 2
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: Directory
+ input_3:
+ default: wb_path
+ inputBinding:
+ position: 3
+ prefix: -p
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: string
+ input_4:
+ default:
+ class: File
+ path: ../../data/worldbank/SP.POP.TOTL.zip
+ inputBinding:
+ position: 4
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: File
+ input_5:
+ default: out_folder
+ inputBinding:
+ position: 5
+ prefix: -p
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: string
+ input_6:
+ default: data/covid-19_rates
+ inputBinding:
+ position: 6
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: string
+ input_7:
+ default:
+ class: File
+ path: ../../notebooks/ToRates.ipynb
+ inputBinding:
+ position: 7
+ prefix: --inject-paths
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: File
+ input_8:
+ default: runs/ToRates.run.ipynb
+ inputBinding:
+ position: 8
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: string
+outputs:
+ output_0:
+ outputBinding:
+ glob: $(inputs.input_8)
+ streamable: false
+ type: File
+ output_1:
+ outputBinding:
+ glob: $(inputs.input_6)
+ streamable: false
+ type: Directory
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+ listing:
+ - entry: '$({"listing": [], "class": "Directory"})'
+ entryname: runs
+ writable: true
+ - entry: '$({"listing": [], "class": "Directory"})'
+ entryname: data/covid-19_rates
+ writable: true
+ - entry: $(inputs.input_2)
+ entryname: data/covid-19_jhu-csse
+ writable: false
+ - entry: $(inputs.input_4)
+ entryname: data/worldbank/SP.POP.TOTL.zip
+ writable: false
+ - entry: $(inputs.input_7)
+ entryname: notebooks/ToRates.ipynb
+ writable: false
+successCodes: []
+temporaryFailCodes: []
diff --git a/.renku/workflow/b1c0a33b463d406a820ff0a61fb3a526_papermill.cwl b/.renku/workflow/b1c0a33b463d406a820ff0a61fb3a526_papermill.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..335e476c4a827ba842a68d5ded0cab96ecc5ad9e
--- /dev/null
+++ b/.renku/workflow/b1c0a33b463d406a820ff0a61fb3a526_papermill.cwl
@@ -0,0 +1,91 @@
+arguments: []
+baseCommand:
+- papermill
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+ input_1:
+ default: ts_folder
+ inputBinding:
+ position: 1
+ prefix: -p
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: string
+ input_2:
+ default:
+ class: Directory
+ listing: []
+ path: ../../data/covid-19_jhu-csse
+ inputBinding:
+ position: 2
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: Directory
+ input_3:
+ default: rates_folder
+ inputBinding:
+ position: 3
+ prefix: -p
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: string
+ input_4:
+ default:
+ class: Directory
+ listing: []
+ path: ../../data/covid-19_rates
+ inputBinding:
+ position: 4
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: Directory
+ input_5:
+ default:
+ class: File
+ path: ../../notebooks/Dashboard.ipynb
+ inputBinding:
+ position: 5
+ prefix: --inject-paths
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: File
+ input_6:
+ default: runs/Dashboard.run.ipynb
+ inputBinding:
+ position: 6
+ separate: true
+ shellQuote: true
+ streamable: false
+ type: string
+outputs:
+ output_0:
+ outputBinding:
+ glob: $(inputs.input_6)
+ streamable: false
+ type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+ listing:
+ - entry: '$({"listing": [], "class": "Directory"})'
+ entryname: runs
+ writable: true
+ - entry: $(inputs.input_2)
+ entryname: data/covid-19_jhu-csse
+ writable: false
+ - entry: $(inputs.input_4)
+ entryname: data/covid-19_rates
+ writable: false
+ - entry: $(inputs.input_5)
+ entryname: notebooks/Dashboard.ipynb
+ writable: false
+successCodes: []
+temporaryFailCodes: []
diff --git a/README.md b/README.md
index a135e86b0a990be4804fecf64c775187f201c0eb..6162ee1b495f28c56215a42efa34ebb51a26d6c5 100644
--- a/README.md
+++ b/README.md
@@ -1,36 +1,15 @@
# covid-19-dashboard
-This is a Renku project - basically a git repository with some
-bells and whistles. You'll find we have already created some
-useful things like `data` and `notebooks` directories and
-a `Dockerfile`.
+A Renku project for exploring Covid-19 data sources.
-## Working with the project
+# Data Sources
-The simplest way to start your project is right from the Renku
-platform - just click on the `Environments` tab and start a new session.
-This will start an interactive environment right in your browser.
+## Covid-19
-To work with the project anywhere outside the Renku platform,
-click the `Settings` tab where you will find the
-git repo URLs - use `git` to clone the project on whichever machine you want.
+- https://github.com/CSSEGISandData/COVID-19
+- https://github.com/COVID19Tracking/covid-19-crawler
+- https://github.com/openZH/covid_19
-### Changing interactive environment dependencies
+## General
-Initially we install a very minimal set of packages to keep the images small.
-However, you can add python and conda packages in `requirements.txt` and
-`environment.yml` to your heart's content. If you need more fine-grained
-control over your environment, please see [the documentation](https://renku.readthedocs.io/en/latest/user/advanced_interfaces.html#dockerfile-modifications).
-
-## Project configuration
-
-Project options can be found in `.renku/renku.ini`. In this
-project there is currently only one option, which specifies
-the default type of environment to open, in this case `/lab` for
-JupyterLab. You may also choose `/tree` to get to the "classic" Jupyter
-interface.
-
-## Moving forward
-
-Once you feel at home with your project, we recommend that you replace
-this README file with your own project documentation! Happy data wrangling!
+- https://data.worldbank.org/indicator/SP.POP.TOTL
diff --git a/data/covid-19_jhu-csse/time_series_19-covid-Confirmed.csv b/data/covid-19_jhu-csse/time_series_19-covid-Confirmed.csv
new file mode 100644
index 0000000000000000000000000000000000000000..40bf63b8c748900b9b4b02affb4c569d80807754
--- /dev/null
+++ b/data/covid-19_jhu-csse/time_series_19-covid-Confirmed.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c16b5036fc6eab53b7e85db11dcfbc9f0eb187092219feb8c8767af7b4113a
+size 50017
diff --git a/data/covid-19_jhu-csse/time_series_19-covid-Deaths.csv b/data/covid-19_jhu-csse/time_series_19-covid-Deaths.csv
new file mode 100644
index 0000000000000000000000000000000000000000..10fd330af2955add95e1a994e69af63791c56a94
--- /dev/null
+++ b/data/covid-19_jhu-csse/time_series_19-covid-Deaths.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:292b7833b07ced4c7388eac4a6783299ad90b3d3261a3366757b1366b92e7489
+size 46566
diff --git a/data/covid-19_jhu-csse/time_series_19-covid-Recovered.csv b/data/covid-19_jhu-csse/time_series_19-covid-Recovered.csv
new file mode 100644
index 0000000000000000000000000000000000000000..cf8446fa038c9230edef9cdaf82d63b4649ed8fe
--- /dev/null
+++ b/data/covid-19_jhu-csse/time_series_19-covid-Recovered.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81dfbd00775fd18e47153f39c001ce3b3d9c2f2ab3f722a54391dc83b696f0b3
+size 48321
diff --git a/data/covid-19_rates/ts_rates_19-covid-confirmed.csv b/data/covid-19_rates/ts_rates_19-covid-confirmed.csv
new file mode 100644
index 0000000000000000000000000000000000000000..68469b73899f1a13e5dfc305c01e517f2372300f
--- /dev/null
+++ b/data/covid-19_rates/ts_rates_19-covid-confirmed.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:953941d2e4414e15f0e840d13c806b56d0cfda23f402d2d8daf840ef9e6ba666
+size 55521
diff --git a/data/covid-19_rates/ts_rates_19-covid-deaths.csv b/data/covid-19_rates/ts_rates_19-covid-deaths.csv
new file mode 100644
index 0000000000000000000000000000000000000000..927fd93f7b7d3b87e3dc685bc8e283c4d007d41d
--- /dev/null
+++ b/data/covid-19_rates/ts_rates_19-covid-deaths.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d07625575b61e275be3ba1b85e04dc96984df348680d2c3f5866a4443144138
+size 28842
diff --git a/data/covid-19_rates/ts_rates_19-covid-recovered.csv b/data/covid-19_rates/ts_rates_19-covid-recovered.csv
new file mode 100644
index 0000000000000000000000000000000000000000..c35fa7b034cd61892a7d26c0bb897288662cf439
--- /dev/null
+++ b/data/covid-19_rates/ts_rates_19-covid-recovered.csv
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eae1d5842d547e04eec2706bb61a5f5c019f244150dbab899c675ad67f166524
+size 38957
diff --git a/data/worldbank/SP.POP.TOTL.zip b/data/worldbank/SP.POP.TOTL.zip
new file mode 100644
index 0000000000000000000000000000000000000000..3fb3f388f06154e4b2db0637095cd43c233b031f
--- /dev/null
+++ b/data/worldbank/SP.POP.TOTL.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd4769dd8f6f38f1b8548ac4c8cebb933d866eaf496ff9cc4f48ed2c990e19a8
+size 78909
diff --git a/notebooks/Dashboard.ipynb b/notebooks/Dashboard.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..b7f64b2ba3651d24319f568fbe5b5810b04fd4ac
--- /dev/null
+++ b/notebooks/Dashboard.ipynb
@@ -0,0 +1,257 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import os\n",
+ "from IPython.display import display, HTML, Markdown"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "tags": [
+ "parameters"
+ ]
+ },
+ "outputs": [],
+ "source": [
+ "ts_folder = \"../data/covid-19_jhu-csse/\"\n",
+ "rates_folder = \"../data/covid-19_rates/\"\n",
+ "out_folder = None\n",
+ "PAPERMILL_OUTPUT_PATH = None"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Read in the data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def read_jhu_covid_df(name):\n",
+ " filename = os.path.join(ts_folder, f\"time_series_19-covid-{name}.csv\")\n",
+ " df = pd.read_csv(filename)\n",
+ " df = df.set_index(['Province/State', 'Country/Region', 'Lat', 'Long'])\n",
+ " df.columns = pd.to_datetime(df.columns)\n",
+ " return df\n",
+ "\n",
+ "\n",
+ "jhu_frames_map = {\n",
+ " \"confirmed\": read_jhu_covid_df(\"Confirmed\"),\n",
+ " \"deaths\": read_jhu_covid_df(\"Deaths\"),\n",
+ " \"recovered\": read_jhu_covid_df(\"Recovered\")\n",
+ "}"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def read_rates_covid_df(name):\n",
+ " filename = os.path.join(rates_folder, f\"ts_rates_19-covid-{name}.csv\")\n",
+ " df = pd.read_csv(filename).drop(\"Unnamed: 0\", axis=1)\n",
+ " df = df.set_index(['Country/Region'])\n",
+ " df.columns = pd.to_datetime(df.columns)\n",
+ " return df\n",
+ "\n",
+ "\n",
+ "rates_frames_map = {\n",
+ " \"confirmed\": read_rates_covid_df(\"confirmed\"),\n",
+ " \"deaths\": read_rates_covid_df(\"deaths\"),\n",
+ " \"recovered\": read_rates_covid_df(\"recovered\")\n",
+ "}"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Compile data needed for the visualizations"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Compute geospatial coordinates\n",
+ "country_coords_df = jhu_frames_map['confirmed'].reset_index([2,3])[['Lat', 'Long']]\n",
+ "country_coords_df = country_coords_df.groupby(level='Country/Region').mean()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Identify countries with 100 or more cases\n",
+ "case_count_ser = jhu_frames_map['confirmed'].iloc[:,-1].groupby(level='Country/Region').sum()\n",
+ "countries_over_thresh = case_count_ser[case_count_ser > 99].index"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Questions About COVID-19 and Its Spread\n",
+ "\n",
+ "These plots should be taken with a large grain of salt. I am not an epidemiologist, so the analyses shown here are completely naive. There are large discrepencies in the data from different countries for a variety of reasons (rates of testing, demographics, etc.) so that make direct comparisons inaccurate. Nonetheless, I think there is a lot of interesting information in this data."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "data_ts = jhu_frames_map['confirmed'].iloc[:,-1].name.strftime(\"%b %d %Y\")\n",
+ "display(HTML(f\"<em>Data up to {data_ts}</em>\"))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## How are cases per 100,000 distributed geographically?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import altair as alt\n",
+ "from vega_datasets import data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Compile the basic df\n",
+ "map_df = pd.concat([\n",
+ " rates_frames_map['confirmed'].iloc[:,-1],\n",
+ " rates_frames_map['deaths'].iloc[:,-1],\n",
+ " rates_frames_map['recovered'].iloc[:,-1],\n",
+ " country_coords_df], axis=1)\n",
+ "# Restrict to countries with 100 or more cases\n",
+ "map_df = map_df.loc[countries_over_thresh].dropna()\n",
+ "map_df = map_df.reset_index()\n",
+ "map_df.columns = ['Country/Region', 'Confirmed', 'Deaths', 'Recovered', 'Lat', 'Long']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def map_of_variable(map_df, variable):\n",
+ " # Data generators for the background\n",
+ " sphere = alt.sphere()\n",
+ " graticule = alt.graticule()\n",
+ "\n",
+ " # Source of land data\n",
+ " source = alt.topo_feature(data.world_110m.url, 'countries')\n",
+ "\n",
+ " # Layering and configuring the components\n",
+ " p = alt.layer(\n",
+ " alt.Chart(sphere).mark_geoshape(fill='#cae6ef'),\n",
+ " alt.Chart(graticule).mark_geoshape(stroke='white', strokeWidth=0.5),\n",
+ " alt.Chart(source).mark_geoshape(fill='#dddddd', stroke='#aaaaaa'),\n",
+ " alt.Chart(map_df).mark_circle(opacity=0.6).encode(\n",
+ " longitude='Long:Q',\n",
+ " latitude='Lat:Q',\n",
+ " size=alt.Size(f'{variable}:Q', title=\"Cases\"),\n",
+ " color=alt.value('steelblue'),\n",
+ " tooltip=[\"Country/Region:N\", \"Confirmed:Q\", \"Deaths:Q\", \"Recovered:Q\"]\n",
+ " )\n",
+ " ).project(\n",
+ " 'naturalEarth1'\n",
+ " ).properties(width=600, height=400, title=f\"{variable} cases per 100,000\"\n",
+ " ).configure_view(stroke=None)\n",
+ " return p"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "display(map_of_variable(map_df, 'Confirmed'))\n",
+ "display(HTML('''\n",
+ "<p style=\"font-size: smaller\">Data Source: \n",
+ " <a href=\"https://github.com/CSSEGISandData/COVID-19\">JHU CSSE</a> and\n",
+ " <a href=\"https://data.worldbank.org/indicator/SP.POP.TOTL\">World Bank</a>\n",
+ "</p>'''))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "bars = alt.Chart(map_df).mark_bar().encode(\n",
+ " x='Confirmed:Q',\n",
+ " y=alt.Y(\"Country/Region:N\", sort='-x')\n",
+ ")\n",
+ "\n",
+ "text = bars.mark_text(\n",
+ " align='left',\n",
+ " baseline='middle',\n",
+ " dx=3 # Nudges text to right so it doesn't appear on top of the bar\n",
+ ").encode(\n",
+ " text=alt.Text('Confirmed:Q', format=\".3\")\n",
+ ")\n",
+ "\n",
+ "(bars + text).properties(height=900)"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.7.6"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/notebooks/Preprocessing-Play.ipynb b/notebooks/Preprocessing-Play.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..71d7c4c09ee6ccfa63f74dde68db7b2a5bae675c
--- /dev/null
+++ b/notebooks/Preprocessing-Play.ipynb
@@ -0,0 +1,804 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Read in JHU CSSE data\n",
+ "\n",
+ "I will switch to [xarray](http://xarray.pydata.org/en/stable/), but ATM, it's easier like this..."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def read_jhu_covid_df(name):\n",
+ " filename = f\"../data/covid-19_jhu-csse/time_series_19-covid-{name}.csv\"\n",
+ " df = pd.read_csv(filename)\n",
+ " df = df.set_index(['Province/State', 'Country/Region', 'Lat', 'Long'])\n",
+ " df.columns = pd.to_datetime(df.columns)\n",
+ " return df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "frames_map = {\n",
+ " \"confirmed\": read_jhu_covid_df(\"Confirmed\"),\n",
+ " \"deaths\": read_jhu_covid_df(\"Deaths\"),\n",
+ " \"recovered\": read_jhu_covid_df(\"Recovered\")\n",
+ "}"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def current_region_totals_df(frames_map):\n",
+ " sers = [df.groupby(level='Country/Region').sum().iloc[:,-1].sort_values(ascending=False)\n",
+ " for name, df in frames_map.items()]\n",
+ " for name, ser in zip(frames_map, sers):\n",
+ " ser.name = name\n",
+ " return pd.concat(sers, axis=1)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>confirmed</th>\n",
+ " <th>deaths</th>\n",
+ " <th>recovered</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>Mainland China</th>\n",
+ " <td>80757</td>\n",
+ " <td>3136</td>\n",
+ " <td>60106</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Italy</th>\n",
+ " <td>10149</td>\n",
+ " <td>631</td>\n",
+ " <td>724</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Iran (Islamic Republic of)</th>\n",
+ " <td>8042</td>\n",
+ " <td>291</td>\n",
+ " <td>2731</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Republic of Korea</th>\n",
+ " <td>7513</td>\n",
+ " <td>54</td>\n",
+ " <td>247</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>France</th>\n",
+ " <td>1784</td>\n",
+ " <td>33</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Spain</th>\n",
+ " <td>1695</td>\n",
+ " <td>35</td>\n",
+ " <td>32</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>US</th>\n",
+ " <td>1670</td>\n",
+ " <td>56</td>\n",
+ " <td>15</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Germany</th>\n",
+ " <td>1457</td>\n",
+ " <td>2</td>\n",
+ " <td>18</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Others</th>\n",
+ " <td>696</td>\n",
+ " <td>6</td>\n",
+ " <td>40</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Japan</th>\n",
+ " <td>581</td>\n",
+ " <td>10</td>\n",
+ " <td>101</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Switzerland</th>\n",
+ " <td>491</td>\n",
+ " <td>3</td>\n",
+ " <td>3</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Norway</th>\n",
+ " <td>400</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>UK</th>\n",
+ " <td>382</td>\n",
+ " <td>6</td>\n",
+ " <td>18</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Netherlands</th>\n",
+ " <td>382</td>\n",
+ " <td>4</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Sweden</th>\n",
+ " <td>355</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Belgium</th>\n",
+ " <td>267</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Denmark</th>\n",
+ " <td>262</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Austria</th>\n",
+ " <td>182</td>\n",
+ " <td>0</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Singapore</th>\n",
+ " <td>160</td>\n",
+ " <td>0</td>\n",
+ " <td>78</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Malaysia</th>\n",
+ " <td>129</td>\n",
+ " <td>0</td>\n",
+ " <td>24</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Hong Kong SAR</th>\n",
+ " <td>120</td>\n",
+ " <td>3</td>\n",
+ " <td>65</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Bahrain</th>\n",
+ " <td>110</td>\n",
+ " <td>0</td>\n",
+ " <td>22</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Australia</th>\n",
+ " <td>107</td>\n",
+ " <td>3</td>\n",
+ " <td>21</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " confirmed deaths recovered\n",
+ "Mainland China 80757 3136 60106\n",
+ "Italy 10149 631 724\n",
+ "Iran (Islamic Republic of) 8042 291 2731\n",
+ "Republic of Korea 7513 54 247\n",
+ "France 1784 33 12\n",
+ "Spain 1695 35 32\n",
+ "US 1670 56 15\n",
+ "Germany 1457 2 18\n",
+ "Others 696 6 40\n",
+ "Japan 581 10 101\n",
+ "Switzerland 491 3 3\n",
+ "Norway 400 0 1\n",
+ "UK 382 6 18\n",
+ "Netherlands 382 4 0\n",
+ "Sweden 355 0 1\n",
+ "Belgium 267 0 1\n",
+ "Denmark 262 0 1\n",
+ "Austria 182 0 4\n",
+ "Singapore 160 0 78\n",
+ "Malaysia 129 0 24\n",
+ "Hong Kong SAR 120 3 65\n",
+ "Bahrain 110 0 22\n",
+ "Australia 107 3 21"
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "current_totals_df = current_region_totals_df(frames_map)\n",
+ "current_totals_df[current_totals_df['confirmed'] > 100]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Read in World Bank data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import zipfile\n",
+ "zf = zipfile.ZipFile(\"../data/worldbank/SP.POP.TOTL.zip\")\n",
+ "pop_df = pd.read_csv(zf.open(\"API_SP.POP.TOTL_DS2_en_csv_v2_821007.csv\"), skiprows=4)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "There is 2018 pop data for all countries/regions except Eritrea"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Country Name</th>\n",
+ " <th>Country Code</th>\n",
+ " <th>Indicator Name</th>\n",
+ " <th>Indicator Code</th>\n",
+ " <th>1960</th>\n",
+ " <th>1961</th>\n",
+ " <th>1962</th>\n",
+ " <th>1963</th>\n",
+ " <th>1964</th>\n",
+ " <th>1965</th>\n",
+ " <th>...</th>\n",
+ " <th>2011</th>\n",
+ " <th>2012</th>\n",
+ " <th>2013</th>\n",
+ " <th>2014</th>\n",
+ " <th>2015</th>\n",
+ " <th>2016</th>\n",
+ " <th>2017</th>\n",
+ " <th>2018</th>\n",
+ " <th>2019</th>\n",
+ " <th>Unnamed: 64</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>67</th>\n",
+ " <td>Eritrea</td>\n",
+ " <td>ERI</td>\n",
+ " <td>Population, total</td>\n",
+ " <td>SP.POP.TOTL</td>\n",
+ " <td>1007590.0</td>\n",
+ " <td>1033328.0</td>\n",
+ " <td>1060486.0</td>\n",
+ " <td>1088854.0</td>\n",
+ " <td>1118159.0</td>\n",
+ " <td>1148189.0</td>\n",
+ " <td>...</td>\n",
+ " <td>3213972.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>108</th>\n",
+ " <td>Not classified</td>\n",
+ " <td>INX</td>\n",
+ " <td>Population, total</td>\n",
+ " <td>SP.POP.TOTL</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>2 rows × 65 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Country Name Country Code Indicator Name Indicator Code 1960 \\\n",
+ "67 Eritrea ERI Population, total SP.POP.TOTL 1007590.0 \n",
+ "108 Not classified INX Population, total SP.POP.TOTL NaN \n",
+ "\n",
+ " 1961 1962 1963 1964 1965 ... 2011 \\\n",
+ "67 1033328.0 1060486.0 1088854.0 1118159.0 1148189.0 ... 3213972.0 \n",
+ "108 NaN NaN NaN NaN NaN ... NaN \n",
+ "\n",
+ " 2012 2013 2014 2015 2016 2017 2018 2019 Unnamed: 64 \n",
+ "67 NaN NaN NaN NaN NaN NaN NaN NaN NaN \n",
+ "108 NaN NaN NaN NaN NaN NaN NaN NaN NaN \n",
+ "\n",
+ "[2 rows x 65 columns]"
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pop_df[pd.isna(pop_df['2018'])]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Fix the country/region names that differ between the World Bank population data and the JHU CSSE data."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "region_wb_jhu_map = {\n",
+ " 'China': 'Mainland China',\n",
+ " 'Iran, Islamic Rep.': 'Iran (Islamic Republic of)',\n",
+ " 'Korea, Rep.': 'Republic of Korea',\n",
+ " 'United States': 'US',\n",
+ " 'United Kingdom': 'UK',\n",
+ " 'Hong Kong SAR, China': 'Hong Kong SAR',\n",
+ " 'Egypt, Arab Rep.': 'Egypt',\n",
+ " 'Vietnam': 'Viet Nam',\n",
+ " 'Macao SAR, China': 'Macao SAR',\n",
+ " 'Slovak Republic': 'Slovakia',\n",
+ " 'Moldova': 'Republic of Moldova',\n",
+ " 'St. Martin (French part)': 'Saint Martin',\n",
+ " 'Brunei Darussalam': 'Brunei'\n",
+ "}\n",
+ "current_pop_ser = pop_df[['Country Name', '2018']].copy().replace(region_wb_jhu_map).set_index('Country Name')['2018']\n",
+ "data_pop_ser = current_pop_ser[current_pop_ser.index.isin(current_totals_df.index)]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "There are some regions that we cannot resolve, but we will just ignore these."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>confirmed</th>\n",
+ " <th>deaths</th>\n",
+ " <th>recovered</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>Others</th>\n",
+ " <td>696</td>\n",
+ " <td>6</td>\n",
+ " <td>40</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Taipei and environs</th>\n",
+ " <td>47</td>\n",
+ " <td>1</td>\n",
+ " <td>17</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>occupied Palestinian territory</th>\n",
+ " <td>25</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>French Guiana</th>\n",
+ " <td>5</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Martinique</th>\n",
+ " <td>2</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Holy See</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Saint Barthelemy</th>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " confirmed deaths recovered\n",
+ "Others 696 6 40\n",
+ "Taipei and environs 47 1 17\n",
+ "occupied Palestinian territory 25 0 0\n",
+ "French Guiana 5 0 0\n",
+ "Martinique 2 0 0\n",
+ "Holy See 1 0 0\n",
+ "Saint Barthelemy 1 0 0"
+ ]
+ },
+ "execution_count": 17,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "current_totals_df[current_totals_df.index.isin(data_pop_ser.index) == False]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Compute rates per 100,000 for regions with more than 100 cases"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 23,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>confirmed</th>\n",
+ " <th>deaths</th>\n",
+ " <th>recovered</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>Italy</th>\n",
+ " <td>16.794282</td>\n",
+ " <td>1.044161</td>\n",
+ " <td>1.198055</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Republic of Korea</th>\n",
+ " <td>14.550136</td>\n",
+ " <td>0.104580</td>\n",
+ " <td>0.478355</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Iran (Islamic Republic of)</th>\n",
+ " <td>9.831264</td>\n",
+ " <td>0.355745</td>\n",
+ " <td>3.338620</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Norway</th>\n",
+ " <td>7.526810</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.018817</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Bahrain</th>\n",
+ " <td>7.008874</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>1.401775</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Mainland China</th>\n",
+ " <td>5.798468</td>\n",
+ " <td>0.225169</td>\n",
+ " <td>4.315697</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Switzerland</th>\n",
+ " <td>5.765250</td>\n",
+ " <td>0.035226</td>\n",
+ " <td>0.035226</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Denmark</th>\n",
+ " <td>4.519231</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.017249</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Spain</th>\n",
+ " <td>3.627705</td>\n",
+ " <td>0.074908</td>\n",
+ " <td>0.068488</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Sweden</th>\n",
+ " <td>3.486143</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.009820</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Singapore</th>\n",
+ " <td>2.837546</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>1.383303</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>France</th>\n",
+ " <td>2.663194</td>\n",
+ " <td>0.049263</td>\n",
+ " <td>0.017914</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Belgium</th>\n",
+ " <td>2.337580</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.008755</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Netherlands</th>\n",
+ " <td>2.216932</td>\n",
+ " <td>0.023214</td>\n",
+ " <td>0.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Austria</th>\n",
+ " <td>2.057186</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.045213</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Germany</th>\n",
+ " <td>1.756947</td>\n",
+ " <td>0.002412</td>\n",
+ " <td>0.021706</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Hong Kong SAR</th>\n",
+ " <td>1.610522</td>\n",
+ " <td>0.040263</td>\n",
+ " <td>0.872366</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>UK</th>\n",
+ " <td>0.574531</td>\n",
+ " <td>0.009024</td>\n",
+ " <td>0.027072</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>US</th>\n",
+ " <td>0.510442</td>\n",
+ " <td>0.017117</td>\n",
+ " <td>0.004585</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Japan</th>\n",
+ " <td>0.459183</td>\n",
+ " <td>0.007903</td>\n",
+ " <td>0.079824</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Australia</th>\n",
+ " <td>0.428131</td>\n",
+ " <td>0.012004</td>\n",
+ " <td>0.084026</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Malaysia</th>\n",
+ " <td>0.409153</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.076121</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " confirmed deaths recovered\n",
+ "Italy 16.794282 1.044161 1.198055\n",
+ "Republic of Korea 14.550136 0.104580 0.478355\n",
+ "Iran (Islamic Republic of) 9.831264 0.355745 3.338620\n",
+ "Norway 7.526810 0.000000 0.018817\n",
+ "Bahrain 7.008874 0.000000 1.401775\n",
+ "Mainland China 5.798468 0.225169 4.315697\n",
+ "Switzerland 5.765250 0.035226 0.035226\n",
+ "Denmark 4.519231 0.000000 0.017249\n",
+ "Spain 3.627705 0.074908 0.068488\n",
+ "Sweden 3.486143 0.000000 0.009820\n",
+ "Singapore 2.837546 0.000000 1.383303\n",
+ "France 2.663194 0.049263 0.017914\n",
+ "Belgium 2.337580 0.000000 0.008755\n",
+ "Netherlands 2.216932 0.023214 0.000000\n",
+ "Austria 2.057186 0.000000 0.045213\n",
+ "Germany 1.756947 0.002412 0.021706\n",
+ "Hong Kong SAR 1.610522 0.040263 0.872366\n",
+ "UK 0.574531 0.009024 0.027072\n",
+ "US 0.510442 0.017117 0.004585\n",
+ "Japan 0.459183 0.007903 0.079824\n",
+ "Australia 0.428131 0.012004 0.084026\n",
+ "Malaysia 0.409153 0.000000 0.076121"
+ ]
+ },
+ "execution_count": 23,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "current_per_100000_df = current_totals_df[current_totals_df['confirmed'] > 100]\n",
+ "current_per_100000_df = current_per_100000_df.div(data_pop_ser, 'index').mul(100000).dropna()\n",
+ "current_per_100000_df.sort_values('confirmed', ascending=False)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.7.6"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/notebooks/ToRates.ipynb b/notebooks/ToRates.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..6a200ae19ce750b8e141b32f30a2dc919ecf3eb1
--- /dev/null
+++ b/notebooks/ToRates.ipynb
@@ -0,0 +1,220 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Convert Series to Rates per 100,000"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import os"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "tags": [
+ "parameters"
+ ]
+ },
+ "outputs": [],
+ "source": [
+ "ts_folder = \"../data/covid-19_jhu-csse/\"\n",
+ "wb_path = \"../data/worldbank/SP.POP.TOTL.zip\"\n",
+ "out_folder = None\n",
+ "PAPERMILL_OUTPUT_PATH = None"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "tags": [
+ "parameters"
+ ]
+ },
+ "source": [
+ "## Read in JHU CSSE data\n",
+ "\n",
+ "I will switch to [xarray](http://xarray.pydata.org/en/stable/), but ATM, it's easier like this..."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def read_jhu_covid_region_df(name):\n",
+ " filename = os.path.join(ts_folder, f\"time_series_19-covid-{name}.csv\")\n",
+ " df = pd.read_csv(filename)\n",
+ " df = df.set_index(['Country/Region', 'Province/State', 'Lat', 'Long'])\n",
+ " df.columns = pd.to_datetime(df.columns)\n",
+ " region_df = df.groupby(level='Country/Region').sum()\n",
+ " loc_df = df.reset_index([2,3]).groupby(level='Country/Region').mean()[['Long', 'Lat']]\n",
+ " return region_df.join(loc_df).set_index(['Long', 'Lat'], append=True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "frames_map = {\n",
+ " \"confirmed\": read_jhu_covid_region_df(\"Confirmed\"),\n",
+ " \"deaths\": read_jhu_covid_region_df(\"Deaths\"),\n",
+ " \"recovered\": read_jhu_covid_region_df(\"Recovered\")\n",
+ "}"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "frames_map['confirmed'].sort_values(frames_map['confirmed'].columns[-1], ascending=False).head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Read in World Bank data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import zipfile\n",
+ "zf = zipfile.ZipFile(wb_path)\n",
+ "pop_df = pd.read_csv(zf.open(\"API_SP.POP.TOTL_DS2_en_csv_v2_821007.csv\"), skiprows=4)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "There is 2018 pop data for all countries/regions except Eritrea"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "pop_df[pd.isna(pop_df['2018'])]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Fix the country/region names that differ between the World Bank population data and the JHU CSSE data."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "region_wb_jhu_map = {\n",
+ " 'China': 'Mainland China',\n",
+ " 'Iran, Islamic Rep.': 'Iran (Islamic Republic of)',\n",
+ " 'Korea, Rep.': 'Republic of Korea',\n",
+ " 'United States': 'US',\n",
+ " 'United Kingdom': 'UK',\n",
+ " 'Hong Kong SAR, China': 'Hong Kong SAR',\n",
+ " 'Egypt, Arab Rep.': 'Egypt',\n",
+ " 'Vietnam': 'Viet Nam',\n",
+ " 'Macao SAR, China': 'Macao SAR',\n",
+ " 'Slovak Republic': 'Slovakia',\n",
+ " 'Moldova': 'Republic of Moldova',\n",
+ " 'St. Martin (French part)': 'Saint Martin',\n",
+ " 'Brunei Darussalam': 'Brunei'\n",
+ "}\n",
+ "current_pop_ser = pop_df[['Country Name', '2018']].copy().replace(region_wb_jhu_map).set_index('Country Name')['2018']\n",
+ "data_pop_ser = current_pop_ser[current_pop_ser.index.isin(frames_map['confirmed'].index.levels[0])]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "There are some regions that we cannot resolve, but we will just ignore these."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Compute rates per 100,000 for regions"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def cases_to_rates_df(df):\n",
+ " per_100000_df = df.reset_index([1, 2], drop=True)\n",
+ " per_100000_df = per_100000_df.div(data_pop_ser, 'index').mul(100000).dropna()\n",
+ " per_100000_df.index.name = 'Country/Region'\n",
+ " return per_100000_df\n",
+ " \n",
+ "def frames_to_rates(frames_map):\n",
+ " return {k: cases_to_rates_df(v) for k,v in frames_map.items()}\n",
+ "\n",
+ "\n",
+ "rates_map = frames_to_rates(frames_map)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "if PAPERMILL_OUTPUT_PATH:\n",
+ " for k, v in rates_map.items():\n",
+ " out_path = os.path.join(out_folder, f\"ts_rates_19-covid-{k}.csv\")\n",
+ " v.reset_index().to_csv(out_path)"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.7.6"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/requirements.txt b/requirements.txt
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..bf54e26b92023e8cb36b44ad827574dc9703aa79 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -0,0 +1,98 @@
+alembic==1.4.0
+altair==4.0.1
+ansiwrap==0.8.4
+argcomplete==1.11.1
+async-generator==1.10
+attrs==19.3.0
+backcall==0.1.0
+bleach==3.1.1
+blinker==1.4
+certifi==2019.11.28
+certipy==0.1.3
+cffi==1.13.2
+chardet==3.0.4
+Click==7.0
+colorama==0.4.3
+conda==4.7.12
+conda-package-handling==1.6.0
+cryptography==2.8
+decorator==4.4.1
+defusedxml==0.6.0
+distro==1.4.0
+entrypoints==0.3
+future==0.18.2
+gitdb==4.0.2
+GitPython==3.1.0
+idna==2.9
+importlib-metadata==1.5.0
+ipykernel==5.1.4
+ipython==7.12.0
+ipython-genutils==0.2.0
+jedi==0.16.0
+Jinja2==2.11.1
+json5==0.9.0
+jsonschema==3.2.0
+jupyter-client==6.0.0
+jupyter-core==4.6.3
+jupyter-telemetry==0.0.5
+jupyterhub==0.9.6
+jupyterlab==1.2.5
+jupyterlab-git==0.9.0
+jupyterlab-server==1.0.6
+Mako==1.1.0
+MarkupSafe==1.1.1
+mistune==0.8.4
+nbconvert==5.6.1
+nbdime==1.1.0
+nbformat==5.0.4
+notebook==6.0.3
+numpy==1.18.1
+oauthlib==3.0.1
+pamela==1.0.0
+pandas==1.0.1
+pandocfilters==1.4.2
+papermill==1.1.0
+parso==0.6.1
+pexpect==4.8.0
+pickleshare==0.7.5
+pipx==0.15.1.3
+powerline-shell==0.7.0
+prometheus-client==0.7.1
+prompt-toolkit==3.0.3
+ptyprocess==0.6.0
+pycosat==0.6.3
+pycparser==2.19
+pycurl==7.43.0.5
+Pygments==2.5.2
+PyJWT==1.7.1
+pyOpenSSL==19.1.0
+pyrsistent==0.15.7
+PySocks==1.7.1
+python-dateutil==2.8.1
+python-editor==1.0.4
+python-json-logger==0.1.11
+python-oauth2==1.1.1
+pytz==2019.3
+PyYAML==5.3
+pyzmq==19.0.0
+requests==2.23.0
+ruamel-yaml==0.15.80
+ruamel.yaml.clib==0.2.0
+Send2Trash==1.5.0
+six==1.14.0
+smmap==3.0.1
+SQLAlchemy==1.3.13
+tenacity==6.1.0
+terminado==0.8.3
+testpath==0.4.4
+textwrap3==0.9.2
+toolz==0.10.0
+tornado==6.0.3
+tqdm==4.43.0
+traitlets==4.3.3
+urllib3==1.25.7
+userpath==1.3.0
+vega-datasets==0.8.0
+wcwidth==0.1.8
+webencodings==0.5.1
+zipp==3.0.0
diff --git a/runs/Dashboard.run.ipynb b/runs/Dashboard.run.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..8ee68b5da01772bb9e712ece6093a1cbf2df62c1
--- /dev/null
+++ b/runs/Dashboard.run.ipynb
@@ -0,0 +1,587 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {
+ "papermill": {
+ "duration": 0.35409,
+ "end_time": "2020-03-13T17:04:15.061697",
+ "exception": false,
+ "start_time": "2020-03-13T17:04:14.707607",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import os\n",
+ "from IPython.display import display, HTML, Markdown"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {
+ "papermill": {
+ "duration": 0.02437,
+ "end_time": "2020-03-13T17:04:15.106586",
+ "exception": false,
+ "start_time": "2020-03-13T17:04:15.082216",
+ "status": "completed"
+ },
+ "tags": [
+ "parameters"
+ ]
+ },
+ "outputs": [],
+ "source": [
+ "ts_folder = \"../data/covid-19_jhu-csse/\"\n",
+ "rates_folder = \"../data/covid-19_rates/\"\n",
+ "out_folder = None\n",
+ "PAPERMILL_OUTPUT_PATH = None"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {
+ "papermill": {
+ "duration": 0.022646,
+ "end_time": "2020-03-13T17:04:15.137496",
+ "exception": false,
+ "start_time": "2020-03-13T17:04:15.114850",
+ "status": "completed"
+ },
+ "tags": [
+ "injected-parameters"
+ ]
+ },
+ "outputs": [],
+ "source": [
+ "# Parameters\n",
+ "PAPERMILL_INPUT_PATH = \"notebooks/Dashboard.ipynb\"\n",
+ "PAPERMILL_OUTPUT_PATH = \"runs/Dashboard.run.ipynb\"\n",
+ "ts_folder = \"./data/covid-19_jhu-csse/\"\n",
+ "rates_folder = \"./data/covid-19_rates/\"\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {
+ "papermill": {
+ "duration": 0.021072,
+ "end_time": "2020-03-13T17:04:15.168525",
+ "exception": false,
+ "start_time": "2020-03-13T17:04:15.147453",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# Read in the data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {
+ "papermill": {
+ "duration": 0.065756,
+ "end_time": "2020-03-13T17:04:15.243131",
+ "exception": false,
+ "start_time": "2020-03-13T17:04:15.177375",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "def read_jhu_covid_df(name):\n",
+ " filename = os.path.join(ts_folder, f\"time_series_19-covid-{name}.csv\")\n",
+ " df = pd.read_csv(filename)\n",
+ " df = df.set_index(['Province/State', 'Country/Region', 'Lat', 'Long'])\n",
+ " df.columns = pd.to_datetime(df.columns)\n",
+ " return df\n",
+ "\n",
+ "\n",
+ "jhu_frames_map = {\n",
+ " \"confirmed\": read_jhu_covid_df(\"Confirmed\"),\n",
+ " \"deaths\": read_jhu_covid_df(\"Deaths\"),\n",
+ " \"recovered\": read_jhu_covid_df(\"Recovered\")\n",
+ "}"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {
+ "papermill": {
+ "duration": 0.038039,
+ "end_time": "2020-03-13T17:04:15.289236",
+ "exception": false,
+ "start_time": "2020-03-13T17:04:15.251197",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "def read_rates_covid_df(name):\n",
+ " filename = os.path.join(rates_folder, f\"ts_rates_19-covid-{name}.csv\")\n",
+ " df = pd.read_csv(filename).drop(\"Unnamed: 0\", axis=1)\n",
+ " df = df.set_index(['Country/Region'])\n",
+ " df.columns = pd.to_datetime(df.columns)\n",
+ " return df\n",
+ "\n",
+ "\n",
+ "rates_frames_map = {\n",
+ " \"confirmed\": read_rates_covid_df(\"confirmed\"),\n",
+ " \"deaths\": read_rates_covid_df(\"deaths\"),\n",
+ " \"recovered\": read_rates_covid_df(\"recovered\")\n",
+ "}"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {
+ "papermill": {
+ "duration": 0.017688,
+ "end_time": "2020-03-13T17:04:15.314301",
+ "exception": false,
+ "start_time": "2020-03-13T17:04:15.296613",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# Compile data needed for the visualizations"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {
+ "papermill": {
+ "duration": 0.040604,
+ "end_time": "2020-03-13T17:04:15.374996",
+ "exception": false,
+ "start_time": "2020-03-13T17:04:15.334392",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# Compute geospatial coordinates\n",
+ "country_coords_df = jhu_frames_map['confirmed'].reset_index([2,3])[['Lat', 'Long']]\n",
+ "country_coords_df = country_coords_df.groupby(level='Country/Region').mean()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {
+ "papermill": {
+ "duration": 0.034326,
+ "end_time": "2020-03-13T17:04:15.424734",
+ "exception": false,
+ "start_time": "2020-03-13T17:04:15.390408",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# Identify countries with 100 or more cases\n",
+ "case_count_ser = jhu_frames_map['confirmed'].iloc[:,-1].groupby(level='Country/Region').sum()\n",
+ "countries_over_thresh = case_count_ser[case_count_ser > 99].index"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "papermill": {
+ "duration": 0.009134,
+ "end_time": "2020-03-13T17:04:15.448316",
+ "exception": false,
+ "start_time": "2020-03-13T17:04:15.439182",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "source": [
+ "# Questions About COVID-19 and Its Spread\n",
+ "\n",
+ "These plots should be taken with a large grain of salt. I am not an epidemiologist, so the analyses shown here are completely naive. There are large discrepencies in the data from different countries for a variety of reasons (rates of testing, demographics, etc.) so that make direct comparisons inaccurate. Nonetheless, I think there is a lot of interesting information in this data."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {
+ "papermill": {
+ "duration": 0.041449,
+ "end_time": "2020-03-13T17:04:15.498158",
+ "exception": false,
+ "start_time": "2020-03-13T17:04:15.456709",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<em>Data up to Mar 10 2020</em>"
+ ],
+ "text/plain": [
+ "<IPython.core.display.HTML object>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "data_ts = jhu_frames_map['confirmed'].iloc[:,-1].name.strftime(\"%b %d %Y\")\n",
+ "display(HTML(f\"<em>Data up to {data_ts}</em>\"))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "papermill": {
+ "duration": 0.009938,
+ "end_time": "2020-03-13T17:04:15.526404",
+ "exception": false,
+ "start_time": "2020-03-13T17:04:15.516466",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "source": [
+ "## How are cases per 100,000 distributed geographically?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "metadata": {
+ "papermill": {
+ "duration": 0.199352,
+ "end_time": "2020-03-13T17:04:15.733984",
+ "exception": false,
+ "start_time": "2020-03-13T17:04:15.534632",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "import altair as alt\n",
+ "from vega_datasets import data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "metadata": {
+ "papermill": {
+ "duration": 0.045428,
+ "end_time": "2020-03-13T17:04:15.799713",
+ "exception": false,
+ "start_time": "2020-03-13T17:04:15.754285",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "# Compile the basic df\n",
+ "map_df = pd.concat([\n",
+ " rates_frames_map['confirmed'].iloc[:,-1],\n",
+ " rates_frames_map['deaths'].iloc[:,-1],\n",
+ " rates_frames_map['recovered'].iloc[:,-1],\n",
+ " country_coords_df], axis=1)\n",
+ "# Restrict to countries with 100 or more cases\n",
+ "map_df = map_df.loc[countries_over_thresh].dropna()\n",
+ "map_df = map_df.reset_index()\n",
+ "map_df.columns = ['Country/Region', 'Confirmed', 'Deaths', 'Recovered', 'Lat', 'Long']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "metadata": {
+ "papermill": {
+ "duration": 0.030132,
+ "end_time": "2020-03-13T17:04:15.844929",
+ "exception": false,
+ "start_time": "2020-03-13T17:04:15.814797",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "def map_of_variable(map_df, variable):\n",
+ " # Data generators for the background\n",
+ " sphere = alt.sphere()\n",
+ " graticule = alt.graticule()\n",
+ "\n",
+ " # Source of land data\n",
+ " source = alt.topo_feature(data.world_110m.url, 'countries')\n",
+ "\n",
+ " # Layering and configuring the components\n",
+ " p = alt.layer(\n",
+ " alt.Chart(sphere).mark_geoshape(fill='#cae6ef'),\n",
+ " alt.Chart(graticule).mark_geoshape(stroke='white', strokeWidth=0.5),\n",
+ " alt.Chart(source).mark_geoshape(fill='#dddddd', stroke='#aaaaaa'),\n",
+ " alt.Chart(map_df).mark_circle(opacity=0.6).encode(\n",
+ " longitude='Long:Q',\n",
+ " latitude='Lat:Q',\n",
+ " size=alt.Size(f'{variable}:Q', title=\"Cases\"),\n",
+ " color=alt.value('steelblue'),\n",
+ " tooltip=[\"Country/Region:N\", \"Confirmed:Q\", \"Deaths:Q\", \"Recovered:Q\"]\n",
+ " )\n",
+ " ).project(\n",
+ " 'naturalEarth1'\n",
+ " ).properties(width=600, height=400, title=f\"{variable} cases per 100,000\"\n",
+ " ).configure_view(stroke=None)\n",
+ " return p"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "metadata": {
+ "papermill": {
+ "duration": 0.100208,
+ "end_time": "2020-03-13T17:04:15.958509",
+ "exception": false,
+ "start_time": "2020-03-13T17:04:15.858301",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "<div id=\"altair-viz-b79eb79d0e8f4b50be1688903bb8f9f0\"></div>\n",
+ "<script type=\"text/javascript\">\n",
+ " (function(spec, embedOpt){\n",
+ " const outputDiv = document.getElementById(\"altair-viz-b79eb79d0e8f4b50be1688903bb8f9f0\");\n",
+ " const paths = {\n",
+ " \"vega\": \"https://cdn.jsdelivr.net/npm//vega@5?noext\",\n",
+ " \"vega-lib\": \"https://cdn.jsdelivr.net/npm//vega-lib?noext\",\n",
+ " \"vega-lite\": \"https://cdn.jsdelivr.net/npm//vega-lite@4.0.2?noext\",\n",
+ " \"vega-embed\": \"https://cdn.jsdelivr.net/npm//vega-embed@6?noext\",\n",
+ " };\n",
+ "\n",
+ " function loadScript(lib) {\n",
+ " return new Promise(function(resolve, reject) {\n",
+ " var s = document.createElement('script');\n",
+ " s.src = paths[lib];\n",
+ " s.async = true;\n",
+ " s.onload = () => resolve(paths[lib]);\n",
+ " s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+ " document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+ " });\n",
+ " }\n",
+ "\n",
+ " function showError(err) {\n",
+ " outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+ " throw err;\n",
+ " }\n",
+ "\n",
+ " function displayChart(vegaEmbed) {\n",
+ " vegaEmbed(outputDiv, spec, embedOpt)\n",
+ " .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+ " }\n",
+ "\n",
+ " if(typeof define === \"function\" && define.amd) {\n",
+ " requirejs.config({paths});\n",
+ " require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+ " } else if (typeof vegaEmbed === \"function\") {\n",
+ " displayChart(vegaEmbed);\n",
+ " } else {\n",
+ " loadScript(\"vega\")\n",
+ " .then(() => loadScript(\"vega-lite\"))\n",
+ " .then(() => loadScript(\"vega-embed\"))\n",
+ " .catch(showError)\n",
+ " .then(() => displayChart(vegaEmbed));\n",
+ " }\n",
+ " })({\"config\": {\"view\": {\"continuousWidth\": 400, \"continuousHeight\": 300, \"stroke\": null}}, \"layer\": [{\"data\": {\"sphere\": true}, \"mark\": {\"type\": \"geoshape\", \"fill\": \"#cae6ef\"}}, {\"data\": {\"graticule\": true}, \"mark\": {\"type\": \"geoshape\", \"stroke\": \"white\", \"strokeWidth\": 0.5}}, {\"data\": {\"url\": \"https://vega.github.io/vega-datasets/data/world-110m.json\", \"format\": {\"feature\": \"countries\", \"type\": \"topojson\"}}, \"mark\": {\"type\": \"geoshape\", \"fill\": \"#dddddd\", \"stroke\": \"#aaaaaa\"}}, {\"data\": {\"name\": \"data-433f706ddfa6221156e78c265aebad1f\"}, \"mark\": {\"type\": \"circle\", \"opacity\": 0.6}, \"encoding\": {\"color\": {\"value\": \"steelblue\"}, \"latitude\": {\"field\": \"Lat\", \"type\": \"quantitative\"}, \"longitude\": {\"field\": \"Long\", \"type\": \"quantitative\"}, \"size\": {\"type\": \"quantitative\", \"field\": \"Confirmed\", \"title\": \"Cases\"}, \"tooltip\": [{\"type\": \"nominal\", \"field\": \"Country/Region\"}, {\"type\": \"quantitative\", \"field\": \"Confirmed\"}, {\"type\": \"quantitative\", \"field\": \"Deaths\"}, {\"type\": \"quantitative\", \"field\": \"Recovered\"}]}}], \"height\": 400, \"projection\": {\"type\": \"naturalEarth1\"}, \"title\": \"Confirmed cases per 100,000\", \"width\": 600, \"$schema\": \"https://vega.github.io/schema/vega-lite/v4.0.2.json\", \"datasets\": {\"data-433f706ddfa6221156e78c265aebad1f\": [{\"Country/Region\": \"Australia\", \"Confirmed\": 0.4281306826095598, \"Deaths\": 0.012003663998398872, \"Recovered\": 0.0840256479887921, \"Lat\": -23.1315375, \"Long\": 140.0609875}, {\"Country/Region\": \"Austria\", \"Confirmed\": 2.057185925638154, \"Deaths\": 0.0, \"Recovered\": 0.04521287748655284, \"Lat\": 47.5162, \"Long\": 14.5501}, {\"Country/Region\": \"Bahrain\", \"Confirmed\": 7.00887387149166, \"Deaths\": 0.0, \"Recovered\": 1.4017747742983322, \"Lat\": 26.0275, \"Long\": 50.55}, {\"Country/Region\": \"Belgium\", \"Confirmed\": 2.3375802000128174, \"Deaths\": 0.0, \"Recovered\": 0.008754982022519914, \"Lat\": 50.8333, \"Long\": 4.0}, {\"Country/Region\": \"Denmark\", \"Confirmed\": 4.519231399481772, \"Deaths\": 0.0, \"Recovered\": 0.01724897480718234, \"Lat\": 56.2639, \"Long\": 9.5018}, {\"Country/Region\": \"France\", \"Confirmed\": 2.663193607427707, \"Deaths\": 0.04926311045129727, \"Recovered\": 0.017913858345926282, \"Lat\": 47.0, \"Long\": 2.0}, {\"Country/Region\": \"Germany\", \"Confirmed\": 1.7569474368355689, \"Deaths\": 0.0024117329263357162, \"Recovered\": 0.021705596337021446, \"Lat\": 51.0, \"Long\": 9.0}, {\"Country/Region\": \"Hong Kong SAR\", \"Confirmed\": 1.61052207757348, \"Deaths\": 0.040263051939337005, \"Recovered\": 0.8723661253523016, \"Lat\": 22.3, \"Long\": 114.2}, {\"Country/Region\": \"Iran (Islamic Republic of)\", \"Confirmed\": 9.831263513326588, \"Deaths\": 0.3557445514023921, \"Recovered\": 3.3386198277660917, \"Lat\": 32.0, \"Long\": 53.0}, {\"Country/Region\": \"Italy\", \"Confirmed\": 16.794281862259982, \"Deaths\": 1.0441611838689575, \"Recovered\": 1.198054987513669, \"Lat\": 43.0, \"Long\": 12.0}, {\"Country/Region\": \"Japan\", \"Confirmed\": 0.4591829073311989, \"Deaths\": 0.007903320263876057, \"Recovered\": 0.07982353466514817, \"Lat\": 36.0, \"Long\": 138.0}, {\"Country/Region\": \"Mainland China\", \"Confirmed\": 5.798467757569664, \"Deaths\": 0.2251692718617392, \"Recovered\": 4.315696509732684, \"Lat\": 33.40693612903227, \"Long\": 111.54290322580646}, {\"Country/Region\": \"Malaysia\", \"Confirmed\": 0.4091525198482584, \"Deaths\": 0.0, \"Recovered\": 0.07612139904153642, \"Lat\": 2.5, \"Long\": 112.5}, {\"Country/Region\": \"Netherlands\", \"Confirmed\": 2.216932407413909, \"Deaths\": 0.02321395191009329, \"Recovered\": 0.0, \"Lat\": 52.1326, \"Long\": 5.2913}, {\"Country/Region\": \"Norway\", \"Confirmed\": 7.526810498997428, \"Deaths\": 0.0, \"Recovered\": 0.018817026247493568, \"Lat\": 60.472, \"Long\": 8.4689}, {\"Country/Region\": \"Republic of Korea\", \"Confirmed\": 14.550136054326911, \"Deaths\": 0.10457970809711876, \"Recovered\": 0.4783553314812655, \"Lat\": 36.0, \"Long\": 128.0}, {\"Country/Region\": \"Singapore\", \"Confirmed\": 2.837545551473431, \"Deaths\": 0.0, \"Recovered\": 1.3833034563432978, \"Lat\": 1.2833, \"Long\": 103.8333}, {\"Country/Region\": \"Spain\", \"Confirmed\": 3.6277054737195855, \"Deaths\": 0.07490837261367876, \"Recovered\": 0.06848765496107773, \"Lat\": 40.0, \"Long\": -4.0}, {\"Country/Region\": \"Sweden\", \"Confirmed\": 3.4861425832316537, \"Deaths\": 0.0, \"Recovered\": 0.009820119952765223, \"Lat\": 63.0, \"Long\": 16.0}, {\"Country/Region\": \"Switzerland\", \"Confirmed\": 5.7652500550986465, \"Deaths\": 0.035225560418118015, \"Recovered\": 0.035225560418118015, \"Lat\": 46.8182, \"Long\": 8.2275}, {\"Country/Region\": \"UK\", \"Confirmed\": 0.5745312032182892, \"Deaths\": 0.009024050312329149, \"Recovered\": 0.027072150936987446, \"Lat\": 55.0, \"Long\": -3.0}, {\"Country/Region\": \"US\", \"Confirmed\": 0.5104420019995022, \"Deaths\": 0.017116618031121033, \"Recovered\": 0.004584808401193134, \"Lat\": 38.77302746113991, \"Long\": -93.61047823834195}]}}, {\"mode\": \"vega-lite\"});\n",
+ "</script>"
+ ],
+ "text/plain": [
+ "alt.LayerChart(...)"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "<p style=\"font-size: smaller\">Data Source: \n",
+ " <a href=\"https://github.com/CSSEGISandData/COVID-19\">JHU CSSE</a> and\n",
+ " <a href=\"https://data.worldbank.org/indicator/SP.POP.TOTL\">World Bank</a>\n",
+ "</p>"
+ ],
+ "text/plain": [
+ "<IPython.core.display.HTML object>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "display(map_of_variable(map_df, 'Confirmed'))\n",
+ "display(HTML('''\n",
+ "<p style=\"font-size: smaller\">Data Source: \n",
+ " <a href=\"https://github.com/CSSEGISandData/COVID-19\">JHU CSSE</a> and\n",
+ " <a href=\"https://data.worldbank.org/indicator/SP.POP.TOTL\">World Bank</a>\n",
+ "</p>'''))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "metadata": {
+ "papermill": {
+ "duration": 0.062654,
+ "end_time": "2020-03-13T17:04:16.037936",
+ "exception": false,
+ "start_time": "2020-03-13T17:04:15.975282",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "<div id=\"altair-viz-a0d74fce564e44529149f3e190cf879e\"></div>\n",
+ "<script type=\"text/javascript\">\n",
+ " (function(spec, embedOpt){\n",
+ " const outputDiv = document.getElementById(\"altair-viz-a0d74fce564e44529149f3e190cf879e\");\n",
+ " const paths = {\n",
+ " \"vega\": \"https://cdn.jsdelivr.net/npm//vega@5?noext\",\n",
+ " \"vega-lib\": \"https://cdn.jsdelivr.net/npm//vega-lib?noext\",\n",
+ " \"vega-lite\": \"https://cdn.jsdelivr.net/npm//vega-lite@4.0.2?noext\",\n",
+ " \"vega-embed\": \"https://cdn.jsdelivr.net/npm//vega-embed@6?noext\",\n",
+ " };\n",
+ "\n",
+ " function loadScript(lib) {\n",
+ " return new Promise(function(resolve, reject) {\n",
+ " var s = document.createElement('script');\n",
+ " s.src = paths[lib];\n",
+ " s.async = true;\n",
+ " s.onload = () => resolve(paths[lib]);\n",
+ " s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
+ " document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
+ " });\n",
+ " }\n",
+ "\n",
+ " function showError(err) {\n",
+ " outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
+ " throw err;\n",
+ " }\n",
+ "\n",
+ " function displayChart(vegaEmbed) {\n",
+ " vegaEmbed(outputDiv, spec, embedOpt)\n",
+ " .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
+ " }\n",
+ "\n",
+ " if(typeof define === \"function\" && define.amd) {\n",
+ " requirejs.config({paths});\n",
+ " require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+ " } else if (typeof vegaEmbed === \"function\") {\n",
+ " displayChart(vegaEmbed);\n",
+ " } else {\n",
+ " loadScript(\"vega\")\n",
+ " .then(() => loadScript(\"vega-lite\"))\n",
+ " .then(() => loadScript(\"vega-embed\"))\n",
+ " .catch(showError)\n",
+ " .then(() => displayChart(vegaEmbed));\n",
+ " }\n",
+ " })({\"config\": {\"view\": {\"continuousWidth\": 400, \"continuousHeight\": 300}}, \"layer\": [{\"mark\": \"bar\", \"encoding\": {\"x\": {\"type\": \"quantitative\", \"field\": \"Confirmed\"}, \"y\": {\"type\": \"nominal\", \"field\": \"Country/Region\", \"sort\": \"-x\"}}}, {\"mark\": {\"type\": \"text\", \"align\": \"left\", \"baseline\": \"middle\", \"dx\": 3}, \"encoding\": {\"text\": {\"type\": \"quantitative\", \"field\": \"Confirmed\", \"format\": \".3\"}, \"x\": {\"type\": \"quantitative\", \"field\": \"Confirmed\"}, \"y\": {\"type\": \"nominal\", \"field\": \"Country/Region\", \"sort\": \"-x\"}}}], \"data\": {\"name\": \"data-433f706ddfa6221156e78c265aebad1f\"}, \"height\": 900, \"$schema\": \"https://vega.github.io/schema/vega-lite/v4.0.2.json\", \"datasets\": {\"data-433f706ddfa6221156e78c265aebad1f\": [{\"Country/Region\": \"Australia\", \"Confirmed\": 0.4281306826095598, \"Deaths\": 0.012003663998398872, \"Recovered\": 0.0840256479887921, \"Lat\": -23.1315375, \"Long\": 140.0609875}, {\"Country/Region\": \"Austria\", \"Confirmed\": 2.057185925638154, \"Deaths\": 0.0, \"Recovered\": 0.04521287748655284, \"Lat\": 47.5162, \"Long\": 14.5501}, {\"Country/Region\": \"Bahrain\", \"Confirmed\": 7.00887387149166, \"Deaths\": 0.0, \"Recovered\": 1.4017747742983322, \"Lat\": 26.0275, \"Long\": 50.55}, {\"Country/Region\": \"Belgium\", \"Confirmed\": 2.3375802000128174, \"Deaths\": 0.0, \"Recovered\": 0.008754982022519914, \"Lat\": 50.8333, \"Long\": 4.0}, {\"Country/Region\": \"Denmark\", \"Confirmed\": 4.519231399481772, \"Deaths\": 0.0, \"Recovered\": 0.01724897480718234, \"Lat\": 56.2639, \"Long\": 9.5018}, {\"Country/Region\": \"France\", \"Confirmed\": 2.663193607427707, \"Deaths\": 0.04926311045129727, \"Recovered\": 0.017913858345926282, \"Lat\": 47.0, \"Long\": 2.0}, {\"Country/Region\": \"Germany\", \"Confirmed\": 1.7569474368355689, \"Deaths\": 0.0024117329263357162, \"Recovered\": 0.021705596337021446, \"Lat\": 51.0, \"Long\": 9.0}, {\"Country/Region\": \"Hong Kong SAR\", \"Confirmed\": 1.61052207757348, \"Deaths\": 0.040263051939337005, \"Recovered\": 0.8723661253523016, \"Lat\": 22.3, \"Long\": 114.2}, {\"Country/Region\": \"Iran (Islamic Republic of)\", \"Confirmed\": 9.831263513326588, \"Deaths\": 0.3557445514023921, \"Recovered\": 3.3386198277660917, \"Lat\": 32.0, \"Long\": 53.0}, {\"Country/Region\": \"Italy\", \"Confirmed\": 16.794281862259982, \"Deaths\": 1.0441611838689575, \"Recovered\": 1.198054987513669, \"Lat\": 43.0, \"Long\": 12.0}, {\"Country/Region\": \"Japan\", \"Confirmed\": 0.4591829073311989, \"Deaths\": 0.007903320263876057, \"Recovered\": 0.07982353466514817, \"Lat\": 36.0, \"Long\": 138.0}, {\"Country/Region\": \"Mainland China\", \"Confirmed\": 5.798467757569664, \"Deaths\": 0.2251692718617392, \"Recovered\": 4.315696509732684, \"Lat\": 33.40693612903227, \"Long\": 111.54290322580646}, {\"Country/Region\": \"Malaysia\", \"Confirmed\": 0.4091525198482584, \"Deaths\": 0.0, \"Recovered\": 0.07612139904153642, \"Lat\": 2.5, \"Long\": 112.5}, {\"Country/Region\": \"Netherlands\", \"Confirmed\": 2.216932407413909, \"Deaths\": 0.02321395191009329, \"Recovered\": 0.0, \"Lat\": 52.1326, \"Long\": 5.2913}, {\"Country/Region\": \"Norway\", \"Confirmed\": 7.526810498997428, \"Deaths\": 0.0, \"Recovered\": 0.018817026247493568, \"Lat\": 60.472, \"Long\": 8.4689}, {\"Country/Region\": \"Republic of Korea\", \"Confirmed\": 14.550136054326911, \"Deaths\": 0.10457970809711876, \"Recovered\": 0.4783553314812655, \"Lat\": 36.0, \"Long\": 128.0}, {\"Country/Region\": \"Singapore\", \"Confirmed\": 2.837545551473431, \"Deaths\": 0.0, \"Recovered\": 1.3833034563432978, \"Lat\": 1.2833, \"Long\": 103.8333}, {\"Country/Region\": \"Spain\", \"Confirmed\": 3.6277054737195855, \"Deaths\": 0.07490837261367876, \"Recovered\": 0.06848765496107773, \"Lat\": 40.0, \"Long\": -4.0}, {\"Country/Region\": \"Sweden\", \"Confirmed\": 3.4861425832316537, \"Deaths\": 0.0, \"Recovered\": 0.009820119952765223, \"Lat\": 63.0, \"Long\": 16.0}, {\"Country/Region\": \"Switzerland\", \"Confirmed\": 5.7652500550986465, \"Deaths\": 0.035225560418118015, \"Recovered\": 0.035225560418118015, \"Lat\": 46.8182, \"Long\": 8.2275}, {\"Country/Region\": \"UK\", \"Confirmed\": 0.5745312032182892, \"Deaths\": 0.009024050312329149, \"Recovered\": 0.027072150936987446, \"Lat\": 55.0, \"Long\": -3.0}, {\"Country/Region\": \"US\", \"Confirmed\": 0.5104420019995022, \"Deaths\": 0.017116618031121033, \"Recovered\": 0.004584808401193134, \"Lat\": 38.77302746113991, \"Long\": -93.61047823834195}]}}, {\"mode\": \"vega-lite\"});\n",
+ "</script>"
+ ],
+ "text/plain": [
+ "alt.LayerChart(...)"
+ ]
+ },
+ "execution_count": 15,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "bars = alt.Chart(map_df).mark_bar().encode(\n",
+ " x='Confirmed:Q',\n",
+ " y=alt.Y(\"Country/Region:N\", sort='-x')\n",
+ ")\n",
+ "\n",
+ "text = bars.mark_text(\n",
+ " align='left',\n",
+ " baseline='middle',\n",
+ " dx=3 # Nudges text to right so it doesn't appear on top of the bar\n",
+ ").encode(\n",
+ " text=alt.Text('Confirmed:Q', format=\".3\")\n",
+ ")\n",
+ "\n",
+ "(bars + text).properties(height=900)"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.7.6"
+ },
+ "papermill": {
+ "duration": 2.520956,
+ "end_time": "2020-03-13T17:04:16.371464",
+ "environment_variables": {},
+ "exception": null,
+ "input_path": "notebooks/Dashboard.ipynb",
+ "output_path": "runs/Dashboard.run.ipynb",
+ "parameters": {
+ "PAPERMILL_INPUT_PATH": "notebooks/Dashboard.ipynb",
+ "PAPERMILL_OUTPUT_PATH": "runs/Dashboard.run.ipynb",
+ "rates_folder": "./data/covid-19_rates/",
+ "ts_folder": "./data/covid-19_jhu-csse/"
+ },
+ "start_time": "2020-03-13T17:04:13.850508",
+ "version": "1.1.0"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
\ No newline at end of file
diff --git a/runs/ToRates.run.ipynb b/runs/ToRates.run.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..2925f4eefd7a6bff1c917d01551b49198f9d0e50
--- /dev/null
+++ b/runs/ToRates.run.ipynb
@@ -0,0 +1,827 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "papermill": {
+ "duration": 0.019737,
+ "end_time": "2020-03-13T14:54:48.276145",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:48.256408",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "source": [
+ "# Convert Series to Rates per 100,000"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {
+ "papermill": {
+ "duration": 0.327112,
+ "end_time": "2020-03-13T14:54:48.613995",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:48.286883",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import os"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {
+ "papermill": {
+ "duration": 0.025647,
+ "end_time": "2020-03-13T14:54:48.658686",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:48.633039",
+ "status": "completed"
+ },
+ "tags": [
+ "parameters"
+ ]
+ },
+ "outputs": [],
+ "source": [
+ "ts_folder = \"../data/covid-19_jhu-csse/\"\n",
+ "wb_path = \"../data/worldbank/SP.POP.TOTL.zip\"\n",
+ "out_folder = None\n",
+ "PAPERMILL_OUTPUT_PATH = None"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {
+ "papermill": {
+ "duration": 0.027378,
+ "end_time": "2020-03-13T14:54:48.697099",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:48.669721",
+ "status": "completed"
+ },
+ "tags": [
+ "injected-parameters"
+ ]
+ },
+ "outputs": [],
+ "source": [
+ "# Parameters\n",
+ "PAPERMILL_INPUT_PATH = \"notebooks/ToRates.ipynb\"\n",
+ "PAPERMILL_OUTPUT_PATH = \"runs/ToRates.run.ipynb\"\n",
+ "ts_folder = \"./data/covid-19_jhu-csse/\"\n",
+ "wb_path = \"./data/worldbank/SP.POP.TOTL.zip\"\n",
+ "out_folder = \"./data/covid-19_rates/\"\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "papermill": {
+ "duration": 0.009984,
+ "end_time": "2020-03-13T14:54:48.724400",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:48.714416",
+ "status": "completed"
+ },
+ "tags": [
+ "parameters"
+ ]
+ },
+ "source": [
+ "## Read in JHU CSSE data\n",
+ "\n",
+ "I will switch to [xarray](http://xarray.pydata.org/en/stable/), but ATM, it's easier like this..."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {
+ "papermill": {
+ "duration": 0.044299,
+ "end_time": "2020-03-13T14:54:48.778200",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:48.733901",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "def read_jhu_covid_region_df(name):\n",
+ " filename = os.path.join(ts_folder, f\"time_series_19-covid-{name}.csv\")\n",
+ " df = pd.read_csv(filename)\n",
+ " df = df.set_index(['Country/Region', 'Province/State', 'Lat', 'Long'])\n",
+ " df.columns = pd.to_datetime(df.columns)\n",
+ " region_df = df.groupby(level='Country/Region').sum()\n",
+ " loc_df = df.reset_index([2,3]).groupby(level='Country/Region').mean()[['Long', 'Lat']]\n",
+ " return region_df.join(loc_df).set_index(['Long', 'Lat'], append=True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {
+ "papermill": {
+ "duration": 0.126546,
+ "end_time": "2020-03-13T14:54:48.922552",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:48.796006",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "frames_map = {\n",
+ " \"confirmed\": read_jhu_covid_region_df(\"Confirmed\"),\n",
+ " \"deaths\": read_jhu_covid_region_df(\"Deaths\"),\n",
+ " \"recovered\": read_jhu_covid_region_df(\"Recovered\")\n",
+ "}"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {
+ "papermill": {
+ "duration": 0.05437,
+ "end_time": "2020-03-13T14:54:48.984940",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:48.930570",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th>2020-01-22</th>\n",
+ " <th>2020-01-23</th>\n",
+ " <th>2020-01-24</th>\n",
+ " <th>2020-01-25</th>\n",
+ " <th>2020-01-26</th>\n",
+ " <th>2020-01-27</th>\n",
+ " <th>2020-01-28</th>\n",
+ " <th>2020-01-29</th>\n",
+ " <th>2020-01-30</th>\n",
+ " <th>2020-01-31</th>\n",
+ " <th>...</th>\n",
+ " <th>2020-03-01</th>\n",
+ " <th>2020-03-02</th>\n",
+ " <th>2020-03-03</th>\n",
+ " <th>2020-03-04</th>\n",
+ " <th>2020-03-05</th>\n",
+ " <th>2020-03-06</th>\n",
+ " <th>2020-03-07</th>\n",
+ " <th>2020-03-08</th>\n",
+ " <th>2020-03-09</th>\n",
+ " <th>2020-03-10</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Country/Region</th>\n",
+ " <th>Long</th>\n",
+ " <th>Lat</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>Mainland China</th>\n",
+ " <th>111.542903</th>\n",
+ " <th>33.406936</th>\n",
+ " <td>547</td>\n",
+ " <td>639</td>\n",
+ " <td>916</td>\n",
+ " <td>1399</td>\n",
+ " <td>2062</td>\n",
+ " <td>2863</td>\n",
+ " <td>5494</td>\n",
+ " <td>6070</td>\n",
+ " <td>8124</td>\n",
+ " <td>9783</td>\n",
+ " <td>...</td>\n",
+ " <td>79826</td>\n",
+ " <td>80026</td>\n",
+ " <td>80151</td>\n",
+ " <td>80271</td>\n",
+ " <td>80422</td>\n",
+ " <td>80573</td>\n",
+ " <td>80652</td>\n",
+ " <td>80699</td>\n",
+ " <td>80735</td>\n",
+ " <td>80757</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Italy</th>\n",
+ " <th>12.000000</th>\n",
+ " <th>43.000000</th>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>2</td>\n",
+ " <td>...</td>\n",
+ " <td>1694</td>\n",
+ " <td>2036</td>\n",
+ " <td>2502</td>\n",
+ " <td>3089</td>\n",
+ " <td>3858</td>\n",
+ " <td>4636</td>\n",
+ " <td>5883</td>\n",
+ " <td>7375</td>\n",
+ " <td>9172</td>\n",
+ " <td>10149</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Iran (Islamic Republic of)</th>\n",
+ " <th>53.000000</th>\n",
+ " <th>32.000000</th>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>978</td>\n",
+ " <td>1501</td>\n",
+ " <td>2336</td>\n",
+ " <td>2922</td>\n",
+ " <td>3513</td>\n",
+ " <td>4747</td>\n",
+ " <td>5823</td>\n",
+ " <td>6566</td>\n",
+ " <td>7161</td>\n",
+ " <td>8042</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Republic of Korea</th>\n",
+ " <th>128.000000</th>\n",
+ " <th>36.000000</th>\n",
+ " <td>1</td>\n",
+ " <td>1</td>\n",
+ " <td>2</td>\n",
+ " <td>2</td>\n",
+ " <td>3</td>\n",
+ " <td>4</td>\n",
+ " <td>4</td>\n",
+ " <td>4</td>\n",
+ " <td>4</td>\n",
+ " <td>11</td>\n",
+ " <td>...</td>\n",
+ " <td>3736</td>\n",
+ " <td>4335</td>\n",
+ " <td>5186</td>\n",
+ " <td>5621</td>\n",
+ " <td>6088</td>\n",
+ " <td>6593</td>\n",
+ " <td>7041</td>\n",
+ " <td>7314</td>\n",
+ " <td>7478</td>\n",
+ " <td>7513</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>France</th>\n",
+ " <th>2.000000</th>\n",
+ " <th>47.000000</th>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>2</td>\n",
+ " <td>3</td>\n",
+ " <td>3</td>\n",
+ " <td>3</td>\n",
+ " <td>4</td>\n",
+ " <td>5</td>\n",
+ " <td>5</td>\n",
+ " <td>5</td>\n",
+ " <td>...</td>\n",
+ " <td>130</td>\n",
+ " <td>191</td>\n",
+ " <td>204</td>\n",
+ " <td>285</td>\n",
+ " <td>377</td>\n",
+ " <td>653</td>\n",
+ " <td>949</td>\n",
+ " <td>1126</td>\n",
+ " <td>1209</td>\n",
+ " <td>1784</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>5 rows × 49 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " 2020-01-22 2020-01-23 \\\n",
+ "Country/Region Long Lat \n",
+ "Mainland China 111.542903 33.406936 547 639 \n",
+ "Italy 12.000000 43.000000 0 0 \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 0 0 \n",
+ "Republic of Korea 128.000000 36.000000 1 1 \n",
+ "France 2.000000 47.000000 0 0 \n",
+ "\n",
+ " 2020-01-24 2020-01-25 \\\n",
+ "Country/Region Long Lat \n",
+ "Mainland China 111.542903 33.406936 916 1399 \n",
+ "Italy 12.000000 43.000000 0 0 \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 0 0 \n",
+ "Republic of Korea 128.000000 36.000000 2 2 \n",
+ "France 2.000000 47.000000 2 3 \n",
+ "\n",
+ " 2020-01-26 2020-01-27 \\\n",
+ "Country/Region Long Lat \n",
+ "Mainland China 111.542903 33.406936 2062 2863 \n",
+ "Italy 12.000000 43.000000 0 0 \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 0 0 \n",
+ "Republic of Korea 128.000000 36.000000 3 4 \n",
+ "France 2.000000 47.000000 3 3 \n",
+ "\n",
+ " 2020-01-28 2020-01-29 \\\n",
+ "Country/Region Long Lat \n",
+ "Mainland China 111.542903 33.406936 5494 6070 \n",
+ "Italy 12.000000 43.000000 0 0 \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 0 0 \n",
+ "Republic of Korea 128.000000 36.000000 4 4 \n",
+ "France 2.000000 47.000000 4 5 \n",
+ "\n",
+ " 2020-01-30 2020-01-31 ... \\\n",
+ "Country/Region Long Lat ... \n",
+ "Mainland China 111.542903 33.406936 8124 9783 ... \n",
+ "Italy 12.000000 43.000000 0 2 ... \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 0 0 ... \n",
+ "Republic of Korea 128.000000 36.000000 4 11 ... \n",
+ "France 2.000000 47.000000 5 5 ... \n",
+ "\n",
+ " 2020-03-01 2020-03-02 \\\n",
+ "Country/Region Long Lat \n",
+ "Mainland China 111.542903 33.406936 79826 80026 \n",
+ "Italy 12.000000 43.000000 1694 2036 \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 978 1501 \n",
+ "Republic of Korea 128.000000 36.000000 3736 4335 \n",
+ "France 2.000000 47.000000 130 191 \n",
+ "\n",
+ " 2020-03-03 2020-03-04 \\\n",
+ "Country/Region Long Lat \n",
+ "Mainland China 111.542903 33.406936 80151 80271 \n",
+ "Italy 12.000000 43.000000 2502 3089 \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 2336 2922 \n",
+ "Republic of Korea 128.000000 36.000000 5186 5621 \n",
+ "France 2.000000 47.000000 204 285 \n",
+ "\n",
+ " 2020-03-05 2020-03-06 \\\n",
+ "Country/Region Long Lat \n",
+ "Mainland China 111.542903 33.406936 80422 80573 \n",
+ "Italy 12.000000 43.000000 3858 4636 \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 3513 4747 \n",
+ "Republic of Korea 128.000000 36.000000 6088 6593 \n",
+ "France 2.000000 47.000000 377 653 \n",
+ "\n",
+ " 2020-03-07 2020-03-08 \\\n",
+ "Country/Region Long Lat \n",
+ "Mainland China 111.542903 33.406936 80652 80699 \n",
+ "Italy 12.000000 43.000000 5883 7375 \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 5823 6566 \n",
+ "Republic of Korea 128.000000 36.000000 7041 7314 \n",
+ "France 2.000000 47.000000 949 1126 \n",
+ "\n",
+ " 2020-03-09 2020-03-10 \n",
+ "Country/Region Long Lat \n",
+ "Mainland China 111.542903 33.406936 80735 80757 \n",
+ "Italy 12.000000 43.000000 9172 10149 \n",
+ "Iran (Islamic Republic of) 53.000000 32.000000 7161 8042 \n",
+ "Republic of Korea 128.000000 36.000000 7478 7513 \n",
+ "France 2.000000 47.000000 1209 1784 \n",
+ "\n",
+ "[5 rows x 49 columns]"
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "frames_map['confirmed'].sort_values(frames_map['confirmed'].columns[-1], ascending=False).head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "papermill": {
+ "duration": 0.011038,
+ "end_time": "2020-03-13T14:54:49.012475",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.001437",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "source": [
+ "# Read in World Bank data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {
+ "papermill": {
+ "duration": 0.043639,
+ "end_time": "2020-03-13T14:54:49.064213",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.020574",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "import zipfile\n",
+ "zf = zipfile.ZipFile(wb_path)\n",
+ "pop_df = pd.read_csv(zf.open(\"API_SP.POP.TOTL_DS2_en_csv_v2_821007.csv\"), skiprows=4)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "papermill": {
+ "duration": 0.010307,
+ "end_time": "2020-03-13T14:54:49.091394",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.081087",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "source": [
+ "There is 2018 pop data for all countries/regions except Eritrea"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {
+ "papermill": {
+ "duration": 0.055137,
+ "end_time": "2020-03-13T14:54:49.154951",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.099814",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Country Name</th>\n",
+ " <th>Country Code</th>\n",
+ " <th>Indicator Name</th>\n",
+ " <th>Indicator Code</th>\n",
+ " <th>1960</th>\n",
+ " <th>1961</th>\n",
+ " <th>1962</th>\n",
+ " <th>1963</th>\n",
+ " <th>1964</th>\n",
+ " <th>1965</th>\n",
+ " <th>...</th>\n",
+ " <th>2011</th>\n",
+ " <th>2012</th>\n",
+ " <th>2013</th>\n",
+ " <th>2014</th>\n",
+ " <th>2015</th>\n",
+ " <th>2016</th>\n",
+ " <th>2017</th>\n",
+ " <th>2018</th>\n",
+ " <th>2019</th>\n",
+ " <th>Unnamed: 64</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>67</th>\n",
+ " <td>Eritrea</td>\n",
+ " <td>ERI</td>\n",
+ " <td>Population, total</td>\n",
+ " <td>SP.POP.TOTL</td>\n",
+ " <td>1007590.0</td>\n",
+ " <td>1033328.0</td>\n",
+ " <td>1060486.0</td>\n",
+ " <td>1088854.0</td>\n",
+ " <td>1118159.0</td>\n",
+ " <td>1148189.0</td>\n",
+ " <td>...</td>\n",
+ " <td>3213972.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>108</th>\n",
+ " <td>Not classified</td>\n",
+ " <td>INX</td>\n",
+ " <td>Population, total</td>\n",
+ " <td>SP.POP.TOTL</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>2 rows × 65 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Country Name Country Code Indicator Name Indicator Code 1960 \\\n",
+ "67 Eritrea ERI Population, total SP.POP.TOTL 1007590.0 \n",
+ "108 Not classified INX Population, total SP.POP.TOTL NaN \n",
+ "\n",
+ " 1961 1962 1963 1964 1965 ... 2011 \\\n",
+ "67 1033328.0 1060486.0 1088854.0 1118159.0 1148189.0 ... 3213972.0 \n",
+ "108 NaN NaN NaN NaN NaN ... NaN \n",
+ "\n",
+ " 2012 2013 2014 2015 2016 2017 2018 2019 Unnamed: 64 \n",
+ "67 NaN NaN NaN NaN NaN NaN NaN NaN NaN \n",
+ "108 NaN NaN NaN NaN NaN NaN NaN NaN NaN \n",
+ "\n",
+ "[2 rows x 65 columns]"
+ ]
+ },
+ "execution_count": 8,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pop_df[pd.isna(pop_df['2018'])]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "papermill": {
+ "duration": 0.009197,
+ "end_time": "2020-03-13T14:54:49.179422",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.170225",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "source": [
+ "Fix the country/region names that differ between the World Bank population data and the JHU CSSE data."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {
+ "papermill": {
+ "duration": 0.048983,
+ "end_time": "2020-03-13T14:54:49.237289",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.188306",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "region_wb_jhu_map = {\n",
+ " 'China': 'Mainland China',\n",
+ " 'Iran, Islamic Rep.': 'Iran (Islamic Republic of)',\n",
+ " 'Korea, Rep.': 'Republic of Korea',\n",
+ " 'United States': 'US',\n",
+ " 'United Kingdom': 'UK',\n",
+ " 'Hong Kong SAR, China': 'Hong Kong SAR',\n",
+ " 'Egypt, Arab Rep.': 'Egypt',\n",
+ " 'Vietnam': 'Viet Nam',\n",
+ " 'Macao SAR, China': 'Macao SAR',\n",
+ " 'Slovak Republic': 'Slovakia',\n",
+ " 'Moldova': 'Republic of Moldova',\n",
+ " 'St. Martin (French part)': 'Saint Martin',\n",
+ " 'Brunei Darussalam': 'Brunei'\n",
+ "}\n",
+ "current_pop_ser = pop_df[['Country Name', '2018']].copy().replace(region_wb_jhu_map).set_index('Country Name')['2018']\n",
+ "data_pop_ser = current_pop_ser[current_pop_ser.index.isin(frames_map['confirmed'].index.levels[0])]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "papermill": {
+ "duration": 0.010552,
+ "end_time": "2020-03-13T14:54:49.263442",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.252890",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "source": [
+ "There are some regions that we cannot resolve, but we will just ignore these."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "papermill": {
+ "duration": 0.008224,
+ "end_time": "2020-03-13T14:54:49.280239",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.272015",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "source": [
+ "# Compute rates per 100,000 for regions"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {
+ "papermill": {
+ "duration": 0.081057,
+ "end_time": "2020-03-13T14:54:49.370031",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.288974",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "def cases_to_rates_df(df):\n",
+ " per_100000_df = df.reset_index([1, 2], drop=True)\n",
+ " per_100000_df = per_100000_df.div(data_pop_ser, 'index').mul(100000).dropna()\n",
+ " per_100000_df.index.name = 'Country/Region'\n",
+ " return per_100000_df\n",
+ " \n",
+ "def frames_to_rates(frames_map):\n",
+ " return {k: cases_to_rates_df(v) for k,v in frames_map.items()}\n",
+ "\n",
+ "\n",
+ "rates_map = frames_to_rates(frames_map)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "metadata": {
+ "papermill": {
+ "duration": 0.065887,
+ "end_time": "2020-03-13T14:54:49.458887",
+ "exception": false,
+ "start_time": "2020-03-13T14:54:49.393000",
+ "status": "completed"
+ },
+ "tags": []
+ },
+ "outputs": [],
+ "source": [
+ "if PAPERMILL_OUTPUT_PATH:\n",
+ " for k, v in rates_map.items():\n",
+ " out_path = os.path.join(out_folder, f\"ts_rates_19-covid-{k}.csv\")\n",
+ " v.reset_index().to_csv(out_path)"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.7.6"
+ },
+ "papermill": {
+ "duration": 2.37776,
+ "end_time": "2020-03-13T14:54:49.786899",
+ "environment_variables": {},
+ "exception": null,
+ "input_path": "notebooks/ToRates.ipynb",
+ "output_path": "runs/ToRates.run.ipynb",
+ "parameters": {
+ "PAPERMILL_INPUT_PATH": "notebooks/ToRates.ipynb",
+ "PAPERMILL_OUTPUT_PATH": "runs/ToRates.run.ipynb",
+ "out_folder": "./data/covid-19_rates/",
+ "ts_folder": "./data/covid-19_jhu-csse/",
+ "wb_path": "./data/worldbank/SP.POP.TOTL.zip"
+ },
+ "start_time": "2020-03-13T14:54:47.409139",
+ "version": "1.1.0"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
\ No newline at end of file