Skip to content
Snippets Groups Projects
Commit 06ef64ff authored by CI-bot's avatar CI-bot Committed by renku 0.10.4
Browse files

renku rerun data/covidtracking/states-metadata.json data/covidtracking/states-daily.json

parent 2e9d10f6
No related branches found
No related tags found
1 merge request!246Automatic update - auto-update_2020-07-14_07-32
Pipeline #47765 failed
Stage: build
    Stage: datasets-update
      Stage: notebooks-update
        Stage: finalize-update
          Hide whitespace changes
          Inline Side-by-side
          .renku/workflow/fa40d0c1c84b401196713f9c9a9b6df1.cwl 0 → 100644
          + 120
          − 0
          View file @ 06ef64ff
          class: Workflow
          cwlVersion: v1.0
          hints: []
          inputs:
          input_1:
          default: out_folder
          streamable: false
          type: string
          input_2:
          default: data/covidtracking
          streamable: false
          type: string
          input_3:
          default:
          class: File
          path: ../../notebooks/process/download-covidtracking-data.ipynb
          streamable: false
          type: File
          input_4:
          default: runs/download-covidtracking-data.runs.ipynb
          streamable: false
          type: string
          input_5:
          default: states-daily.json
          streamable: false
          type: string
          input_6:
          default: states-metadata.json
          streamable: false
          type: string
          outputs:
          output_2:
          outputSource: step_1/output_0
          streamable: false
          type: File
          output_3:
          outputSource: step_1/output_1
          streamable: false
          type: Directory
          requirements: []
          steps:
          step_1:
          in:
          input_1: input_1
          input_2: input_2
          input_3: input_3
          input_4: input_4
          out:
          - output_0
          - output_1
          run: a17d560c41a54f5aa307ce5f3c5effe5_papermill.cwl
          step_2:
          in:
          filename: input_5
          input_directory: step_1/output_1
          out:
          - output_file
          run:
          arguments: []
          baseCommand:
          - 'true'
          class: CommandLineTool
          cwlVersion: v1.0
          hints: []
          inputs:
          filename:
          default: states-daily.json
          streamable: false
          type: string
          input_directory:
          streamable: false
          type: Directory
          outputs:
          output_file:
          outputBinding:
          glob: $(inputs.filename)
          streamable: false
          type: File
          permanentFailCodes: []
          requirements:
          - &id001
          class: InlineJavascriptRequirement
          - &id002
          class: InitialWorkDirRequirement
          listing: $(inputs.input_directory.listing)
          successCodes: []
          temporaryFailCodes: []
          step_3:
          in:
          filename: input_6
          input_directory: step_1/output_1
          out:
          - output_file
          run:
          arguments: []
          baseCommand:
          - 'true'
          class: CommandLineTool
          cwlVersion: v1.0
          hints: []
          inputs:
          filename:
          default: states-metadata.json
          streamable: false
          type: string
          input_directory:
          streamable: false
          type: Directory
          outputs:
          output_file:
          outputBinding:
          glob: $(inputs.filename)
          streamable: false
          type: File
          permanentFailCodes: []
          requirements:
          - *id001
          - *id002
          successCodes: []
          temporaryFailCodes: []
          data/covidtracking/states-daily.json LFS
          + 2
          − 2
          View file @ 06ef64ff
          source diff could not be displayed: it is stored in LFS. Options to address this: view the blob.
          data/covidtracking/states-metadata.json LFS
          + 2
          − 2
          View file @ 06ef64ff
          source diff could not be displayed: it is stored in LFS. Options to address this: view the blob.
          runs/download-covidtracking-data.runs.ipynb
          + 62
          − 62
          View file @ 06ef64ff
          %% Cell type:code id: tags:
          ``` python
          import requests
          import os
          import pandas as pd
          ```
          %% Cell type:code id: tags:parameters
          ``` python
          out_folder = "../data/covidtracking/"
          PAPERMILL_OUTPUT_PATH = None
          ```
          %% Cell type:code id: tags:injected-parameters
          ``` python
          # Parameters
          PAPERMILL_INPUT_PATH = "/tmp/sy1d927i/notebooks/process/download-covidtracking-data.ipynb"
          PAPERMILL_INPUT_PATH = "/tmp/to3ihk72/notebooks/process/download-covidtracking-data.ipynb"
          PAPERMILL_OUTPUT_PATH = "runs/download-covidtracking-data.runs.ipynb"
          out_folder = "data/covidtracking"
          ```
          %% Cell type:markdown id: tags:
          # Download state metadata
          Download a dataset of URLs for data for each US state and several territories. See [Google Doc](https://docs.google.com/spreadsheets/d/18oVRrHj3c183mHmq3m89_163yuYltLNlOmPerQ18E8w/htmlview?sle=true).
          %% Cell type:code id: tags:
          ``` python
          url = 'http://covidtracking.com/api/states/info'
          r = requests.get(url, allow_redirects=True)
          states_metadata_json = r.content
          ```
          %% Cell type:code id: tags:
          ``` python
          # save the result
          if PAPERMILL_OUTPUT_PATH:
          out_path = os.path.join(out_folder, 'states-metadata.json')
          with open(out_path, 'wb') as f:
          f.write(states_metadata_json)
          ```
          %% Cell type:code id: tags:
          ``` python
          metadata_df = pd.read_json(states_metadata_json)
          print(len(metadata_df), "states and territories have metadata")
          metadata_df.head(2)
          ```
          %% Output
          56 states and territories have metadata
          state notes \
          0 AK Negatives = (Totals – Positives)\nPositives oc...
          1 AL Negatives = (Totals - Positives) \nPositives o...
          covid19Site \
          0 http://dhss.alaska.gov/dph/Epi/id/Pages/COVID-...
          1 https://alpublichealth.maps.arcgis.com/apps/op...
          covid19SiteSecondary \
          0 http://dhss.alaska.gov/dph/Epi/id/Pages/COVID-...
          1 https://dph1.adph.state.al.us/covid-19/
          covid19SiteTertiary twitter \
          0 https://alaska-dhss.maps.arcgis.com/apps/opsda... @Alaska_DHSS
          1 @alpublichealth
          covid19SiteOld name fips pui pum
          0 http://dhss.alaska.gov/dph/Epi/id/Pages/COVID-... Alaska 2 False
          1 http://www.alabamapublichealth.gov/infectiousd... Alabama 1 False
          %% Cell type:markdown id: tags:
          # Download daily state data
          %% Cell type:code id: tags:
          ``` python
          url = 'https://covidtracking.com/api/states/daily'
          r = requests.get(url, allow_redirects=True)
          states_daily_json = r.content
          ```
          %% Cell type:code id: tags:
          ``` python
          # save the result
          if PAPERMILL_OUTPUT_PATH:
          out_path = os.path.join(out_folder, 'states-daily.json')
          with open(out_path, 'wb') as f:
          f.write(states_daily_json)
          ```
          %% Cell type:code id: tags:
          ``` python
          data_df = pd.read_json(states_daily_json)
          print(len(data_df), "data points")
          data_df.head(2)
          ```
          %% Output
          7185 data points
          7241 data points
          date state positive negative pending hospitalizedCurrently \
          0 20200711 AK 1385.0 141991.0 NaN 31.0
          1 20200711 AL 51947.0 450073.0 NaN 1068.0
          0 20200712 AK 1479.0 143996.0 NaN 27.0
          1 20200712 AL 53587.0 457919.0 NaN 1068.0
          hospitalizedCumulative inIcuCurrently inIcuCumulative \
          0 NaN NaN NaN
          1 6745.0 NaN 904.0
          1 6745.0 NaN 911.0
          onVentilatorCurrently ... posNeg deathIncrease hospitalizedIncrease \
          0 1.0 ... 143376 0 0
          1 NaN ... 502020 10 3656
          0 0.0 ... 145475 0 0
          1 NaN ... 511506 7 0
          hash commercialScore \
          0 d88f70b7bfa373ef0fb14998ccb0d0d3a9c806fb 0
          1 d4bd3a01be0c8af28a542861a4de75cf38649a10 0
          0 a0d3d26cd6bfe23ff076e92f50acd2e1ee43cfc4 0
          1 fb4327f63eb6b270a2ead2bbdd438615bb7c361f 0
          negativeRegularScore negativeScore positiveScore score grade
          0 0 0 0 0
          1 0 0 0 0
          [2 rows x 41 columns]
          ......
          0% or .
          You are about to add 0 people to the discussion. Proceed with caution.
          Finish editing this message first!
          Please register or to comment

          This GitLab is a part of renkulab.io