Récupération des DESCRIPTION depuis l'extraction des dépôts Github


In [2]:
import pandas
from debian import deb822

repositories = pandas.DataFrame.from_csv('../data/github-descr-readme.csv', sep=';', header=None, index_col=None)

In [13]:
packages = []
for index, row in repositories.iterrows():
    descriptions = row[2]
    for description in descriptions.split(', '):
        description = description.strip()
        if len(description) == 0:
            continue
        try:
            d = deb822.Deb822(open(description))
            if not 'Package' in d: 
                raise KeyError('Package key is missing')
            d['gh_owner'] = row[0]
            d['gh_repository'] = row[1]
            packages.append(d)
        except KeyError as e:
            print 'KeyError for:', description
        except IOError as e:
            print 'IOError for:', description


KeyError for: /data/github/cran/hoa/DESCRIPTION
KeyError for: /data/github/jcheng5/leaflet-shiny/inst/examples/choropleth/DESCRIPTION
KeyError for: /data/github/shaptonstahl/abtest/demo/ab/DESCRIPTION
KeyError for: /data/github/CruGlobal/R-Library/shiny/examples/06_tabsets/DESCRIPTION
KeyError for: /data/github/CruGlobal/R-Library/shiny/examples/09_upload/DESCRIPTION
KeyError for: /data/github/CruGlobal/R-Library/shiny/examples/03_reactivity/DESCRIPTION
KeyError for: /data/github/CruGlobal/R-Library/shiny/examples/07_widgets/DESCRIPTION
KeyError for: /data/github/CruGlobal/R-Library/shiny/examples/05_sliders/DESCRIPTION
KeyError for: /data/github/CruGlobal/R-Library/shiny/examples/10_download/DESCRIPTION
KeyError for: /data/github/CruGlobal/R-Library/shiny/examples/04_mpg/DESCRIPTION
KeyError for: /data/github/CruGlobal/R-Library/shiny/examples/02_text/DESCRIPTION
KeyError for: /data/github/CruGlobal/R-Library/shiny/examples/11_timer/DESCRIPTION
KeyError for: /data/github/CruGlobal/R-Library/shiny/examples/08_html/DESCRIPTION
KeyError for: /data/github/CruGlobal/R-Library/shiny/examples/01_hello/DESCRIPTION
IOError for: /data/github/jitans/Finance/packrat/lib/x86_64-pc-linux-gnu/3.1.1/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (long)/packrat/DESCRIPTION
IOError for: /data/github/jitans/Finance/packrat/lib/x86_64-pc-linux-gnu/3.1.1/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (long)/toast/DESCRIPTION
IOError for: /data/github/jitans/Finance/packrat/lib/x86_64-pc-linux-gnu/3.1.1/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (long)/bread/DESCRIPTION
IOError for: /data/github/jitans/Finance/packrat/lib/x86_64-pc-linux-gnu/3.1.1/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (long)/oatmeal/DESCRIPTION
IOError for: /data/github/jitans/Finance/packrat/lib/x86_64-pc-linux-gnu/3.1.1/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (long)/breakfast/DESCRIPTION
KeyError for: /data/github/TiphaineCMartin/coMET/www/DESCRIPTION
KeyError for: /data/github/rstudio/DT/inst/examples/DT-info/DESCRIPTION
KeyError for: /data/github/rstudio/DT/inst/examples/DT-checkbox/DESCRIPTION
KeyError for: /data/github/rstudio/DT/inst/examples/DT-scroller/DESCRIPTION
KeyError for: /data/github/rstudio/DT/inst/examples/DT-filter/DESCRIPTION
KeyError for: /data/github/wch/uploadfile/DESCRIPTION
KeyError for: /data/github/kaja-a/shiny/reproductive_number/DESCRIPTION
KeyError for: /data/github/callinSwitzer/S135/S135FinalCallinSwitzer/S135App4/DESCRIPTION
KeyError for: /data/github/joey711/shiny-phyloseq/DESCRIPTION
KeyError for: /data/github/sethrfore/shiny/inst/examples/06_tabsets/DESCRIPTION
KeyError for: /data/github/sethrfore/shiny/inst/examples/09_upload/DESCRIPTION
KeyError for: /data/github/sethrfore/shiny/inst/examples/03_reactivity/DESCRIPTION
KeyError for: /data/github/sethrfore/shiny/inst/examples/07_widgets/DESCRIPTION
KeyError for: /data/github/sethrfore/shiny/inst/examples/05_sliders/DESCRIPTION
KeyError for: /data/github/sethrfore/shiny/inst/examples/10_download/DESCRIPTION
KeyError for: /data/github/sethrfore/shiny/inst/examples/04_mpg/DESCRIPTION
KeyError for: /data/github/sethrfore/shiny/inst/examples/02_text/DESCRIPTION
KeyError for: /data/github/sethrfore/shiny/inst/examples/11_timer/DESCRIPTION
KeyError for: /data/github/sethrfore/shiny/inst/examples/08_html/DESCRIPTION
KeyError for: /data/github/sethrfore/shiny/inst/examples/01_hello/DESCRIPTION
KeyError for: /data/github/JeffreyP506/devdataprod_shiny/DESCRIPTION
KeyError for: /data/github/googlegenomics/api-client-r/shiny/DESCRIPTION
KeyError for: /data/github/mblanche/coverage-app/DESCRIPTION
KeyError for: /data/github/loerasg/GitR/inst/Etapa01/DESCRIPTION
KeyError for: /data/github/loerasg/GitR/inst/Extremos/DESCRIPTION
KeyError for: /data/github/busasquatch/MathFactApp/MathApp/DESCRIPTION
KeyError for: /data/github/tech-sketch/CodeZine-wordcloud/DESCRIPTION
KeyError for: /data/github/daten-kieker/devdataprod_project/DESCRIPTION
KeyError for: /data/github/jp4711/DevelopingDataProducts_Assignment1/DESCRIPTION
KeyError for: /data/github/xspeedcruiser/datasci/stock_chart/DESCRIPTION
KeyError for: /data/github/krlmlr/r-snap/R/lib/R/library/formatR/shiny/DESCRIPTION
KeyError for: /data/github/cran/HH/inst/shiny/NormalAndTplot/DESCRIPTION
KeyError for: /data/github/cran/HH/inst/shiny/PopulationPyramid/DESCRIPTION
KeyError for: /data/github/Rappster/shiny-forked/inst/examples/06_tabsets/DESCRIPTION
KeyError for: /data/github/Rappster/shiny-forked/inst/examples/09_upload/DESCRIPTION
KeyError for: /data/github/Rappster/shiny-forked/inst/examples/03_reactivity/DESCRIPTION
KeyError for: /data/github/Rappster/shiny-forked/inst/examples/07_widgets/DESCRIPTION
KeyError for: /data/github/Rappster/shiny-forked/inst/examples/05_sliders/DESCRIPTION
KeyError for: /data/github/Rappster/shiny-forked/inst/examples/10_download/DESCRIPTION
KeyError for: /data/github/Rappster/shiny-forked/inst/examples/04_mpg/DESCRIPTION
KeyError for: /data/github/Rappster/shiny-forked/inst/examples/02_text/DESCRIPTION
KeyError for: /data/github/Rappster/shiny-forked/inst/examples/11_timer/DESCRIPTION
KeyError for: /data/github/Rappster/shiny-forked/inst/examples/08_html/DESCRIPTION
KeyError for: /data/github/Rappster/shiny-forked/inst/examples/01_hello/DESCRIPTION
KeyError for: /data/github/cran/chipPCR/inst/MFIaggr.gui/DESCRIPTION
KeyError for: /data/github/cran/chipPCR/inst/AmpSim.gui/DESCRIPTION
KeyError for: /data/github/cran/chipPCR/inst/amptester.gui/DESCRIPTION
KeyError for: /data/github/edman/calories-shiny/DESCRIPTION
KeyError for: /data/github/jlanga-coursera/developping-data-products-shiny/DESCRIPTION
KeyError for: /data/github/cran/shiny/inst/examples/06_tabsets/DESCRIPTION
KeyError for: /data/github/cran/shiny/inst/examples/09_upload/DESCRIPTION
KeyError for: /data/github/cran/shiny/inst/examples/03_reactivity/DESCRIPTION
KeyError for: /data/github/cran/shiny/inst/examples/07_widgets/DESCRIPTION
KeyError for: /data/github/cran/shiny/inst/examples/05_sliders/DESCRIPTION
KeyError for: /data/github/cran/shiny/inst/examples/10_download/DESCRIPTION
KeyError for: /data/github/cran/shiny/inst/examples/04_mpg/DESCRIPTION
KeyError for: /data/github/cran/shiny/inst/examples/02_text/DESCRIPTION
KeyError for: /data/github/cran/shiny/inst/examples/11_timer/DESCRIPTION
KeyError for: /data/github/cran/shiny/inst/examples/08_html/DESCRIPTION
KeyError for: /data/github/cran/shiny/inst/examples/01_hello/DESCRIPTION
KeyError for: /data/github/yihui/formatR/inst/shiny/DESCRIPTION
KeyError for: /data/github/unikum/ga-dimsmets/DESCRIPTION
KeyError for: /data/github/InfrastructureAnalytics/CapitalStocksFlows/inst/shiny/DESCRIPTION
KeyError for: /data/github/jcheng5/kmeans/DESCRIPTION
KeyError for: /data/github/cran/dseplus/DESCRIPTION
KeyError for: /data/github/J110/Developing_Data_Prods/DESCRIPTION
KeyError for: /data/github/projectprioritisationprotocol/ppp/ppp/DESCRIPTION
KeyError for: /data/github/genome/shiny_aml31/DESCRIPTION
IOError for: /data/github/jaeddy/jhuDataScience/mathematicalBiostatistics/packrat/lib/x86_64-apple-darwin13.1.0/3.1.1/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (it's pretty long too
IOError for: I hope that's okay)/packrat/DESCRIPTION
IOError for: /data/github/jaeddy/jhuDataScience/mathematicalBiostatistics/packrat/lib/x86_64-apple-darwin13.1.0/3.1.1/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (it's pretty long too
IOError for: I hope that's okay)/toast/DESCRIPTION
IOError for: /data/github/jaeddy/jhuDataScience/mathematicalBiostatistics/packrat/lib/x86_64-apple-darwin13.1.0/3.1.1/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (it's pretty long too
IOError for: I hope that's okay)/bread/DESCRIPTION
IOError for: /data/github/jaeddy/jhuDataScience/mathematicalBiostatistics/packrat/lib/x86_64-apple-darwin13.1.0/3.1.1/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (it's pretty long too
IOError for: I hope that's okay)/oatmeal/DESCRIPTION
IOError for: /data/github/jaeddy/jhuDataScience/mathematicalBiostatistics/packrat/lib/x86_64-apple-darwin13.1.0/3.1.1/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (it's pretty long too
IOError for: I hope that's okay)/breakfast/DESCRIPTION
KeyError for: /data/github/varmatieto/mpg_vs_am/DESCRIPTION
KeyError for: /data/github/bungalow-bill/arima_models/DESCRIPTION
KeyError for: /data/github/martinwpedersen/spict/spictapp/DESCRIPTION
KeyError for: /data/github/mblanche/heatmap-app/DESCRIPTION
KeyError for: /data/github/AlejandroRuete/IgnoranceMaps/SLWapp/DESCRIPTION
KeyError for: /data/github/jmarshallnz/talks/rstudio_rmarkdown/kmeans/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/054-nvd3-line-chart-output/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/055-observer-demo/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/041-dynamic-ui/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/019-mathjax/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/008-html/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/066-upload-file/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/015-layout-navbar/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/007-widgets/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/074-widget-numeric/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/057-plot-plus-three-columns/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/050-kmeans-example/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/023-optgroup-server/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/047-image-output/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/017-select-vs-selectize/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/034-current-time/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/018-datatable-options/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/075-widget-radio/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/053-navlistpanel-example/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/063-superzip-example/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/072-widget-date-range/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/011-timer/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/020-knit-html/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/022-unicode-chinese/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/084-single-file/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/077-widget-slider/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/059-reactive-poll-and-file-reader/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/026-shiny-inline/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/080-widget-text/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/010-download/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/081-widgets-gallery/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/027-absolutely-positioned-panels/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/073-widget-file/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/037-date-and-date-range/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/001-hello/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/085-progress/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/033-conditionalpanel-demo/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/024-optgroup-selectize/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/016-knitr-pdf/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/068-widget-action-button/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/065-update-input-demo/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/051-movie-explorer/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/035-custom-input-bindings/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/071-widget-date/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/048-including-html-text-and-markdown-files/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/015-layout-sidebar/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/064-telephones-by-region/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/002-text/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/070-widget-checkbox/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/009-upload/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/086-bus-dashboard/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/036-custom-input-control/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/005-sliders/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/076-widget-select/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/025-loop-ui/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/079-widget-submit/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/032-client-data-and-query-string/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/083-front-page/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/069-widget-check-group/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/040-dynamic-clustering/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/060-retirement-simulation/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/082-word-cloud/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/049-isolate-demo/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/039-download-file/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/062-submitbutton-demo/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/078-widget-slider-range/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/061-server-to-client-custom-messages/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/030-basic-datatable/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/052-navbar-example/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/006-tabsets/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/021-selectize-plot/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/067-vertical-layout/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/012-datatables/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/003-reactivity/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/014-onflushed/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/028-actionbutton-demo/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/013-selectize/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-examples/004-mpg/DESCRIPTION
KeyError for: /data/github/mdrasche/Mediation-app-/DESCRIPTION
KeyError for: /data/github/rjournal/rj/inst/sample/Rejected/2012-04/DESCRIPTION
KeyError for: /data/github/rjournal/rj/inst/sample/Rejected/2012-03/DESCRIPTION
KeyError for: /data/github/rjournal/rj/inst/sample/Submitted/2012-05/DESCRIPTION
KeyError for: /data/github/rjournal/rj/inst/sample/Accepted/2012-01/DESCRIPTION
KeyError for: /data/github/rjournal/rj/inst/sample/Accepted/2012-02/DESCRIPTION
KeyError for: /data/github/flr/devel/templates/pkg/DESCRIPTION
KeyError for: /data/github/CrazyFarang/DevelopingDataProducts/bmi/DESCRIPTION
KeyError for: /data/github/cran/roxygen2/tests/testthat/empty/DESCRIPTION
KeyError for: /data/github/vsharma1/DataScienceCoursera/Developing_Data_Products/BMIApp/DESCRIPTION
KeyError for: /data/github/hadley/mturkr/inst/template/DESCRIPTION
KeyError for: /data/github/cran/formatR/inst/shiny/DESCRIPTION
KeyError for: /data/github/srobin04005/devDataProducts/DESCRIPTION
KeyError for: /data/github/mul118/shinyMCE/inst/demo/apps/02-options/DESCRIPTION
KeyError for: /data/github/mul118/shinyMCE/inst/demo/apps/01-basic/DESCRIPTION
KeyError for: /data/github/mul118/shinyMCE/inst/demo/apps/03-update/DESCRIPTION
KeyError for: /data/github/mul118/shinyMCE/inst/demo/apps/04-renderUI/DESCRIPTION
KeyError for: /data/github/mul118/shinyMCE/demo/apps/02-options/DESCRIPTION
KeyError for: /data/github/mul118/shinyMCE/demo/apps/01-basic/DESCRIPTION
KeyError for: /data/github/mul118/shinyMCE/demo/apps/03-update/DESCRIPTION
KeyError for: /data/github/mul118/shinyMCE/demo/apps/04-renderUI/DESCRIPTION
KeyError for: /data/github/AnjaKa/Kaczmara/Shiny/optional_stopping/DESCRIPTION
KeyError for: /data/github/AnjaKa/Kaczmara/Shiny/binomial_gaussian/DESCRIPTION
KeyError for: /data/github/AnjaKa/Kaczmara/Shiny/confidence_intervals/DESCRIPTION
KeyError for: /data/github/cran/dygraphs/inst/examples/shiny/DESCRIPTION
KeyError for: /data/github/cran/VR/DESCRIPTION
KeyError for: /data/github/kvistrup/DevDataProd_CourseProj/DESCRIPTION
KeyError for: /data/github/cran/reports/inst/extdata/doc_library/apa6.mod.quant_rnw/DESCRIPTION
KeyError for: /data/github/cran/reports/inst/extdata/doc_library/apa6.qual_tex/DESCRIPTION
KeyError for: /data/github/cran/reports/inst/extdata/doc_library/apa6.quant_rnw/DESCRIPTION
KeyError for: /data/github/cran/reports/inst/extdata/doc_library/basic_web/DESCRIPTION
KeyError for: /data/github/cran/reports/inst/extdata/doc_library/apa6.mod.qual_tex/DESCRIPTION
KeyError for: /data/github/cran/reports/inst/extdata/doc_library/apa6.qual_doc/DESCRIPTION
KeyError for: /data/github/cran/reports/inst/extdata/doc_temp/rnw/DESCRIPTION
KeyError for: /data/github/cran/reports/inst/extdata/doc_temp/tex/DESCRIPTION
KeyError for: /data/github/cran/reports/inst/extdata/doc_temp/doc/DESCRIPTION
KeyError for: /data/github/cran/reports/inst/extdata/doc_temp/web/DESCRIPTION
KeyError for: /data/github/lingani/MyDataProduct/DESCRIPTION
KeyError for: /data/github/ferreras/DevelopingDataProducts/DESCRIPTION
KeyError for: /data/github/bartev/san-tan/hadleypackages/R/DESCRIPTION
KeyError for: /data/github/johndharrison/shinyGWorks/inst/examples/01_animations/DESCRIPTION
KeyError for: /data/github/manelvcmb/tutorial_bayesiano/metropolis/DESCRIPTION
KeyError for: /data/github/manelvcmb/tutorial_bayesiano/dosPriors/DESCRIPTION
KeyError for: /data/github/manelvcmb/tutorial_bayesiano/gibbs/DESCRIPTION
KeyError for: /data/github/manelvcmb/tutorial_bayesiano/teorema/DESCRIPTION
KeyError for: /data/github/manelvcmb/tutorial_bayesiano/piMonteCarlo/DESCRIPTION
KeyError for: /data/github/jcheng5/googleCharts/inst/examples/bubble/DESCRIPTION
KeyError for: /data/github/mblanche/coverage-app-c8/DESCRIPTION
KeyError for: /data/github/rstudio/leaflet/inst/legacy/examples/choropleth/DESCRIPTION
KeyError for: /data/github/ysung/STA250/DESCRIPTION
KeyError for: /data/github/NadiyaLozynska/Developing-Data-Products-Project-Part1/DESCRIPTION
KeyError for: /data/github/jhsdatascience/fb-pivotal/DESCRIPTION
KeyError for: /data/github/varmatieto/sanita_3one/DESCRIPTION
KeyError for: /data/github/wch/image-output/DESCRIPTION
KeyError for: /data/github/wch/shinyapps-encoding/testapp/DESCRIPTION
KeyError for: /data/github/sbushmanov/shiny/returns/DESCRIPTION
IOError for: /data/github/chrlaney/sel-baid_wsn_shinyapp/packrat/lib/x86_64-apple-darwin10.8.0/3.0.2/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (long)/packrat/DESCRIPTION
IOError for: /data/github/chrlaney/sel-baid_wsn_shinyapp/packrat/lib/x86_64-apple-darwin10.8.0/3.0.2/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (long)/toast/DESCRIPTION
IOError for: /data/github/chrlaney/sel-baid_wsn_shinyapp/packrat/lib/x86_64-apple-darwin10.8.0/3.0.2/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (long)/bread/DESCRIPTION
IOError for: /data/github/chrlaney/sel-baid_wsn_shinyapp/packrat/lib/x86_64-apple-darwin10.8.0/3.0.2/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (long)/oatmeal/DESCRIPTION
IOError for: /data/github/chrlaney/sel-baid_wsn_shinyapp/packrat/lib/x86_64-apple-darwin10.8.0/3.0.2/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (long)/breakfast/DESCRIPTION
KeyError for: /data/github/mhnierhoff/DDP_Shiny_Project/DESCRIPTION
KeyError for: /data/github/rforge/gcur/pkg/DESCRIPTION
KeyError for: /data/github/netterie/HIVBackCalc_App/DESCRIPTION
KeyError for: /data/github/p-robot/PPP/DESCRIPTION
KeyError for: /data/github/ihstevenson/sample_means/DESCRIPTION
KeyError for: /data/github/azk/hacked_citrus_ui/inst/extdata/example5/DESCRIPTION
KeyError for: /data/github/kireru/datasciencecoursera-repo/Developing data products/assignment/DESCRIPTION
KeyError for: /data/github/albertruizgce/App-developing-Data-Products/DESCRIPTION
KeyError for: /data/github/wkvong/StateTraceAnalysis/DESCRIPTION
KeyError for: /data/github/jpolonsky/HeRAMS_CAR/DESCRIPTION
IOError for: /data/github/CVNRneuroimaging/proj.ag.diss.r21ad/00.scripts/rstats-proj.ag.diss.r21ad/packrat/lib/x86_64-apple-darwin13.1.0/3.1.1/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (long)/packrat/DESCRIPTION
IOError for: /data/github/CVNRneuroimaging/proj.ag.diss.r21ad/00.scripts/rstats-proj.ag.diss.r21ad/packrat/lib/x86_64-apple-darwin13.1.0/3.1.1/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (long)/toast/DESCRIPTION
IOError for: /data/github/CVNRneuroimaging/proj.ag.diss.r21ad/00.scripts/rstats-proj.ag.diss.r21ad/packrat/lib/x86_64-apple-darwin13.1.0/3.1.1/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (long)/bread/DESCRIPTION
IOError for: /data/github/CVNRneuroimaging/proj.ag.diss.r21ad/00.scripts/rstats-proj.ag.diss.r21ad/packrat/lib/x86_64-apple-darwin13.1.0/3.1.1/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (long)/oatmeal/DESCRIPTION
IOError for: /data/github/CVNRneuroimaging/proj.ag.diss.r21ad/00.scripts/rstats-proj.ag.diss.r21ad/packrat/lib/x86_64-apple-darwin13.1.0/3.1.1/packrat/tests/testthat/Ugly
IOError for: but legal
IOError for: path for a project (long)/breakfast/DESCRIPTION
KeyError for: /data/github/cran/forecasting/DESCRIPTION
KeyError for: /data/github/tomassve/DevDataProd_CourseProject/DESCRIPTION
KeyError for: /data/github/jcizel/SovereignCrisis/shiny/DESCRIPTION
KeyError for: /data/github/csgillespie/travis-examples/knitr/DESCRIPTION
KeyError for: /data/github/rstudio/shinyBootstrap2/inst/examples/setinput/DESCRIPTION
KeyError for: /data/github/rstudio/shinyBootstrap2/inst/examples/inline/DESCRIPTION
KeyError for: /data/github/rstudio/shinyBootstrap2/inst/examples/fluidpage/DESCRIPTION
KeyError for: /data/github/wch/movies/DESCRIPTION
KeyError for: /data/github/michbur/chipPCR/inst/MFIaggr.gui/DESCRIPTION
KeyError for: /data/github/michbur/chipPCR/inst/AmpSim.gui/DESCRIPTION
KeyError for: /data/github/michbur/chipPCR/inst/amptester.gui/DESCRIPTION
KeyError for: /data/github/stephaniehicks/postMUT/DESCRIPTION
KeyError for: /data/github/magicDGS/DistributionCalculator/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-testapp/dynamic_ui/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-testapp/invalidatelater/DESCRIPTION
KeyError for: /data/github/rstudio/shiny-testapp/actionbutton/DESCRIPTION
KeyError for: /data/github/wch/send-custom-message/DESCRIPTION

In [15]:
len(repositories), len(packages)


Out[15]:
(52470, 14376)

In [37]:
count = {}
for p in packages:
    repo = p['gh_owner'] + '/' + p['gh_repository']
    count[repo] = count.setdefault(repo, 0) + 1

In [38]:
len(count)


Out[38]:
12920

In [39]:
m = filter(lambda v: v[1] > 1, count.iteritems())
m.sort(key=lambda x: x[1], reverse=True)
len(m)


Out[39]:
422

In [40]:
df = pandas.DataFrame.from_dict(packages)

In [41]:
df.to_csv('../data/github-all-description.csv', encoding='utf-8')

In [42]:
df


Out[42]:
Acknowledgement Acknowledgements Acknowledgments Additional_repositories Address Adress Affiliations AggregateMethods Architecture Archs ... organism package provider provider_version release_date release_name source_url species xCollate xxxLazyLoad
0 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
1 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
2 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
3 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
4 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
5 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
6 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
7 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
8 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
9 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
10 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
11 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
12 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
13 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
15 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
16 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
17 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
18 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
19 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
20 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
21 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
22 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
23 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
24 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
25 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
26 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
27 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
28 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
29 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
14346 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14347 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14348 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14349 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14350 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14351 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14352 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14353 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14354 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14355 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14356 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14357 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14358 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14359 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14360 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14361 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14362 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14363 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14364 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14365 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14366 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14367 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14368 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14369 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14370 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14371 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14372 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14373 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14374 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN
14375 NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN ... NaN NaN NaN NaN NaN NaN NaN NaN NaN NaN

14376 rows × 221 columns