Getting started with Italian data on COVID-19

(require '[panthera.panthera :as pt])

(require '[libpython-clj.python :refer [call-attr]])

(defonce provinces-url 

  "https://raw.githubusercontent.com/pcm-dpc/COVID-19/master/dati-province/dpc-covid19-ita-province.csv")

(defonce regions-url

  "https://raw.githubusercontent.com/pcm-dpc/COVID-19/master/dati-regioni/dpc-covid19-ita-regioni.csv")

(def provinces

  (pt/read-csv provinces-url))

(def regions

   (pt/read-csv regions-url))

(defn show

  [obj]

  (if (pt/series? obj)

  	{:nextjournal/viewer "html" 

     :nextjournal.viewer/value (call-attr (call-attr obj "to_frame") "to_html")}

    {:nextjournal/viewer "html" 

     :nextjournal.viewer/value (call-attr obj "to_html")}))

(show (pt/head provinces))

(print (pt/names provinces))

(def mapper-provinces

  {:data :date

   :stato :state

   :codice_regione :region-code

   :denominazione_regione :region-name

   :codice_provincia :province-code

   :denominazione_provincia :province-name

   :sigla_provincia :province-abbreviation

   :lat :lat

   :long :lon

   :totale_casi :cases})

(show (pt/head (pt/rename provinces {:columns mapper-provinces})))

(defn renamer

  [df mapper]

  (pt/rename df {:columns mapper}))

(def provinces-renamed

  (renamer provinces mapper-provinces))

(print (pt/unique (pt/subset-cols provinces-renamed :province-name)))

(-> (pt/subset-cols provinces-renamed :province-name)

  pt/n-unique)

(defn clean-data

  [df mapper]

  (as-> (renamer df mapper) d

        (pt/filter-rows d

          (pt/ne (pt/subset-cols d :province-name) 

            "In fase di definizione/aggiornamento"))))

(show (pt/head (clean-data provinces mapper-provinces)))

(print (pt/names regions))

(def mapper-regions

  (merge 

    mapper-provinces

    {:ricoverati_con_sintomi :hospitalized

     :terapia_intensiva :icu

     :totale_ospedalizzati :tot-hospitalized

     :isolamento_domiciliare :quarantined

     :totale_attualmente_positivi :tot-positives

     :nuovi_attualmente_positivi :new-positives

     :dimessi_guariti :recovered

     :deceduti :dead

     :tamponi :tests}))

(show (pt/head (renamer regions mapper-regions)))

(pt/n-unique (pt/subset-cols regions :denominazione_regione))

(print (pt/unique (pt/subset-cols regions :denominazione_regione)))

(def regions-clean (renamer regions mapper-regions))

(-> regions (renamer mapper-regions) (pt/groupby [:date]) pt/sum pt/head show)

(def regions-tests

  (-> (pt/subset-cols regions-clean :date :tests :new-positives)

      (pt/groupby :date)

      pt/sum))

(print (pt/shape regions-tests))

(defn daily-tests []

  (-> regions-tests

    (pt/subset-cols :tests)

    pt/diff

    (pt/fill-na (first (pt/values (pt/subset-cols (pt/subset-rows regions-tests 1) :tests))))))

(print (pt/shape (daily-tests)))

(first (pt/values (pt/subset-cols (pt/subset-rows regions-tests 1) :tests)))

(-> (pt/subset-rows regions-tests 1) (pt/subset-cols :tests) pt/values first)

(as-> regions-tests r 

  (pt/assign r {:daily-tests (daily-tests)}) 

  (pt/assign r {:new-by-test (pt/div (pt/subset-cols r :new-positives) (pt/subset-cols r :daily-tests))})

  (pt/shape r)

  (print r))

(def r (pt/assign regions-tests {:daily-tests (daily-tests)}))