gaza-stats/src/gaza_stats/core.clj

226 lines
10 KiB
Clojure

(ns gaza-stats.core
"Functions to interrogate the [`gaza.onl`](https://gaza.onl/app.db) database."
(:require [clojure.string :refer [capitalize]]
[cljc.java-time.local-date :as ld]
[com.hypirion.clj-xchart :refer [xy-chart]]
[korma.core :refer [as-sql fields join select where]]
[korma.db :refer [defdb sqlite3]])
(:import [java.util Date]
[java.time LocalDate ZoneId ZoneOffset]))
;; create db
(def db-spec
"Database specification in a format which can be used with either JDBC or
Korma."
{:classname "org.sqlite.JDBC"
:subprotocol "sqlite"
:subname "resources/app.db"})
(defdb db
;; Korma-specific database handle.
(sqlite3 db-spec))
(defmacro local-date?
"Is this `x` an instance of `java.time.LocalDate`?"
[x]
`(instance? LocalDate ~x))
(defmacro normalise-date
"More messing around with Java's bizarre mess of date/time classes. We want
our default date representation to be `java.time.LocalDate`, except, of
course, when we don't."
[date default]
`(cond (local-date? ~date) ~date
(string? ~date) (ld/parse ~date)
;; this one should catch java.sql.Date as well, since it is a subclass
(instance? Date ~date) (.toLocalDate
(.atZone (.toInstant ~date)
(ZoneId/systemDefault)))
(nil? ~date) (ld/now)
;; if I'd written this as a fn, I'd just recurse,,, might be worth it.
:else (if (local-date? ~default)
~default
(ld/parse (str ~default)))))
(defn total-donations-by-weeks
"Return a list of pairs `[java.time.LocalDate date, float amount]` representing
the total of donations made between `start-date` and `end-date`. Arguments may
be supplied as `java.time.LocalDate` objects, or as strings in the format
`yyyy-mm-dd`. If `end-date` is not supplied, data for a single week will be
returned."
([start-date]
(let [sd (normalise-date start-date "2024-01-01")]
(total-donations-by-weeks sd (ld/plus-days sd 7))))
([start-date end-date]
(let [sd (normalise-date start-date "2024-01-01")
ed (normalise-date end-date (ld/now))]
(loop [s sd
i (ld/plus-days sd 7)
r nil]
(let [data (select 'campaign_donations
(fields :amount)
(where (and {:created_at [> s]}
{:created_at [<= i]})))
amounts (map :amount data)
r' (cons
[s {:total (reduce + amounts)
:n (count data)
:max (apply max amounts)
:min (apply min amounts)}]
r)]
(if (ld/is-before ed i) (reverse r')
(recur i (ld/plus-days i 7) r')))))))
(defmacro local-date->date
"Construct and return a new `java.util.Date` object from a
`java.time.LocalDate` object. As usual, doing anything with Java time/date
stuff is a complete bureaucratic nightmare."
[x]
`(Date/from
(.toInstant (.atStartOfDay ~x)
(ZoneOffset/ofHours 0))))
(defn chart-donations-by-weeks
"Create and return an XY chart of data on field represented by `key` of
donations made between `start-date` and `end-date`. Arguments may be supplied as
`java.time.LocalDate` objects, or as strings in the format `yyyy-mm-dd`."
[start-date end-date key]
(let [data (total-donations-by-weeks start-date end-date)]
(xy-chart {(format "%s Donations" (capitalize (name key)))
[(map #(local-date->date (first %)) data)
(map #(:n (nth % 1)) data)]})))
(defn chart-total-donations-by-weeks
"Create and return an XY chart of data on total donations made between
`start-date` and `end-date`. Arguments may be supplied as
`java.time.LocalDate` objects, or as strings in the format `yyyy-mm-dd`."
[start-date end-date]
(chart-donations-by-weeks start-date end-date :total))
(defn chart-number-donations-by-weeks
"Create and return an XY chart of data on number of donations made between
`start-date` and `end-date`. Arguments may be supplied as
`java.time.LocalDate` objects, or as strings in the format `yyyy-mm-dd`."
[start-date end-date]
(chart-donations-by-weeks start-date end-date :n))
(defn enhance-account-with-donations
"Take this `account_map`, which must at least have a valid value for the
key `:campaign_url` and return a similar map including the key `:donations`,
whose value is a float representing the total donations received by that
campaign URL between the dates `sd` (exclusive) and `ed` (inclusive). Date
arguments should be supplied as `java.time.LocalDate` objects."
[account-map sd ed]
(assoc account-map :donations
(reduce + 0 (map :amount
(select 'campaign_donations
(fields :amount)
(where (and
{:campaign_url [= (:campaign_url account-map)]}
{:created_at [> sd]}
{:created_at [<= ed]})))))))
(defn active-accounts
"Return, as an integer, the number of accounts believed to have been active
on this `date`, which should be
supplied as `java.time.LocalDate` objects, or as strings in the format
`yyyy-mm-dd`"
[date]
(let [d (normalise-date date (ld/now))]
(select 'accounts
(fields :id :display_name :created_at :campaign_url)
(where {:created_at [< d]}))))
(defn accounts-with-donations-by-date-range
"Return a list of maps, each representing one account from the `gaza.onl`
database, with a key `:donations`, whose value is a float representing the
total donations received by that account between the dates `start-date`
(exclusive) and `end-date` (inclusive). Date arguments should be supplied
as `java.time.LocalDate` objects, or as strings in the format `yyyy-mm-dd`."
[start-date end-date]
(let [sd (normalise-date start-date "2024-01-01")
ed (normalise-date end-date (ld/now))]
(map #(enhance-account-with-donations % sd ed) (active-accounts sd))))
(defn chart-donations-by-accounts-in-date-range
"Return a chart of donations received by individual accounts between
`start-date` (exclusive) and `end-date` (inclusive). Arguments should be
supplied as `java.time.LocalDate` objects, or as strings in the format
`yyyy-mm-dd`. Accounts are identified in the chart only by rank order."
[start-date end-date]
(let [data (accounts-with-donations-by-date-range start-date end-date)]
(xy-chart {(format "Donations between\n%s and\n%s" start-date end-date)
[(range (count data)) (sort (map :donations data))]})))
(defn chart-donations-as-percentage-in-date-range
"Return a chart of donations received by individual accounts between
`start-date` (exclusive) and `end-date` (inclusive). Arguments should be
supplied as `java.time.LocalDate` objects, or as strings in the format
`yyyy-mm-dd`. Accounts are identified in the chart only by rank order."
[start-date end-date]
(let [data (accounts-with-donations-by-date-range start-date end-date)
donations (sort (map :donations data))
total (reduce + donations)
percentages (map #(* 100.0 (/ % total)) donations)]
(xy-chart {(format "Donations as percent\nof total donations\nbetween %s and\n%s" start-date end-date)
[(range (count data)) percentages]})))
(defn chart-accounts-with-donations-by-months-in-range
"Return a chart with one line for each calendar month covering from
`start-date` (inclusive) to `end-date` (inclusive). Arguments should be
supplied as `java.time.LocalDate` objects, or as strings in the format
`yyyy-mm-dd`, showing donations as for
`chart-donations-by-accounts-in-date-range`, q.v."
[start-date end-date]
(let [sd (normalise-date start-date "2024-01-01")
ed (normalise-date end-date (ld/now))]
(loop [s (.withDayOfMonth sd 1)
i (.withDayOfMonth (.plusMonths sd 1) 1)
m (sorted-map)]
(let [data (accounts-with-donations-by-date-range s i)
m' (assoc m (format "Donations between\n%s and\n%s" s i)
[(range (count data)) (sort (map :donations data))])]
(if (ld/is-before ed i) (xy-chart m')
(recur i (.withDayOfMonth (.plusMonths i 1) 1) m'))))))
;; this does not work and I don't know why
;; (as-sql '(select 'campaign_donations
;; (fields :amount :campaign_url :created_at)
;; (where (and
;; {:campaign_url [= "https://www.chuffed.org/project/128261-photographer-from-gaza-rebuilding-life-dreams"]}
;; {:created_at [> "2024-04-01"]}
;; {:created_at [<= "2o24-04-30"]}))))
(defn average-donations-received-by-month
"Return data as a map keyed by the date of the first of each month between
`start-date` and `end-date`; the values are maps with keys `:average`,
`:count` and `:total`. Arguments should be supplied as `java.time.LocalDate`
objects, or as strings in the format `yyyy-mm-dd`."
[start-date end-date]
(let [sd (normalise-date start-date "2024-01-01")
ed (normalise-date end-date (ld/now))]
(loop [s (.withDayOfMonth sd 1)
i (.withDayOfMonth (.plusMonths sd 1) 1)
m (sorted-map)]
(let [accs (accounts-with-donations-by-date-range s i)
n (count accs)
total (reduce + (map :donations accs))
av (if (zero? n)
n
(float (/ total n)))
m' (assoc m s {:average av :count n :total total})]
(if (ld/is-before ed i)
m'
(recur i (.withDayOfMonth (.plusMonths i 1) 1) m'))))))
(defn chart-average-donations-received-by-month
"Return a chart comparing the average donations received per account with
the total number of active accounts per month between `start-date` and
`end-date`. Arguments should be supplied as `java.time.LocalDate` objects,
or as strings in the format `yyyy-mm-dd`."
[start-date end-date]
(let [data (average-donations-received-by-month start-date end-date)]
(xy-chart {(format "Average donations\nper active account\nbetween\n%s and\n%s" start-date end-date)
[(map #(local-date->date %) (keys data)) (map :average (vals data))]
(format "Active accounts\nbetween\n%s and\n%s" start-date end-date)
[(map #(local-date->date %) (keys data)) (map :count (vals data))]})))