Skip to content
Snippets Groups Projects
Commit d0b74d8c authored by Simon Belak's avatar Simon Belak
Browse files

remove notebook cruf

parent bda27844
No related branches found
No related tags found
No related merge requests found
;; gorilla-repl.fileformat = 1
;; **
;;; # Fingerprints
;;;
;;; See [design doc](https://docs.google.com/document/d/1VhuDkFSkUEObtT-KVofmvkbfCeuAqr5KQOpgTc1Qaqg/edit#)
;; **
;; @@
(ns metaml-notebook.fingerprints
(:require [bigml.histogram.core :as hist]
[bigml.sketchy.hyper-loglog :as hyper-loglog]
[clojure.core.reducers :as r]
[gorilla-plot.core :as plot]
[kixi.stats.core :as stats]
[kixi.stats.math :as math]
[kixi.stats.random :as random]
[net.cgrand.xforms :as x]
[redux.core :as redux]))
;; @@
;; =>
;;; {"type":"html","content":"<span class='clj-nil'>nil</span>","value":"nil"}
;; <=
;; @@
(def cardinality-error 0.01)
;; @@
;; =>
;;; {"type":"html","content":"<span class='clj-var'>#&#x27;metaml-notebook.fingerprints/cardinality-error</span>","value":"#'metaml-notebook.fingerprints/cardinality-error"}
;; <=
;; @@
(defn histogram
([] (hist/create))
([acc] acc)
([acc x] (hist/insert! acc x)))
(defn cardinality
([] (hyper-loglog/create cardinality-error))
([acc] (hyper-loglog/distinct-count acc))
([acc x] (hyper-loglog/insert acc x)))
;; @@
;; =>
;;; {"type":"html","content":"<span class='clj-var'>#&#x27;metaml-notebook.fingerprints/cardinality</span>","value":"#'metaml-notebook.fingerprints/cardinality"}
;; <=
;; @@
(defn entropy
[histogram]
(let [total (hist/total-count histogram)]
(transduce (comp (map :count)
(filter pos?)
(map #(let [p (/ % total)]
(* p (math/log p)))))
(redux/post-complete + -)
(hist/bins histogram))))
;; @@
;; =>
;;; {"type":"html","content":"<span class='clj-var'>#&#x27;metaml-notebook.fingerprints/entropy</span>","value":"#'metaml-notebook.fingerprints/entropy"}
;; <=
;; @@
(defn fingerprint [field]
(transduce identity
(redux/post-complete
(redux/fuse {:histogram histogram
:cardinality cardinality
:kurtosis stats/kurtosis
:skewness stats/skewness})
(fn [{:keys [histogram cardinality kurtosis skewness]}]
(let [var (hist/variance histogram)
sd (math/sqrt var)
count (hist/total-count histogram)]
{:histogram (into {}
(map (juxt :mean :count))
(hist/bins histogram))
:cardinality cardinality
:min (hist/minimum histogram)
:max (hist/maximum histogram)
:mean (hist/mean histogram)
:median (hist/median histogram)
:var var
:sd sd
:count count
:kurtosis kurtosis
:skewness skewness
:all-distinct? (> (/ cardinality count)
(- 1 cardinality-error))
:entropy (entropy histogram)})))
field))
;; @@
;; =>
;;; {"type":"html","content":"<span class='clj-var'>#&#x27;metaml-notebook.fingerprints/fingerprint</span>","value":"#'metaml-notebook.fingerprints/fingerprint"}
;; <=
;; @@
(def xs-gaussian (random/sample 1000 (random/normal {:mu 0 :sd 1})))
(def xs-ints (random/sample 1000 (random/categorical (range 10) (repeat 10 0.1))))
;; @@
;; =>
;;; {"type":"html","content":"<span class='clj-var'>#&#x27;metaml-notebook.fingerprints/xs-ints</span>","value":"#'metaml-notebook.fingerprints/xs-ints"}
;; <=
;; @@
(fingerprint xs-gaussian)
;; @@
;; =>
;;; {"type":"list-like","open":"<span class='clj-map'>{</span>","close":"<span class='clj-map'>}</span>","separator":", ","items":[{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:skewness</span>","value":":skewness"},{"type":"html","content":"<span class='clj-double'>0.10840647077419092</span>","value":"0.10840647077419092"}],"value":"[:skewness 0.10840647077419092]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:min</span>","value":":min"},{"type":"html","content":"<span class='clj-double'>-3.5574250646107766</span>","value":"-3.5574250646107766"}],"value":"[:min -3.5574250646107766]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:all-distinct?</span>","value":":all-distinct?"},{"type":"html","content":"<span class='clj-unkown'>true</span>","value":"true"}],"value":"[:all-distinct? true]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:histogram</span>","value":":histogram"},{"type":"list-like","open":"<span class='clj-map'>{</span>","close":"<span class='clj-map'>}</span>","separator":", ","items":[{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-0.3634453941134561</span>","value":"-0.3634453941134561"},{"type":"html","content":"<span class='clj-long'>47</span>","value":"47"}],"value":"[-0.3634453941134561 47]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>1.275941202036357</span>","value":"1.275941202036357"},{"type":"html","content":"<span class='clj-long'>22</span>","value":"22"}],"value":"[1.275941202036357 22]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>1.829479779013279</span>","value":"1.829479779013279"},{"type":"html","content":"<span class='clj-long'>8</span>","value":"8"}],"value":"[1.829479779013279 8]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-2.26358300678107</span>","value":"-2.26358300678107"},{"type":"html","content":"<span class='clj-long'>5</span>","value":"5"}],"value":"[-2.26358300678107 5]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-2.618763898549087</span>","value":"-2.618763898549087"},{"type":"html","content":"<span class='clj-long'>2</span>","value":"2"}],"value":"[-2.618763898549087 2]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>2.411856355613832</span>","value":"2.411856355613832"},{"type":"html","content":"<span class='clj-long'>3</span>","value":"3"}],"value":"[2.411856355613832 3]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>0.8205047125682139</span>","value":"0.8205047125682139"},{"type":"html","content":"<span class='clj-long'>13</span>","value":"13"}],"value":"[0.8205047125682139 13]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>1.3739439607173798</span>","value":"1.3739439607173798"},{"type":"html","content":"<span class='clj-long'>6</span>","value":"6"}],"value":"[1.3739439607173798 6]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-0.6407702482086556</span>","value":"-0.6407702482086556"},{"type":"html","content":"<span class='clj-long'>32</span>","value":"32"}],"value":"[-0.6407702482086556 32]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>0.8904347501327857</span>","value":"0.8904347501327857"},{"type":"html","content":"<span class='clj-long'>17</span>","value":"17"}],"value":"[0.8904347501327857 17]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-1.9347402481538132</span>","value":"-1.9347402481538132"},{"type":"html","content":"<span class='clj-long'>2</span>","value":"2"}],"value":"[-1.9347402481538132 2]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-1.206643082349383</span>","value":"-1.206643082349383"},{"type":"html","content":"<span class='clj-long'>9</span>","value":"9"}],"value":"[-1.206643082349383 9]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-0.15624398661074435</span>","value":"-0.15624398661074435"},{"type":"html","content":"<span class='clj-long'>22</span>","value":"22"}],"value":"[-0.15624398661074435 22]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-0.8425324899296989</span>","value":"-0.8425324899296989"},{"type":"html","content":"<span class='clj-long'>29</span>","value":"29"}],"value":"[-0.8425324899296989 29]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-1.7052672906025281</span>","value":"-1.7052672906025281"},{"type":"html","content":"<span class='clj-long'>9</span>","value":"9"}],"value":"[-1.7052672906025281 9]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-1.8304043454094165</span>","value":"-1.8304043454094165"},{"type":"html","content":"<span class='clj-long'>14</span>","value":"14"}],"value":"[-1.8304043454094165 14]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-0.554683894776815</span>","value":"-0.554683894776815"},{"type":"html","content":"<span class='clj-long'>30</span>","value":"30"}],"value":"[-0.554683894776815 30]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>0.19163979463776482</span>","value":"0.19163979463776482"},{"type":"html","content":"<span class='clj-long'>36</span>","value":"36"}],"value":"[0.19163979463776482 36]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>1.5890112541125738</span>","value":"1.5890112541125738"},{"type":"html","content":"<span class='clj-long'>7</span>","value":"7"}],"value":"[1.5890112541125738 7]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-0.2435522328150168</span>","value":"-0.2435522328150168"},{"type":"html","content":"<span class='clj-long'>40</span>","value":"40"}],"value":"[-0.2435522328150168 40]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-0.9168871285037822</span>","value":"-0.9168871285037822"},{"type":"html","content":"<span class='clj-long'>21</span>","value":"21"}],"value":"[-0.9168871285037822 21]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>0.2738707897824631</span>","value":"0.2738707897824631"},{"type":"html","content":"<span class='clj-long'>25</span>","value":"25"}],"value":"[0.2738707897824631 25]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-0.024399780086671014</span>","value":"-0.024399780086671014"},{"type":"html","content":"<span class='clj-long'>19</span>","value":"19"}],"value":"[-0.024399780086671014 19]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-3.5574250646107766</span>","value":"-3.5574250646107766"},{"type":"html","content":"<span class='clj-long'>1</span>","value":"1"}],"value":"[-3.5574250646107766 1]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-1.1313714240993815</span>","value":"-1.1313714240993815"},{"type":"html","content":"<span class='clj-long'>16</span>","value":"16"}],"value":"[-1.1313714240993815 16]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>1.5180617376471197</span>","value":"1.5180617376471197"},{"type":"html","content":"<span class='clj-long'>14</span>","value":"14"}],"value":"[1.5180617376471197 14]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>2.216605779169832</span>","value":"2.216605779169832"},{"type":"html","content":"<span class='clj-long'>7</span>","value":"7"}],"value":"[2.216605779169832 7]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>0.5336381901013918</span>","value":"0.5336381901013918"},{"type":"html","content":"<span class='clj-long'>25</span>","value":"25"}],"value":"[0.5336381901013918 25]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>1.4400363139975345</span>","value":"1.4400363139975345"},{"type":"html","content":"<span class='clj-long'>14</span>","value":"14"}],"value":"[1.4400363139975345 14]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-0.0915728182859809</span>","value":"-0.0915728182859809"},{"type":"html","content":"<span class='clj-long'>29</span>","value":"29"}],"value":"[-0.0915728182859809 29]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>2.6700895585504694</span>","value":"2.6700895585504694"},{"type":"html","content":"<span class='clj-long'>3</span>","value":"3"}],"value":"[2.6700895585504694 3]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-1.6428256467934432</span>","value":"-1.6428256467934432"},{"type":"html","content":"<span class='clj-long'>1</span>","value":"1"}],"value":"[-1.6428256467934432 1]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>1.0464802971800422</span>","value":"1.0464802971800422"},{"type":"html","content":"<span class='clj-long'>18</span>","value":"18"}],"value":"[1.0464802971800422 18]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-1.4273927506795212</span>","value":"-1.4273927506795212"},{"type":"html","content":"<span class='clj-long'>10</span>","value":"10"}],"value":"[-1.4273927506795212 10]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>0.03937840677845021</span>","value":"0.03937840677845021"},{"type":"html","content":"<span class='clj-long'>25</span>","value":"25"}],"value":"[0.03937840677845021 25]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>1.9825458516100158</span>","value":"1.9825458516100158"},{"type":"html","content":"<span class='clj-long'>5</span>","value":"5"}],"value":"[1.9825458516100158 5]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>2.0541784669589562</span>","value":"2.0541784669589562"},{"type":"html","content":"<span class='clj-long'>4</span>","value":"4"}],"value":"[2.0541784669589562 4]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>1.2010399515937409</span>","value":"1.2010399515937409"},{"type":"html","content":"<span class='clj-long'>14</span>","value":"14"}],"value":"[1.2010399515937409 14]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>2.4766646187081727</span>","value":"2.4766646187081727"},{"type":"html","content":"<span class='clj-long'>3</span>","value":"3"}],"value":"[2.4766646187081727 3]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>2.7883011073280386</span>","value":"2.7883011073280386"},{"type":"html","content":"<span class='clj-long'>2</span>","value":"2"}],"value":"[2.7883011073280386 2]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>0.35158091792962215</span>","value":"0.35158091792962215"},{"type":"html","content":"<span class='clj-long'>41</span>","value":"41"}],"value":"[0.35158091792962215 41]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>0.5991416673723217</span>","value":"0.5991416673723217"},{"type":"html","content":"<span class='clj-long'>25</span>","value":"25"}],"value":"[0.5991416673723217 25]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>2.8838945081281397</span>","value":"2.8838945081281397"},{"type":"html","content":"<span class='clj-long'>1</span>","value":"1"}],"value":"[2.8838945081281397 1]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-2.0273295192458574</span>","value":"-2.0273295192458574"},{"type":"html","content":"<span class='clj-long'>8</span>","value":"8"}],"value":"[-2.0273295192458574 8]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-0.7309842922756689</span>","value":"-0.7309842922756689"},{"type":"html","content":"<span class='clj-long'>31</span>","value":"31"}],"value":"[-0.7309842922756689 31]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>3.302625203359918</span>","value":"3.302625203359918"},{"type":"html","content":"<span class='clj-long'>1</span>","value":"1"}],"value":"[3.302625203359918 1]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>2.1229749577737107</span>","value":"2.1229749577737107"},{"type":"html","content":"<span class='clj-long'>8</span>","value":"8"}],"value":"[2.1229749577737107 8]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>0.10875203586991143</span>","value":"0.10875203586991143"},{"type":"html","content":"<span class='clj-long'>32</span>","value":"32"}],"value":"[0.10875203586991143 32]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-2.1343627259760747</span>","value":"-2.1343627259760747"},{"type":"html","content":"<span class='clj-long'>2</span>","value":"2"}],"value":"[-2.1343627259760747 2]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>1.7406212522702815</span>","value":"1.7406212522702815"},{"type":"html","content":"<span class='clj-long'>10</span>","value":"10"}],"value":"[1.7406212522702815 10]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>1.1294085120553696</span>","value":"1.1294085120553696"},{"type":"html","content":"<span class='clj-long'>15</span>","value":"15"}],"value":"[1.1294085120553696 15]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-1.0428957177724258</span>","value":"-1.0428957177724258"},{"type":"html","content":"<span class='clj-long'>30</span>","value":"30"}],"value":"[-1.0428957177724258 30]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>1.903380047512444</span>","value":"1.903380047512444"},{"type":"html","content":"<span class='clj-long'>6</span>","value":"6"}],"value":"[1.903380047512444 6]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-1.2765833510372362</span>","value":"-1.2765833510372362"},{"type":"html","content":"<span class='clj-long'>12</span>","value":"12"}],"value":"[-1.2765833510372362 12]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-1.5456759789571637</span>","value":"-1.5456759789571637"},{"type":"html","content":"<span class='clj-long'>17</span>","value":"17"}],"value":"[-1.5456759789571637 17]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-1.347504809673842</span>","value":"-1.347504809673842"},{"type":"html","content":"<span class='clj-long'>14</span>","value":"14"}],"value":"[-1.347504809673842 14]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>0.6858372993242408</span>","value":"0.6858372993242408"},{"type":"html","content":"<span class='clj-long'>32</span>","value":"32"}],"value":"[0.6858372993242408 32]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>2.333245763754761</span>","value":"2.333245763754761"},{"type":"html","content":"<span class='clj-long'>2</span>","value":"2"}],"value":"[2.333245763754761 2]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>0.44504897634573587</span>","value":"0.44504897634573587"},{"type":"html","content":"<span class='clj-long'>22</span>","value":"22"}],"value":"[0.44504897634573587 22]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-0.4606488130023291</span>","value":"-0.4606488130023291"},{"type":"html","content":"<span class='clj-long'>36</span>","value":"36"}],"value":"[-0.4606488130023291 36]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>0.9735242550538568</span>","value":"0.9735242550538568"},{"type":"html","content":"<span class='clj-long'>19</span>","value":"19"}],"value":"[0.9735242550538568 19]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>1.6595186654599194</span>","value":"1.6595186654599194"},{"type":"html","content":"<span class='clj-long'>11</span>","value":"11"}],"value":"[1.6595186654599194 11]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>0.743996102699194</span>","value":"0.743996102699194"},{"type":"html","content":"<span class='clj-long'>15</span>","value":"15"}],"value":"[0.743996102699194 15]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>-3.1206271039673883</span>","value":"-3.1206271039673883"},{"type":"html","content":"<span class='clj-long'>1</span>","value":"1"}],"value":"[-3.1206271039673883 1]"}],"value":"{-0.3634453941134561 47, 1.275941202036357 22, 1.829479779013279 8, -2.26358300678107 5, -2.618763898549087 2, 2.411856355613832 3, 0.8205047125682139 13, 1.3739439607173798 6, -0.6407702482086556 32, 0.8904347501327857 17, -1.9347402481538132 2, -1.206643082349383 9, -0.15624398661074435 22, -0.8425324899296989 29, -1.7052672906025281 9, -1.8304043454094165 14, -0.554683894776815 30, 0.19163979463776482 36, 1.5890112541125738 7, -0.2435522328150168 40, -0.9168871285037822 21, 0.2738707897824631 25, -0.024399780086671014 19, -3.5574250646107766 1, -1.1313714240993815 16, 1.5180617376471197 14, 2.216605779169832 7, 0.5336381901013918 25, 1.4400363139975345 14, -0.0915728182859809 29, 2.6700895585504694 3, -1.6428256467934432 1, 1.0464802971800422 18, -1.4273927506795212 10, 0.03937840677845021 25, 1.9825458516100158 5, 2.0541784669589562 4, 1.2010399515937409 14, 2.4766646187081727 3, 2.7883011073280386 2, 0.35158091792962215 41, 0.5991416673723217 25, 2.8838945081281397 1, -2.0273295192458574 8, -0.7309842922756689 31, 3.302625203359918 1, 2.1229749577737107 8, 0.10875203586991143 32, -2.1343627259760747 2, 1.7406212522702815 10, 1.1294085120553696 15, -1.0428957177724258 30, 1.903380047512444 6, -1.2765833510372362 12, -1.5456759789571637 17, -1.347504809673842 14, 0.6858372993242408 32, 2.333245763754761 2, 0.44504897634573587 22, -0.4606488130023291 36, 0.9735242550538568 19, 1.6595186654599194 11, 0.743996102699194 15, -3.1206271039673883 1}"}],"value":"[:histogram {-0.3634453941134561 47, 1.275941202036357 22, 1.829479779013279 8, -2.26358300678107 5, -2.618763898549087 2, 2.411856355613832 3, 0.8205047125682139 13, 1.3739439607173798 6, -0.6407702482086556 32, 0.8904347501327857 17, -1.9347402481538132 2, -1.206643082349383 9, -0.15624398661074435 22, -0.8425324899296989 29, -1.7052672906025281 9, -1.8304043454094165 14, -0.554683894776815 30, 0.19163979463776482 36, 1.5890112541125738 7, -0.2435522328150168 40, -0.9168871285037822 21, 0.2738707897824631 25, -0.024399780086671014 19, -3.5574250646107766 1, -1.1313714240993815 16, 1.5180617376471197 14, 2.216605779169832 7, 0.5336381901013918 25, 1.4400363139975345 14, -0.0915728182859809 29, 2.6700895585504694 3, -1.6428256467934432 1, 1.0464802971800422 18, -1.4273927506795212 10, 0.03937840677845021 25, 1.9825458516100158 5, 2.0541784669589562 4, 1.2010399515937409 14, 2.4766646187081727 3, 2.7883011073280386 2, 0.35158091792962215 41, 0.5991416673723217 25, 2.8838945081281397 1, -2.0273295192458574 8, -0.7309842922756689 31, 3.302625203359918 1, 2.1229749577737107 8, 0.10875203586991143 32, -2.1343627259760747 2, 1.7406212522702815 10, 1.1294085120553696 15, -1.0428957177724258 30, 1.903380047512444 6, -1.2765833510372362 12, -1.5456759789571637 17, -1.347504809673842 14, 0.6858372993242408 32, 2.333245763754761 2, 0.44504897634573587 22, -0.4606488130023291 36, 0.9735242550538568 19, 1.6595186654599194 11, 0.743996102699194 15, -3.1206271039673883 1}]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:mean</span>","value":":mean"},{"type":"html","content":"<span class='clj-double'>0.062391462847620746</span>","value":"0.062391462847620746"}],"value":"[:mean 0.062391462847620746]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:var</span>","value":":var"},{"type":"html","content":"<span class='clj-double'>1.047368668682761</span>","value":"1.047368668682761"}],"value":"[:var 1.047368668682761]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:median</span>","value":":median"},{"type":"html","content":"<span class='clj-double'>0.035523759349793155</span>","value":"0.035523759349793155"}],"value":"[:median 0.035523759349793155]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:max</span>","value":":max"},{"type":"html","content":"<span class='clj-double'>3.302625203359918</span>","value":"3.302625203359918"}],"value":"[:max 3.302625203359918]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:count</span>","value":":count"},{"type":"html","content":"<span class='clj-double'>1000.0</span>","value":"1000.0"}],"value":"[:count 1000.0]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:entropy</span>","value":":entropy"},{"type":"html","content":"<span class='clj-double'>3.857770367988303</span>","value":"3.857770367988303"}],"value":"[:entropy 3.857770367988303]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:sd</span>","value":":sd"},{"type":"html","content":"<span class='clj-double'>1.0234103129648249</span>","value":"1.0234103129648249"}],"value":"[:sd 1.0234103129648249]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:kurtosis</span>","value":":kurtosis"},{"type":"html","content":"<span class='clj-double'>-0.10509189623556336</span>","value":"-0.10509189623556336"}],"value":"[:kurtosis -0.10509189623556336]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:cardinality</span>","value":":cardinality"},{"type":"html","content":"<span class='clj-long'>1003</span>","value":"1003"}],"value":"[:cardinality 1003]"}],"value":"{:skewness 0.10840647077419092, :min -3.5574250646107766, :all-distinct? true, :histogram {-0.3634453941134561 47, 1.275941202036357 22, 1.829479779013279 8, -2.26358300678107 5, -2.618763898549087 2, 2.411856355613832 3, 0.8205047125682139 13, 1.3739439607173798 6, -0.6407702482086556 32, 0.8904347501327857 17, -1.9347402481538132 2, -1.206643082349383 9, -0.15624398661074435 22, -0.8425324899296989 29, -1.7052672906025281 9, -1.8304043454094165 14, -0.554683894776815 30, 0.19163979463776482 36, 1.5890112541125738 7, -0.2435522328150168 40, -0.9168871285037822 21, 0.2738707897824631 25, -0.024399780086671014 19, -3.5574250646107766 1, -1.1313714240993815 16, 1.5180617376471197 14, 2.216605779169832 7, 0.5336381901013918 25, 1.4400363139975345 14, -0.0915728182859809 29, 2.6700895585504694 3, -1.6428256467934432 1, 1.0464802971800422 18, -1.4273927506795212 10, 0.03937840677845021 25, 1.9825458516100158 5, 2.0541784669589562 4, 1.2010399515937409 14, 2.4766646187081727 3, 2.7883011073280386 2, 0.35158091792962215 41, 0.5991416673723217 25, 2.8838945081281397 1, -2.0273295192458574 8, -0.7309842922756689 31, 3.302625203359918 1, 2.1229749577737107 8, 0.10875203586991143 32, -2.1343627259760747 2, 1.7406212522702815 10, 1.1294085120553696 15, -1.0428957177724258 30, 1.903380047512444 6, -1.2765833510372362 12, -1.5456759789571637 17, -1.347504809673842 14, 0.6858372993242408 32, 2.333245763754761 2, 0.44504897634573587 22, -0.4606488130023291 36, 0.9735242550538568 19, 1.6595186654599194 11, 0.743996102699194 15, -3.1206271039673883 1}, :mean 0.062391462847620746, :var 1.047368668682761, :median 0.035523759349793155, :max 3.302625203359918, :count 1000.0, :entropy 3.857770367988303, :sd 1.0234103129648249, :kurtosis -0.10509189623556336, :cardinality 1003}"}
;; <=
;; @@
(fingerprint xs-ints)
;; @@
;; =>
;;; {"type":"list-like","open":"<span class='clj-map'>{</span>","close":"<span class='clj-map'>}</span>","separator":", ","items":[{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:skewness</span>","value":":skewness"},{"type":"html","content":"<span class='clj-double'>0.09150887435907215</span>","value":"0.09150887435907215"}],"value":"[:skewness 0.09150887435907215]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:min</span>","value":":min"},{"type":"html","content":"<span class='clj-double'>0.0</span>","value":"0.0"}],"value":"[:min 0.0]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:all-distinct?</span>","value":":all-distinct?"},{"type":"html","content":"<span class='clj-unkown'>false</span>","value":"false"}],"value":"[:all-distinct? false]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:histogram</span>","value":":histogram"},{"type":"list-like","open":"<span class='clj-map'>{</span>","close":"<span class='clj-map'>}</span>","separator":", ","items":[{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>0.0</span>","value":"0.0"},{"type":"html","content":"<span class='clj-long'>109</span>","value":"109"}],"value":"[0.0 109]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>2.0</span>","value":"2.0"},{"type":"html","content":"<span class='clj-long'>107</span>","value":"107"}],"value":"[2.0 107]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>4.0</span>","value":"4.0"},{"type":"html","content":"<span class='clj-long'>101</span>","value":"101"}],"value":"[4.0 101]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>8.0</span>","value":"8.0"},{"type":"html","content":"<span class='clj-long'>93</span>","value":"93"}],"value":"[8.0 93]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>1.0</span>","value":"1.0"},{"type":"html","content":"<span class='clj-long'>108</span>","value":"108"}],"value":"[1.0 108]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>9.0</span>","value":"9.0"},{"type":"html","content":"<span class='clj-long'>109</span>","value":"109"}],"value":"[9.0 109]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>5.0</span>","value":"5.0"},{"type":"html","content":"<span class='clj-long'>99</span>","value":"99"}],"value":"[5.0 99]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>3.0</span>","value":"3.0"},{"type":"html","content":"<span class='clj-long'>102</span>","value":"102"}],"value":"[3.0 102]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>6.0</span>","value":"6.0"},{"type":"html","content":"<span class='clj-long'>84</span>","value":"84"}],"value":"[6.0 84]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-double'>7.0</span>","value":"7.0"},{"type":"html","content":"<span class='clj-long'>88</span>","value":"88"}],"value":"[7.0 88]"}],"value":"{0.0 109, 2.0 107, 4.0 101, 8.0 93, 1.0 108, 9.0 109, 5.0 99, 3.0 102, 6.0 84, 7.0 88}"}],"value":"[:histogram {0.0 109, 2.0 107, 4.0 101, 8.0 93, 1.0 108, 9.0 109, 5.0 99, 3.0 102, 6.0 84, 7.0 88}]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:mean</span>","value":":mean"},{"type":"html","content":"<span class='clj-double'>4.372</span>","value":"4.372"}],"value":"[:mean 4.372]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:var</span>","value":":var"},{"type":"html","content":"<span class='clj-double'>8.556172172172172</span>","value":"8.556172172172172"}],"value":"[:var 8.556172172172172]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:median</span>","value":":median"},{"type":"html","content":"<span class='clj-double'>4.0</span>","value":"4.0"}],"value":"[:median 4.0]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:max</span>","value":":max"},{"type":"html","content":"<span class='clj-double'>9.0</span>","value":"9.0"}],"value":"[:max 9.0]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:count</span>","value":":count"},{"type":"html","content":"<span class='clj-double'>1000.0</span>","value":"1000.0"}],"value":"[:count 1000.0]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:entropy</span>","value":":entropy"},{"type":"html","content":"<span class='clj-double'>2.2988613148798835</span>","value":"2.2988613148798835"}],"value":"[:entropy 2.2988613148798835]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:sd</span>","value":":sd"},{"type":"html","content":"<span class='clj-double'>2.925093532209213</span>","value":"2.925093532209213"}],"value":"[:sd 2.925093532209213]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:kurtosis</span>","value":":kurtosis"},{"type":"html","content":"<span class='clj-double'>-1.24202236218906</span>","value":"-1.24202236218906"}],"value":"[:kurtosis -1.24202236218906]"},{"type":"list-like","open":"","close":"","separator":" ","items":[{"type":"html","content":"<span class='clj-keyword'>:cardinality</span>","value":":cardinality"},{"type":"html","content":"<span class='clj-long'>8</span>","value":"8"}],"value":"[:cardinality 8]"}],"value":"{:skewness 0.09150887435907215, :min 0.0, :all-distinct? false, :histogram {0.0 109, 2.0 107, 4.0 101, 8.0 93, 1.0 108, 9.0 109, 5.0 99, 3.0 102, 6.0 84, 7.0 88}, :mean 4.372, :var 8.556172172172172, :median 4.0, :max 9.0, :count 1000.0, :entropy 2.2988613148798835, :sd 2.925093532209213, :kurtosis -1.24202236218906, :cardinality 8}"}
;; <=
;; @@
;; @@
......@@ -83,15 +83,13 @@
[toucan "1.0.3" ; Model layer, hydration, and DB utilities
:exclusions [honeysql]]
; Notebook utilities and prototypes
; Proposed additions for fingerprinting
[bigml/histogram "4.1.3"]
[bigml/sketchy "0.4.1"]
[net.cgrand/xforms "0.9.2"]
[kixi/stats "0.3.8"]
[redux "0.1.4"]]
:repositories [["bintray" "https://dl.bintray.com/crate/crate"]] ; Repo for Crate JDBC driver
:plugins [[lein-environ "1.1.0"] ; easy access to environment variables
[lein-gorilla "0.4.0"] ; interactive notebooks
:plugins [[lein-environ "1.1.0"] ; easy access to environment variables
[lein-ring "0.11.0" ; start the HTTP server with 'lein ring server'
:exclusions [org.clojure/clojure]]] ; TODO - should this be a dev dependency ?
:main ^:skip-aot metabase.core
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment