Add article about apriori algorithm with anonymized data

Author: tombarys

deps.edn

@@ -13,7 +13,8 @@
   clj-thamil/clj-thamil                       {:mvn/version "0.2.0"}
   org.scicloj/clay                            {#_#_:mvn/version "2-beta54"
                                                :git/url "https://github.com/scicloj/clay.git"
-                                               :git/sha "26fb97b5ea2f72a98f8a64d5b8b8abf705767a39"}
+                                               :git/sha "c4fa35c11034614d42c48c1223d8767267cad385"}
+  org.scicloj/kindly                          {:mvn/version "4-beta20"}
   thi.ng/geom                                 {:mvn/version "1.0.1"}
   org.eclipse.elk/org.eclipse.elk.core        {:mvn/version "0.10.0"}
   org.eclipse.elk/org.eclipse.elk.graph       {:mvn/version "0.10.0"}

src/data_analysis/book_sales_analysis/about_apriori.clj

@@ -0,0 +1,46 @@
+(ns data-analysis.book-sales-analysis.data-sources-v2
+  (:require [tablecloth.api :as tc]
+            [data-analysis.book-sales-analysis.core-helpers-v2 :as helpers]))
+
+;; ## Central Data Loading
+;; All CSV datasets are loaded here with consistent names and simple tc/dataset calls
+
+;; ### Main Orders Data (WooCommerce exports)
+
+#_(def anonymized-presentation-ds
+  "Anonymized customers full dataset of all orders - for presentation purposes
+   ❗ NOT FOR SHARING"
+  (tc/dataset
+   (helpers/merge-csvs
+    ["data/anonymized-customers-only-presentation-v2.csv"]
+    {:header? true
+     :separator ","
+     :key-fn #(keyword (helpers/sanitize-str %))})))
+
+(def anonymized-shareable-ds
+  "Fully anonymized slice of db - for sharing purposes
+   ✅ SAFE TO SHARE"
+  (tc/dataset
+   (helpers/merge-csvs
+    ["src/data_analysis/book_sales_analysis/anonymized-all-sliced-sharing-V2.csv"]
+    {:header? true
+     :separator ","
+     :key-fn #(keyword (helpers/sanitize-str %))})))
+
+;; ### Book Metadata
+
+#_(def enriched-book-metadata-ds
+  (helpers/enrich-metadata-csv "data/summary-all-time-all-books-300725.csv"))
+
+;; ## Quick Access
+;; Most commonly used datasets with short aliases
+
+(def orders-share anonymized-shareable-ds)
+#_(def orders-slides anonymized-presentation-ds)
+
+(def corr-matrix-precalculated 
+  (tc/dataset "src/data_analysis/book_sales_analysis/corr-matrix.nippy"))
+
+corr-matrix-precalculated
+
+(prn "Data sources loaded.")