From 8e4030c7c10f75d88584b04f4623449bb8589fb8 Mon Sep 17 00:00:00 2001
From: daslu <daniel.slutsky@gmail.com>
Date: Tue, 11 Feb 2025 01:09:11 +0200
Subject: [PATCH] updated datasets namespace

---
 notebooks/noj_book/datasets.clj | 50 +++++++++++----------------------
 1 file changed, 17 insertions(+), 33 deletions(-)

diff --git a/notebooks/noj_book/datasets.clj b/notebooks/noj_book/datasets.clj
index 4797126..7542185 100644
--- a/notebooks/noj_book/datasets.clj
+++ b/notebooks/noj_book/datasets.clj
@@ -2,52 +2,36 @@
 
 ;; author: Daniel Slutsky, Ken Huang
 
-;; ## Rdatasets
-;; For our tutorials here,
-;; let us fetch some datasets from [Rdatasets](https://vincentarelbundock.github.io/Rdatasets/):
+;; We may use various sources of datasets for our tutorials here.
 
 (ns noj-book.datasets
-  (:require [tablecloth.api :as tc]))
+  (:require [tablecloth.api :as tc]
+            [scicloj.metamorph.ml.rdatasets :as rdatasets]))
 
-(def iris
-  (-> "https://vincentarelbundock.github.io/Rdatasets/csv/datasets/iris.csv"
-      (tc/dataset {:key-fn keyword})
-      (tc/rename-columns {:Sepal.Length :sepal-length
-                          :Sepal.Width :sepal-width
-                          :Petal.Length :petal-length
-                          :Petal.Width :petal-width
-                          :Species :species})))
+;; ## rdatasets
+;; One of the main sources is the `rdatasets` namespace of [metamorph.ml](https://github.com/scicloj/metamorph.ml),
+;; which can fetch datasets from the [Rdatasets](https://vincentarelbundock.github.io/Rdatasets/) collection.
 
-iris
+(rdatasets/datasets-iris)
 
-(def mtcars
-  (-> "https://vincentarelbundock.github.io/Rdatasets/csv/datasets/mtcars.csv"
-      (tc/dataset {:key-fn keyword})))
+(rdatasets/ggplot2-mpg)
 
-mtcars
-
-(def scatter
-  (-> "https://vincentarelbundock.github.io/Rdatasets/csv/openintro/simulated_scatter.csv"
-      (tc/dataset {:key-fn keyword})))
-
-(tc/head scatter)
+(rdatasets/openintro-simulated_scatter)
 
 ;; ## Plotly
 ;; We can also use datasets from [Plotly Sample Datasets](https://plotly.github.io/datasets/)
 
-(-> "https://raw.githubusercontent.com/plotly/datasets/refs/heads/master/1962_2006_walmart_store_openings.csv"
-    (tc/dataset {:key-fn keyword
-                 :parser-fn {:OPENDATE :string
-                             :date_super :string}})
-    (tc/head))
+(tc/dataset
+ "https://raw.githubusercontent.com/plotly/datasets/refs/heads/master/1962_2006_walmart_store_openings.csv"
+ {:key-fn keyword
+  :parser-fn {:OPENDATE :string
+              :date_super :string}})
 
 ;; ## tech.ml.dataset (TMD)
 ;; [TMD's repo](https://github.com/techascent/tech.ml.dataset/tree/master/test/data)
 ;; also has some datasets that we can use:
 
-(def stocks
-  (tc/dataset
-   "https://raw.githubusercontent.com/techascent/tech.ml.dataset/master/test/data/stocks.csv"
-   {:key-fn keyword}))
+(tc/dataset
+ "https://raw.githubusercontent.com/techascent/tech.ml.dataset/master/test/data/stocks.csv"
+ {:key-fn keyword})
 
-stocks