Clean NLP notebooks (#215)

* Update 01_intro.Rmd * Update 02_exoclean.Rmd * Automated changes * Automated changes * Automated changes * fix onyxia links on website (#214) * Automated changes * Automated changes * pb interprétation sprintf * Automated changes * Automated changes Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Romain Avouac <43444134+avouacr@users.noreply.github.com>
linogaliana · Jan 8, 2022 · 3299f1d · 3299f1d
1 parent ed2ddec
commit 3299f1d
Show file tree

Hide file tree

Showing 3 changed files with 27 additions and 4 deletions.
diff --git a/.Rprofile b/.Rprofile
@@ -82,6 +82,8 @@ reminder_badges <- function(notebook = "", onyxia_only = FALSE, split = NULL,
       'https://nbviewer.jupyter.org/github/linogaliana/python-datascientist/blob/master%s',
       notebook
     )
+    chapter <- tools::file_path_sans_ext(basename(notebook))
+    section <- basename(dirname(notebook))
   } else{
     github_link <- 'https://github.com/linogaliana/python-datascientist'
     binder_path <- ""  
@@ -118,10 +120,26 @@ reminder_badges <- function(notebook = "", onyxia_only = FALSE, split = NULL,
     )
   }
 
+  chapter <- tools::file_path_sans_ext(basename(notebook))
+  section <- basename(dirname(notebook))
+
+  onyxia_link_tmplt <- paste0(
+    "https://datalab.sspcloud.fr/launcher/inseefrlab-helm-charts-datascience/jupyter",
+    "?autoLaunch=true&onyxia.friendlyName=%C2%ABpython-datascience%C2%BB",
+    "&init.personalInit=%C2%ABhttps%3A%2F%2Fraw.githubusercontent.com%2Flinogaliana%2Fpython-datascientist%2Fmaster%2Fsspcloud%2Finit-jupyter.sh%C2%BB",
+    "&init.personalInitArgs=%C2%AB${section}%20${chapter}%C2%BB&security.allowlist.enabled=false"
+  )
+  onyxia_link_launcher <- stringr::str_interp(onyxia_link_tmplt, list(section=section, chapter=chapter))
   if (type == "md"){
-    onyxia_link <- "[![Onyxia](https://img.shields.io/badge/SSPcloud-Tester%20via%20SSP--cloud-informational&color=yellow?logo=Python)](https://datalab.sspcloud.fr/launcher/inseefrlab-helm-charts-datascience/jupyter?onyxia.friendlyName=«python-datascientist»&resources.requests.memory=«4Gi»&security.allowlist.enabled=false&init.personalInit=«https://raw.githubusercontent.com/linogaliana/python-datascientist/master/init_onyxia.sh»)"
+    onyxia_link <- paste0(
+      "[![Onyxia](https://img.shields.io/badge/SSPcloud-Tester%20via%20SSP--cloud-informational&color=yellow?logo=Python)]",
+      "(",onyxia_link_launcher,")"
+    )
   } else{
-    onyxia_link <- '<a href="https://datalab.sspcloud.fr/launcher/inseefrlab-helm-charts-datascience/jupyter?onyxia.friendlyName=%c2%abpython-datascientist%c2%bb&amp;resources.requests.memory=%c2%ab4Gi%c2%bb&amp;security.allowlist.enabled=false&amp;init.personalInit=%c2%abhttps://raw.githubusercontent.com/linogaliana/python-datascientist/master/init_onyxia.sh%c2%bb" target="_blank" rel="noopener"><img src="https://img.shields.io/badge/SSPcloud-Tester%20via%20SSP--cloud-informational&amp;color=yellow?logo=Python" alt="Onyxia"></a>'
+    onyxia_link <- sprintf(
+      '<a href="%s" target="_blank" rel="noopener"><img src="https://img.shields.io/badge/SSPcloud-Tester%20via%20SSP--cloud-informational&amp;color=yellow?logo=Python" alt="Onyxia"></a>',
+      onyxia_link_launcher
+    )
   }
 
   if (!is.null(split) && (4 %in% split)){

diff --git a/content/course/NLP/01_intro.Rmd b/content/course/NLP/01_intro.Rmd
@@ -24,8 +24,10 @@ tags:
 categories:
   - Tutoriel
 summary: |
-  Le NLP est un immense domaine de recherche. Ce chapitre va
-  explorer quelques méthodes classiques en s'appuyant
+  Les corpus textuels étant des objets de très grande dimension
+  où le ratio signal/bruit est faible, il est nécessaire de mettre
+  en oeuvre une série d'étapes de nettoyage de texte. Ce chapitre va
+  explorer quelques méthodes classiques de nettoyage en s'appuyant
   sur le Comte de Monte Cristo. 
 ---
 

diff --git a/content/course/NLP/02_exoclean.Rmd b/content/course/NLP/02_exoclean.Rmd
@@ -27,6 +27,9 @@ summary: |
   Ce chapitre continue de présenter l'approche de data-cleaning
   du NLP en s'appuyant sur le corpus de trois auteurs
   anglo-saxons : Mary Shelley, Edgar Allan Poe, H.P. Lovecraft.
+  Dans cette série d'exercice nous mettons en oeuvre de manière
+  plus approfondie les différentes méthodes présentées
+  précedemment
 ---
 
 ```{r setup, include=FALSE}