Agregar preparación para sección de embeddings y material

felipegonzalez · Nov 1, 2023 · 5d20141 · 5d20141
1 parent 715db74
commit 5d20141
Show file tree

Hide file tree

Showing 10 changed files with 1,142 additions and 0 deletions.
diff --git a/.github/workflows/notas-docker.yml b/.github/workflows/notas-docker.yml
@@ -17,6 +17,9 @@ jobs:
         run: |
           remotes::install_github("https://github.com/tidymodels/probably/", upgrade = "always", force = TRUE)
         shell: Rscript {0}
+      - name: install wordvectors
+        run: |
+          remotes::install_github("bmschmidt/wordVectors", dependencies = TRUE, upgrade = "always", force = TRUE)
       - name: Install others
         run: |
           install.packages(c("discrim"))

diff --git a/datos/noticias/.gitkeep b/datos/noticias/.gitkeep
diff --git a/notas/15-reduccion-dim.qmd b/notas/15-reduccion-dim.qmd
@@ -1,5 +1,12 @@
 # Aprendizaje no supervisado: reducción de dimensionalidad
 
+```{r, include = FALSE}
+library(tidyverse)
+library(tidymodels)
+cbbPalette <- c("#000000", "#E69F00", "#56B4E9", "#009E73", "#F0E442", "#0072B2", "#D55E00", "#CC79A7")
+theme_set(theme_minimal())
+```
+
 En esta parte veremos técnicas de reducción de dimensionalidad  que buscan preservar la mayor parte de la información contenida en los datos originales en una
 representación más compacta que sea útil para hacer análisis o construir modelos.
 

diff --git a/notas/16-recom-factorizacion.qmd b/notas/16-recom-factorizacion.qmd
diff --git a/notas/cache/noticias_vectors.bin b/notas/cache/noticias_vectors.bin
diff --git a/notas/figuras/1_neural_model.png b/notas/figuras/1_neural_model.png
diff --git a/notas/figuras/cbow_fig.png b/notas/figuras/cbow_fig.png
diff --git a/notas/figuras/div_muestra_1_dot.png b/notas/figuras/div_muestra_1_dot.png
diff --git a/notas/figuras/skipgram.png b/notas/figuras/skipgram.png
diff --git a/notas/referencias/book.bib b/notas/referencias/book.bib
@@ -186,3 +186,35 @@ @Book{goodfellow2016
     note={\url{http://www.deeplearningbook.org}},
     year={2016}
 }
+
+@article{bengio,
+ author = {Bengio, Yoshua and Ducharme, R{\'e}jean and Vincent, Pascal and Janvin, Christian},
+ title = {A Neural Probabilistic Language Model},
+ journal = {J. Mach. Learn. Res.},
+ issue_date = {3/1/2003},
+ volume = {3},
+ month = mar,
+ year = {2003},
+ issn = {1532-4435},
+ pages = {1137--1155},
+ numpages = {19},
+ url = {http://dl.acm.org/citation.cfm?id=944919.944966},
+ acmid = {944966},
+ publisher = {JMLR.org},
+}
+@article{word2vec,
+  author    = {Tomas Mikolov and
+               Kai Chen and
+               Greg Corrado and
+               Jeffrey Dean},
+  title     = {Efficient Estimation of Word Representations in Vector Space},
+  journal   = {CoRR},
+  volume    = {abs/1301.3781},
+  year      = {2013},
+  url       = {http://arxiv.org/abs/1301.3781},
+  archivePrefix = {arXiv},
+  eprint    = {1301.3781},
+  timestamp = {Wed, 07 Jun 2017 14:42:25 +0200},
+  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1301-3781},
+  bibsource = {dblp computer science bibliography, https://dblp.org}
+}