Reviewed posts/data-storage-comparison

.Rhistory

@@ -426,3 +426,69 @@ JuliaCall::julia_setup()
 JuliaCall::julia_setup("/Applications/Julia-1.9.app/Contents/Resources/julia/bin/julia")
 JuliaCall::julia_setup("/Applications/Julia-1.9.app/Contents/Resources/julia/bin/julia/bin/")
 JuliaCall::julia_setup("/Applications/Julia-1.9.app/Contents/Resources/julia/bin/")
+#| message: false
+library(dplyr)
+data_r <- tibble(
+character_column = c("A", "B", "C", "D"),
+date_column = as.Date(c("2023-01-01", "2023-02-01", "2023-03-01", "2023-04-01")),
+datetime_column = as.POSIXct(c("2023-01-01 10:00:00", "2023-02-01 11:00:00", "2023-03-01 12:00:00", "2023-04-01 13:00:00")),
+numeric_column = c(1.5, 2.5, 3.5, 4.5),
+integer_column = as.integer(c(1, 2, 3, 4)),
+logical_column = c(TRUE, FALSE, FALSE, TRUE)
+)
+extract_column_classes <- function(df) {
+sapply(sapply(df, class), function(x) paste(x, collapse = ", "))
+}
+tibble("data_r" = extract_column_classes(data_r))
+reticulate::repl_python()
+#| message: false
+library(readr)
+write_csv(data_r, file = "data_r.csv")
+data_r_csv <- read_csv("data_r.csv")
+glimpse(data_r_csv)
+#| message: false
+data_python_csv <- read_csv("data_python.csv")
+reticulate::repl_python()
+#| message: false
+data_python_csv <- read_csv("data_python.csv")
+tibble(
+"data_r_csv" = extract_column_classes(data_r_csv),
+"data_python_csv" = extract_column_classes(data_python_csv)
+)
+reticulate::repl_python()
+library(RSQLite)
+con_sqlite_r <- dbConnect(SQLite(), "data_r.sqlite")
+dbWriteTable(con_sqlite_r, "data", data_r, overwrite = TRUE)
+data_r_sqlite <- dbReadTable(con_sqlite_r, "data")
+dbDisconnect(con_sqlite_r)
+glimpse(data_r_sqlite)
+con_sqlite_python <- dbConnect(SQLite(), "data_python.sqlite")
+data_python_sqlite <- dbReadTable(con_sqlite_python, "data")
+reticulate::repl_python()
+#| message: false
+library(arrow)
+write_parquet(data_r, "data_r.parquet")
+data_r_parquet <- read_parquet("data_r.parquet")
+glimpse(data_r_parquet)
+?write_feather()
+#| message: false
+write_feather(data_r, "data_r.feather")
+#| message: false
+write_feather(data_r, "data_r.feather")
+data_r_feather <- read_feather("data_r.feather")
+glimpse(data_r_parquet)
+glimpse(data_r_feather)
+reticulate::repl_python()
+data_python_feather <- read_feather("data_python.feather")
+tibble(
+"data_r_feather" = extract_column_classes(data_r_feather),
+"data_python_feather" = extract_column_classes(data_python_feather)
+)
+data_python_feather
+reticulate::repl_python()
+#| message: false
+library(arrow)
+write_parquet(data_r, "data_r.parquet")
+data_r_parquet <- read_parquet("data_r.parquet")
+glimpse(data_r_parquet)
+reticulate::repl_python()

docs/index.html

@@ -206,7 +206,7 @@
 
 <div class="quarto-listing quarto-listing-container-grid" id="listing-listing">
 <div class="list grid quarto-listing-cols-3">
-<div class="g-col-1" data-index="0" data-listing-date-sort="1705618800000" data-listing-file-modified-sort="1705664169329" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="12" data-listing-word-count-sort="2280">
+<div class="g-col-1" data-index="0" data-listing-date-sort="1705705200000" data-listing-file-modified-sort="1705750762210" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="13" data-listing-word-count-sort="2494">
 <a href="./posts/data-storage-comparison/index.html" class="quarto-grid-link">
 <div class="quarto-grid-item card h-100 card-left">
 <p class="card-img-top">

docs/posts/ggplot2-vs-seaborn/index.html

@@ -1005,7 +1005,7 @@ <h1>Conclusion</h1>
     </div>
   </div>
 </footer>
-<script>var lightboxQuarto = GLightbox({"selector":".lightbox","loop":false,"openEffect":"zoom","descPosition":"bottom","closeEffect":"zoom"});
+<script>var lightboxQuarto = GLightbox({"loop":false,"openEffect":"zoom","closeEffect":"zoom","descPosition":"bottom","selector":".lightbox"});
 window.onload = () => {
   lightboxQuarto.on('slide_before_load', (data) => {
     const { slideIndex, slideNode, slideConfig, player, trigger } = data;

docs/search.json

@@ -599,7 +599,7 @@
     "href": "posts/data-storage-comparison/index.html",
     "title": "Tidy Data: Tabular Data Storage Comparison",
     "section": "",
-    "text": "Sharing data between different collaborators, machines, or programming languages can be cumbersome. In this post, we look into the issue of column types and how different storage technologies handle them. We focus on self-contained technologies that are easy to install and run on your machine without setting up a separate backend server. This requirement typically arises in academic contexts, educational settings, or when you quickly want to prototype something without spending time on setting up a data backend.\nWe start with simple CSV, then move on to the popular SQLite database before we look at the rising star DuckDB. We close the comparison with a look at the Parquet file format. We always check how the column type depends on the language that is used to store the data in the corresponding storage technology."
+    "text": "Sharing data between different collaborators, machines, or programming languages can be cumbersome for many reasons. In this post, I look into the issue of column types and how different storage technologies handle them. I focus on self-contained technologies that are easy to install and run on your machine without setting up a separate backend server. This requirement typically arises in academic contexts, educational settings, or when you quickly want to prototype something without spending time on setting up a data backend.\nI start with simple CSV, then move on to the popular SQLite database before I look at the rising star DuckDB. We close the comparison with a look at the Parquet and Feather file formats. I always check how the column type depends on the language that is used to store the data in the corresponding storage technology."
   },
   {
     "objectID": "posts/data-storage-comparison/index.html#footnotes",

docs/sitemap.xml

@@ -50,6 +50,6 @@
   </url>
   <url>
     <loc>https://blog.tidy-intelligence.com/posts/data-storage-comparison/index.html</loc>
-    <lastmod>2024-01-19T11:36:09.329Z</lastmod>
+    <lastmod>2024-01-20T11:39:22.210Z</lastmod>
   </url>
 </urlset>