Built site for gh-pages

.nojekyll

@@ -1 +1 @@
-2ab4581c
+58d24817

robots.txt

@@ -0,0 +1 @@
+Sitemap: https://GeertvanGeest.github.io/glittr-stats/sitemap.xml

search.json

@@ -46,14 +46,14 @@
     "href": "index.html#categories",
     "title": "Glittr stats",
     "section": "Categories",
-    "text": "Categories\n\n\nCode\ncat_count_plot <- table(category = repo_info$main_category) |>\n  as.data.frame() |>\n  ggplot(aes(x = reorder(category, Freq), y = Freq, fill = category)) +\n  geom_bar(stat = \"identity\") +\n  scale_fill_manual(values = glittr_cols) +\n  coord_flip() +\n  theme_classic() +\n  ggtitle(\"Categories\") +\n  theme(legend.position = \"none\",\n        axis.title.y = element_blank()) +\n  ylab(\"Number of repositories\")\n\nprint(cat_count_plot)\n\n\n\n\n\n\n\nCode\ncategory_count <- table(category = repo_info$main_category) |> as.data.frame()\nknitr::kable(category_count)\n\n\n\n\n\ncategory\nFreq\n\n\n\n\nScripting and languages\n314\n\n\nComputational methods and pipelines\n54\n\n\nOmics analysis\n84\n\n\nReproducibility and data management\n51\n\n\nStatistics and machine learning\n40\n\n\nOthers\n23"
+    "text": "Categories\n\n\nCode\ncat_count_plot <- table(category = repo_info$main_category) |>\n  as.data.frame() |>\n  ggplot(aes(x = reorder(category, Freq), y = Freq, fill = category)) +\n  geom_bar(stat = \"identity\") +\n  scale_fill_manual(values = glittr_cols) +\n  coord_flip() +\n  theme_classic() +\n  ggtitle(\"Categories\") +\n  theme(legend.position = \"none\",\n        axis.title.y = element_blank()) +\n  ylab(\"Number of repositories\")\n\nprint(cat_count_plot)\n\n\n\n\n\n\n\n\n\n\n\nCode\ncategory_count <- table(category = repo_info$main_category) |> as.data.frame()\nknitr::kable(category_count)\n\n\n\n\n\ncategory\nFreq\n\n\n\n\nScripting and languages\n314\n\n\nComputational methods and pipelines\n54\n\n\nOmics analysis\n84\n\n\nReproducibility and data management\n51\n\n\nStatistics and machine learning\n40\n\n\nOthers\n23"
   },
   {
     "objectID": "index.html#licensing",
     "href": "index.html#licensing",
     "title": "Glittr stats",
     "section": "Licensing",
-    "text": "Licensing\n\n\nCode\nlic_freq_data <- table(license = repo_info$license,\n                       main_category = repo_info$main_category) |>\n  as.data.frame()\n\nlic_freq_data$main_category <- factor(lic_freq_data$main_category,\n                                     levels = names(cat_table))\n\nlic_freq_plot <- lic_freq_data |>\n  ggplot(aes(x = reorder(license, Freq), y = Freq, fill = main_category)) +\n  geom_bar(stat = \"identity\") +\n  coord_flip() +\n  scale_fill_manual(values = glittr_cols) +\n  theme_classic() +\n  ggtitle(\"License type\") +\n  ylab(\"Number of repositories\") +\n  theme(legend.position = \"none\",\n        axis.title.y = element_blank())\n\nprint(lic_freq_plot)\n\n\n\n\n\n\n\nCode\nrepo_info$license |>\n  table() |>\n  as.data.frame() |>\n  mutate(perc = round(Freq/nrow(repo_info)*100, 1)) |>\n  arrange(desc(Freq)) |>\n  knitr::kable()\n\n\n\n\n\nVar1\nFreq\nperc\n\n\n\n\nother\n211\n37.3\n\n\nnone\n172\n30.4\n\n\nmit\n59\n10.4\n\n\ncc-by-sa-4.0\n30\n5.3\n\n\ngpl-3.0\n26\n4.6\n\n\ncc-by-4.0\n23\n4.1\n\n\ncc0-1.0\n22\n3.9\n\n\napache-2.0\n10\n1.8\n\n\nbsd-3-clause\n7\n1.2\n\n\nagpl-3.0\n2\n0.4\n\n\nartistic-2.0\n2\n0.4\n\n\nunlicense\n1\n0.2\n\n\nwtfpl\n1\n0.2"
+    "text": "Licensing\n\n\nCode\nlic_freq_data <- table(license = repo_info$license,\n                       main_category = repo_info$main_category) |>\n  as.data.frame()\n\nlic_freq_data$main_category <- factor(lic_freq_data$main_category,\n                                     levels = names(cat_table))\n\nlic_freq_plot <- lic_freq_data |>\n  ggplot(aes(x = reorder(license, Freq), y = Freq, fill = main_category)) +\n  geom_bar(stat = \"identity\") +\n  coord_flip() +\n  scale_fill_manual(values = glittr_cols) +\n  theme_classic() +\n  ggtitle(\"License type\") +\n  ylab(\"Number of repositories\") +\n  theme(legend.position = \"none\",\n        axis.title.y = element_blank())\n\nprint(lic_freq_plot)\n\n\n\n\n\n\n\n\n\n\n\nCode\nrepo_info$license |>\n  table() |>\n  as.data.frame() |>\n  mutate(perc = round(Freq/nrow(repo_info)*100, 1)) |>\n  arrange(desc(Freq)) |>\n  knitr::kable()\n\n\n\n\n\nVar1\nFreq\nperc\n\n\n\n\nother\n211\n37.3\n\n\nnone\n172\n30.4\n\n\nmit\n59\n10.4\n\n\ncc-by-sa-4.0\n30\n5.3\n\n\ngpl-3.0\n26\n4.6\n\n\ncc-by-4.0\n23\n4.1\n\n\ncc0-1.0\n22\n3.9\n\n\napache-2.0\n10\n1.8\n\n\nbsd-3-clause\n7\n1.2\n\n\nagpl-3.0\n2\n0.4\n\n\nartistic-2.0\n2\n0.4\n\n\nunlicense\n1\n0.2\n\n\nwtfpl\n1\n0.2"
   },
   {
     "objectID": "index.html#authors",
@@ -67,21 +67,21 @@
     "href": "index.html#tags",
     "title": "Glittr stats",
     "section": "Tags",
-    "text": "Tags\n\n\nCode\ntag_freq_plot <- tag_df |>\n  filter(repositories > 10) |>\n  ggplot(aes(x = reorder(name, repositories),\n             y = repositories, fill = category)) +\n  geom_bar(stat = \"identity\") +\n  coord_flip() +\n  scale_fill_manual(values = glittr_cols) +\n  ggtitle(\"Tags with > 10 repositories\") +\n  ylab(\"Number of repositories\") +\n  annotate(geom = \"text\", x = 2, y = 150,\n           label = paste(\"Total number of tags: \",\n                         nrow(tag_df)),\n           color=\"black\") +\n  theme_classic() +\n  theme(legend.position = \"none\",\n        axis.title.y = element_blank())\n\nprint(tag_freq_plot)\n\n\n\n\n\n\n\nCode\ntag_df |>\n  filter(repositories > 10) |>\n  arrange(desc(repositories)) |>\n  knitr::kable(row.names = FALSE)\n\n\n\n\n\n\n\n\n\n\nname\ncategory\nrepositories\n\n\n\n\nR\nScripting and languages\n230\n\n\nPython\nScripting and languages\n81\n\n\nTranscriptomics\nOmics analysis\n74\n\n\nRNA-seq\nOmics analysis\n65\n\n\nStatistics\nStatistics and machine learning\n54\n\n\nNext generation sequencing\nOmics analysis\n48\n\n\nData science\nStatistics and machine learning\n45\n\n\nMachine learning\nStatistics and machine learning\n41\n\n\nGenomics\nOmics analysis\n37\n\n\nUnix/Linux\nScripting and languages\n34\n\n\nSingle-cell sequencing\nOmics analysis\n34\n\n\nData management\nReproducibility and data management\n34\n\n\nReproducibility\nReproducibility and data management\n29\n\n\nFAIR data\nReproducibility and data management\n28\n\n\nGeneral\nOthers\n28\n\n\nData visualization\nScripting and languages\n27\n\n\nVariant analysis\nOmics analysis\n23\n\n\nVersion control\nScripting and languages\n21\n\n\nContainerization\nComputational methods and pipelines\n18\n\n\nWorkflows\nComputational methods and pipelines\n17\n\n\nShiny\nScripting and languages\n15\n\n\nMetagenomics\nOmics analysis\n15\n\n\nDocker\nComputational methods and pipelines\n13\n\n\nJulia\nScripting and languages\n12\n\n\nNextflow\nComputational methods and pipelines\n12\n\n\nChIP-seq\nOmics analysis\n11"
+    "text": "Tags\n\n\nCode\ntag_freq_plot <- tag_df |>\n  filter(repositories > 10) |>\n  ggplot(aes(x = reorder(name, repositories),\n             y = repositories, fill = category)) +\n  geom_bar(stat = \"identity\") +\n  coord_flip() +\n  scale_fill_manual(values = glittr_cols) +\n  ggtitle(\"Tags with > 10 repositories\") +\n  ylab(\"Number of repositories\") +\n  annotate(geom = \"text\", x = 2, y = 150,\n           label = paste(\"Total number of tags: \",\n                         nrow(tag_df)),\n           color=\"black\") +\n  theme_classic() +\n  theme(legend.position = \"none\",\n        axis.title.y = element_blank())\n\nprint(tag_freq_plot)\n\n\n\n\n\n\n\n\n\n\n\nCode\ntag_df |>\n  filter(repositories > 10) |>\n  arrange(desc(repositories)) |>\n  knitr::kable(row.names = FALSE)\n\n\n\n\n\n\n\n\n\n\nname\ncategory\nrepositories\n\n\n\n\nR\nScripting and languages\n230\n\n\nPython\nScripting and languages\n81\n\n\nTranscriptomics\nOmics analysis\n74\n\n\nRNA-seq\nOmics analysis\n65\n\n\nStatistics\nStatistics and machine learning\n54\n\n\nNext generation sequencing\nOmics analysis\n48\n\n\nData science\nStatistics and machine learning\n45\n\n\nMachine learning\nStatistics and machine learning\n41\n\n\nGenomics\nOmics analysis\n37\n\n\nUnix/Linux\nScripting and languages\n34\n\n\nSingle-cell sequencing\nOmics analysis\n34\n\n\nData management\nReproducibility and data management\n34\n\n\nReproducibility\nReproducibility and data management\n29\n\n\nFAIR data\nReproducibility and data management\n28\n\n\nGeneral\nOthers\n28\n\n\nData visualization\nScripting and languages\n27\n\n\nVariant analysis\nOmics analysis\n23\n\n\nVersion control\nScripting and languages\n21\n\n\nContainerization\nComputational methods and pipelines\n18\n\n\nWorkflows\nComputational methods and pipelines\n17\n\n\nShiny\nScripting and languages\n15\n\n\nMetagenomics\nOmics analysis\n15\n\n\nDocker\nComputational methods and pipelines\n13\n\n\nJulia\nScripting and languages\n12\n\n\nNextflow\nComputational methods and pipelines\n12\n\n\nChIP-seq\nOmics analysis\n11"
   },
   {
     "objectID": "index.html#contributors-boxplot",
     "href": "index.html#contributors-boxplot",
     "title": "Glittr stats",
     "section": "Contributors boxplot",
-    "text": "Contributors boxplot\n\n\nCode\nrepo_info_gh$main_category <- factor(repo_info_gh$main_category,\n                                     levels = names(cat_table))\n\ncontributors_plot <- repo_info_gh |>\n  ggplot(aes(x = main_category, y = contributors, fill = main_category)) +\n  geom_violin(scale = \"width\") +\n  geom_boxplot(width = 0.1, col = \"darkgrey\") +\n  coord_flip() +\n  ggtitle(\"Contributors\") +\n  ylab(\"Number of contributors\") +\n  scale_y_sqrt() +\n  scale_fill_manual(values = glittr_cols) +\n  theme_bw() +\n  theme(legend.position = \"none\",\n        axis.title.y = element_blank(),\n        plot.margin = margin(t = 5, r = 10, b = 5, l = 10))\n\nprint(contributors_plot)\n\n\n\n\n\n\n\nCode\nnna_contr <- repo_info_gh$contributors\nparam1 <- sum(nna_contr > 10)/length(nna_contr)\n# 27.3% have more than 10 contributors\nparam2 <- sum(nna_contr > 1)/length(nna_contr)\n# 78.6% have more than one contributor\n# 115 repos with only one contributor\nparam3 <- sum(nna_contr <= 5)/length(nna_contr)\n\n\n\nMore than 10 contributors: 25.6%\nMore than 1 contributor: 78.8%\nBetween 1 and 5 contributors: 59.9%"
+    "text": "Contributors boxplot\n\n\nCode\nrepo_info_gh$main_category <- factor(repo_info_gh$main_category,\n                                     levels = names(cat_table))\n\ncontributors_plot <- repo_info_gh |>\n  ggplot(aes(x = main_category, y = contributors, fill = main_category)) +\n  geom_violin(scale = \"width\") +\n  geom_boxplot(width = 0.1, col = \"darkgrey\") +\n  coord_flip() +\n  ggtitle(\"Contributors\") +\n  ylab(\"Number of contributors\") +\n  scale_y_sqrt() +\n  scale_fill_manual(values = glittr_cols) +\n  theme_bw() +\n  theme(legend.position = \"none\",\n        axis.title.y = element_blank(),\n        plot.margin = margin(t = 5, r = 10, b = 5, l = 10))\n\nprint(contributors_plot)\n\n\n\n\n\n\n\n\n\n\n\nCode\nnna_contr <- repo_info_gh$contributors\nparam1 <- sum(nna_contr > 10)/length(nna_contr)\n# 27.3% have more than 10 contributors\nparam2 <- sum(nna_contr > 1)/length(nna_contr)\n# 78.6% have more than one contributor\n# 115 repos with only one contributor\nparam3 <- sum(nna_contr <= 5)/length(nna_contr)\n\n\n\nMore than 10 contributors: 25.6%\nMore than 1 contributor: 78.8%\nBetween 1 and 5 contributors: 59.9%"
   },
   {
     "objectID": "index.html#countries",
     "href": "index.html#countries",
     "title": "Glittr stats",
     "section": "Countries",
-    "text": "Countries\n\n\nCode\ncountry_freq <- table(country = repo_info$country, \n                      main_category = repo_info$main_category) |>\n  as.data.frame()\n\ncountry_freq$main_category <- factor(country_freq$main_category,\n                                     levels = names(cat_table))\n\ncountry_freq_plot <- country_freq |>\n  filter(country != \"undefined\") |>\n  ggplot(aes(x = reorder(country, Freq), y = Freq, fill = main_category)) +\n  geom_bar(stat = \"identity\") +\n  coord_flip() +\n  ggtitle(\"Country\") +\n  ylab(\"Number of repositories\") +\n  scale_fill_manual(values = glittr_cols) +\n  annotate(geom = \"text\", x = 2, y = 70,\n           label = paste(\"Repos with undefined country: \",\n                         sum(repo_info$country == \"undefined\")),\n           color=\"black\") +\n  theme_classic() +\n  theme(legend.position = \"none\",\n        axis.title.y = element_blank())\n\nprint(country_freq_plot)\n\n\n\n\n\n\n\nCode\nrepo_info$country |> table() |> as.data.frame() |> arrange(desc(Freq)) |> knitr::kable()\n\n\n\n\n\nVar1\nFreq\n\n\n\n\nundefined\n244\n\n\nUnited States\n132\n\n\nSwitzerland\n27\n\n\nCanada\n26\n\n\nSweden\n21\n\n\nUnited Kingdom\n19\n\n\nAustralia\n15\n\n\nGermany\n12\n\n\nFrance\n11\n\n\nNetherlands\n11\n\n\nPortugal\n11\n\n\nBelgium\n10\n\n\nSpain\n8\n\n\nDenmark\n4\n\n\nItaly\n3\n\n\nBulgaria\n2\n\n\nIreland\n2\n\n\nArgentina\n1\n\n\nChina\n1\n\n\nFinland\n1\n\n\nIndia\n1\n\n\nLuxembourg\n1\n\n\nNorway\n1\n\n\nPoland\n1\n\n\nUkraine\n1"
+    "text": "Countries\n\n\nCode\ncountry_freq <- table(country = repo_info$country, \n                      main_category = repo_info$main_category) |>\n  as.data.frame()\n\ncountry_freq$main_category <- factor(country_freq$main_category,\n                                     levels = names(cat_table))\n\ncountry_freq_plot <- country_freq |>\n  filter(country != \"undefined\") |>\n  ggplot(aes(x = reorder(country, Freq), y = Freq, fill = main_category)) +\n  geom_bar(stat = \"identity\") +\n  coord_flip() +\n  ggtitle(\"Country\") +\n  ylab(\"Number of repositories\") +\n  scale_fill_manual(values = glittr_cols) +\n  annotate(geom = \"text\", x = 2, y = 70,\n           label = paste(\"Repos with undefined country: \",\n                         sum(repo_info$country == \"undefined\")),\n           color=\"black\") +\n  theme_classic() +\n  theme(legend.position = \"none\",\n        axis.title.y = element_blank())\n\nprint(country_freq_plot)\n\n\n\n\n\n\n\n\n\n\n\nCode\nrepo_info$country |> table() |> as.data.frame() |> arrange(desc(Freq)) |> knitr::kable()\n\n\n\n\n\nVar1\nFreq\n\n\n\n\nundefined\n244\n\n\nUnited States\n132\n\n\nSwitzerland\n27\n\n\nCanada\n26\n\n\nSweden\n21\n\n\nUnited Kingdom\n19\n\n\nAustralia\n15\n\n\nGermany\n12\n\n\nFrance\n11\n\n\nNetherlands\n11\n\n\nPortugal\n11\n\n\nBelgium\n10\n\n\nSpain\n8\n\n\nDenmark\n4\n\n\nItaly\n3\n\n\nBulgaria\n2\n\n\nIreland\n2\n\n\nArgentina\n1\n\n\nChina\n1\n\n\nFinland\n1\n\n\nIndia\n1\n\n\nLuxembourg\n1\n\n\nNorway\n1\n\n\nPoland\n1\n\n\nUkraine\n1"
   },
   {
     "objectID": "index.html#summary-plot",