class: center, middle, inverse, title-slide # The <a href="https://github.com/ropensci/drake">drake</a> R package ## make for R ### Kirill Müller ### 2018-02-01, rstudio::conf(), San Diego --- background-image: url(images/humane.png) ??? From Jenny's presentation: https://github.com/jennybc/what-they-forgot --- ```r library(drake) library(tidyverse) plan <- drake_plan( raw_data = readxl::read_xlsx("raw-data.xlsx"), data = raw_data %>% mutate(Species = forcats::fct_inorder(Species)), hist = ggplot(data, aes(x = Petal.Width, fill = Species)) + geom_histogram(), model = lm(Sepal.Width ~ Petal.Width + Species, data) ) ``` --- <div id="htmlwidget-ec897849c5c50a6f7846" style="width:100%;height:504px;" class="visNetwork html-widget"></div> <script type="application/json" data-for="htmlwidget-ec897849c5c50a6f7846">{"x":{"nodes":{"id":["raw_data","data","hist","model"],"label":["raw_data","data","hist","model"],"status":["outdated","outdated","outdated","outdated"],"type":["object","object","object","object"],"level":[0,1,2,2],"font.size":[20,20,20,20],"color":["#000000","#000000","#000000","#000000"],"shape":["dot","dot","dot","dot"],"hover_label":["readxl::read_xlsx('raw-data.xlsx')","raw_data %>% mutate(Species =\nforcats::fct_inorder(Species))","ggplot(data, aes(x = Petal.Width, fill = Species)) +\ngeom_histogram()","lm(Sepal.Width ~ Petal.Width + Species, data)"],"x":[0,0,-1,1],"y":[-1,0,1,1]},"edges":{"from":["raw_data","data","data"],"to":["data","hist","model"],"arrows":["to","to","to"]},"nodesToDataframe":true,"edgesToDataframe":true,"options":{"width":"100%","height":"100%","nodes":{"shape":"dot","physics":false},"manipulation":{"enabled":false},"layout":{"hierarchical":{"enabled":true,"direction":"LR"}},"edges":{"smooth":false},"physics":{"stabilization":false},"interaction":{"navigationButtons":true,"hover":true}},"groups":null,"width":"100%","height":null,"idselection":{"enabled":false},"byselection":{"enabled":false},"main":{"text":"Workflow graph","style":"font-family:Georgia, Times New Roman, Times, serif;font-weight:bold;font-size:20px;text-align:center;"},"submain":null,"footer":null,"background":"rgba(0, 0, 0, 0)","legend":{"width":0.2,"useGroups":false,"position":"left","ncol":1,"stepX":100,"stepY":100,"zoom":true,"nodes":{"label":["Outdated"],"color":["#000000"],"shape":["dot"],"font.color":["black"],"font.size":[20],"id":[2]},"nodesToDataframe":true},"igraphlayout":{"type":"square"},"tooltipStay":300,"tooltipStyle":"position: fixed;visibility:hidden;padding: 5px;white-space: nowrap;font-family: verdana;font-size:14px;font-color:#000000;background-color: #f5f4ed;-moz-border-radius: 3px;-webkit-border-radius: 3px;border-radius: 3px;border: 1px solid #808074;box-shadow: 3px 3px 10px rgba(0, 0, 0, 0.2);","events":{"hoverNode":"function(e){\n var label_info = this.body.data.nodes.get({\n fields: ['label', 'hover_label'],\n filter: function (item) {\n return item.id === e.node\n },\n returnType :'Array'\n });\n this.body.data.nodes.update({\n id: e.node,\n label : label_info[0].hover_label,\n hover_label : label_info[0].label\n });\n }","blurNode":"function(e){\n var label_info = this.body.data.nodes.get({\n fields: ['label', 'hover_label'],\n filter: function (item) {\n return item.id === e.node\n },\n returnType :'Array'\n });\n this.body.data.nodes.update({\n id: e.node,\n label : label_info[0].hover_label,\n hover_label : label_info[0].label\n });\n }"}},"evals":["events.hoverNode","events.blurNode"],"jsHooks":[]}</script> --- ```r make(plan) ## cache /home/muelleki/git/R/drake-pitch/.drake ## connect 4 imports: check_local_env, knit_print.data.frame, con... ## connect 4 targets: raw_data, data, hist, model ## check 10 items: 'raw-data.xlsx', aes, forcats::fct_inorder, ge... ## check 1 item: raw_data ## target raw_data ## check 1 item: data ## target data ## check 2 items: hist, model ## unload 1 item: raw_data ## target hist ## target model ``` --- ```r make(plan) ## cache /home/muelleki/git/R/drake-pitch/.drake ## Unloading targets from environment: ## hist ## data ## model ## connect 4 imports: check_local_env, knit_print.data.frame, con... ## connect 4 targets: raw_data, data, hist, model ## check 10 items: 'raw-data.xlsx', aes, forcats::fct_inorder, ge... ## check 1 item: raw_data ## check 1 item: data ## check 2 items: hist, model ## All targets are already up to date. ``` --- <div id="htmlwidget-ac00066e7f6365b7f0d3" style="width:100%;height:504px;" class="visNetwork html-widget"></div> <script type="application/json" data-for="htmlwidget-ac00066e7f6365b7f0d3">{"x":{"nodes":{"id":["raw_data","data","hist","model"],"label":["raw_data","data","hist","model"],"status":["up to date","up to date","up to date","up to date"],"type":["object","object","object","object"],"level":[0,1,2,2],"font.size":[20,20,20,20],"color":["#228B22","#228B22","#228B22","#228B22"],"shape":["dot","dot","dot","dot"],"hover_label":["readxl::read_xlsx('raw-data.xlsx')","raw_data %>% mutate(Species =\nforcats::fct_inorder(Species))","ggplot(data, aes(x = Petal.Width, fill = Species)) +\ngeom_histogram()","lm(Sepal.Width ~ Petal.Width + Species, data)"],"x":[0,0,-1,1],"y":[-1,0,1,1]},"edges":{"from":["raw_data","data","data"],"to":["data","hist","model"],"arrows":["to","to","to"]},"nodesToDataframe":true,"edgesToDataframe":true,"options":{"width":"100%","height":"100%","nodes":{"shape":"dot","physics":false},"manipulation":{"enabled":false},"layout":{"hierarchical":{"enabled":true,"direction":"LR"}},"edges":{"smooth":false},"physics":{"stabilization":false},"interaction":{"navigationButtons":true,"hover":true}},"groups":null,"width":"100%","height":null,"idselection":{"enabled":false},"byselection":{"enabled":false},"main":{"text":"Workflow graph","style":"font-family:Georgia, Times New Roman, Times, serif;font-weight:bold;font-size:20px;text-align:center;"},"submain":null,"footer":null,"background":"rgba(0, 0, 0, 0)","legend":{"width":0.2,"useGroups":false,"position":"left","ncol":1,"stepX":100,"stepY":100,"zoom":true,"nodes":{"label":["Up to date"],"color":["#228B22"],"shape":["dot"],"font.color":["black"],"font.size":[20],"id":[1]},"nodesToDataframe":true},"igraphlayout":{"type":"square"},"tooltipStay":300,"tooltipStyle":"position: fixed;visibility:hidden;padding: 5px;white-space: nowrap;font-family: verdana;font-size:14px;font-color:#000000;background-color: #f5f4ed;-moz-border-radius: 3px;-webkit-border-radius: 3px;border-radius: 3px;border: 1px solid #808074;box-shadow: 3px 3px 10px rgba(0, 0, 0, 0.2);","events":{"hoverNode":"function(e){\n var label_info = this.body.data.nodes.get({\n fields: ['label', 'hover_label'],\n filter: function (item) {\n return item.id === e.node\n },\n returnType :'Array'\n });\n this.body.data.nodes.update({\n id: e.node,\n label : label_info[0].hover_label,\n hover_label : label_info[0].label\n });\n }","blurNode":"function(e){\n var label_info = this.body.data.nodes.get({\n fields: ['label', 'hover_label'],\n filter: function (item) {\n return item.id === e.node\n },\n returnType :'Array'\n });\n this.body.data.nodes.update({\n id: e.node,\n label : label_info[0].hover_label,\n hover_label : label_info[0].label\n });\n }"}},"evals":["events.hoverNode","events.blurNode"],"jsHooks":[]}</script> --- ```r loadd(data, verbose = 0) data ## # A tibble: 150 x 6 ## X__1 Sepal.Length Sepal.Width Petal.Length Petal.Width ## <dbl> <dbl> <dbl> <dbl> <dbl> ## 1 1.00 5.10 3.50 1.40 0.200 ## 2 2.00 4.90 3.00 1.40 0.200 ## 3 3.00 4.70 3.20 1.30 0.200 ## 4 4.00 4.60 3.10 1.50 0.200 ## 5 5.00 5.00 3.60 1.40 0.200 ## 6 6.00 5.40 3.90 1.70 0.400 ## 7 7.00 4.60 3.40 1.40 0.300 ## 8 8.00 5.00 3.40 1.50 0.200 ## 9 9.00 4.40 2.90 1.40 0.200 ## 10 10.0 4.90 3.10 1.50 0.100 ## # ... with 140 more rows, and 1 more variable: Species <fct> ``` --- ```r loadd(hist, verbose = 0) hist ## `stat_bin()` using `bins = 30`. Pick better value with ## `binwidth`. ``` <!-- --> --- ```r loadd(model, verbose = 0) model ## ## Call: ## lm(formula = Sepal.Width ~ Petal.Width + Species, data = data) ## ## Coefficients: ## (Intercept) Petal.Width Speciesversicolor ## 3.236 0.781 -1.501 ## Speciesvirginica ## -1.844 summary(model) ## ## Call: ## lm(formula = Sepal.Width ~ Petal.Width + Species, data = data) ## ## Residuals: ## Min 1Q Median 3Q Max ## -1.17017 -0.19105 0.00793 0.19173 0.85172 ## ## Coefficients: ## Estimate Std. Error t value Pr(>|t|) ## (Intercept) 3.23587 0.05194 62.295 < 2e-16 *** ## Petal.Width 0.78102 0.12121 6.443 1.59e-09 *** ## Speciesversicolor -1.50150 0.14407 -10.422 < 2e-16 *** ## Speciesvirginica -1.84421 0.22399 -8.234 9.35e-14 *** ## --- ## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 ## ## Residual standard error: 0.3008 on 146 degrees of freedom ## Multiple R-squared: 0.5335, Adjusted R-squared: 0.5239 ## F-statistic: 55.65 on 3 and 146 DF, p-value: < 2.2e-16 ``` --- ```r plan <- drake_plan( raw_data = readxl::read_xlsx("raw-data.xlsx"), data = raw_data %>% mutate(Species = forcats::fct_inorder(Species)) %>% * select(-X__1), hist = ggplot(data, aes(x = Petal.Width, fill = Species)) + * geom_histogram(bins = 10), model = lm(Sepal.Width ~ Petal.Width + Species, data) ) ``` --- <div id="htmlwidget-a261f1c13aea9e511342" style="width:100%;height:504px;" class="visNetwork html-widget"></div> <script type="application/json" data-for="htmlwidget-a261f1c13aea9e511342">{"x":{"nodes":{"id":["raw_data","data","hist","model"],"label":["raw_data","data","hist","model"],"status":["up to date","outdated","outdated","outdated"],"type":["object","object","object","object"],"level":[0,1,2,2],"font.size":[20,20,20,20],"color":["#228B22","#000000","#000000","#000000"],"shape":["dot","dot","dot","dot"],"hover_label":["readxl::read_xlsx('raw-data.xlsx')","raw_data %>% mutate(Species =\nforcats::fct_inorder(Species)) %>% select(-X__1)","ggplot(data, aes(x = Petal.Width, fill = Species)) +\ngeom_histogram(bins = 10)","lm(Sepal.Width ~ Petal.Width + Species, data)"],"x":[0,0,-1,1],"y":[-1,0,1,1]},"edges":{"from":["raw_data","data","data"],"to":["data","hist","model"],"arrows":["to","to","to"]},"nodesToDataframe":true,"edgesToDataframe":true,"options":{"width":"100%","height":"100%","nodes":{"shape":"dot","physics":false},"manipulation":{"enabled":false},"layout":{"hierarchical":{"enabled":true,"direction":"LR"}},"edges":{"smooth":false},"physics":{"stabilization":false},"interaction":{"navigationButtons":true,"hover":true}},"groups":null,"width":"100%","height":null,"idselection":{"enabled":false},"byselection":{"enabled":false},"main":{"text":"Workflow graph","style":"font-family:Georgia, Times New Roman, Times, serif;font-weight:bold;font-size:20px;text-align:center;"},"submain":null,"footer":null,"background":"rgba(0, 0, 0, 0)","legend":{"width":0.2,"useGroups":false,"position":"left","ncol":1,"stepX":100,"stepY":100,"zoom":true,"nodes":{"label":["Up to date","Outdated"],"color":["#228B22","#000000"],"shape":["dot","dot"],"font.color":["black","black"],"font.size":[20,20],"id":[1,2]},"nodesToDataframe":true},"igraphlayout":{"type":"square"},"tooltipStay":300,"tooltipStyle":"position: fixed;visibility:hidden;padding: 5px;white-space: nowrap;font-family: verdana;font-size:14px;font-color:#000000;background-color: #f5f4ed;-moz-border-radius: 3px;-webkit-border-radius: 3px;border-radius: 3px;border: 1px solid #808074;box-shadow: 3px 3px 10px rgba(0, 0, 0, 0.2);","events":{"hoverNode":"function(e){\n var label_info = this.body.data.nodes.get({\n fields: ['label', 'hover_label'],\n filter: function (item) {\n return item.id === e.node\n },\n returnType :'Array'\n });\n this.body.data.nodes.update({\n id: e.node,\n label : label_info[0].hover_label,\n hover_label : label_info[0].label\n });\n }","blurNode":"function(e){\n var label_info = this.body.data.nodes.get({\n fields: ['label', 'hover_label'],\n filter: function (item) {\n return item.id === e.node\n },\n returnType :'Array'\n });\n this.body.data.nodes.update({\n id: e.node,\n label : label_info[0].hover_label,\n hover_label : label_info[0].label\n });\n }"}},"evals":["events.hoverNode","events.blurNode"],"jsHooks":[]}</script> --- ```r make(plan, verbose = 0) loadd(hist, verbose = 0) hist ``` <!-- -->