PJ Hampton
GitHub
commit
19a3e011b3
|
|
@ -0,0 +1,200 @@
|
|||
{
|
||||
"id" : "dplyr_cheat_sheet",
|
||||
"name" : "Dplyr",
|
||||
"description" : "Dplyr is a library in R to perform various data manipulation tasks with data frame like objects",
|
||||
"metadata" : {
|
||||
"sourceName" : "R studio",
|
||||
"sourceUrl" : "https://www.rstudio.com/wp-content/uploads/2015/02/data-wrangling-cheatsheet.pdf"
|
||||
},
|
||||
"aliases": [
|
||||
"dplyr syntax","data wrangling in r", "data cleaning in r", "data munging in r"
|
||||
],
|
||||
"template_type": "terminal",
|
||||
"section_order" : [
|
||||
"Basics",
|
||||
"Reshaping Data",
|
||||
"Subset Observations (Row)",
|
||||
"Subset Variables (Columns)",
|
||||
"Summarize Data",
|
||||
"Make New Variables",
|
||||
"Combine Data Sets",
|
||||
"Group Data"
|
||||
],
|
||||
"sections" : {
|
||||
"Basics" : [
|
||||
{
|
||||
"key" : "dplyr::tbl_df(iris)",
|
||||
"val" : "Converts data to tbl class. tbl's are easier to examine than data frames"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::glimpse(iris)",
|
||||
"val" : "Information dense summary of tbl data"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::%>%",
|
||||
"val" : "Passes object on left as 1st argument of function on right. x %>% f(y) is the same as f(x, y)"
|
||||
}
|
||||
],
|
||||
"Reshaping Data" : [
|
||||
{
|
||||
"key" : "dplyr::data_frame(a = 1:3, b = 4:6)",
|
||||
"val" : "Combine vectors into data frame (optimized)"
|
||||
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::arrange(dataframe, variableName)",
|
||||
"val" : "Order rows in dataframe by values of variableName (low to high)"
|
||||
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::arrange(dataframe, desc(variableName))",
|
||||
"val" : "Order rows in dataframe by values of variableName (high to low)"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::rename(dataframe, newname1 = oldname1, newname2 = oldname2)",
|
||||
"val" : "Rename the columns of a dataframe"
|
||||
}
|
||||
],
|
||||
"Subset Observations (Row)" : [
|
||||
{
|
||||
"key" : "dplyr::filter(iris, Sepal.Length > 7)",
|
||||
"val" : "Extract rows that meet logical criteria"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::distinct(iris)",
|
||||
"val" : "Remove duplicate rows"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::sample_frac(iris, 0.5, replace = TRUE)",
|
||||
"val" : "Randomly select fraction of rows"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::sample_n(iris, 10, replace = TRUE)",
|
||||
"val" : "Randomly select n rows"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::slice(iris, 10:15)",
|
||||
"val" : "Select rows by position"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::top_n(iris, 2, Sepal.Length)",
|
||||
"val" : "Select and order top n entries (by group if grouped data)"
|
||||
}
|
||||
],
|
||||
"Subset Variables (Columns)" : [
|
||||
{
|
||||
"key" : "dplyr::select(iris, Sepal.Width, Petal.Length, Species)",
|
||||
"val" : "Select columns by name"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::select(iris, contains('.'))",
|
||||
"val" : "Select columns whose name contains a character string"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::select(iris, starts_with('Sepal'))",
|
||||
"val" : "Select columns whose name starts with a character string"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::select(iris, ends_with('Length'))",
|
||||
"val" : "Select columns whose name ends with a character string"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::select(iris, num_range('x', 1:5))",
|
||||
"val" : "Select columns named x1, x2, x3, x4, x5"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::select(iris, one_of(c('Species', 'Genus')))",
|
||||
"val" : "Select columns whose names are in a group of names"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::select(iris, -Species)",
|
||||
"val" : "Select all columns except Species"
|
||||
}
|
||||
],
|
||||
"Summarize Data" : [
|
||||
{
|
||||
"key" : "dplyr::summarise(iris, avg = mean(Sepal.Length))",
|
||||
"val" : "Summarise data into single row of values"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::summarise_each(select(iris,-Species), funs('mean','min','max'))",
|
||||
"val" : "Apply summary function (funs) to each column"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::count(iris, Species, wt = Sepal.Length)",
|
||||
"val" : "Count number of rows with each unique value of variable (with or without weights)"
|
||||
}
|
||||
],
|
||||
"Make New Variables" : [
|
||||
{
|
||||
"key" : "dplyr::mutate(iris, sepal = Sepal.Length + Sepal.Width)",
|
||||
"val" : "Compute and append one or more new columns"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::mutate_each(select(iris,-Species), funs(. * 0.5))",
|
||||
"val" : "Apply window function (funs) to each column"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::transmute(iris, sepal = Sepal.Length + Sepal.Width)",
|
||||
"val" : "Compute one or more new columns. Drop original columns"
|
||||
}
|
||||
],
|
||||
"Combine Data Sets" : [
|
||||
{
|
||||
"key" : "dplyr::left_join(a, b, by = 'x1')",
|
||||
"val" : "Join matching rows from b to a"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::right_join(a, b, by = 'x1')",
|
||||
"val" : "Join matching rows from a to b"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::inner_join(a, b, by = 'x1')",
|
||||
"val" : "Join data. Retain only rows in both sets"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::full_join(a, b, by = 'x1')",
|
||||
"val" : "Join data. Retain all values, all rows"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::semi_join(a, b, by = 'x1')",
|
||||
"val" : "All rows in a that have a match in b"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::anti_join(a, b, by = 'x1')",
|
||||
"val" : "All rows in a that do not have a match in b"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::intersect(y, z)",
|
||||
"val" : "Rows that appear in both y and z"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::union(y, z)",
|
||||
"val" : "Rows that appear in either or both y and z"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::setdiff(y, z)",
|
||||
"val" : "Rows that appear in y but not z"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::bind_rows(y, z)",
|
||||
"val" : "Append z to y as new rows"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::bind_cols(y, z)",
|
||||
"val" : "Append z to y as new columns. Caution: matches rows by position"
|
||||
}
|
||||
],
|
||||
"Group Data" : [
|
||||
{
|
||||
"key" : "dplyr::group_by(iris, Species)",
|
||||
"val" : "Group data into rows with the same value of Species"
|
||||
},
|
||||
{
|
||||
"key" : "dplyr::ungroup(iris)",
|
||||
"val" : "Remove grouping information from data frame"
|
||||
}
|
||||
]
|
||||
|
||||
}
|
||||
}
|
||||
Loading…
Reference in New Issue