galaaz 0.4.7 → 0.4.8
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +1179 -39
- data/Rakefile +4 -2
- data/bin/grun +1 -1
- data/bin/gstudio +1 -1
- data/blogs/dev/dev.Rmd +2 -56
- data/blogs/dev/dev.md +32 -61
- data/blogs/dev/dev2.Rmd +65 -0
- data/blogs/dplyr/dplyr.Rmd +29 -0
- data/blogs/{dev/dev.html → dplyr/dplyr.html} +88 -57
- data/blogs/dplyr/dplyr.md +58 -0
- data/blogs/gknit/gknit.html +1262 -25
- data/blogs/gknit/gknit.md +471 -27
- data/blogs/gknit/gknit_files/figure-html/bubble-1.png +0 -0
- data/blogs/manual/graph.rb +29 -0
- data/blogs/manual/manual.Rmd +567 -29
- data/blogs/manual/manual.html +743 -46
- data/blogs/manual/manual.md +1179 -39
- data/blogs/nse_dplyr/nse_dplyr.Rmd +466 -11
- data/blogs/nse_dplyr/nse_dplyr.html +472 -37
- data/blogs/nse_dplyr/nse_dplyr.md +645 -32
- data/blogs/ruby_plot/ruby_plot.Rmd +4 -4
- data/blogs/ruby_plot/ruby_plot.html +217 -2
- data/blogs/ruby_plot/ruby_plot.md +226 -1
- data/blogs/ruby_plot/ruby_plot_files/figure-html/dose_len.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/dose_len.svg +2 -2
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facet_by_delivery.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facet_by_delivery.svg +70 -70
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facet_by_dose.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facet_by_dose.svg +72 -72
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facets_by_delivery_color.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facets_by_delivery_color.svg +116 -116
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facets_by_delivery_color2.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facets_by_delivery_color2.svg +176 -176
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facets_with_decorations.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facets_with_jitter.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facets_with_jitter.svg +236 -236
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facets_with_points.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/facets_with_points.svg +176 -176
- data/blogs/ruby_plot/ruby_plot_files/figure-html/final_box_plot.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/final_box_plot.svg +160 -160
- data/blogs/ruby_plot/ruby_plot_files/figure-html/final_violin_plot.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/final_violin_plot.svg +105 -105
- data/blogs/ruby_plot/ruby_plot_files/figure-html/violin_with_jitter.png +0 -0
- data/blogs/ruby_plot/ruby_plot_files/figure-html/violin_with_jitter.svg +121 -121
- data/examples/islr/ch2.spec.rb +1 -1
- data/examples/islr/ch3_boston.rb +4 -4
- data/examples/islr/x_y_rnorm.jpg +0 -0
- data/lib/R_interface/r.rb +1 -1
- data/lib/R_interface/r_methods.rb +2 -2
- data/lib/R_interface/rdata_frame.rb +8 -5
- data/lib/R_interface/rindexed_object.rb +1 -2
- data/lib/R_interface/rlist.rb +1 -0
- data/lib/R_interface/robject.rb +0 -1
- data/lib/R_interface/rpkg.rb +14 -6
- data/lib/R_interface/rsupport.rb +7 -9
- data/lib/R_interface/ruby_extensions.rb +17 -5
- data/lib/gknit/knitr_engine.rb +9 -2
- data/lib/util/exec_ruby.rb +2 -2
- data/specs/r_dataframe.spec.rb +173 -0
- data/specs/r_list.spec.rb +4 -4
- data/specs/ruby_expression.spec.rb +2 -11
- data/specs/tmp.rb +76 -34
- data/version.rb +1 -1
- metadata +17 -6
- data/blogs/dev/dev_files/figure-html/bubble-1.png +0 -0
- data/blogs/dev/dev_files/figure-html/diverging_bar. +0 -0
- data/blogs/dev/dev_files/figure-html/diverging_bar.png +0 -0
@@ -22,16 +22,87 @@ library('tibble')
|
|
22
22
|
|
23
23
|
# Introduction
|
24
24
|
|
25
|
-
|
26
|
-
|
27
|
-
|
25
|
+
In this post we will see how to program with dplyr in Galaaz.
|
26
|
+
|
27
|
+
### But first, what is Galaaz??
|
28
|
+
|
29
|
+
Galaaz is a system for tightly coupling Ruby and R. Ruby is a powerful language, with
|
30
|
+
a large community, a very large set of libraries and great for web development. However,
|
31
|
+
it lacks libraries for data science, statistics, scientific plotting and machine learning.
|
32
|
+
On the other hand, R is considered one of the most powerful languages for solving all of the
|
33
|
+
above problems. Maybe the strongest competitor to R is Python with libraries such as NumPy,
|
34
|
+
Panda, SciPy, SciKit-Learn and a couple more.
|
35
|
+
|
36
|
+
With Galaaz we do not intend to re-implement any of the scientific libraries in R. However, we
|
37
|
+
allow for very tight coupling between the two languages to the point that the Ruby
|
38
|
+
developer does not need to know that there is an R engine running. For this to happen we
|
39
|
+
use new technologies provided by Oracle: GraalVM, TruffleRuby and FastR:
|
40
|
+
|
41
|
+
GraalVM is a universal virtual machine for running applications
|
42
|
+
written in JavaScript, Python 3, Ruby, R, JVM-based languages like Java,
|
43
|
+
Scala, Kotlin, and LLVM-based languages such as C and C++.
|
44
|
+
|
45
|
+
GraalVM removes the isolation between programming languages and enables
|
46
|
+
interoperability in a shared runtime. It can run either standalone or in
|
47
|
+
the context of OpenJDK, Node.js, Oracle Database, or MySQL.
|
48
|
+
|
49
|
+
GraalVM allows you to write polyglot applications with a seamless way to
|
50
|
+
pass values from one language to another. With GraalVM there is no copying
|
51
|
+
or marshaling necessary as it is with other polyglot systems. This lets
|
52
|
+
you achieve high performance when language boundaries are crossed. Most
|
53
|
+
of the time there is no additional cost for crossing a language boundary
|
54
|
+
at all.
|
55
|
+
|
56
|
+
Often developers have to make uncomfortable compromises that require them
|
57
|
+
to rewrite their software in other languages. For example:
|
58
|
+
|
59
|
+
* “That library is not available in my language. I need to rewrite it.”
|
60
|
+
* “That language would be the perfect fit for my problem, but we cannot
|
61
|
+
run it in our environment.”
|
62
|
+
* “That problem is already solved in my language, but the language is
|
63
|
+
too slow.”
|
64
|
+
|
65
|
+
With GraalVM we aim to allow developers to freely choose the right language
|
66
|
+
for the task at hand without making compromises.
|
67
|
+
|
68
|
+
Interested readers should also check out the following sites:
|
69
|
+
|
70
|
+
* [GraalVM Home](https://www.graalvm.org/)
|
71
|
+
* [TruffleRuby](https://github.com/oracle/truffleruby)
|
72
|
+
* [FastR](https://github.com/oracle/fastr)
|
73
|
+
* [Faster R with FastR](https://medium.com/graalvm/faster-r-with-fastr-4b8db0e0dceb)
|
74
|
+
|
75
|
+
### Programming with dplyr
|
76
|
+
|
77
|
+
According to Hardley (https://dplyr.tidyverse.org/articles/programming.html)
|
78
|
+
|
79
|
+
> Most dplyr functions use non-standard evaluation (NSE). This is a catch-all term that
|
80
|
+
> means they don’t follow the usual R rules of evaluation. Instead, they capture the
|
81
|
+
> expression that you typed and evaluate it in a custom way. This has two main
|
82
|
+
> benefits for dplyr code:
|
83
|
+
|
84
|
+
> Operations on data frames can be expressed succinctly because you don’t need to repeat
|
85
|
+
> the name of the data frame. For example, you can write filter(df, x == 1, y == 2, z == 3)
|
86
|
+
> instead of df[df$x == 1 & df$y ==2 & df$z == 3, ].
|
87
|
+
|
88
|
+
> dplyr can choose to compute results in a different way to base R. This is important for
|
89
|
+
> database backends because dplyr itself doesn’t do any work, but instead generates the SQL
|
90
|
+
> that tells the database what to do.
|
91
|
+
|
92
|
+
> Unfortunately these benefits do not come for free. There are two main drawbacks:
|
28
93
|
|
94
|
+
> Most dplyr arguments are not referentially transparent. That means you can’t replace a value
|
95
|
+
> with a seemingly equivalent object that you’ve defined elsewhere. In other words, this code:
|
96
|
+
|
97
|
+
```{r tibble, eval=FALSE}
|
98
|
+
df <- data.frame(x = 1:3, y = 3:1)
|
29
99
|
print(filter(df, x == 1))
|
30
100
|
#> # A tibble: 1 x 2
|
31
101
|
#> x y
|
32
102
|
#> <int> <int>
|
33
103
|
#> 1 1 3
|
34
104
|
```
|
105
|
+
> Is not equivalent to this code:
|
35
106
|
|
36
107
|
```{r my_var_err, eval = FALSE}
|
37
108
|
my_var <- x
|
@@ -39,18 +110,164 @@ my_var <- x
|
|
39
110
|
filter(df, my_var == 1)
|
40
111
|
#> Error: object 'my_var' not found
|
41
112
|
```
|
113
|
+
> This makes it hard to create functions with arguments that change how dplyr verbs are computed.
|
114
|
+
|
115
|
+
In this post we will see that programming with dplyr in Galaaz does not require knowledge of
|
116
|
+
non-standard evaluation in R and can be accomplished by utilizing normal Ruby constructs.
|
117
|
+
|
118
|
+
# Writing Expressions in Galaaz
|
119
|
+
|
120
|
+
Galaaz extends Ruby to work with complex expressions, similar to R's expressions build with 'quote'
|
121
|
+
(base R) or 'quo' (tidyverse). Let's take a look at some of those expressions.
|
122
|
+
|
123
|
+
## Expressions from operators
|
124
|
+
|
125
|
+
The code bellow
|
126
|
+
creates an expression summing two symbols
|
127
|
+
|
128
|
+
```{ruby expressions}
|
129
|
+
exp1 = :a + :b
|
130
|
+
puts exp1
|
131
|
+
```
|
132
|
+
We can build any complex mathematical expression
|
133
|
+
|
134
|
+
```{ruby expr2}
|
135
|
+
exp2 = (:a + :b) * 2.0 + :c ** 2 / :z
|
136
|
+
puts exp2
|
137
|
+
```
|
138
|
+
|
139
|
+
It is also possible to use inequality operators in building expressions
|
140
|
+
|
141
|
+
```{ruby expr3}
|
142
|
+
exp3 = (:a + :b) >= :z
|
143
|
+
puts exp3
|
144
|
+
```
|
145
|
+
|
146
|
+
Galaaz provides both symbolic representations for operators, such as (>, <, !=) as functional
|
147
|
+
notation for those operators such as (.gt, .ge, etc.). So the same expression written
|
148
|
+
above can also be written as
|
149
|
+
|
150
|
+
```{ruby expr4}
|
151
|
+
exp4 = (:a + :b).ge :z
|
152
|
+
puts exp4
|
153
|
+
```
|
154
|
+
|
155
|
+
Two type of expression can only be created with the functional representation of the operators,
|
156
|
+
those are expressions involving '==', and '='. In order to write an expression involving '==' we
|
157
|
+
need to use the method '.eq' and for '=' we need the function '.assign'
|
158
|
+
|
159
|
+
```{ruby expr5}
|
160
|
+
exp5 = (:a + :b).eq :z
|
161
|
+
puts exp5
|
162
|
+
```
|
163
|
+
|
164
|
+
```{ruby expr6}
|
165
|
+
exp6 = :y.assign :a + :b
|
166
|
+
puts exp6
|
167
|
+
```
|
168
|
+
In general we think that using the functional notation is preferable to using the
|
169
|
+
symbolic notation as otherwise, we end up writing invalid expressions such as
|
170
|
+
|
171
|
+
```{ruby exp_wrong, warning=FALSE}
|
172
|
+
exp_wrong = (:a + :b) == :z
|
173
|
+
puts exp_wrong
|
174
|
+
```
|
175
|
+
and it might be difficult to understand what is going on here. The problem lies with the fact that
|
176
|
+
when using '==' we are comparing expression (:a + :b) to expression :z with '=='. When the
|
177
|
+
comparison is executed, the system tries to evaluate :a, :b and :z, and those symbols at
|
178
|
+
this time are not bound to anything and we get a "object 'a' not found" message.
|
179
|
+
If we only use functional notation, this type of error will not occur.
|
180
|
+
|
181
|
+
## Expressions with R methods
|
182
|
+
|
183
|
+
It is often necessary to create an expression that uses a method or function. For instance, in
|
184
|
+
mathematics, it's quite natural to write an expressin such as $y = sin(x)$. In this case, the
|
185
|
+
'sin' function is part of the expression and should not immediately executed. Now, let's say
|
186
|
+
that 'x' is an angle of 45$^\circ$ and we acttually want our expression to be $y = 0.850...$.
|
187
|
+
When we want the function to be part of the expression, we call the function preceeding it
|
188
|
+
by the letter E, such as 'E.sin(x)'
|
189
|
+
|
190
|
+
```{ruby method_expression}
|
191
|
+
exp7 = :y.assign E.sin(:x)
|
192
|
+
puts exp7
|
193
|
+
```
|
194
|
+
|
195
|
+
# Using Galaaz to call R functions
|
196
|
+
|
197
|
+
Galaaz tries to emulate as closely as possible the way R functions are called and migrating from
|
198
|
+
R to Galaaz should be quite easy requiring only minor syntactic changes to an R script. In
|
199
|
+
this post, we do not have enough space to write a complety manual to Galaaz, so we will
|
200
|
+
present only a few examples scripts using Galaaz.
|
201
|
+
|
202
|
+
Basically, to call an R function from Ruby with Galaaz, one only needs to preceed the function
|
203
|
+
with 'R.'. For instance, to create a vector in R, the 'c' function is used. From Galaaz, a
|
204
|
+
vector can be created by using 'R.c':
|
205
|
+
|
206
|
+
```{ruby vector}
|
207
|
+
@vec = R.c(1.0, 2, 3)
|
208
|
+
puts @vec
|
209
|
+
```
|
210
|
+
A list is created in R with the 'list' function, so in Galaaz we do:
|
211
|
+
|
212
|
+
```{ruby list}
|
213
|
+
@list = R.list(a: 1.0, b: 2, c: 3)
|
214
|
+
puts @list
|
215
|
+
```
|
216
|
+
Note that we can use named arguments in our list. The same code in R would be:
|
217
|
+
|
218
|
+
```{r list2}
|
219
|
+
lst = list(a = 1, b = 2L, c = 3L)
|
220
|
+
print(lst)
|
221
|
+
```
|
222
|
+
|
223
|
+
|
224
|
+
However, if we want the function to be evaluated, then
|
225
|
+
we use the normal call to function with R as 'R.sin(x)'.
|
226
|
+
|
227
|
+
```{ruby method_exc}
|
228
|
+
x = 45
|
229
|
+
exp8 = :y.assign R.sin(x)
|
230
|
+
puts exp8
|
231
|
+
```
|
232
|
+
|
233
|
+
|
234
|
+
# Filtering using expressions
|
235
|
+
|
236
|
+
Now that we now how to write expression, we can use then to filter a data frame by expressions.
|
237
|
+
Let's first start by creating a simple data frame with two columns named 'x' and 'y'
|
42
238
|
|
43
239
|
```{ruby df}
|
44
240
|
@df = R.data__frame(x: (1..3), y: (3..1))
|
45
241
|
puts @df
|
242
|
+
```
|
243
|
+
In the code bellow we want to filter the data frame by rows in which the value of 'x' is
|
244
|
+
equal to 1.
|
46
245
|
|
246
|
+
```{ruby filter_exp}
|
47
247
|
puts @df.filter(:x.eq 1)
|
48
248
|
```
|
49
249
|
|
250
|
+
In R, and when coding with 'tidyverse', arguments to a function are usually not
|
251
|
+
*referencially transparent*. That is, ou can’t replace a value with a seemingly equivalent
|
252
|
+
object that you’ve defined elsewhere. In other words, this code
|
253
|
+
|
254
|
+
```{r not_transp, eval=FALSE}
|
255
|
+
my_var <- x
|
256
|
+
filter(df, my_var == 1)
|
257
|
+
```
|
258
|
+
Generates the following error: "object 'x' not found.
|
259
|
+
|
260
|
+
However, in Ruby and Galaaz, arguments are referencially transparent as can be seen by the
|
261
|
+
code bellow. Note, initally that 'my_var = :x' will not give the error "object 'x' not found"
|
262
|
+
since ':x' is treated as an expression and assigned to my\_var. Then when doing (my\_var.eq 1),
|
263
|
+
my\_var is a variable that resolves to ':x' and it becomes equivalent to (:x.eq 1) which is
|
264
|
+
what we want.
|
265
|
+
|
50
266
|
```{ruby my_var}
|
51
267
|
my_var = :x
|
52
268
|
puts @df.filter(my_var.eq 1)
|
53
269
|
```
|
270
|
+
As stated by Hardley
|
54
271
|
|
55
272
|
> dplyr code is ambiguous. Depending on what variables are defined where,
|
56
273
|
> filter(df, x == y) could be equivalent to any of:
|
@@ -61,15 +278,253 @@ df[df$x == y, ]
|
|
61
278
|
df[x == df$y, ]
|
62
279
|
df[x == y, ]
|
63
280
|
```
|
281
|
+
In galaaz this ambiguity does not exist, filter(df, x.eq y) is not a valid expression as
|
282
|
+
expressions are build with symbols. In doing filter(df, :x.eq y) we are looking for elements
|
283
|
+
of the 'x' column that are equal to a previously defined y variable. Finally,
|
284
|
+
filter(df, :x.eq :y) we are looking for elements in which the 'x' column value is equal to
|
285
|
+
the 'y' column value. This can be seen in the following two chunks of code:
|
64
286
|
|
65
|
-
|
287
|
+
```{ruby disamb1}
|
288
|
+
@y = 1
|
289
|
+
@x = 2
|
290
|
+
|
291
|
+
# looking for values where the 'x' column is equal to the 'y' column
|
292
|
+
puts @df.filter(:x.eq :y)
|
293
|
+
```
|
294
|
+
|
295
|
+
```{ruby disamb2}
|
296
|
+
# looking for values where the 'x' column is equal to the 'y' variable
|
297
|
+
# in this case, the number 1
|
298
|
+
puts @df.filter(:x.eq @y)
|
299
|
+
```
|
300
|
+
# Writing a function that applies to different data sets
|
301
|
+
|
302
|
+
|
303
|
+
|
304
|
+
```
|
305
|
+
mutate(df1, y = a + x)
|
306
|
+
mutate(df2, y = a + x)
|
307
|
+
mutate(df3, y = a + x)
|
308
|
+
mutate(df4, y = a + x)
|
309
|
+
```
|
310
|
+
|
311
|
+
Here we create a mutate_y Ruby method.
|
312
|
+
|
313
|
+
```{ruby mutate_y, warning=FALSE}
|
314
|
+
def mutate_y(df)
|
315
|
+
df.mutate(:y.assign :a + :x)
|
316
|
+
end
|
317
|
+
```
|
318
|
+
|
319
|
+
Note that contrary to what happens in R, method mutate_y will fail independetly from the fact
|
320
|
+
that variable 'a' is defined or not.
|
321
|
+
|
322
|
+
```{ruby call_mutate, warning=FALSE}
|
323
|
+
df1 = R.data__frame(x: (1..3))
|
324
|
+
puts df1
|
325
|
+
a = 10
|
326
|
+
mutate_y(df1)
|
327
|
+
```
|
328
|
+
|
329
|
+
# Different expressions
|
330
|
+
|
331
|
+
```{r diff_expr}
|
332
|
+
df <- data.frame(
|
333
|
+
g1 = c(1, 1, 2, 2, 2),
|
334
|
+
g2 = c(1, 2, 1, 2, 1),
|
335
|
+
a = sample(5),
|
336
|
+
b = sample(5)
|
337
|
+
)
|
338
|
+
|
339
|
+
d2 <- df %>%
|
340
|
+
group_by(g1) %>%
|
341
|
+
summarise(a = mean(a))
|
342
|
+
|
343
|
+
as.data.frame(d2)
|
344
|
+
|
345
|
+
d2 <- df %>%
|
346
|
+
group_by(g2) %>%
|
347
|
+
summarise(a = mean(a))
|
348
|
+
|
349
|
+
as.data.frame(d2)
|
350
|
+
```
|
351
|
+
|
352
|
+
Trying to write a function in R that will receive two argumens, the first a variable and
|
353
|
+
the second an expression is not trivia. As shown by Hardley, one might expect this function
|
354
|
+
to do the trick:
|
355
|
+
|
356
|
+
```{r diff_exp_fnc}
|
357
|
+
my_summarise <- function(df, group_var) {
|
358
|
+
df %>%
|
359
|
+
group_by(group_var) %>%
|
360
|
+
summarise(a = mean(a))
|
361
|
+
}
|
362
|
+
|
363
|
+
# my_summarise(df, g1)
|
364
|
+
#> Error: Column `group_var` is unknown
|
365
|
+
```
|
366
|
+
|
367
|
+
In order to solve this problem, coding with dplyr requires the introduction of many new concepts
|
368
|
+
and functions such as 'quo', 'quos', 'enquo', 'enquos', '!!' (bang bang), '!!!' (triple bang).
|
369
|
+
|
370
|
+
Now, let's try to implement the same function in galaaz. The next code block first prints the
|
371
|
+
'df' data frame define previously in R, then creates the my_summarize function and calls it
|
372
|
+
passing the R data frame and the group by variable ':g1'
|
373
|
+
|
374
|
+
```{ruby diff_exp_ruby_func}
|
375
|
+
puts ~:df
|
376
|
+
print "\n"
|
377
|
+
|
378
|
+
def my_summarize(df, group_var)
|
379
|
+
df.group_by(group_var).
|
380
|
+
summarize(a: E.mean(:a))
|
381
|
+
end
|
382
|
+
|
383
|
+
puts my_summarize((~:df), :g1).as__data__frame
|
384
|
+
```
|
385
|
+
It works!!! Well let's make sure this was not just some coincidence
|
386
|
+
|
387
|
+
```{ruby group_g2}
|
388
|
+
puts my_summarize((~:df), :g2).as__data__frame
|
389
|
+
```
|
390
|
+
|
391
|
+
Great, everything is fine! No magic, no new functions, no complexities, just normal, standard Ruby
|
392
|
+
code. If you've ever done NSE in R, this certainly feels much safer and easy to implement.
|
393
|
+
|
394
|
+
# Different input variables
|
395
|
+
|
396
|
+
In the previous section we've managed to get rid of all NSE formulation for a simple example, but
|
397
|
+
does this remain true for more complex examples, or will the Ruby way prove inpractical for
|
398
|
+
more complex code?
|
399
|
+
|
400
|
+
In the next example Hardley proposes us to write a function that given an expression such as 'a'
|
401
|
+
or 'a * b', calculates three summaries. What we want a function that does the same as these R
|
402
|
+
statements:
|
403
|
+
|
404
|
+
```
|
405
|
+
summarise(df, mean = mean(a), sum = sum(a), n = n())
|
406
|
+
#> # A tibble: 1 x 3
|
407
|
+
#> mean sum n
|
408
|
+
#> <dbl> <int> <int>
|
409
|
+
#> 1 3 15 5
|
410
|
+
|
411
|
+
summarise(df, mean = mean(a * b), sum = sum(a * b), n = n())
|
412
|
+
#> # A tibble: 1 x 3
|
413
|
+
#> mean sum n
|
414
|
+
#> <dbl> <int> <int>
|
415
|
+
#> 1 9.6 48 5
|
416
|
+
```
|
417
|
+
|
418
|
+
Let's try it in galaaz:
|
419
|
+
|
420
|
+
```{ruby summarize_method}
|
421
|
+
def my_summarise2(df, expr)
|
422
|
+
df.summarize(
|
423
|
+
mean: E.mean(expr),
|
424
|
+
sum: E.sum(expr),
|
425
|
+
n: E.n
|
426
|
+
)
|
427
|
+
end
|
428
|
+
|
429
|
+
puts my_summarise2((~:df), :a)
|
430
|
+
puts my_summarise2((~:df), :a * :b)
|
431
|
+
```
|
432
|
+
|
433
|
+
Once again, there is no need to use any special theory or functions. The only point to be
|
434
|
+
careful about is the use of 'E' to build an expression that uses the mean, sum and n.
|
435
|
+
|
436
|
+
# Different input and output variable
|
437
|
+
|
438
|
+
Now the next challenge presented by Hardley is to vary the name of the output variables based on
|
439
|
+
the received expression. So, if the input expression is 'a', we want our data frame columns to
|
440
|
+
be named 'mean\_a' and 'sum\_a'. Now, if the input expression is 'b', columns
|
441
|
+
should be named 'mean\_b' and 'sum\_b'.
|
442
|
+
|
443
|
+
```
|
444
|
+
mutate(df, mean_a = mean(a), sum_a = sum(a))
|
445
|
+
#> # A tibble: 5 x 6
|
446
|
+
#> g1 g2 a b mean_a sum_a
|
447
|
+
#> <dbl> <dbl> <int> <int> <dbl> <int>
|
448
|
+
#> 1 1 1 1 3 3 15
|
449
|
+
#> 2 1 2 4 2 3 15
|
450
|
+
#> 3 2 1 2 1 3 15
|
451
|
+
#> 4 2 2 5 4 3 15
|
452
|
+
#> # … with 1 more row
|
453
|
+
|
454
|
+
mutate(df, mean_b = mean(b), sum_b = sum(b))
|
455
|
+
#> # A tibble: 5 x 6
|
456
|
+
#> g1 g2 a b mean_b sum_b
|
457
|
+
#> <dbl> <dbl> <int> <int> <dbl> <int>
|
458
|
+
#> 1 1 1 1 3 3 15
|
459
|
+
#> 2 1 2 4 2 3 15
|
460
|
+
#> 3 2 1 2 1 3 15
|
461
|
+
#> 4 2 2 5 4 3 15
|
462
|
+
#> # … with 1 more row
|
463
|
+
```
|
464
|
+
|
465
|
+
Here is our Ruby code
|
466
|
+
|
467
|
+
```{ruby name_change}
|
468
|
+
def my_mutate(df, expr)
|
469
|
+
mean_name = "mean_#{expr.to_s}"
|
470
|
+
sum_name = "sum_#{expr.to_s}"
|
471
|
+
|
472
|
+
df.mutate(mean_name => E.mean(expr),
|
473
|
+
sum_name => E.sum(expr))
|
474
|
+
end
|
475
|
+
|
476
|
+
puts my_mutate((~:df), :a)
|
477
|
+
puts my_mutate((~:df), :b)
|
478
|
+
```
|
479
|
+
It really seems that "Non Standard Evaluation" is actually quite standard in Galaaz! But, you
|
480
|
+
might have noticed a small change in the way the arguments to the mutate method were called.
|
481
|
+
In a previous example we used df.summarise(mean: E.mean(:a), ...) where the column name was
|
482
|
+
followed by a ':' colom. In this example, we have df.mutate(mean_name => E.mean(expr), ...)
|
483
|
+
and variable mean\_name is not followed by ':' but by '=>'. This is standard Ruby notation.
|
484
|
+
|
485
|
+
[explain....]
|
486
|
+
|
487
|
+
# Capturing multiple variables
|
488
|
+
|
489
|
+
```{ruby multiple_vars}
|
490
|
+
def my_summarise3(df, *group_vars)
|
491
|
+
df.group_by(*group_vars).
|
492
|
+
summarise(a: E.mean(:a))
|
493
|
+
end
|
494
|
+
|
495
|
+
puts my_summarise3((~:df), :g1, :g2).as__data__frame
|
496
|
+
```
|
497
|
+
|
498
|
+
# Advanced dplyr features
|
499
|
+
https://www.r-bloggers.com/programming-with-dplyr-by-using-dplyr/
|
500
|
+
|
501
|
+
```{ruby starwars}
|
502
|
+
puts (~:starwars).head.as__data__frame
|
503
|
+
```
|
504
|
+
|
505
|
+
```{r grouped_mean}
|
506
|
+
grouped_mean <- function(data, grouping_variables, value_variables) {
|
507
|
+
data %>%
|
508
|
+
group_by_at(grouping_variables) %>%
|
509
|
+
mutate(count = n()) %>%
|
510
|
+
summarise_at(c(value_variables, "count"), mean, na.rm = TRUE) %>%
|
511
|
+
rename_at(value_variables, funs(paste0("mean_", .)))
|
512
|
+
}
|
513
|
+
|
514
|
+
gm = starwars %>%
|
515
|
+
grouped_mean("eye_color", c("mass", "birth_year"))
|
516
|
+
|
517
|
+
as.data.frame(gm)
|
518
|
+
```
|
66
519
|
|
67
|
-
```{ruby
|
68
|
-
|
69
|
-
|
520
|
+
```{ruby advanced_starwars}
|
521
|
+
def grouped_mean(data, grouping_variables, value_variables)
|
522
|
+
data.
|
523
|
+
group_by_at(grouping_variables).
|
524
|
+
mutate(count: E.n).
|
525
|
+
summarise_at(E.c(value_variables, "count"), ~:mean, na__rm: true).
|
526
|
+
rename_at(value_variables, R.funs(E.paste0("mean_", value_variables)))
|
527
|
+
end
|
70
528
|
|
71
|
-
puts
|
72
|
-
puts @df[:x.eq y, :all]
|
73
|
-
# @df[x.eq :y, :all]
|
74
|
-
# @df[x == y, :all]
|
529
|
+
puts grouped_mean((~:starwars), "eye_color", R.c("mass", "birth_year")).as__data__frame
|
75
530
|
```
|