rover-df 0.2.0 → 0.2.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +5 -0
- data/README.md +17 -1
- data/lib/rover.rb +7 -3
- data/lib/rover/data_frame.rb +51 -3
- data/lib/rover/group.rb +5 -1
- data/lib/rover/vector.rb +1 -1
- data/lib/rover/version.rb +1 -1
- metadata +7 -7
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 1c750c49e4cb313565a3b52a273c4820ae406471a1007ddb8e83742f3f2640f1
|
4
|
+
data.tar.gz: 2a7469abd672a87c9b4c874469baf07f42b22067ac2281c424eeb7b60841bbfe
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 24e7874a67e498cadb8c2b4773f00c5cf53ab76e8231b7c762b8f403c2d4783809beb44ba3b37cb50b801032c3a3a9c140b18e1a10967eb331c517b5dd5251aa
|
7
|
+
data.tar.gz: b62f4bfd7591e9c4869ab13e4e6efeba5c4e121c92470bc81d517ec85045a2fdc080a7a6ca3f61a15e7c98335543fcb11893d00d374cb5a3cf1294e12ed65130
|
data/CHANGELOG.md
CHANGED
data/README.md
CHANGED
@@ -4,7 +4,9 @@ Simple, powerful data frames for Ruby
|
|
4
4
|
|
5
5
|
:mountain: Designed for data exploration and machine learning, and powered by [Numo](https://github.com/ruby-numo/numo-narray)
|
6
6
|
|
7
|
-
[
|
7
|
+
:evergreen_tree: Uses [Vega](https://github.com/ankane/vega) for visualization
|
8
|
+
|
9
|
+
[![Build Status](https://github.com/ankane/rover/workflows/build/badge.svg?branch=master)](https://github.com/ankane/rover/actions)
|
8
10
|
|
9
11
|
## Installation
|
10
12
|
|
@@ -198,6 +200,20 @@ Multiple groups
|
|
198
200
|
df.group([:a, :b]).count
|
199
201
|
```
|
200
202
|
|
203
|
+
## Visualization [master]
|
204
|
+
|
205
|
+
Add [Vega](https://github.com/ankane/vega) to your application’s Gemfile:
|
206
|
+
|
207
|
+
```ruby
|
208
|
+
gem 'vega'
|
209
|
+
```
|
210
|
+
|
211
|
+
And use:
|
212
|
+
|
213
|
+
```ruby
|
214
|
+
df.plot(:a, :b)
|
215
|
+
```
|
216
|
+
|
201
217
|
## Updating Data
|
202
218
|
|
203
219
|
Add a new column
|
data/lib/rover.rb
CHANGED
@@ -11,12 +11,12 @@ module Rover
|
|
11
11
|
class << self
|
12
12
|
def read_csv(path, types: nil, **options)
|
13
13
|
require "csv"
|
14
|
-
csv_to_df(CSV.read(path, **csv_options(options)), types: types)
|
14
|
+
csv_to_df(CSV.read(path, **csv_options(options)), types: types, headers: options[:headers])
|
15
15
|
end
|
16
16
|
|
17
17
|
def parse_csv(str, types: nil, **options)
|
18
18
|
require "csv"
|
19
|
-
csv_to_df(CSV.parse(str, **csv_options(options)), types: types)
|
19
|
+
csv_to_df(CSV.parse(str, **csv_options(options)), types: types, headers: options[:headers])
|
20
20
|
end
|
21
21
|
|
22
22
|
private
|
@@ -28,7 +28,11 @@ module Rover
|
|
28
28
|
options
|
29
29
|
end
|
30
30
|
|
31
|
-
def csv_to_df(table, types: nil)
|
31
|
+
def csv_to_df(table, types: nil, headers: nil)
|
32
|
+
if headers && headers.size < table.headers.size
|
33
|
+
raise ArgumentError, "Expected #{table.headers.size} headers, got #{headers.size}"
|
34
|
+
end
|
35
|
+
|
32
36
|
table.by_col!
|
33
37
|
data = {}
|
34
38
|
table.each do |k, v|
|
data/lib/rover/data_frame.rb
CHANGED
@@ -237,7 +237,12 @@ module Rover
|
|
237
237
|
# for IRuby
|
238
238
|
def to_html
|
239
239
|
require "iruby"
|
240
|
-
|
240
|
+
if size > 7
|
241
|
+
# pass 8 rows so maxrows is applied
|
242
|
+
IRuby::HTML.table((self[0..4] + self[-4..-1]).to_h, maxrows: 7)
|
243
|
+
else
|
244
|
+
IRuby::HTML.table(to_h)
|
245
|
+
end
|
241
246
|
end
|
242
247
|
|
243
248
|
# TODO handle long text better
|
@@ -291,8 +296,8 @@ module Rover
|
|
291
296
|
dup.sort_by!(&block)
|
292
297
|
end
|
293
298
|
|
294
|
-
def group(columns)
|
295
|
-
Group.new(self, columns)
|
299
|
+
def group(*columns)
|
300
|
+
Group.new(self, columns.flatten)
|
296
301
|
end
|
297
302
|
|
298
303
|
[:max, :min, :median, :mean, :percentile, :sum].each do |name|
|
@@ -357,6 +362,49 @@ module Rover
|
|
357
362
|
keys.all? { |k| self[k] == other[k] }
|
358
363
|
end
|
359
364
|
|
365
|
+
def plot(x = nil, y = nil, type: nil)
|
366
|
+
require "vega"
|
367
|
+
|
368
|
+
raise ArgumentError, "Must specify columns" if keys.size != 2 && (!x || !y)
|
369
|
+
x ||= keys[0]
|
370
|
+
y ||= keys[1]
|
371
|
+
type ||= begin
|
372
|
+
if self[x].numeric? && self[y].numeric?
|
373
|
+
"scatter"
|
374
|
+
elsif types[x] == :object && self[y].numeric?
|
375
|
+
"column"
|
376
|
+
else
|
377
|
+
raise "Cannot determine type"
|
378
|
+
end
|
379
|
+
end
|
380
|
+
data = self[[x, y]]
|
381
|
+
|
382
|
+
case type
|
383
|
+
when "scatter"
|
384
|
+
Vega.lite
|
385
|
+
.data(data)
|
386
|
+
.mark(type: "circle", tooltip: true)
|
387
|
+
.encoding(
|
388
|
+
x: {field: x, type: "quantitative", scale: {zero: false}},
|
389
|
+
y: {field: y, type: "quantitative", scale: {zero: false}},
|
390
|
+
size: {value: 60}
|
391
|
+
)
|
392
|
+
.config(axis: {title: nil, labelFontSize: 12})
|
393
|
+
when "column"
|
394
|
+
Vega.lite
|
395
|
+
.data(data)
|
396
|
+
.mark(type: "bar", tooltip: true)
|
397
|
+
.encoding(
|
398
|
+
# TODO determine label angle
|
399
|
+
x: {field: x, type: "nominal", sort: "none", axis: {labelAngle: 0}},
|
400
|
+
y: {field: y, type: "quantitative"}
|
401
|
+
)
|
402
|
+
.config(axis: {title: nil, labelFontSize: 12})
|
403
|
+
else
|
404
|
+
raise ArgumentError, "Invalid type: #{type}"
|
405
|
+
end
|
406
|
+
end
|
407
|
+
|
360
408
|
private
|
361
409
|
|
362
410
|
def check_key(key)
|
data/lib/rover/group.rb
CHANGED
@@ -2,7 +2,11 @@ module Rover
|
|
2
2
|
class Group
|
3
3
|
def initialize(df, columns)
|
4
4
|
@df = df
|
5
|
-
@columns =
|
5
|
+
@columns = columns
|
6
|
+
end
|
7
|
+
|
8
|
+
def group(*columns)
|
9
|
+
Group.new(@df, @columns + columns.flatten)
|
6
10
|
end
|
7
11
|
|
8
12
|
[:count, :max, :min, :mean, :median, :percentile, :sum].each do |name|
|
data/lib/rover/vector.rb
CHANGED
@@ -95,7 +95,7 @@ module Rover
|
|
95
95
|
define_method(op) do |other|
|
96
96
|
other = other.to_numo if other.is_a?(Vector)
|
97
97
|
# TODO better logic
|
98
|
-
if @data.is_a?(Numo::RObject)
|
98
|
+
if @data.is_a?(Numo::RObject) && !other.is_a?(Numo::RObject)
|
99
99
|
map { |v| v.send(op, other) }
|
100
100
|
else
|
101
101
|
Vector.new(@data.send(op, other))
|
data/lib/rover/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: rover-df
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Andrew Kane
|
8
|
-
autorequire:
|
8
|
+
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2020-
|
11
|
+
date: 2020-11-24 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: numo-narray
|
@@ -108,7 +108,7 @@ dependencies:
|
|
108
108
|
- - ">="
|
109
109
|
- !ruby/object:Gem::Version
|
110
110
|
version: '0'
|
111
|
-
description:
|
111
|
+
description:
|
112
112
|
email: andrew@chartkick.com
|
113
113
|
executables: []
|
114
114
|
extensions: []
|
@@ -127,7 +127,7 @@ homepage: https://github.com/ankane/rover
|
|
127
127
|
licenses:
|
128
128
|
- MIT
|
129
129
|
metadata: {}
|
130
|
-
post_install_message:
|
130
|
+
post_install_message:
|
131
131
|
rdoc_options: []
|
132
132
|
require_paths:
|
133
133
|
- lib
|
@@ -142,8 +142,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
142
142
|
- !ruby/object:Gem::Version
|
143
143
|
version: '0'
|
144
144
|
requirements: []
|
145
|
-
rubygems_version: 3.1.
|
146
|
-
signing_key:
|
145
|
+
rubygems_version: 3.1.4
|
146
|
+
signing_key:
|
147
147
|
specification_version: 4
|
148
148
|
summary: Simple, powerful data frames for Ruby
|
149
149
|
test_files: []
|