mode 0.0.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/.rspec +2 -0
- data/.travis.yml +7 -0
- data/Gemfile +6 -0
- data/LICENSE.txt +202 -0
- data/README.md +138 -0
- data/Rakefile +6 -0
- data/bin/mode +13 -0
- data/lib/mode.rb +13 -0
- data/lib/mode/cli.rb +6 -0
- data/lib/mode/cli/analyze.rb +20 -0
- data/lib/mode/cli/base.rb +15 -0
- data/lib/mode/cli/helpers.rb +22 -0
- data/lib/mode/cli/import.rb +62 -0
- data/lib/mode/cli/package.rb +13 -0
- data/lib/mode/cli/setup.rb +12 -0
- data/lib/mode/commands/analyze_field.rb +70 -0
- data/lib/mode/commands/analyze_schema.rb +88 -0
- data/lib/mode/commands/helpers.rb +10 -0
- data/lib/mode/commands/import.rb +37 -0
- data/lib/mode/commands/package.rb +60 -0
- data/lib/mode/commands/setup.rb +36 -0
- data/lib/mode/config.rb +54 -0
- data/lib/mode/version.rb +3 -0
- data/mode.gemspec +36 -0
- data/spec/commands/analyze_schema_spec.rb +24 -0
- data/spec/commands/setup_spec.rb +62 -0
- data/spec/config_spec.rb +34 -0
- data/spec/fixtures/MOCK_DATA.csv +100001 -0
- data/spec/fixtures/cb_clean_small.csv +100000 -0
- data/spec/fixtures/duplicate_keys.csv +3 -0
- data/spec/fixtures/espn_draft.csv +1 -0
- data/spec/fixtures/format_examples.csv.txt +6 -0
- data/spec/fixtures/format_examples_after_excel.csv.txt +1 -0
- data/spec/spec_helper.rb +19 -0
- metadata +232 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 808b8322502a62ca8f0902865261604f91c10fb6
|
4
|
+
data.tar.gz: 5257839cf15428d9586c76bfae9f0eed43eeaa72
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 70ff00782afa3768c2b56a206ce0b86d7751efc1bead5fdd3665797c3bcf9e17f68916ef19ba99a2addc32acebb5e955dab45646e939fd1bbc5e6a3b8412568a
|
7
|
+
data.tar.gz: 0e12149f13ad6a40da8f8f2a34ef29b6ee8de4640a2b368c77f63b0162e766d28ab596c8fcf689de6b2fdda00d8de89209c1f93aca6b6bad312516701136464d
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,202 @@
|
|
1
|
+
Apache License
|
2
|
+
Version 2.0, January 2004
|
3
|
+
http://www.apache.org/licenses/
|
4
|
+
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
6
|
+
|
7
|
+
1. Definitions.
|
8
|
+
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
11
|
+
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
13
|
+
the copyright owner that is granting the License.
|
14
|
+
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
16
|
+
other entities that control, are controlled by, or are under common
|
17
|
+
control with that entity. For the purposes of this definition,
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
19
|
+
direction or management of such entity, whether by contract or
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
22
|
+
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
24
|
+
exercising permissions granted by this License.
|
25
|
+
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
27
|
+
including but not limited to software source code, documentation
|
28
|
+
source, and configuration files.
|
29
|
+
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
31
|
+
transformation or translation of a Source form, including but
|
32
|
+
not limited to compiled object code, generated documentation,
|
33
|
+
and conversions to other media types.
|
34
|
+
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
36
|
+
Object form, made available under the License, as indicated by a
|
37
|
+
copyright notice that is included in or attached to the work
|
38
|
+
(an example is provided in the Appendix below).
|
39
|
+
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
46
|
+
the Work and Derivative Works thereof.
|
47
|
+
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
49
|
+
the original version of the Work and any modifications or additions
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
61
|
+
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
64
|
+
subsequently incorporated within the Work.
|
65
|
+
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
72
|
+
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
78
|
+
where such license applies only to those patent claims licensable
|
79
|
+
by such Contributor that are necessarily infringed by their
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
82
|
+
institute patent litigation against any entity (including a
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
85
|
+
or contributory patent infringement, then any patent licenses
|
86
|
+
granted to You under this License for that Work shall terminate
|
87
|
+
as of the date such litigation is filed.
|
88
|
+
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
91
|
+
modifications, and in Source or Object form, provided that You
|
92
|
+
meet the following conditions:
|
93
|
+
|
94
|
+
(a) You must give any other recipients of the Work or
|
95
|
+
Derivative Works a copy of this License; and
|
96
|
+
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
98
|
+
stating that You changed the files; and
|
99
|
+
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
102
|
+
attribution notices from the Source form of the Work,
|
103
|
+
excluding those notices that do not pertain to any part of
|
104
|
+
the Derivative Works; and
|
105
|
+
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
108
|
+
include a readable copy of the attribution notices contained
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
111
|
+
of the following places: within a NOTICE text file distributed
|
112
|
+
as part of the Derivative Works; within the Source form or
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
114
|
+
within a display generated by the Derivative Works, if and
|
115
|
+
wherever such third-party notices normally appear. The contents
|
116
|
+
of the NOTICE file are for informational purposes only and
|
117
|
+
do not modify the License. You may add Your own attribution
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
120
|
+
that such additional attribution notices cannot be construed
|
121
|
+
as modifying the License.
|
122
|
+
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
124
|
+
may provide additional or different license terms and conditions
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
128
|
+
the conditions stated in this License.
|
129
|
+
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
133
|
+
this License, without any additional terms or conditions.
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
135
|
+
the terms of any separate license agreement you may have executed
|
136
|
+
with Licensor regarding such Contributions.
|
137
|
+
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
140
|
+
except as required for reasonable and customary use in describing the
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
142
|
+
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
152
|
+
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
158
|
+
incidental, or consequential damages of any character arising as a
|
159
|
+
result of this License or out of the use or inability to use the
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
162
|
+
other commercial damages or losses), even if such Contributor
|
163
|
+
has been advised of the possibility of such damages.
|
164
|
+
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
168
|
+
or other liability obligations and/or rights consistent with this
|
169
|
+
License. However, in accepting such obligations, You may act only
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
174
|
+
of your accepting any such warranty or additional liability.
|
175
|
+
|
176
|
+
END OF TERMS AND CONDITIONS
|
177
|
+
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
179
|
+
|
180
|
+
To apply the Apache License to your work, attach the following
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "{}"
|
182
|
+
replaced with your own identifying information. (Don't include
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
184
|
+
comment syntax for the file format. We also recommend that a
|
185
|
+
file or class name and description of purpose be included on the
|
186
|
+
same "printed page" as the copyright notice for easier
|
187
|
+
identification within third-party archives.
|
188
|
+
|
189
|
+
Copyright {yyyy} {name of copyright owner}
|
190
|
+
|
191
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
192
|
+
you may not use this file except in compliance with the License.
|
193
|
+
You may obtain a copy of the License at
|
194
|
+
|
195
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
196
|
+
|
197
|
+
Unless required by applicable law or agreed to in writing, software
|
198
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
199
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
200
|
+
See the License for the specific language governing permissions and
|
201
|
+
limitations under the License.
|
202
|
+
|
data/README.md
ADDED
@@ -0,0 +1,138 @@
|
|
1
|
+
# Mode
|
2
|
+
|
3
|
+
This package provides command line tools for managing datasets and connecting data to Mode including:
|
4
|
+
|
5
|
+
* Cloud data warehouse management
|
6
|
+
* Personal data warehouse connectivity
|
7
|
+
* Dataset formatting and importing (CSV)
|
8
|
+
|
9
|
+
## Installation
|
10
|
+
|
11
|
+
### Standalone
|
12
|
+
|
13
|
+
From your terminal run:
|
14
|
+
|
15
|
+
$ gem install mode
|
16
|
+
|
17
|
+
### Bundler
|
18
|
+
|
19
|
+
Add this line to your application's Gemfile:
|
20
|
+
|
21
|
+
gem 'mode'
|
22
|
+
|
23
|
+
And then execute:
|
24
|
+
|
25
|
+
$ bundle
|
26
|
+
|
27
|
+
## Setup
|
28
|
+
|
29
|
+
### Init
|
30
|
+
|
31
|
+
Initializes a new configuration file at the specified path which holds API credentials and other information
|
32
|
+
|
33
|
+
```
|
34
|
+
$ mode setup
|
35
|
+
|
36
|
+
Initializing configuration at /Users/josh/.mode.yml
|
37
|
+
Mode username: besquared
|
38
|
+
Your can view your access tokens at http://www.modeanalytics.com/accounts/besquared/access_tokens
|
39
|
+
Access token for besquared: ...
|
40
|
+
Wrote configuration to /Users/josh/.mode.yml
|
41
|
+
```
|
42
|
+
|
43
|
+
## Working with CSV Data
|
44
|
+
|
45
|
+
### Analyze
|
46
|
+
|
47
|
+
The analyze command performs two useful functions:
|
48
|
+
|
49
|
+
* Ensures that the csv is well formed with no syntax errors
|
50
|
+
* Tells you how Mode will recognize data types and format data
|
51
|
+
|
52
|
+
For better performance analyze only inspects a sampled subset of file.
|
53
|
+
|
54
|
+
You can optionally set the sampling rate by passing the --sample option with a number between 0 and 1.
|
55
|
+
|
56
|
+
```
|
57
|
+
$ mode analyze bikeshare_small.csv
|
58
|
+
|
59
|
+
# Analyzing bikeshare_small.csv (Sampling 12.70%)...
|
60
|
+
# Analyzed 12040 of 99999 rows
|
61
|
+
+------------+-----+----------+------------+-------------+------------+---------------+-------------+-----------+
|
62
|
+
| Field | Key | Type | String (%) | Integer (%) | Number (%) | Date/Time (%) | Boolean (%) | Empty (%) |
|
63
|
+
+------------+-----+----------+------------+-------------+------------+---------------+-------------+-----------+
|
64
|
+
| start_time | No | datetime | | | | 100.00% | | |
|
65
|
+
| type | No | string | 100.00% | | | | | |
|
66
|
+
+------------+-----+----------+------------+-------------+------------+---------------+-------------+-----------+
|
67
|
+
```
|
68
|
+
|
69
|
+
### Import
|
70
|
+
|
71
|
+
More to come!
|
72
|
+
|
73
|
+
### Package
|
74
|
+
|
75
|
+
The package command will analyze your dataset and create a data package based on the field types that are recognized.
|
76
|
+
|
77
|
+
The data package can then be imported into the data warehouse.
|
78
|
+
|
79
|
+
```
|
80
|
+
```
|
81
|
+
|
82
|
+
### Package Format
|
83
|
+
|
84
|
+
Mode packages are inspired by and compatible with [Open Knowledge Foundation Standards](http://data.okfn.org/standards), and specifically:
|
85
|
+
|
86
|
+
* [Data Packages](http://data.okfn.org/standards/data-package)
|
87
|
+
* [Simple Data Format](http://data.okfn.org/standards/simple-data-format)
|
88
|
+
|
89
|
+
The most basic Mode data packages contains a normalized csv data file as well as a file describing the data.
|
90
|
+
|
91
|
+
* data.csv
|
92
|
+
* datapackage.json
|
93
|
+
|
94
|
+
Additionally they may contain a README.md, scripts and other resources.
|
95
|
+
|
96
|
+
#### datapackage.json
|
97
|
+
|
98
|
+
The datapackage.json file contains descriptive information of the data available in the package including naming, formatting and schema information.
|
99
|
+
|
100
|
+
```
|
101
|
+
{
|
102
|
+
"name" : "my-dataset",
|
103
|
+
"version": 0.0.1,
|
104
|
+
"title": "a human friendly title"
|
105
|
+
|
106
|
+
"resources": [
|
107
|
+
{
|
108
|
+
"name": "data",
|
109
|
+
"format": "csv",
|
110
|
+
"path": "data.csv",
|
111
|
+
|
112
|
+
"dialect": {
|
113
|
+
"delimiter": ",",
|
114
|
+
"quoteChar": "\"",
|
115
|
+
"doubleQuote": false,
|
116
|
+
"lineTerminator": "\r\n",
|
117
|
+
"skipInitialSpace": false
|
118
|
+
},
|
119
|
+
|
120
|
+
"schema": {
|
121
|
+
"fields": [
|
122
|
+
{
|
123
|
+
"name": "name of field (e.g. column name)",
|
124
|
+
"title": "A nicer human readable label or title for the field",
|
125
|
+
"type": "A string specifying the type",
|
126
|
+
"format": "A string specifying a format",
|
127
|
+
"description": "A description for the field"
|
128
|
+
...
|
129
|
+
},
|
130
|
+
],
|
131
|
+
|
132
|
+
"primaryKey": ['field1', 'field2', ...]
|
133
|
+
}
|
134
|
+
}
|
135
|
+
]
|
136
|
+
}
|
137
|
+
|
138
|
+
```
|
data/Rakefile
ADDED
data/bin/mode
ADDED
data/lib/mode.rb
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
require 'thor'
|
2
|
+
require 'data_kit'
|
3
|
+
|
4
|
+
# Base
|
5
|
+
require "mode/version"
|
6
|
+
require 'mode/config'
|
7
|
+
|
8
|
+
# Commands
|
9
|
+
require 'mode/commands/helpers'
|
10
|
+
require 'mode/commands/setup'
|
11
|
+
require 'mode/commands/import'
|
12
|
+
require 'mode/commands/analyze_field'
|
13
|
+
require 'mode/commands/analyze_schema'
|
data/lib/mode/cli.rb
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
module Mode
|
2
|
+
module CLI
|
3
|
+
class Base < Thor
|
4
|
+
desc "analyze PATH [--field=POSITION] [--match-type=TYPE]", "Analyzes a dataset or a field "
|
5
|
+
option :sample, :banner => 'RATE (Example: 0.5)'
|
6
|
+
option :field, :banner => 'POSITION (Beginning at 0, Example: 10)'
|
7
|
+
option :match_type, :banner => 'TYPE (One of: string, number, integer, datetime, boolean)'
|
8
|
+
# option :keys, :banner => 'POSITIONS (ex: 0,2)', :default => String.new
|
9
|
+
def analyze(path = nil)
|
10
|
+
#keys = options[:keys].split(',').collect(&:strip).collect(&:to_i)
|
11
|
+
|
12
|
+
if field_pos = options[:field]
|
13
|
+
Mode::Commands::AnalyzeField.new(path, field_pos, options).execute
|
14
|
+
else
|
15
|
+
Mode::Commands::AnalyzeSchema.new(path, options).execute
|
16
|
+
end
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|