[R] what is wrong with this dataset?

[Carl Witthoft]

  As the Kroger  Data Munger Guru would say,  "What is the problem you 
are trying to solve?"

The datasets look just fine from a structural point of view. What do you 
want to do and what is wrong with the results you get?

<quote>
From: Kaiyin Zhong <kindlychung_at_gmail.com>
Date: Thu, 24 Nov 2011 09:39:20 +0800

 > d = data.frame(gender=rep(c('f','m'), 5), pos=rep(c('worker', 'manager',
'speaker', 'sales', 'investor'), 2), lot1=rnorm(10), lot2=rnorm(10))
 > d

    gender      pos       lot1       lot2
1       f   worker  1.1035316  0.8710510
2       m  manager -0.4824027 -0.2595865
3       f  speaker  0.8933589 -0.5966119
4       m    sales  0.4489920  0.4971199
5       f investor  0.9246900 -0.7531117
6       m   worker  0.2777642 -0.3338369
7       f  manager -1.0890828  0.7073686
8       m  speaker -1.3045821  0.4373199
9       f    sales  0.3092965 -2.6441382
10      m investor -0.5770073 -1.5200347

 > cast(melt(d))

Using gender, pos as id variables
    gender      pos       lot1       lot2
1       f investor  0.9246900 -0.7531117
2       f  manager -1.0890828  0.7073686
3       f    sales  0.3092965 -2.6441382
4       f  speaker  0.8933589 -0.5966119
5       f   worker  1.1035316  0.8710510
6       m investor -0.5770073 -1.5200347
7       m  manager -0.4824027 -0.2595865
8       m    sales  0.4489920  0.4971199
9       m  speaker -1.3045821  0.4373199
10      m   worker  0.2777642 -0.3338369

 > dataset = read.csv('datalist.csv')
 > dataset
    Gender     Title Category Salary
1       M   Manager        3  27000
2       F   Manager        2  22500
3       M Sales Rep        1  18000
4       M Sales Rep        3  27000
5       F   Manager        3  27000
6       M Secretary        4  31500
7       M Sales Rep        2  22500
8       M Secretary        2  22500
9       M    Worker        4  40500
10      M   Manager        4  37100
11      F Secretary        2  22500
12      F   Manager        3  27000
13      M    Worker        2  20000
14      M   Manager        4  32000
15      F Sales Rep        2  22900
16      M Sales Rep        3  27000
17      F Sales Rep        2  22500
18      M   Manager        1  18000
19      M Secretary        3  27000
20      F Sales Rep        3  27000
21      M Secretary        4  31500
22      M    Worker        2  22500
23      M   Manager        2  22500
24      M    Worker        4  40500
25      M    Worker        4  37100
26      F Secretary        2  22500
27      F   Manager        3  27000
28      M    Worker        2  20000
29      M   Manager        4  32000
30      F Sales Rep        2  22900

 > cast(melt(dataset))

Using Gender, Title as id variables
Aggregation requires fun.aggregate: length used as default
   Gender     Title Category Salary
1      F   Manager        4      4
2      F Sales Rep        4      4
3      F Secretary        2      2
4      M   Manager        6      6
5      M Sales Rep        4      4
6      M Secretary        4      4
7      M    Worker        6      6

The content of datalist.xls is here:
http://paste.pound-python.org/show/15098/
-- 

Sent from my Cray XK6
"Pendeo-navem mei anguillae plena est."