Ghost (version 0.1.0)

saxTransform: saxTransform

Description

This function is added to the package to enable users converting numeric data to discrete data. This is due to the fact that Ghost designed for discrete data and this function discretize numeric data and prepare them for the ghost algorithm.

Usage

saxTransform(data_frame, buckets,skipColumnVec,constraint_row)

Arguments

data_frame

A data frame with numeric values.

buckets

The Input data range is divided to this number.

skipColumnVec

Column number that is not used in the algorithm.

constraint_row

Column number that is considered for constant column.

References

1- Rawassizadeh, Reza, Hamidreza Keshavarz, and Michael Pazzani. "Ghost Imputation: Accurately Reconstructing Missing Data of the Off Period." IEEE Transactions on Knowledge and Data Engineering (to appear).

2- Lin, J., Keogh, E., Lonardi, S., & Chiu, B. (2003). A symbolic representation of time series, with implications for streaming algorithms. In Proceedings of the 8th ACM SIGMOD workshop on Research issues in data mining and knowledge discovery (pp. 2-11). ACM.

Examples

# NOT RUN {
data(sax_test)

#### Input dataframe-----------------------
#   S0  S1  S2 S3
#1   1   2  54 65
#2   1  NA  21 54
#3   2  34  32 87
#4   1  23  58 52
#5   1  43  75 56
#6   2  12  20 95
#7   1  54  14 87
#8   3  -6  NA 30
#9   2   5 -60 32
#10  1 -85  58 25
#11  2  78  95 45
#12  3  52  52 62
#13  2  20  NA 58
#14  3  NA -62 78
#15  1  20 -10 96
#16  1  30  -6 NA
#17  1  12 -85 45
#18  1  NA  78 20
#19  1  23  95 NA

saxTransform(sax_test,buckets =10,skipColumnVec=1, constraint_row=1)

### Output data----------------------------------------------
#     S0  S1  S2   S3
# [1,] "1" "2" "54" "65"
# [2,] "1" ""  "f"  "h"
# [3,] "2" "g" "g"  "j"
# [4,] "1" "g" "h"  "h"
# [5,] "1" "h" "i"  "h"
# [6,] "2" "f" "f"  "k"
# [7,] "1" "h" "f"  "j"
# [8,] "3" "e" ""   "g"
# [9,] "2" "f" "b"  "g"
#[10,] "1" "a" "h"  "g"
#[11,] "2" "j" "k"  "h"
#[12,] "3" "h" "h"  "i"
#[13,] "2" "f" ""   "h"
#[14,] "3" ""  "b"  "j"
#[15,] "1" "f" "e"  "k"
#[16,] "1" "g" "e"  ""
#[17,] "1" "f" "a"  "h"
#[18,] "1" ""  "j"  "f"
#[19,] "1" "g" "k"  ""
# }