This is an automated email from the ASF dual-hosted git repository.
baunsgaard pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/systemds.git
The following commit(s) were added to refs/heads/master by this push:
new 4898c95 [DOCS] Kmeans update docs
4898c95 is described below
commit 4898c955d54bdb44be32e1f5d228f737fffadc88
Author: baunsgaard <[email protected]>
AuthorDate: Fri Oct 30 11:40:16 2020 +0100
[DOCS] Kmeans update docs
---
docs/site/builtins-reference.md | 8 +++++---
scripts/builtin/kmeans.dml | 1 +
src/test/scripts/functions/builtin/kmeansPredict.dml | 2 +-
src/test/scripts/functions/builtin/smote.dml | 2 +-
4 files changed, 8 insertions(+), 5 deletions(-)
diff --git a/docs/site/builtins-reference.md b/docs/site/builtins-reference.md
index 66b2299..22c1491 100644
--- a/docs/site/builtins-reference.md
+++ b/docs/site/builtins-reference.md
@@ -557,7 +557,7 @@ imputeByFD(X, sourceAttribute, targetAttribute, threshold)
### Example
```r
-X = matrix("1 1 1 2 4 5 5 3 3 NaN 4 5 4 1", rows=7, cols=2)
+X = matrix("1 1 1 2 4 5 5 3 3 NaN 4 5 4 1", rows=7, cols=2)
imputeByFD(X = X, source = 1, target = 2, threshold = 0.6, verbose = FALSE)
```
@@ -568,7 +568,7 @@ The kmeans() implements the KMeans Clustering algorithm.
### Usage
```r
-kmeans(X = X, k = 20, runs = 10, max_iter = 5000, eps = 0.000001, is_verbose =
FALSE, avg_sample_size_per_centroid = 50)
+kmeans(X = X, k = 20, runs = 10, max_iter = 5000, eps = 0.000001, is_verbose =
FALSE, avg_sample_size_per_centroid = 50, seed = -1)
```
### Arguments
@@ -581,6 +581,8 @@ kmeans(X = X, k = 20, runs = 10, max_iter = 5000, eps =
0.000001, is_verbose = F
| max_iter | Int | `100` |Max no. of iterations allowed |
| eps | Double | `0.000001` | Tolerance (epsilon) for WCSS
change ratio |
| is_verbose | Boolean | FALSE | do not print per-iteration stats
|
+| avg_sample_size_per_centroid | int | 50 | Number of samples to
make in the initialization |
+| seed | int | -1 | The seed used for initial sampling. If set to
-1 random seeds are selected. |
### Returns
@@ -593,7 +595,7 @@ kmeans(X = X, k = 20, runs = 10, max_iter = 5000, eps =
0.000001, is_verbose = F
```r
X = rand (rows = 3972, cols = 972)
-kmeans(X = X, k = 20, runs = 10, max_iter = 5000, eps = 0.000001, is_verbose =
FALSE, avg_sample_size_per_centroid = 50)
+kmeans(X = X, k = 20, runs = 10, max_iter = 5000, eps = 0.000001, is_verbose =
FALSE, avg_sample_size_per_centroid = 50, seed = -1)
```
## `lm`-Function
diff --git a/scripts/builtin/kmeans.dml b/scripts/builtin/kmeans.dml
index 646ec34..ee66e3d 100644
--- a/scripts/builtin/kmeans.dml
+++ b/scripts/builtin/kmeans.dml
@@ -32,6 +32,7 @@
# eps Double 0.000001 Tolerance (epsilon) for
WCSS change ratio
# is_verbose Boolean FALSE do not print
per-iteration stats
# avg_sample_size_per_centroid Int 50 Average number of
records per centroid in data samples
+# seed Int -1 The seed used for
initial sampling. If set to -1 random seeds are selected.
#
#
# RETURN VALUES
diff --git a/src/test/scripts/functions/builtin/kmeansPredict.dml
b/src/test/scripts/functions/builtin/kmeansPredict.dml
index a96fc28..59dc726 100644
--- a/src/test/scripts/functions/builtin/kmeansPredict.dml
+++ b/src/test/scripts/functions/builtin/kmeansPredict.dml
@@ -21,7 +21,7 @@
X = read($X)
-[C, Y] = kmeans(X, $k, $runs, $max_iter, $eps, TRUE, 50)
+[C, Y] = kmeans(X, $k, $runs, $max_iter, $eps, TRUE, 50, 1324)
Y_1 = kmeansPredict(X, C)
res = mean(Y==Y_1)
diff --git a/src/test/scripts/functions/builtin/smote.dml
b/src/test/scripts/functions/builtin/smote.dml
index 3891c98..5a8d5d6 100644
--- a/src/test/scripts/functions/builtin/smote.dml
+++ b/src/test/scripts/functions/builtin/smote.dml
@@ -30,7 +30,7 @@ T = read($T);
A_B = rbind(A, B)
n = nrow(A_B)
# group data into k=2 clusters
-[C, Y] = kmeans(rbind(A_B, T), 2, 10, 100, 0.000001, FALSE, 50)
+[C, Y] = kmeans(rbind(A_B, T), 2, 10, 100, 0.000001, FALSE, 50, 314)
# check if the instances of A and B fall in same cluster
check = matrix(as.scalar(Y[1,1]), n, 1)
testSum = sum(check - Y[1:n,])
