RFView() {
// hide in generated query page
_oobee._hideInQuery = true;
_numTrees._readOnly = true;
_job._hideInQuery = true;
_dest._hideInQuery = true;
}
@Override
protected Response serve() {
InputStream s = null;
String urlStr = _url.value();
try {
// if( urlStr.startsWith("file://") ) {
// urlStr = urlStr.substring("file://".length());
if (urlStr.startsWith("file:///")) {
urlStr = urlStr.substring("file:///".length());
File f = new File(urlStr);
// urlStr = "file://"+f.getCanonicalPath();
urlStr = "file:///" + f.getCanonicalPath();
}
URL url = new URL(urlStr);
Key k = _key.value();
if (k == null) k = Key.make(urlStr);
s = url.openStream();
if (s == null) return Response.error("Unable to open stream to URL " + url.toString());
ValueArray.readPut(k, s);
JsonObject json = new JsonObject();
json.addProperty(KEY, k.toString());
json.addProperty(URL, urlStr);
Response r = Response.done(json);
r.setBuilder(KEY, new KeyElementBuilder());
return r;
} catch (IllegalArgumentException e) {
return Response.error("Not a valid key: " + urlStr);
} catch (IOException e) {
return Response.error(e);
} finally {
Closeables.closeQuietly(s);
}
}
public ImportUrl() {
_requestHelp = "Imports the given URL.";
_url._requestHelp = "URL to import.";
_key._requestHelp = "Key to store the url contents under.";
}
@Override
protected Response serve() {
int tasks = 0;
int finished = 0;
RFModel model = _modelKey.value();
double[] weights = _weights.value();
// Finish refresh after rf model is done and confusion matrix for all trees is computed
boolean done = false;
int classCol = _classCol.specified() ? _classCol.value() : findResponseIdx(model);
tasks = model._totalTrees;
finished = model.size();
// Handle cancelled/aborted jobs
if (_job.value() != null) {
Job jjob = Job.findJob(_job.value());
if (jjob != null && jjob.isCancelled())
return Response.error(
jjob.exception == null ? "Job was cancelled by user!" : jjob.exception);
}
JsonObject response = defaultJsonResponse();
// CM return and possible computation is requested
if (!_noCM.value() && (finished == tasks || _iterativeCM.value()) && finished > 0) {
// Compute the highest number of trees which is less then a threshold
int modelSize = tasks * _refreshThresholdCM.value() / 100;
modelSize =
modelSize == 0 || finished == tasks ? finished : modelSize * (finished / modelSize);
// Get the computing the matrix - if no job is computing, then start a new job
Job cmJob =
ConfusionTask.make(
model, modelSize, _dataKey.value()._key, classCol, weights, _oobee.value());
// Here the the job is running - it saved a CM which can be already finished or in invalid
// state.
CMFinal confusion = UKV.get(cmJob.dest());
// if the matrix is valid, report it in the JSON
if (confusion != null && confusion.valid() && modelSize > 0) {
// finished += 1;
JsonObject cm = new JsonObject();
JsonArray cmHeader = new JsonArray();
JsonArray matrix = new JsonArray();
cm.addProperty(JSON_CM_TYPE, _oobee.value() ? "OOB error estimate" : "full scoring");
cm.addProperty(JSON_CM_CLASS_ERR, confusion.classError());
cm.addProperty(JSON_CM_ROWS_SKIPPED, confusion.skippedRows());
cm.addProperty(JSON_CM_ROWS, confusion.rows());
// create the header
for (String s : cfDomain(confusion, 1024)) cmHeader.add(new JsonPrimitive(s));
cm.add(JSON_CM_HEADER, cmHeader);
// add the matrix
final int nclasses = confusion.dimension();
JsonArray classErrors = new JsonArray();
for (int crow = 0; crow < nclasses; ++crow) {
JsonArray row = new JsonArray();
int classHitScore = 0;
for (int ccol = 0; ccol < nclasses; ++ccol) {
row.add(new JsonPrimitive(confusion.matrix(crow, ccol)));
if (crow != ccol) classHitScore += confusion.matrix(crow, ccol);
}
// produce infinity members in case of 0.f/0
classErrors.add(
new JsonPrimitive(
(float) classHitScore / (classHitScore + confusion.matrix(crow, crow))));
matrix.add(row);
}
cm.add(JSON_CM_CLASSES_ERRORS, classErrors);
cm.add(JSON_CM_MATRIX, matrix);
cm.addProperty(JSON_CM_TREES, modelSize);
response.add(JSON_CM, cm);
// Signal end only and only if all trees were generated and confusion matrix is valid
done = finished == tasks;
}
} else if (_noCM.value() && finished == tasks) done = true;
// Trees
JsonObject trees = new JsonObject();
trees.addProperty(Constants.TREE_COUNT, model.size());
if (model.size() > 0) {
trees.add(Constants.TREE_DEPTH, model.depth().toJson());
trees.add(Constants.TREE_LEAVES, model.leaves().toJson());
}
response.add(Constants.TREES, trees);
// Build a response
Response r;
if (done) {
r = jobDone(response);
r.addHeader(
"<div class='alert'>"
+ /*RFScore.link(MODEL_KEY, model._key, "Use this model for scoring.") */ GeneratePredictionsPage
.link(model._key, "Predict!")
+ " </div>");
} else {
r = Response.poll(response, finished, tasks);
}
r.setBuilder(JSON_CM, new ConfusionMatrixBuilder());
r.setBuilder(TREES, new TreeListBuilder());
return r;
}
