class FileBrowser(QWidget):
fileSelectedSignal = pyqtSignal(QString)
directorySelectedSignal = pyqtSignal(QString)
def __init__(self, *args):
super(FileBrowser, self).__init__(*args)
layout = QVBoxLayout()
model = QFileSystemModel()
filters = ["*.jpg", "*.JPG", "*.jpeg", "*.JPEG","*.png","*.PNG"]
model.setNameFilters(filters)
self.directoryTree = QTreeView()
self.directoryTree.setModel(model)
self.directoryTree.currentChanged = self.currentChanged
self.directoryTree.setSortingEnabled(True)
self.directoryTree.sortByColumn(0, Qt.AscendingOrder)
self.fileList = QListWidget()
layout.addWidget(self.directoryTree)
self.setLayout(layout)
root = model.setRootPath(QDir.homePath())
self.directoryTree.setRootIndex(root)
def currentChanged(self, current, previous):
QTreeView.currentChanged(self.directoryTree, current, previous)
currentIndex = self.directoryTree.selectionModel().currentIndex()
path = str ( self.directoryTree.model().filePath(currentIndex) )
if self.directoryTree.model().isDir(currentIndex):
self.directorySelectedSignal.emit(path)
else:
self.directorySelectedSignal.emit(os.path.dirname(path))
self.fileSelectedSignal.emit(path)
class FileBrowser(QWidget):
fileSelectedSignal = pyqtSignal(QString)
directorySelectedSignal = pyqtSignal(QString)
def __init__(self, *args):
super(FileBrowser, self).__init__(*args)
layout = QVBoxLayout()
model = QFileSystemModel()
filters = ["*.jpg", "*.JPG", "*.jpeg", "*.JPEG", "*.png", "*.PNG"]
model.setNameFilters(filters)
self.directoryTree = QTreeView()
self.directoryTree.setModel(model)
self.directoryTree.currentChanged = self.currentChanged
self.directoryTree.setSortingEnabled(True)
self.directoryTree.sortByColumn(0, Qt.AscendingOrder)
self.fileList = QListWidget()
layout.addWidget(self.directoryTree)
self.setLayout(layout)
root = model.setRootPath(QDir.homePath())
self.directoryTree.setRootIndex(root)
def currentChanged(self, current, previous):
QTreeView.currentChanged(self.directoryTree, current, previous)
currentIndex = self.directoryTree.selectionModel().currentIndex()
path = str(self.directoryTree.model().filePath(currentIndex))
if self.directoryTree.model().isDir(currentIndex):
self.directorySelectedSignal.emit(path)
else:
self.directorySelectedSignal.emit(os.path.dirname(path))
self.fileSelectedSignal.emit(path)
class OWGeneInfo(widget.OWWidget):
name = "Gene Info"
description = "Displays gene information from NCBI and other sources."
icon = "../widgets/icons/GeneInfo.svg"
priority = 2010
inputs = [("Data", Orange.data.Table, "setData")]
outputs = [("Data Subset", Orange.data.Table)]
settingsHandler = settings.DomainContextHandler()
organism_index = settings.ContextSetting(0)
taxid = settings.ContextSetting("9606")
gene_attr = settings.ContextSetting(0)
auto_commit = settings.Setting(False)
search_string = settings.Setting("")
useAttr = settings.ContextSetting(False)
useAltSource = settings.ContextSetting(False)
def __init__(self, parent=None, ):
super().__init__(self, parent)
self.selectionChangedFlag = False
self.__initialized = False
self.initfuture = None
self.itemsfuture = None
self.infoLabel = gui.widgetLabel(
gui.widgetBox(self.controlArea, "Info", addSpace=True),
"Initializing\n"
)
self.organisms = None
self.organismBox = gui.widgetBox(
self.controlArea, "Organism", addSpace=True)
self.organismComboBox = gui.comboBox(
self.organismBox, self, "organism_index",
callback=self._onSelectedOrganismChanged)
# For now only support one alt source, with a checkbox
# In the future this can be extended to multiple selections
self.altSourceCheck = gui.checkBox(
self.organismBox, self, "useAltSource",
"Show information from dictyBase",
callback=self.onAltSourceChange)
self.altSourceCheck.hide()
box = gui.widgetBox(self.controlArea, "Gene names", addSpace=True)
self.geneAttrComboBox = gui.comboBox(
box, self, "gene_attr",
"Gene atttibute", callback=self.updateInfoItems
)
self.geneAttrComboBox.setEnabled(not self.useAttr)
cb = gui.checkBox(box, self, "useAttr", "Use attribute names",
callback=self.updateInfoItems)
cb.toggled[bool].connect(self.geneAttrComboBox.setDisabled)
gui.auto_commit(self.controlArea, self, "auto_commit", "Commit")
# A label for dictyExpress link (Why oh god why???)
self.dictyExpressBox = gui.widgetBox(
self.controlArea, "Dicty Express")
self.linkLabel = gui.widgetLabel(self.dictyExpressBox, "")
self.linkLabel.setOpenExternalLinks(False)
self.linkLabel.linkActivated.connect(self.onDictyExpressLink)
self.dictyExpressBox.hide()
gui.rubber(self.controlArea)
gui.lineEdit(self.mainArea, self, "search_string", "Filter",
callbackOnType=True, callback=self.searchUpdate)
self.treeWidget = QTreeView(
self.mainArea,
selectionMode=QTreeView.ExtendedSelection,
rootIsDecorated=False,
uniformRowHeights=True,
sortingEnabled=True)
self.treeWidget.setItemDelegate(
gui.LinkStyledItemDelegate(self.treeWidget))
self.treeWidget.viewport().setMouseTracking(True)
self.mainArea.layout().addWidget(self.treeWidget)
box = gui.widgetBox(self.mainArea, "", orientation="horizontal")
gui.button(box, self, "Select Filtered", callback=self.selectFiltered)
gui.button(box, self, "Clear Selection",
callback=self.treeWidget.clearSelection)
self.geneinfo = []
self.cells = []
self.row2geneinfo = {}
self.data = None
# : (# input genes, # matches genes)
self.matchedInfo = 0, 0
self.setBlocking(True)
self.executor = ThreadExecutor(self)
self.progressBarInit()
task = Task(
function=partial(
taxonomy.ensure_downloaded,
callback=methodinvoke(self, "advance", ())
)
)
task.resultReady.connect(self.initialize)
task.exceptionReady.connect(self._onInitializeError)
self.initfuture = self.executor.submit(task)
def sizeHint(self):
return QSize(1024, 720)
@Slot()
def advance(self):
assert self.thread() is QThread.currentThread()
self.progressBarSet(self.progressBarValue + 1,
processEvents=None)
def initialize(self):
if self.__initialized:
# Already initialized
return
self.__initialized = True
self.organisms = sorted(
set([name.split(".")[-2] for name in
serverfiles.listfiles("NCBI_geneinfo")] +
gene.NCBIGeneInfo.common_taxids())
)
self.organismComboBox.addItems(
[taxonomy.name(tax_id) for tax_id in self.organisms]
)
if self.taxid in self.organisms:
self.organism_index = self.organisms.index(self.taxid)
else:
self.organism_index = 0
self.taxid = self.organisms[self.organism_index]
self.altSourceCheck.setVisible(self.taxid == DICTY_TAXID)
self.dictyExpressBox.setVisible(self.taxid == DICTY_TAXID)
self.infoLabel.setText("No data on input\n")
self.initfuture = None
self.setBlocking(False)
self.progressBarFinished(processEvents=None)
def _onInitializeError(self, exc):
sys.excepthook(type(exc), exc.args, None)
self.error(0, "Could not download the necessary files.")
def _onSelectedOrganismChanged(self):
assert 0 <= self.organism_index <= len(self.organisms)
self.taxid = self.organisms[self.organism_index]
self.altSourceCheck.setVisible(self.taxid == DICTY_TAXID)
self.dictyExpressBox.setVisible(self.taxid == DICTY_TAXID)
if self.data is not None:
self.updateInfoItems()
def setData(self, data=None):
if not self.__initialized:
self.initfuture.result()
self.initialize()
if self.itemsfuture is not None:
raise Exception("Already processing")
self.closeContext()
self.data = data
if data is not None:
self.geneAttrComboBox.clear()
self.attributes = \
[attr for attr in data.domain.variables + data.domain.metas
if isinstance(attr, (Orange.data.StringVariable,
Orange.data.DiscreteVariable))]
for var in self.attributes:
self.geneAttrComboBox.addItem(*gui.attributeItem(var))
self.taxid = data_hints.get_hint(self.data, "taxid", self.taxid)
self.useAttr = data_hints.get_hint(
self.data, "genesinrows", self.useAttr)
self.openContext(data)
self.gene_attr = min(self.gene_attr, len(self.attributes) - 1)
if self.taxid in self.organisms:
self.organism_index = self.organisms.index(self.taxid)
else:
self.organism_index = 0
self.taxid = self.organisms[self.organism_index]
self.updateInfoItems()
else:
self.clear()
def infoSource(self):
""" Return the current selected info source getter function from
INFO_SOURCES
"""
org = self.organisms[min(self.organism_index, len(self.organisms) - 1)]
if org not in INFO_SOURCES:
org = "default"
sources = INFO_SOURCES[org]
name, func = sources[min(self.useAltSource, len(sources) - 1)]
return name, func
def inputGenes(self):
if self.useAttr:
genes = [attr.name for attr in self.data.domain.attributes]
elif self.attributes:
attr = self.attributes[self.gene_attr]
genes = [str(ex[attr]) for ex in self.data
if not math.isnan(ex[attr])]
else:
genes = []
return genes
def updateInfoItems(self):
self.warning(0)
if self.data is None:
return
genes = self.inputGenes()
if self.useAttr:
genes = [attr.name for attr in self.data.domain.attributes]
elif self.attributes:
attr = self.attributes[self.gene_attr]
genes = [str(ex[attr]) for ex in self.data
if not math.isnan(ex[attr])]
else:
genes = []
if not genes:
self.warning(0, "Could not extract genes from input dataset.")
self.warning(1)
org = self.organisms[min(self.organism_index, len(self.organisms) - 1)]
source_name, info_getter = self.infoSource()
self.error(0)
self.updateDictyExpressLink(genes, show=org == DICTY_TAXID)
self.altSourceCheck.setVisible(org == DICTY_TAXID)
self.progressBarInit()
self.setBlocking(True)
self.setEnabled(False)
self.infoLabel.setText("Retrieving info records.\n")
self.genes = genes
task = Task(
function=partial(
info_getter, org, genes,
advance=methodinvoke(self, "advance", ()))
)
self.itemsfuture = self.executor.submit(task)
task.finished.connect(self._onItemsCompleted)
def _onItemsCompleted(self):
self.setBlocking(False)
self.progressBarFinished()
self.setEnabled(True)
try:
schema, geneinfo = self.itemsfuture.result()
finally:
self.itemsfuture = None
self.geneinfo = geneinfo = list(zip(self.genes, geneinfo))
self.cells = cells = []
self.row2geneinfo = {}
links = []
for i, (_, gi) in enumerate(geneinfo):
if gi:
row = []
for _, item in zip(schema, gi):
if isinstance(item, Link):
# TODO: This should be handled by delegates
row.append(item.text)
links.append(item.link)
else:
row.append(item)
cells.append(row)
self.row2geneinfo[len(cells) - 1] = i
model = TreeModel(cells, [str(col) for col in schema], None)
model.setColumnLinks(0, links)
proxyModel = QSortFilterProxyModel(self)
proxyModel.setSourceModel(model)
self.treeWidget.setModel(proxyModel)
self.treeWidget.selectionModel().selectionChanged.connect(self.commit)
for i in range(7):
self.treeWidget.resizeColumnToContents(i)
self.treeWidget.setColumnWidth(
i, min(self.treeWidget.columnWidth(i), 200)
)
self.infoLabel.setText("%i genes\n%i matched NCBI's IDs" %
(len(self.genes), len(cells)))
self.matchedInfo = len(self.genes), len(cells)
def clear(self):
self.infoLabel.setText("No data on input\n")
self.treeWidget.setModel(
TreeModel([], ["NCBI ID", "Symbol", "Locus Tag",
"Chromosome", "Description", "Synonyms",
"Nomenclature"], self.treeWidget))
self.geneAttrComboBox.clear()
self.send("Data Subset", None)
def commit(self):
if self.data is None:
self.send("Data Subset", None)
return
model = self.treeWidget.model()
selection = self.treeWidget.selectionModel().selection()
selection = model.mapSelectionToSource(selection)
selectedRows = list(
chain(*(range(r.top(), r.bottom() + 1) for r in selection))
)
model = model.sourceModel()
selectedGeneids = [self.row2geneinfo[row] for row in selectedRows]
selectedIds = [self.geneinfo[i][0] for i in selectedGeneids]
selectedIds = set(selectedIds)
gene2row = dict((self.geneinfo[self.row2geneinfo[row]][0], row)
for row in selectedRows)
isselected = selectedIds.__contains__
if self.useAttr:
def is_selected(attr):
return attr.name in selectedIds
attrs = [attr for attr in self.data.domain.attributes
if isselected(attr.name)]
domain = Orange.data.Domain(
attrs, self.data.domain.class_vars, self.data.domain.metas)
newdata = self.data.from_table(domain, self.data)
self.send("Data Subset", newdata)
elif self.attributes:
attr = self.attributes[self.gene_attr]
gene_col = [attr.str_val(v)
for v in self.data.get_column_view(attr)[0]]
gene_col = [(i, name) for i, name in enumerate(gene_col)
if isselected(name)]
indices = [i for i, _ in gene_col]
# Add a gene info columns to the output
headers = [str(model.headerData(i, Qt.Horizontal, Qt.DisplayRole))
for i in range(model.columnCount())]
metas = [Orange.data.StringVariable(name) for name in headers]
domain = Orange.data.Domain(
self.data.domain.attributes, self.data.domain.class_vars,
self.data.domain.metas + tuple(metas))
newdata = self.data.from_table(domain, self.data)[indices]
model_rows = [gene2row[gene] for _, gene in gene_col]
for col, meta in zip(range(model.columnCount()), metas):
col_data = [str(model.index(row, col).data(Qt.DisplayRole))
for row in model_rows]
newdata[:, meta] = col_data
if not len(newdata):
newdata = None
self.send("Data Subset", newdata)
else:
self.send("Data Subset", None)
def rowFiltered(self, row):
searchStrings = self.search_string.lower().split()
row = " ".join(self.cells[row]).lower()
return not all([s in row for s in searchStrings])
def searchUpdate(self):
if not self.data:
return
searchStrings = self.search_string.lower().split()
index = self.treeWidget.model().sourceModel().index
mapFromSource = self.treeWidget.model().mapFromSource
for i, row in enumerate(self.cells):
row = " ".join(row).lower()
self.treeWidget.setRowHidden(
mapFromSource(index(i, 0)).row(),
QModelIndex(),
not all([s in row for s in searchStrings]))
def selectFiltered(self):
if not self.data:
return
itemSelection = QItemSelection()
index = self.treeWidget.model().sourceModel().index
mapFromSource = self.treeWidget.model().mapFromSource
for i, row in enumerate(self.cells):
if not self.rowFiltered(i):
itemSelection.select(mapFromSource(index(i, 0)),
mapFromSource(index(i, 0)))
self.treeWidget.selectionModel().select(
itemSelection,
QItemSelectionModel.Select | QItemSelectionModel.Rows)
def updateDictyExpressLink(self, genes, show=False):
def fix(ddb):
if ddb.startswith("DDB"):
if not ddb.startswith("DDB_G"):
ddb = ddb.replace("DDB", "DDB_G")
return ddb
return None
if show:
genes = [fix(gene) for gene in genes if fix(gene)]
link1 = '<a href="http://dictyexpress.biolab.si/run/index.php?gene=%s">Microarray profile</a>'
link2 = '<a href="http://dictyexpress.biolab.si/run/index.php?gene=%s&db=rnaseq">RNA-Seq profile</a>'
self.linkLabel.setText(link1 + "<br/>" + link2)
show = any(genes)
if show:
self.dictyExpressBox.show()
else:
self.dictyExpressBox.hide()
def onDictyExpressLink(self, link):
if not self.data:
return
selectedIndexes = self.treeWidget.selectedIndexes()
if not len(selectedIndexes):
QMessageBox.information(
self, "No gene ids selected",
"Please select some genes and try again."
)
return
model = self.treeWidget.model()
mapToSource = model.mapToSource
selectedRows = self.treeWidget.selectedIndexes()
selectedRows = [mapToSource(index).row() for index in selectedRows]
model = model.sourceModel()
selectedGeneids = [self.row2geneinfo[row] for row in selectedRows]
selectedIds = [self.geneinfo[i][0] for i in selectedGeneids]
selectedIds = set(selectedIds)
def fix(ddb):
if ddb.startswith("DDB"):
if not ddb.startswith("DDB_G"):
ddb = ddb.replace("DDB", "DDB_G")
return ddb
return None
genes = [fix(gene) for gene in selectedIds if fix(gene)]
url = str(link) % " ".join(genes)
QDesktopServices.openUrl(QUrl(url))
def onAltSourceChange(self):
self.updateInfoItems()
def onDeleteWidget(self):
# try to cancel pending tasks
if self.initfuture:
self.initfuture.cancel()
if self.itemsfuture:
self.itemsfuture.cancel()
self.executor.shutdown(wait=False)
super().onDeleteWidget()
class OWGEODatasets(OWWidget):
name = "GEO Data Sets"
description = DESCRIPTION
icon = "../widgets/icons/GEODataSets.svg"
priority = PRIORITY
inputs = []
outputs = [("Expression Data", Orange.data.Table)]
settingsList = [
"outputRows", "mergeSpots", "gdsSelectionStates", "splitterSettings",
"currentGds", "autoCommit", "datasetNames"
]
outputRows = Setting(True)
mergeSpots = Setting(True)
gdsSelectionStates = Setting({})
currentGds = Setting(None)
datasetNames = Setting({})
splitterSettings = Setting((
b'\x00\x00\x00\xff\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x01\xea\x00\x00\x00\xd7\x01\x00\x00\x00\x07\x01\x00\x00\x00\x02',
b'\x00\x00\x00\xff\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x01\xb5\x00\x00\x02\x10\x01\x00\x00\x00\x07\x01\x00\x00\x00\x01'
))
autoCommit = Setting(False)
def __init__(self, parent=None, signalManager=None, name=" GEO Data Sets"):
OWWidget.__init__(self, parent, signalManager, name)
self.selectionChanged = False
self.filterString = ""
self.datasetName = ""
## GUI
box = gui.widgetBox(self.controlArea, "Info", addSpace=True)
self.infoBox = gui.widgetLabel(box, "Initializing\n\n")
box = gui.widgetBox(self.controlArea, "Output", addSpace=True)
gui.radioButtonsInBox(box,
self,
"outputRows",
["Genes in rows", "Samples in rows"],
"Rows",
callback=self.commitIf)
gui.checkBox(box,
self,
"mergeSpots",
"Merge spots of same gene",
callback=self.commitIf)
gui.separator(box)
self.nameEdit = gui.lineEdit(
box,
self,
"datasetName",
"Data set name",
tooltip="Override the default output data set name",
callback=self.onNameEdited)
self.nameEdit.setPlaceholderText("")
if sys.version_info < (3, ):
box = gui.widgetBox(self.controlArea, "Commit", addSpace=True)
self.commitButton = gui.button(box,
self,
"Commit",
callback=self.commit)
cb = gui.checkBox(box, self, "autoCommit", "Commit on any change")
gui.setStopper(self, self.commitButton, cb, "selectionChanged",
self.commit)
else:
gui.auto_commit(self.controlArea,
self,
"autoCommit",
"Commit",
box="Commit")
self.commitIf = self.commit
gui.rubber(self.controlArea)
gui.widgetLabel(self.mainArea, "Filter")
self.filterLineEdit = QLineEdit(textChanged=self.filter)
self.completer = TokenListCompleter(self,
caseSensitivity=Qt.CaseInsensitive)
self.filterLineEdit.setCompleter(self.completer)
self.mainArea.layout().addWidget(self.filterLineEdit)
splitter = QSplitter(Qt.Vertical, self.mainArea)
self.mainArea.layout().addWidget(splitter)
self.treeWidget = QTreeView(splitter)
self.treeWidget.setSelectionMode(QTreeView.SingleSelection)
self.treeWidget.setRootIsDecorated(False)
self.treeWidget.setSortingEnabled(True)
self.treeWidget.setAlternatingRowColors(True)
self.treeWidget.setUniformRowHeights(True)
self.treeWidget.setEditTriggers(QTreeView.NoEditTriggers)
linkdelegate = LinkStyledItemDelegate(self.treeWidget)
self.treeWidget.setItemDelegateForColumn(1, linkdelegate)
self.treeWidget.setItemDelegateForColumn(8, linkdelegate)
self.treeWidget.setItemDelegateForColumn(
0, gui.IndicatorItemDelegate(self.treeWidget, role=Qt.DisplayRole))
proxyModel = MySortFilterProxyModel(self.treeWidget)
self.treeWidget.setModel(proxyModel)
self.treeWidget.selectionModel().selectionChanged.connect(
self.updateSelection)
self.treeWidget.viewport().setMouseTracking(True)
splitterH = QSplitter(Qt.Horizontal, splitter)
box = gui.widgetBox(splitterH, "Description")
self.infoGDS = gui.widgetLabel(box, "")
self.infoGDS.setWordWrap(True)
gui.rubber(box)
box = gui.widgetBox(splitterH, "Sample Annotations")
self.annotationsTree = QTreeWidget(box)
self.annotationsTree.setHeaderLabels(
["Type (Sample annotations)", "Sample count"])
self.annotationsTree.setRootIsDecorated(True)
box.layout().addWidget(self.annotationsTree)
self.annotationsTree.itemChanged.connect(
self.annotationSelectionChanged)
self._annotationsUpdating = False
self.splitters = splitter, splitterH
for sp, setting in zip(self.splitters, self.splitterSettings):
sp.splitterMoved.connect(self.splitterMoved)
sp.restoreState(setting)
self.searchKeys = [
"dataset_id", "title", "platform_organism", "description"
]
self.gds = []
self.gds_info = None
self.resize(1000, 600)
self.setBlocking(True)
self.setEnabled(False)
self.progressBarInit()
self._executor = ThreadExecutor()
func = partial(get_gds_model,
methodinvoke(self, "_setProgress", (float, )))
self._inittask = Task(function=func)
self._inittask.finished.connect(self._initializemodel)
self._executor.submit(self._inittask)
self._datatask = None
@Slot(float)
def _setProgress(self, value):
self.progressBarValue = value
def _initializemodel(self):
assert self.thread() is QThread.currentThread()
model, self.gds_info, self.gds = self._inittask.result()
model.setParent(self)
proxy = self.treeWidget.model()
proxy.setFilterKeyColumn(0)
proxy.setFilterRole(TextFilterRole)
proxy.setFilterCaseSensitivity(False)
proxy.setFilterFixedString(self.filterString)
proxy.setSourceModel(model)
proxy.sort(0, Qt.DescendingOrder)
self.progressBarFinished()
self.setBlocking(False)
self.setEnabled(True)
filter_items = " ".join(gds[key] for gds in self.gds
for key in self.searchKeys)
tr_chars = ",.:;!?(){}[]_-+\\|/%#@$^&*<>~`"
tr_table = str.maketrans(tr_chars, " " * len(tr_chars))
filter_items = filter_items.translate(tr_table)
filter_items = sorted(set(filter_items.split(" ")))
filter_items = [item for item in filter_items if len(item) > 3]
self.completer.setTokenList(filter_items)
if self.currentGds:
current_id = self.currentGds["dataset_id"]
gdss = [(i, qunpack(proxy.data(proxy.index(i, 1), Qt.DisplayRole)))
for i in range(proxy.rowCount())]
current = [i for i, data in gdss if data and data == current_id]
if current:
current_index = proxy.index(current[0], 0)
self.treeWidget.selectionModel().select(
current_index,
QItemSelectionModel.Select | QItemSelectionModel.Rows)
self.treeWidget.scrollTo(current_index,
QTreeView.PositionAtCenter)
for i in range(8):
self.treeWidget.resizeColumnToContents(i)
self.treeWidget.setColumnWidth(
1, min(self.treeWidget.columnWidth(1), 300))
self.treeWidget.setColumnWidth(
2, min(self.treeWidget.columnWidth(2), 200))
self.updateInfo()
def updateInfo(self):
gds_info = self.gds_info
text = ("%i datasets\n%i datasets cached\n" %
(len(gds_info),
len(glob.glob(serverfiles.localpath("GEO") + "/GDS*"))))
filtered = self.treeWidget.model().rowCount()
if len(self.gds) != filtered:
text += ("%i after filtering") % filtered
self.infoBox.setText(text)
def updateSelection(self, *args):
current = self.treeWidget.selectedIndexes()
mapToSource = self.treeWidget.model().mapToSource
current = [mapToSource(index).row() for index in current]
if current:
self.currentGds = self.gds[current[0]]
self.setAnnotations(self.currentGds)
self.infoGDS.setText(self.currentGds.get("description", ""))
self.nameEdit.setPlaceholderText(self.currentGds["title"])
self.datasetName = \
self.datasetNames.get(self.currentGds["dataset_id"], "")
else:
self.currentGds = None
self.nameEdit.setPlaceholderText("")
self.datasetName = ""
self.commitIf()
def setAnnotations(self, gds):
self._annotationsUpdating = True
self.annotationsTree.clear()
annotations = defaultdict(set)
subsetscount = {}
for desc in gds["subsets"]:
annotations[desc["type"]].add(desc["description"])
subsetscount[desc["description"]] = str(len(desc["sample_id"]))
for type, subsets in annotations.items():
key = (gds["dataset_id"], type)
subsetItem = QTreeWidgetItem(self.annotationsTree, [type])
subsetItem.setFlags(subsetItem.flags() | Qt.ItemIsUserCheckable
| Qt.ItemIsTristate)
subsetItem.setCheckState(
0, self.gdsSelectionStates.get(key, Qt.Checked))
subsetItem.key = key
for subset in subsets:
key = (gds["dataset_id"], type, subset)
item = QTreeWidgetItem(
subsetItem, [subset, subsetscount.get(subset, "")])
item.setFlags(item.flags() | Qt.ItemIsUserCheckable)
item.setCheckState(
0, self.gdsSelectionStates.get(key, Qt.Checked))
item.key = key
self._annotationsUpdating = False
self.annotationsTree.expandAll()
for i in range(self.annotationsTree.columnCount()):
self.annotationsTree.resizeColumnToContents(i)
def annotationSelectionChanged(self, item, column):
if self._annotationsUpdating:
return
for i in range(self.annotationsTree.topLevelItemCount()):
item = self.annotationsTree.topLevelItem(i)
self.gdsSelectionStates[item.key] = item.checkState(0)
for j in range(item.childCount()):
child = item.child(j)
self.gdsSelectionStates[child.key] = child.checkState(0)
def filter(self):
filter_string = unicode(self.filterLineEdit.text())
proxyModel = self.treeWidget.model()
if proxyModel:
strings = filter_string.lower().strip().split()
proxyModel.setFilterFixedStrings(strings)
self.updateInfo()
def selectedSamples(self):
"""
Return the currently selected sample annotations.
The return value is a list of selected (sample type, sample value)
tuples.
.. note:: if some Sample annotation type has no selected values.
this method will return all values for it.
"""
samples = []
unused_types = []
used_types = []
for stype in childiter(self.annotationsTree.invisibleRootItem()):
selected_values = []
all_values = []
for sval in childiter(stype):
value = (str(stype.text(0)), str(sval.text(0)))
if self.gdsSelectionStates.get(sval.key, True):
selected_values.append(value)
all_values.append(value)
if selected_values:
samples.extend(selected_values)
used_types.append(str(stype.text(0)))
else:
# If no sample of sample type is selected we don't filter
# on it.
samples.extend(all_values)
unused_types.append(str(stype.text(0)))
return samples, used_types
def commitIf(self):
if self.autoCommit:
self.commit()
else:
self.selectionChanged = True
@Slot(int, int)
def progressCompleted(self, value, total):
if total > 0:
self.progressBarSet(100. * value / total, processEvents=False)
else:
pass
# TODO: report 'indeterminate progress'
def commit(self):
if self.currentGds:
self.error(0)
sample_type = None
self.progressBarInit(processEvents=None)
_, groups = self.selectedSamples()
if len(groups) == 1 and self.outputRows:
sample_type = groups[0]
self.setEnabled(False)
self.setBlocking(True)
progress = methodinvoke(self, "progressCompleted", (int, int))
def get_data(gds_id, report_genes, transpose, sample_type, title):
gds_ensure_downloaded(gds_id, progress)
gds = geo.GDS(gds_id)
data = gds.getdata(report_genes=report_genes,
transpose=transpose,
sample_type=sample_type)
data.name = title
return data
get_data = partial(get_data,
self.currentGds["dataset_id"],
report_genes=self.mergeSpots,
transpose=self.outputRows,
sample_type=sample_type,
title=self.datasetName
or self.currentGds["title"])
self._datatask = Task(function=get_data)
self._datatask.finished.connect(self._on_dataready)
self._executor.submit(self._datatask)
def _on_dataready(self):
self.setEnabled(True)
self.setBlocking(False)
self.progressBarFinished(processEvents=False)
try:
data = self._datatask.result()
except urlrequest.URLError as error:
self.error(0, ("Error while connecting to the NCBI ftp server! "
"'%s'" % error))
sys.excepthook(type(error), error, getattr(error, "__traceback__"))
return
finally:
self._datatask = None
data_name = data.name
samples, _ = self.selectedSamples()
self.warning(0)
message = None
if self.outputRows:
def samplesinst(ex):
out = []
for meta in data.domain.metas:
out.append((meta.name, ex[meta].value))
if data.domain.class_var.name != 'class':
out.append((data.domain.class_var.name,
ex[data.domain.class_var].value))
return out
samples = set(samples)
mask = [samples.issuperset(samplesinst(ex)) for ex in data]
data = data[numpy.array(mask, dtype=bool)]
if len(data) == 0:
message = "No samples with selected sample annotations."
else:
samples = set(samples)
domain = Orange.data.Domain([
attr for attr in data.domain.attributes
if samples.issuperset(attr.attributes.items())
], data.domain.class_var, data.domain.metas)
# domain.addmetas(data.domain.getmetas())
if len(domain.attributes) == 0:
message = "No samples with selected sample annotations."
stypes = set(s[0] for s in samples)
for attr in domain.attributes:
attr.attributes = dict(
(key, value) for key, value in attr.attributes.items()
if key in stypes)
data = Orange.data.Table(domain, data)
if message is not None:
self.warning(0, message)
data_hints.set_hint(data, "taxid", self.currentGds.get("taxid", ""),
10.0)
data_hints.set_hint(data, "genesinrows", self.outputRows, 10.0)
data.name = data_name
self.send("Expression Data", data)
model = self.treeWidget.model().sourceModel()
row = self.gds.index(self.currentGds)
model.setData(model.index(row, 0), " ", Qt.DisplayRole)
self.updateInfo()
self.selectionChanged = False
def splitterMoved(self, *args):
self.splitterSettings = [
bytes(sp.saveState()) for sp in self.splitters
]
def send_report(self):
self.report_items("GEO Dataset",
[("ID", self.currentGds['dataset_id']),
("Title", self.currentGds['title']),
("Organism", self.currentGds['sample_organism'])])
self.report_items("Data",
[("Samples", self.currentGds['sample_count']),
("Features", self.currentGds['feature_count']),
("Genes", self.currentGds['gene_count'])])
self.report_name("Sample annotations")
subsets = defaultdict(list)
for subset in self.currentGds['subsets']:
subsets[subset['type']].append(
(subset['description'], len(subset['sample_id'])))
self.report_html += "<ul>"
for type in subsets:
self.report_html += "<b>" + type + ":</b></br>"
for desc, count in subsets[type]:
self.report_html += 9 * " " + "<b>{}:</b> {}</br>".format(
desc, count)
self.report_html += "</ul>"
def onDeleteWidget(self):
if self._inittask:
self._inittask.future().cancel()
self._inittask.finished.disconnect(self._initializemodel)
if self._datatask:
self._datatask.future().cancel()
self._datatask.finished.disconnect(self._on_dataready)
self._executor.shutdown(wait=False)
super(OWGEODatasets, self).onDeleteWidget()
def onNameEdited(self):
if self.currentGds:
gds_id = self.currentGds["dataset_id"]
self.datasetNames[gds_id] = unicode(self.nameEdit.text())
self.commitIf()
class OWTestLearners(widget.OWWidget):
name = "Test Learners"
description = ""
icon = "icons/TestLearners1.svg"
priority = 100
inputs = [("Learner", Orange.classification.Learner,
"set_learner", widget.Multiple),
("Data", Orange.data.Table, "set_train_data", widget.Default),
("Test Data", Orange.data.Table, "set_test_data")]
outputs = [("Evaluation Results", testing.Results)]
#: Resampling/testing types
KFold, LeaveOneOut, Bootstrap, TestOnTrain, TestOnTest = 0, 1, 2, 3, 4
#: Selected resampling type
resampling = settings.Setting(0)
#: Number of folds for K-fold cross validation
k_folds = settings.Setting(10)
#: Number of repeats for bootstrap sampling
n_repeat = settings.Setting(10)
#: Bootstrap sampling p
sample_p = settings.Setting(75)
def __init__(self, parent=None):
super().__init__(parent)
self.train_data = None
self.test_data = None
#: An Ordered dictionary with current inputs and their testing
#: results.
self.learners = OrderedDict()
sbox = gui.widgetBox(self.controlArea, "Sampling")
rbox = gui.radioButtons(
sbox, self, "resampling", callback=self._param_changed
)
gui.appendRadioButton(rbox, "Cross validation")
ibox = gui.indentedBox(rbox)
gui.spin(ibox, self, "k_folds", 2, 50, label="Number of folds:",
callback=self.kfold_changed)
gui.appendRadioButton(rbox, "Leave one out")
gui.appendRadioButton(rbox, "Random sampling")
ibox = gui.indentedBox(rbox)
gui.spin(ibox, self, "n_repeat", 2, 50, label="Repeat train/test",
callback=self.bootstrap_changed)
gui.widgetLabel(ibox, "Relative training set size:")
gui.hSlider(ibox, self, "sample_p", minValue=1, maxValue=100,
ticks=20, vertical=False, labelFormat="%d %%",
callback=self.bootstrap_changed)
gui.appendRadioButton(rbox, "Test on train data")
gui.appendRadioButton(rbox, "Test on test data")
rbox.layout().addSpacing(5)
gui.button(rbox, self, "Apply", callback=self.apply)
gui.rubber(self.controlArea)
self.view = QTreeView(
rootIsDecorated=False,
uniformRowHeights=True,
wordWrap=True,
editTriggers=QTreeView.NoEditTriggers
)
header = self.view.header()
header.setResizeMode(QHeaderView.ResizeToContents)
header.setDefaultAlignment(Qt.AlignCenter)
header.setStretchLastSection(False)
self.result_model = QStandardItemModel()
self.view.setModel(self.result_model)
self.view.setItemDelegate(ItemDelegate())
self._update_header()
box = gui.widgetBox(self.mainArea, "Evaluation Results")
box.layout().addWidget(self.view)
def set_learner(self, learner, key):
if key in self.learners and learner is None:
del self.learners[key]
else:
self.learners[key] = Input(learner, None, ())
self._update_stats_model()
def set_train_data(self, data):
self.error(0)
if data is not None:
if data.domain.class_var is None:
self.error(0, "Train data input requires a class variable")
data = None
self.train_data = data
self._update_header()
self._invalidate()
def set_test_data(self, data):
self.error(1)
if data is not None:
if data.domain.class_var is None:
self.error(1, "Test data input requires a class variable")
data = None
self.test_data = data
if self.resampling == OWTestLearners.TestOnTest:
self._invalidate()
def handleNewSignals(self):
self.update_results()
self.commit()
def kfold_changed(self):
self.resampling = OWTestLearners.KFold
self._param_changed()
def bootstrap_changed(self):
self.resampling = OWTestLearners.Bootstrap
self._param_changed()
def _param_changed(self):
self._invalidate()
def update_results(self):
self.warning([1, 2])
self.error(2)
if self.train_data is None:
return
if self.resampling == OWTestLearners.TestOnTest:
if self.test_data is None:
self.warning(2, "Missing separate test data input")
return
elif self.test_data.domain.class_var != \
self.train_data.domain.class_var:
self.error(2, ("Inconsistent class variable between test " +
"and train data sets"))
return
# items in need of an update
items = [(key, input) for key, input in self.learners.items()
if input.results is None]
learners = [input.learner for _, input in items]
self.setStatusMessage("Running")
if self.test_data is not None and \
self.resampling != OWTestLearners.TestOnTest:
self.warning(1, "Test data is present but unused. "
"Select 'Test on test data' to use it.")
# TODO: Test each learner individually
if self.resampling == OWTestLearners.KFold:
results = testing.CrossValidation(
self.train_data, learners, k=self.k_folds, store_data=True
)
elif self.resampling == OWTestLearners.LeaveOneOut:
results = testing.LeaveOneOut(
self.train_data, learners, store_data=True
)
elif self.resampling == OWTestLearners.Bootstrap:
p = self.sample_p / 100.0
results = testing.Bootstrap(
self.train_data, learners, n_resamples=self.n_repeat, p=p,
store_data=True
)
elif self.resampling == OWTestLearners.TestOnTrain:
results = testing.TestOnTrainingData(
self.train_data, learners, store_data=True
)
elif self.resampling == OWTestLearners.TestOnTest:
if self.test_data is None:
return
results = testing.TestOnTestData(
self.train_data, self.test_data, learners, store_data=True
)
else:
assert False
results = list(split_by_model(results))
class_var = self.train_data.domain.class_var
if is_discrete(class_var):
test_stats = classification_stats
else:
test_stats = regression_stats
self._update_header()
stats = [test_stats(res) for res in results]
for (key, input), res, stat in zip(items, results, stats):
self.learners[key] = input._replace(results=res, stats=stat)
self.setStatusMessage("")
self._update_stats_model()
def _update_header(self):
headers = ["Method"]
if self.train_data is not None:
if is_discrete(self.train_data.domain.class_var):
headers.extend(classification_stats.headers)
else:
headers.extend(regression_stats.headers)
for i in reversed(range(len(headers),
self.result_model.columnCount())):
self.result_model.takeColumn(i)
self.result_model.setHorizontalHeaderLabels(headers)
def _update_stats_model(self):
model = self.view.model()
for r in reversed(range(model.rowCount())):
model.takeRow(r)
for input in self.learners.values():
name = learner_name(input.learner)
row = []
head = QStandardItem()
head.setData(name, Qt.DisplayRole)
row.append(head)
for stat in input.stats:
item = QStandardItem()
item.setData(" {:.3f} ".format(stat[0]), Qt.DisplayRole)
row.append(item)
model.appendRow(row)
def _invalidate(self, which=None):
if which is None:
which = self.learners.keys()
all_keys = list(self.learners.keys())
model = self.view.model()
for key in which:
self.learners[key] = \
self.learners[key]._replace(results=None, stats=None)
if key in self.learners:
row = all_keys.index(key)
for c in range(1, model.columnCount()):
item = model.item(row, c)
if item is not None:
item.setData(None, Qt.DisplayRole)
def apply(self):
self.update_results()
self.commit()
def commit(self):
results = [val.results for val in self.learners.values()
if val.results is not None]
if results:
combined = results_merge(results)
combined.learner_names = [learner_name(val.learner)
for val in self.learners.values()]
else:
combined = None
self.send("Evaluation Results", combined)
class OWTestLearners(widget.OWWidget):
name = "Test & Score"
description = "Cross-validation accuracy estimation."
icon = "icons/TestLearners1.svg"
priority = 100
inputs = [("Learner", Learner,
"set_learner", widget.Multiple),
("Data", Table, "set_train_data", widget.Default),
("Test Data", Table, "set_test_data"),
("Preprocessor", Preprocess, "set_preprocessor")]
outputs = [("Predictions", Orange.data.Table),
("Evaluation Results", Orange.evaluation.Results)]
settingsHandler = settings.ClassValuesContextHandler()
#: Resampling/testing types
KFold, LeaveOneOut, ShuffleSplit, TestOnTrain, TestOnTest = 0, 1, 2, 3, 4
#: Selected resampling type
resampling = settings.Setting(0)
#: Number of folds for K-fold cross validation
k_folds = settings.Setting(10)
#: Number of repeats for ShuffleSplit sampling
n_repeat = settings.Setting(10)
#: ShuffleSplit sampling p
sample_p = settings.Setting(75)
TARGET_AVERAGE = "(Average over classes)"
class_selection = settings.ContextSetting(TARGET_AVERAGE)
def __init__(self):
super().__init__()
self.data = None
self.test_data = None
self.preprocessor = None
self.train_data_missing_vals = False
self.test_data_missing_vals = False
#: An Ordered dictionary with current inputs and their testing
#: results.
self.learners = OrderedDict()
sbox = gui.widgetBox(self.controlArea, "Sampling")
rbox = gui.radioButtons(
sbox, self, "resampling", callback=self._param_changed
)
gui.appendRadioButton(rbox, "Cross validation")
ibox = gui.indentedBox(rbox)
gui.spin(ibox, self, "k_folds", 2, 50, label="Number of folds:",
callback=self.kfold_changed)
gui.appendRadioButton(rbox, "Leave one out")
gui.appendRadioButton(rbox, "Random sampling")
ibox = gui.indentedBox(rbox)
gui.spin(ibox, self, "n_repeat", 2, 50, label="Repeat train/test",
callback=self.shuffle_split_changed)
gui.widgetLabel(ibox, "Relative training set size:")
gui.hSlider(ibox, self, "sample_p", minValue=1, maxValue=99,
ticks=20, vertical=False, labelFormat="%d %%",
callback=self.shuffle_split_changed)
gui.appendRadioButton(rbox, "Test on train data")
gui.appendRadioButton(rbox, "Test on test data")
rbox.layout().addSpacing(5)
self.apply_button = gui.button(
rbox, self, "Apply", callback=self.apply, default=True)
self.cbox = gui.widgetBox(self.controlArea, "Target class")
self.class_selection_combo = gui.comboBox(
self.cbox, self, "class_selection", items=[],
sendSelectedValue=True, valueType=str,
callback=self._on_target_class_changed,
contentsLength=8)
gui.rubber(self.controlArea)
self.view = QTreeView(
rootIsDecorated=False,
uniformRowHeights=True,
wordWrap=True,
editTriggers=QTreeView.NoEditTriggers
)
header = self.view.header()
header.setResizeMode(QHeaderView.ResizeToContents)
header.setDefaultAlignment(Qt.AlignCenter)
header.setStretchLastSection(False)
self.result_model = QStandardItemModel(self)
self.result_model.setHorizontalHeaderLabels(["Method"])
self.view.setModel(self.result_model)
self.view.setItemDelegate(ItemDelegate())
box = gui.widgetBox(self.mainArea, "Evaluation Results")
box.layout().addWidget(self.view)
def sizeHint(self):
return QSize(780, 1)
def set_learner(self, learner, key):
"""
Set the input `learner` for `key`.
"""
if key in self.learners and learner is None:
# Removed
del self.learners[key]
else:
self.learners[key] = Input(learner, None, None)
self._invalidate([key])
def set_train_data(self, data):
"""
Set the input training dataset.
"""
self.error(0)
self.information(0)
if data and not data.domain.class_var:
self.error(0, "Train data input requires a class variable")
data = None
if isinstance(data, SqlTable):
if data.approx_len() < AUTO_DL_LIMIT:
data = Table(data)
else:
self.information(0, "Train data has been sampled")
data_sample = data.sample_time(1, no_cache=True)
data_sample.download_data(AUTO_DL_LIMIT, partial=True)
data = Table(data_sample)
self.warning(4)
self.train_data_missing_vals = data is not None and \
np.isnan(data.Y).any()
if self.train_data_missing_vals or self.test_data_missing_vals:
self.warning(4, self._get_missing_data_warning(
self.train_data_missing_vals, self.test_data_missing_vals
))
if data:
data = RemoveNaNClasses(data)
self.data = data
self.closeContext()
if data is not None:
self._update_class_selection()
self.openContext(data.domain.class_var)
self._invalidate()
def set_test_data(self, data):
"""
Set the input separate testing dataset.
"""
self.error(1)
self.information(1)
if data and not data.domain.class_var:
self.error(1, "Test data input requires a class variable")
data = None
if isinstance(data, SqlTable):
if data.approx_len() < AUTO_DL_LIMIT:
data = Table(data)
else:
self.information(1, "Test data has been sampled")
data_sample = data.sample_time(1, no_cache=True)
data_sample.download_data(AUTO_DL_LIMIT, partial=True)
data = Table(data_sample)
self.warning(4)
self.test_data_missing_vals = data is not None and \
np.isnan(data.Y).any()
if self.train_data_missing_vals or self.test_data_missing_vals:
self.warning(4, self._get_missing_data_warning(
self.train_data_missing_vals, self.test_data_missing_vals
))
if data:
data = RemoveNaNClasses(data)
self.test_data = data
if self.resampling == OWTestLearners.TestOnTest:
self._invalidate()
def _get_missing_data_warning(self, train_missing, test_missing):
return "Instances with unknown target values were removed from{}data"\
.format(train_missing * test_missing * " "
or train_missing * " train " or test_missing * " test ")
def set_preprocessor(self, preproc):
"""
Set the input preprocessor to apply on the training data.
"""
self.preprocessor = preproc
self._invalidate()
def handleNewSignals(self):
"""Reimplemented from OWWidget.handleNewSignals."""
self._update_class_selection()
self.apply()
def kfold_changed(self):
self.resampling = OWTestLearners.KFold
self._param_changed()
def shuffle_split_changed(self):
self.resampling = OWTestLearners.ShuffleSplit
self._param_changed()
def _param_changed(self):
self._invalidate()
def _update_results(self):
"""
Run/evaluate the learners.
"""
self.warning([1, 2])
self.error(2)
if self.data is None:
return
class_var = self.data.domain.class_var
if self.resampling == OWTestLearners.TestOnTest:
if self.test_data is None:
self.warning(2, "Missing separate test data input")
return
elif self.test_data.domain.class_var != class_var:
self.error(2, ("Inconsistent class variable between test " +
"and train data sets"))
return
# items in need of an update
items = [(key, slot) for key, slot in self.learners.items()
if slot.results is None]
learners = [slot.learner for _, slot in items]
if len(items) == 0:
return
if self.test_data is not None and \
self.resampling != OWTestLearners.TestOnTest:
self.warning(1, "Test data is present but unused. "
"Select 'Test on test data' to use it.")
rstate = 42
def update_progress(finished):
self.progressBarSet(100 * finished)
common_args = dict(
store_data=True,
preprocessor=self.preprocessor,
callback=update_progress)
self.setStatusMessage("Running")
self.progressBarInit()
try:
if self.resampling == OWTestLearners.KFold:
warnings = []
results = Orange.evaluation.CrossValidation(
self.data, learners, k=self.k_folds, random_state=rstate,
warnings=warnings, **common_args)
if warnings:
self.warning(2, warnings[0])
elif self.resampling == OWTestLearners.LeaveOneOut:
results = Orange.evaluation.LeaveOneOut(
self.data, learners, **common_args)
elif self.resampling == OWTestLearners.ShuffleSplit:
train_size = self.sample_p / 100
results = Orange.evaluation.ShuffleSplit(
self.data, learners, n_resamples=self.n_repeat,
train_size=train_size, test_size=None,
random_state=rstate, **common_args)
elif self.resampling == OWTestLearners.TestOnTrain:
results = Orange.evaluation.TestOnTrainingData(
self.data, learners, **common_args)
elif self.resampling == OWTestLearners.TestOnTest:
results = Orange.evaluation.TestOnTestData(
self.data, self.test_data, learners, **common_args)
else:
assert False
except RuntimeError as e:
self.error(2, str(e))
self.setStatusMessage("")
self.progressBarFinished()
return
learner_key = {slot.learner: key for key, slot in self.learners.items()}
for learner, result in zip(learners, split_by_model(results)):
stats = None
if class_var.is_discrete:
scorers = classification_stats.scores
elif class_var.is_continuous:
scorers = regression_stats.scores
else:
scorers = None
if scorers:
ex = result.failed[0]
if ex:
stats = [Try.Fail(ex)] * len(scorers)
result = Try.Fail(ex)
else:
stats = [Try(lambda: score(result)) for score in scorers]
result = Try.Success(result)
key = learner_key[learner]
self.learners[key] = \
self.learners[key]._replace(results=result, stats=stats)
self.setStatusMessage("")
self.progressBarFinished()
def _update_header(self):
# Set the correct horizontal header labels on the results_model.
headers = ["Method"]
if self.data is not None:
if self.data.domain.has_discrete_class:
headers.extend(classification_stats.headers)
else:
headers.extend(regression_stats.headers)
# remove possible extra columns from the model.
for i in reversed(range(len(headers),
self.result_model.columnCount())):
self.result_model.takeColumn(i)
self.result_model.setHorizontalHeaderLabels(headers)
def _update_stats_model(self):
# Update the results_model with up to date scores.
# Note: The target class specific scores (if requested) are
# computed as needed in this method.
model = self.view.model()
# clear the table model, but preserving the header labels
for r in reversed(range(model.rowCount())):
model.takeRow(r)
target_index = None
if self.data is not None:
class_var = self.data.domain.class_var
if class_var.is_discrete and \
self.class_selection != self.TARGET_AVERAGE:
target_index = class_var.values.index(self.class_selection)
else:
class_var = None
errors = []
has_missing_scores = False
for key, slot in self.learners.items():
name = learner_name(slot.learner)
head = QStandardItem(name)
head.setData(key, Qt.UserRole)
if isinstance(slot.results, Try.Fail):
head.setToolTip(str(slot.results.exception))
head.setText("{} (error)".format(name))
head.setForeground(QtGui.QBrush(Qt.red))
errors.append("{name} failed with error:\n"
"{exc.__class__.__name__}: {exc!s}"
.format(name=name, exc=slot.results.exception))
row = [head]
if class_var is not None and class_var.is_discrete and \
target_index is not None:
if slot.results is not None and slot.results.success:
ovr_results = results_one_vs_rest(
slot.results.value, target_index)
stats = [Try(lambda: score(ovr_results))
for score in classification_stats.scores]
else:
stats = None
else:
stats = slot.stats
if stats is not None:
for stat in stats:
item = QStandardItem()
if stat.success:
item.setText("{:.3f}".format(stat.value[0]))
else:
item.setToolTip(str(stat.exception))
has_missing_scores = True
row.append(item)
model.appendRow(row)
if errors:
self.error(3, "\n".join(errors))
else:
self.error(3)
if has_missing_scores:
self.warning(3, "Some scores could not be computed")
else:
self.warning(3)
def _update_class_selection(self):
self.class_selection_combo.setCurrentIndex(-1)
self.class_selection_combo.clear()
if not self.data:
return
if self.data.domain.has_discrete_class:
self.cbox.setVisible(True)
class_var = self.data.domain.class_var
items = [self.TARGET_AVERAGE] + class_var.values
self.class_selection_combo.addItems(items)
class_index = 0
if self.class_selection in class_var.values:
class_index = class_var.values.index(self.class_selection) + 1
self.class_selection_combo.setCurrentIndex(class_index)
self.class_selection = items[class_index]
else:
self.cbox.setVisible(False)
def _on_target_class_changed(self):
self._update_stats_model()
def _invalidate(self, which=None):
# Invalidate learner results for `which` input keys
# (if None then all learner results are invalidated)
if which is None:
which = self.learners.keys()
model = self.view.model()
statmodelkeys = [model.item(row, 0).data(Qt.UserRole)
for row in range(model.rowCount())]
for key in which:
self.learners[key] = \
self.learners[key]._replace(results=None, stats=None)
if key in statmodelkeys:
row = statmodelkeys.index(key)
for c in range(1, model.columnCount()):
item = model.item(row, c)
if item is not None:
item.setData(None, Qt.DisplayRole)
item.setData(None, Qt.ToolTipRole)
self.apply_button.setEnabled(True)
def apply(self):
self.apply_button.setEnabled(False)
self._update_header()
# Update the view to display the model names
self._update_stats_model()
self._update_results()
self._update_stats_model()
self.commit()
def commit(self):
valid = [slot for slot in self.learners.values()
if slot.results is not None and slot.results.success]
if valid:
# Evaluation results
combined = results_merge([slot.results.value for slot in valid])
combined.learner_names = [learner_name(slot.learner)
for slot in valid]
# Predictions & Probabilities
predictions = combined.get_augmented_data(combined.learner_names)
else:
combined = None
predictions = None
self.send("Evaluation Results", combined)
self.send("Predictions", predictions)
class AddToProject(QDialog):
"""Dialog to let the user choose one of the folders from the opened proj"""
def __init__(self, projects, parent=None):
super(AddToProject, self).__init__(parent)
# pathProjects must be a list
self._projects = projects
self.setWindowTitle("XX")
self.pathSelected = ''
vbox = QVBoxLayout(self)
hbox = QHBoxLayout()
self._list = QListWidget()
for project in self._projects:
self._list.addItem(project['name'])
# self._list.setCurrentRow(0)
self._tree = QTreeView()
# self._tree.header().setHidden(True)
# self._tree.setSelectionMode(QTreeView.SingleSelection)
# self._tree.setAnimated(True)
self.load_tree(self._projects[0])
hbox.addWidget(self._list)
hbox.addWidget(self._tree)
vbox.addLayout(hbox)
hbox2 = QHBoxLayout()
btnAdd = QPushButton("XX")
btnCancel = QPushButton("XX")
hbox2.addWidget(btnCancel)
hbox2.addWidget(btnAdd)
vbox.addLayout(hbox2)
self.connect(btnCancel, SIGNAL("clicked()"), self.close)
self.connect(btnAdd, SIGNAL("clicked()"), self._select_path)
self.connect(
self._list,
SIGNAL("currentItemChanged(QTreeWidgetItem*, QTreeWidgetItem*)"),
self._project_changed)
def _project_changed(self, item, previous):
# FIXME, this is not being called, at least in osx
for each_project in self._projects:
if each_project.name == item.text():
self.load_tree(each_project)
def load_tree(self, project):
"""Load the tree view on the right based on the project selected."""
qfsm = QFileSystemModel()
qfsm.setRootPath(project['path'])
load_index = qfsm.index(qfsm.rootPath())
# qfsm.setFilter(QDir.AllDirs | QDir.NoDotAndDotDot)
# qfsm.setNameFilterDisables(False)
# pext = ["*{0}".format(x) for x in project['extensions']]
# qfsm.setNameFilters(pext)
self._tree.setModel(qfsm)
self._tree.setRootIndex(load_index)
t_header = self._tree.header()
# t_header.setHorizontalScrollMode(QAbstractItemView.ScrollPerPixel)
# t_header.setResizeMode(0, QHeaderView.Stretch)
# t_header.setStretchLastSection(False)
# t_header.setClickable(True)
#
# self._tree.hideColumn(1) # Size
# self._tree.hideColumn(2) # Type
# self._tree.hideColumn(3) # Modification date
# FIXME: Changing the name column's title requires some magic
# Please look at the project tree
def _select_path(self):
"""Set pathSelected to the folder selected in the tree."""
path = self._tree.model().filePath(self._tree.currentIndex())
if path:
self.pathSelected = path
self.close()
class OWGEODatasets(OWWidget):
name = "GEO Data Sets"
description = DESCRIPTION
icon = "../widgets/icons/GEODataSets.svg"
priority = PRIORITY
inputs = []
outputs = [("Expression Data", Orange.data.Table)]
settingsList = ["outputRows", "mergeSpots", "gdsSelectionStates",
"splitterSettings", "currentGds", "autoCommit",
"datasetNames"]
outputRows = Setting(False)
mergeSpots = Setting(True)
gdsSelectionStates = Setting({})
currentGds = Setting(None)
datasetNames = Setting({})
splitterSettings = Setting(
(b'\x00\x00\x00\xff\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x01\xea\x00\x00\x00\xd7\x01\x00\x00\x00\x07\x01\x00\x00\x00\x02',
b'\x00\x00\x00\xff\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x01\xb5\x00\x00\x02\x10\x01\x00\x00\x00\x07\x01\x00\x00\x00\x01')
)
autoCommit = Setting(True)
def __init__(self, parent=None, signalManager=None, name=" GEO Data Sets"):
OWWidget.__init__(self, parent, signalManager, name)
self.selectionChanged = False
self.filterString = ""
self.datasetName = ""
## GUI
box = gui.widgetBox(self.controlArea, "Info", addSpace=True)
self.infoBox = gui.widgetLabel(box, "Initializing\n\n")
box = gui.widgetBox(self.controlArea, "Output", addSpace=True)
gui.radioButtonsInBox(box, self, "outputRows",
["Genes or spots", "Samples"], "Rows",
callback=self.commitIf)
gui.checkBox(box, self, "mergeSpots", "Merge spots of same gene",
callback=self.commitIf)
gui.separator(box)
self.nameEdit = gui.lineEdit(
box, self, "datasetName", "Data set name",
tooltip="Override the default output data set name",
callback=self.onNameEdited
)
self.nameEdit.setPlaceholderText("")
if sys.version_info < (3, ):
box = gui.widgetBox(self.controlArea, "Commit", addSpace=True)
self.commitButton = gui.button(
box, self, "Commit", callback=self.commit)
cb = gui.checkBox(box, self, "autoCommit", "Commit on any change")
gui.setStopper(self, self.commitButton, cb, "selectionChanged",
self.commit)
else:
gui.auto_commit(self.controlArea, self, "autoCommit", "Commit",
box="Commit")
gui.rubber(self.controlArea)
# self.filterLineEdit = OWGUIEx.lineEditHint(
# self.mainArea, self, "filterString", "Filter",
# caseSensitive=False, matchAnywhere=True,
# callback=self.filter, delimiters=" ")
gui.widgetLabel(self.mainArea, "Filter")
self.filterLineEdit = QLineEdit(
textChanged=self.filter
)
self.completer = QCompleter(
caseSensitivity=Qt.CaseInsensitive
)
self.completer.setModel(QStringListModel(self))
self.filterLineEdit.setCompleter(self.completer)
self.mainArea.layout().addWidget(self.filterLineEdit)
splitter = QSplitter(Qt.Vertical, self.mainArea)
self.mainArea.layout().addWidget(splitter)
self.treeWidget = QTreeView(splitter)
self.treeWidget.setSelectionMode(QTreeView.SingleSelection)
self.treeWidget.setRootIsDecorated(False)
self.treeWidget.setSortingEnabled(True)
self.treeWidget.setAlternatingRowColors(True)
self.treeWidget.setUniformRowHeights(True)
self.treeWidget.setEditTriggers(QTreeView.NoEditTriggers)
linkdelegate = LinkStyledItemDelegate(self.treeWidget)
self.treeWidget.setItemDelegateForColumn(1, linkdelegate)
self.treeWidget.setItemDelegateForColumn(8, linkdelegate)
self.treeWidget.setItemDelegateForColumn(
0, gui.IndicatorItemDelegate(self.treeWidget,
role=Qt.DisplayRole))
proxyModel = MySortFilterProxyModel(self.treeWidget)
self.treeWidget.setModel(proxyModel)
self.treeWidget.selectionModel().selectionChanged.connect(
self.updateSelection
)
self.treeWidget.viewport().setMouseTracking(True)
splitterH = QSplitter(Qt.Horizontal, splitter)
box = gui.widgetBox(splitterH, "Description")
self.infoGDS = gui.widgetLabel(box, "")
self.infoGDS.setWordWrap(True)
gui.rubber(box)
box = gui.widgetBox(splitterH, "Sample Annotations")
self.annotationsTree = QTreeWidget(box)
self.annotationsTree.setHeaderLabels(
["Type (Sample annotations)", "Sample count"]
)
self.annotationsTree.setRootIsDecorated(True)
box.layout().addWidget(self.annotationsTree)
self.annotationsTree.itemChanged.connect(
self.annotationSelectionChanged
)
self._annotationsUpdating = False
self.splitters = splitter, splitterH
for sp, setting in zip(self.splitters, self.splitterSettings):
sp.splitterMoved.connect(self.splitterMoved)
sp.restoreState(setting)
self.searchKeys = ["dataset_id", "title", "platform_organism",
"description"]
self.gds = []
self.gds_info = None
self.resize(1000, 600)
self.setBlocking(True)
self.setEnabled(False)
self.progressBarInit()
self._executor = ThreadExecutor()
func = partial(get_gds_model,
methodinvoke(self, "_setProgress", (float,)))
self._inittask = Task(function=func)
self._inittask.finished.connect(self._initializemodel)
self._executor.submit(self._inittask)
self._datatask = None
@Slot(float)
def _setProgress(self, value):
self.progressBarValue = value
def _initializemodel(self):
assert self.thread() is QThread.currentThread()
model, self.gds_info, self.gds = self._inittask.result()
model.setParent(self)
proxy = self.treeWidget.model()
proxy.setFilterKeyColumn(0)
proxy.setFilterRole(TextFilterRole)
proxy.setFilterCaseSensitivity(False)
proxy.setFilterFixedString(self.filterString)
proxy.setSourceModel(model)
proxy.sort(0, Qt.DescendingOrder)
self.progressBarFinished()
self.setBlocking(False)
self.setEnabled(True)
filter_items = " ".join(
gds[key] for gds in self.gds for key in self.searchKeys
)
tr_chars = ",.:;!?(){}[]_-+\\|/%#@$^&*<>~`"
tr_table = str.maketrans(tr_chars, " " * len(tr_chars))
filter_items = filter_items.translate(tr_table)
filter_items = sorted(set(filter_items.split(" ")))
filter_items = [item for item in filter_items if len(item) > 3]
self.completer.model().setStringList(filter_items)
# self.filterLineEdit.setItems(filter_items)
if self.currentGds:
current_id = self.currentGds["dataset_id"]
gdss = [(i, qunpack(proxy.data(proxy.index(i, 1), Qt.DisplayRole)))
for i in range(proxy.rowCount())]
current = [i for i, data in gdss if data and data == current_id]
if current:
current_index = proxy.index(current[0], 0)
self.treeWidget.selectionModel().select(
current_index,
QItemSelectionModel.Select | QItemSelectionModel.Rows
)
self.treeWidget.scrollTo(
current_index, QTreeView.PositionAtCenter)
for i in range(8):
self.treeWidget.resizeColumnToContents(i)
self.treeWidget.setColumnWidth(
1, min(self.treeWidget.columnWidth(1), 300))
self.treeWidget.setColumnWidth(
2, min(self.treeWidget.columnWidth(2), 200))
self.updateInfo()
def updateInfo(self):
gds_info = self.gds_info
text = ("%i datasets\n%i datasets cached\n" %
(len(gds_info),
len(glob.glob(serverfiles.localpath("GEO") + "/GDS*"))))
filtered = self.treeWidget.model().rowCount()
if len(self.gds) != filtered:
text += ("%i after filtering") % filtered
self.infoBox.setText(text)
def updateSelection(self, *args):
current = self.treeWidget.selectedIndexes()
mapToSource = self.treeWidget.model().mapToSource
current = [mapToSource(index).row() for index in current]
if current:
self.currentGds = self.gds[current[0]]
self.setAnnotations(self.currentGds)
self.infoGDS.setText(self.currentGds.get("description", ""))
self.nameEdit.setPlaceholderText(self.currentGds["title"])
self.datasetName = \
self.datasetNames.get(self.currentGds["dataset_id"], "")
else:
self.currentGds = None
self.nameEdit.setPlaceholderText("")
self.datasetName = ""
self.commitIf()
def setAnnotations(self, gds):
self._annotationsUpdating = True
self.annotationsTree.clear()
annotations = defaultdict(set)
subsetscount = {}
for desc in gds["subsets"]:
annotations[desc["type"]].add(desc["description"])
subsetscount[desc["description"]] = str(len(desc["sample_id"]))
for type, subsets in annotations.items():
key = (gds["dataset_id"], type)
subsetItem = QTreeWidgetItem(self.annotationsTree, [type])
subsetItem.setFlags(subsetItem.flags() | Qt.ItemIsUserCheckable |
Qt.ItemIsTristate)
subsetItem.setCheckState(
0, self.gdsSelectionStates.get(key, Qt.Checked)
)
subsetItem.key = key
for subset in subsets:
key = (gds["dataset_id"], type, subset)
item = QTreeWidgetItem(
subsetItem, [subset, subsetscount.get(subset, "")]
)
item.setFlags(item.flags() | Qt.ItemIsUserCheckable)
item.setCheckState(
0, self.gdsSelectionStates.get(key, Qt.Checked)
)
item.key = key
self._annotationsUpdating = False
self.annotationsTree.expandAll()
for i in range(self.annotationsTree.columnCount()):
self.annotationsTree.resizeColumnToContents(i)
def annotationSelectionChanged(self, item, column):
if self._annotationsUpdating:
return
for i in range(self.annotationsTree.topLevelItemCount()):
item = self.annotationsTree.topLevelItem(i)
self.gdsSelectionStates[item.key] = item.checkState(0)
for j in range(item.childCount()):
child = item.child(j)
self.gdsSelectionStates[child.key] = child.checkState(0)
def filter(self):
filter_string = unicode(self.filterLineEdit.text())
proxyModel = self.treeWidget.model()
if proxyModel:
strings = filter_string.lower().strip().split()
proxyModel.setFilterFixedStrings(strings)
self.updateInfo()
def selectedSamples(self):
"""
Return the currently selected sample annotations.
The return value is a list of selected (sample type, sample value)
tuples.
.. note:: if some Sample annotation type has no selected values.
this method will return all values for it.
"""
samples = []
unused_types = []
used_types = []
for stype in childiter(self.annotationsTree.invisibleRootItem()):
selected_values = []
all_values = []
for sval in childiter(stype):
value = (str(stype.text(0)), str(sval.text(0)))
if self.gdsSelectionStates.get(sval.key, True):
selected_values.append(value)
all_values.append(value)
if selected_values:
samples.extend(selected_values)
used_types.append(str(stype.text(0)))
else:
# If no sample of sample type is selected we don't filter
# on it.
samples.extend(all_values)
unused_types.append(str(stype.text(0)))
return samples, used_types
def commitIf(self):
if self.autoCommit:
self.commit()
else:
self.selectionChanged = True
def commit(self):
if self.currentGds:
self.error(0)
sample_type = None
self.progressBarInit()
self.progressBarSet(10)
_, groups = self.selectedSamples()
if len(groups) == 1 and self.outputRows:
sample_type = groups[0]
self.setEnabled(False)
self.setBlocking(True)
def get_data(gds_id, report_genes, transpose, sample_type, title):
gds = geo.GDS(gds_id)
data = gds.getdata(
report_genes=report_genes, transpose=transpose,
sample_type=sample_type
)
data.name = title
return data
get_data = partial(
get_data, self.currentGds["dataset_id"],
report_genes=self.mergeSpots,
transpose=self.outputRows,
sample_type=sample_type,
title=self.datasetName or self.currentGds["title"]
)
self._datatask = Task(function=get_data)
self._datatask.finished.connect(self._on_dataready)
self._executor.submit(self._datatask)
def _on_dataready(self):
self.setEnabled(True)
self.setBlocking(False)
self.progressBarSet(50)
try:
data = self._datatask.result()
except urlrequest.URLError as error:
self.error(0, "Error while connecting to the NCBI ftp server! %r" %
error)
self._datatask = None
self.progressBarFinished()
return
self._datatask = None
data_name = data.name
samples, _ = self.selectedSamples()
self.warning(0)
message = None
if self.outputRows:
def samplesinst(ex):
out = []
for meta in data.domain.metas:
out.append((meta.name, ex[meta].value))
if data.domain.class_var.name != 'class':
out.append((data.domain.class_var.name,
ex[data.domain.class_var].value))
return out
samples = set(samples)
mask = [samples.issuperset(samplesinst(ex)) for ex in data]
data = data[numpy.array(mask, dtype=bool)]
if len(data) == 0:
message = "No samples with selected sample annotations."
else:
samples = set(samples)
domain = Orange.data.Domain(
[attr for attr in data.domain.attributes
if samples.issuperset(attr.attributes.items())],
data.domain.class_var,
data.domain.metas
)
# domain.addmetas(data.domain.getmetas())
if len(domain.attributes) == 0:
message = "No samples with selected sample annotations."
stypes = set(s[0] for s in samples)
for attr in domain.attributes:
attr.attributes = dict(
(key, value) for key, value in attr.attributes.items()
if key in stypes
)
data = Orange.data.Table(domain, data)
if message is not None:
self.warning(0, message)
data_hints.set_hint(data, "taxid", self.currentGds.get("taxid", ""),
10.0)
data_hints.set_hint(data, "genesinrows", self.outputRows, 10.0)
self.progressBarFinished()
data.name = data_name
self.send("Expression Data", data)
model = self.treeWidget.model().sourceModel()
row = self.gds.index(self.currentGds)
model.setData(model.index(row, 0), " ", Qt.DisplayRole)
self.updateInfo()
self.selectionChanged = False
def splitterMoved(self, *args):
self.splitterSettings = [str(sp.saveState()) for sp in self.splitters]
def onDeleteWidget(self):
if self._inittask:
self._inittask.future().cancel()
self._inittask.finished.disconnect(self._initializemodel)
if self._datatask:
self._datatask.future().cancel()
self._datatask.finished.disconnect(self._on_dataready)
self._executor.shutdown(wait=False)
super(OWGEODatasets, self).onDeleteWidget()
def onNameEdited(self):
if self.currentGds:
gds_id = self.currentGds["dataset_id"]
self.datasetNames[gds_id] = unicode(self.nameEdit.text())
self.commitIf()
class OWTestLearners(widget.OWWidget):
name = "Test & Score"
description = "Cross-validation accuracy estimation."
icon = "icons/TestLearners1.svg"
priority = 100
inputs = [("Learner", Learner, "set_learner", widget.Multiple),
("Data", Table, "set_train_data", widget.Default),
("Test Data", Table, "set_test_data"),
("Preprocessor", Preprocess, "set_preprocessor")]
outputs = [("Predictions", Orange.data.Table),
("Evaluation Results", Orange.evaluation.Results)]
settingsHandler = settings.ClassValuesContextHandler()
#: Resampling/testing types
KFold, ShuffleSplit, LeaveOneOut, TestOnTrain, TestOnTest = 0, 1, 2, 3, 4
#: Selected resampling type
resampling = settings.Setting(0)
#: Number of folds for K-fold cross validation
k_folds = settings.Setting(10)
#: Stratified sampling for K-fold
cv_stratified = settings.Setting(True)
#: Number of repeats for ShuffleSplit sampling
n_repeat = settings.Setting(10)
#: ShuffleSplit sampling p
sample_p = settings.Setting(75)
#: Stratified sampling for Random Sampling
shuffle_stratified = settings.Setting(True)
TARGET_AVERAGE = "(Average over classes)"
class_selection = settings.ContextSetting(TARGET_AVERAGE)
def __init__(self):
super().__init__()
self.data = None
self.test_data = None
self.preprocessor = None
self.train_data_missing_vals = False
self.test_data_missing_vals = False
#: An Ordered dictionary with current inputs and their testing
#: results.
self.learners = OrderedDict()
sbox = gui.widgetBox(self.controlArea, "Sampling")
rbox = gui.radioButtons(sbox,
self,
"resampling",
callback=self._param_changed)
gui.appendRadioButton(rbox, "Cross validation")
ibox = gui.indentedBox(rbox)
gui.spin(ibox,
self,
"k_folds",
2,
50,
label="Number of folds:",
callback=self.kfold_changed)
gui.checkBox(ibox,
self,
"cv_stratified",
"Stratified",
callback=self.kfold_changed)
gui.appendRadioButton(rbox, "Random sampling")
ibox = gui.indentedBox(rbox)
gui.spin(ibox,
self,
"n_repeat",
2,
50,
label="Repeat train/test",
callback=self.shuffle_split_changed)
gui.widgetLabel(ibox, "Relative training set size:")
gui.hSlider(ibox,
self,
"sample_p",
minValue=1,
maxValue=99,
ticks=20,
vertical=False,
labelFormat="%d %%",
callback=self.shuffle_split_changed)
gui.checkBox(ibox,
self,
"shuffle_stratified",
"Stratified",
callback=self.shuffle_split_changed)
gui.appendRadioButton(rbox, "Leave one out")
gui.appendRadioButton(rbox, "Test on train data")
gui.appendRadioButton(rbox, "Test on test data")
rbox.layout().addSpacing(5)
self.apply_button = gui.button(rbox,
self,
"Apply",
callback=self.apply,
default=True)
self.cbox = gui.widgetBox(self.controlArea, "Target class")
self.class_selection_combo = gui.comboBox(
self.cbox,
self,
"class_selection",
items=[],
sendSelectedValue=True,
valueType=str,
callback=self._on_target_class_changed,
contentsLength=8)
gui.rubber(self.controlArea)
self.view = QTreeView(rootIsDecorated=False,
uniformRowHeights=True,
wordWrap=True,
editTriggers=QTreeView.NoEditTriggers)
header = self.view.header()
header.setResizeMode(QHeaderView.ResizeToContents)
header.setDefaultAlignment(Qt.AlignCenter)
header.setStretchLastSection(False)
self.result_model = QStandardItemModel(self)
self.result_model.setHorizontalHeaderLabels(["Method"])
self.view.setModel(self.result_model)
self.view.setItemDelegate(ItemDelegate())
box = gui.widgetBox(self.mainArea, "Evaluation Results")
box.layout().addWidget(self.view)
def sizeHint(self):
return QSize(780, 1)
def set_learner(self, learner, key):
"""
Set the input `learner` for `key`.
"""
if key in self.learners and learner is None:
# Removed
del self.learners[key]
else:
self.learners[key] = Input(learner, None, None)
self._invalidate([key])
def set_train_data(self, data):
"""
Set the input training dataset.
"""
self.error(0)
self.information(0)
if data and not data.domain.class_var:
self.error(0, "Train data input requires a class variable")
data = None
if isinstance(data, SqlTable):
if data.approx_len() < AUTO_DL_LIMIT:
data = Table(data)
else:
self.information(0, "Train data has been sampled")
data_sample = data.sample_time(1, no_cache=True)
data_sample.download_data(AUTO_DL_LIMIT, partial=True)
data = Table(data_sample)
self.warning(4)
self.train_data_missing_vals = data is not None and \
np.isnan(data.Y).any()
if self.train_data_missing_vals or self.test_data_missing_vals:
self.warning(
4,
self._get_missing_data_warning(self.train_data_missing_vals,
self.test_data_missing_vals))
if data:
data = RemoveNaNClasses(data)
self.data = data
self.closeContext()
if data is not None:
self._update_class_selection()
self.openContext(data.domain.class_var)
self._invalidate()
def set_test_data(self, data):
"""
Set the input separate testing dataset.
"""
self.error(1)
self.information(1)
if data and not data.domain.class_var:
self.error(1, "Test data input requires a class variable")
data = None
if isinstance(data, SqlTable):
if data.approx_len() < AUTO_DL_LIMIT:
data = Table(data)
else:
self.information(1, "Test data has been sampled")
data_sample = data.sample_time(1, no_cache=True)
data_sample.download_data(AUTO_DL_LIMIT, partial=True)
data = Table(data_sample)
self.warning(4)
self.test_data_missing_vals = data is not None and \
np.isnan(data.Y).any()
if self.train_data_missing_vals or self.test_data_missing_vals:
self.warning(
4,
self._get_missing_data_warning(self.train_data_missing_vals,
self.test_data_missing_vals))
if data:
data = RemoveNaNClasses(data)
self.test_data = data
if self.resampling == OWTestLearners.TestOnTest:
self._invalidate()
def _get_missing_data_warning(self, train_missing, test_missing):
return "Instances with unknown target values were removed from{}data"\
.format(train_missing * test_missing * " "
or train_missing * " train " or test_missing * " test ")
def set_preprocessor(self, preproc):
"""
Set the input preprocessor to apply on the training data.
"""
self.preprocessor = preproc
self._invalidate()
def handleNewSignals(self):
"""Reimplemented from OWWidget.handleNewSignals."""
self._update_class_selection()
self.apply()
def kfold_changed(self):
self.resampling = OWTestLearners.KFold
self._param_changed()
def shuffle_split_changed(self):
self.resampling = OWTestLearners.ShuffleSplit
self._param_changed()
def _param_changed(self):
self._invalidate()
def _update_results(self):
"""
Run/evaluate the learners.
"""
self.warning([1, 2])
self.error([2, 4])
if self.data is None:
return
class_var = self.data.domain.class_var
if self.resampling == OWTestLearners.TestOnTest:
if self.test_data is None:
self.warning(2, "Missing separate test data input")
return
elif self.test_data.domain.class_var != class_var:
self.error(2, ("Inconsistent class variable between test " +
"and train data sets"))
return
# items in need of an update
items = [(key, slot) for key, slot in self.learners.items()
if slot.results is None]
learners = [slot.learner for _, slot in items]
if len(items) == 0:
return
if self.test_data is not None and \
self.resampling != OWTestLearners.TestOnTest:
self.warning(
1, "Test data is present but unused. "
"Select 'Test on test data' to use it.")
rstate = 42
def update_progress(finished):
self.progressBarSet(100 * finished)
common_args = dict(store_data=True,
preprocessor=self.preprocessor,
callback=update_progress)
self.setStatusMessage("Running")
with self.progressBar():
try:
if self.resampling == OWTestLearners.KFold:
if len(self.data) < self.k_folds:
self.error(4, "Number of folds exceeds the data size")
return
warnings = []
results = Orange.evaluation.CrossValidation(
self.data,
learners,
k=self.k_folds,
random_state=rstate,
warnings=warnings,
**common_args)
if warnings:
self.warning(2, warnings[0])
elif self.resampling == OWTestLearners.LeaveOneOut:
results = Orange.evaluation.LeaveOneOut(
self.data, learners, **common_args)
elif self.resampling == OWTestLearners.ShuffleSplit:
train_size = self.sample_p / 100
results = Orange.evaluation.ShuffleSplit(
self.data,
learners,
n_resamples=self.n_repeat,
train_size=train_size,
test_size=None,
stratified=self.shuffle_stratified,
random_state=rstate,
**common_args)
elif self.resampling == OWTestLearners.TestOnTrain:
results = Orange.evaluation.TestOnTrainingData(
self.data, learners, **common_args)
elif self.resampling == OWTestLearners.TestOnTest:
results = Orange.evaluation.TestOnTestData(
self.data, self.test_data, learners, **common_args)
else:
assert False
except RuntimeError as e:
self.error(2, str(e))
self.setStatusMessage("")
return
learner_key = {
slot.learner: key
for key, slot in self.learners.items()
}
for learner, result in zip(learners, split_by_model(results)):
stats = None
if class_var.is_discrete:
scorers = classification_stats.scores
elif class_var.is_continuous:
scorers = regression_stats.scores
else:
scorers = None
if scorers:
ex = result.failed[0]
if ex:
stats = [Try.Fail(ex)] * len(scorers)
result = Try.Fail(ex)
else:
stats = [Try(lambda: score(result)) for score in scorers]
result = Try.Success(result)
key = learner_key[learner]
self.learners[key] = \
self.learners[key]._replace(results=result, stats=stats)
self.setStatusMessage("")
def _update_header(self):
# Set the correct horizontal header labels on the results_model.
headers = ["Method"]
if self.data is not None:
if self.data.domain.has_discrete_class:
headers.extend(classification_stats.headers)
else:
headers.extend(regression_stats.headers)
# remove possible extra columns from the model.
for i in reversed(range(len(headers),
self.result_model.columnCount())):
self.result_model.takeColumn(i)
self.result_model.setHorizontalHeaderLabels(headers)
def _update_stats_model(self):
# Update the results_model with up to date scores.
# Note: The target class specific scores (if requested) are
# computed as needed in this method.
model = self.view.model()
# clear the table model, but preserving the header labels
for r in reversed(range(model.rowCount())):
model.takeRow(r)
target_index = None
if self.data is not None:
class_var = self.data.domain.class_var
if self.data.domain.has_discrete_class and \
self.class_selection != self.TARGET_AVERAGE:
target_index = class_var.values.index(self.class_selection)
else:
class_var = None
errors = []
has_missing_scores = False
for key, slot in self.learners.items():
name = learner_name(slot.learner)
head = QStandardItem(name)
head.setData(key, Qt.UserRole)
if isinstance(slot.results, Try.Fail):
head.setToolTip(str(slot.results.exception))
head.setText("{} (error)".format(name))
head.setForeground(QtGui.QBrush(Qt.red))
errors.append("{name} failed with error:\n"
"{exc.__class__.__name__}: {exc!s}".format(
name=name, exc=slot.results.exception))
row = [head]
if class_var is not None and class_var.is_discrete and \
target_index is not None:
if slot.results is not None and slot.results.success:
ovr_results = results_one_vs_rest(slot.results.value,
target_index)
stats = [
Try(lambda: score(ovr_results))
for score in classification_stats.scores
]
else:
stats = None
else:
stats = slot.stats
if stats is not None:
for stat in stats:
item = QStandardItem()
if stat.success:
item.setText("{:.3f}".format(stat.value[0]))
else:
item.setToolTip(str(stat.exception))
has_missing_scores = True
row.append(item)
model.appendRow(row)
if errors:
self.error(3, "\n".join(errors))
else:
self.error(3)
if has_missing_scores:
self.warning(3, "Some scores could not be computed")
else:
self.warning(3)
def _update_class_selection(self):
self.class_selection_combo.setCurrentIndex(-1)
self.class_selection_combo.clear()
if not self.data:
return
if self.data.domain.has_discrete_class:
self.cbox.setVisible(True)
class_var = self.data.domain.class_var
items = [self.TARGET_AVERAGE] + class_var.values
self.class_selection_combo.addItems(items)
class_index = 0
if self.class_selection in class_var.values:
class_index = class_var.values.index(self.class_selection) + 1
self.class_selection_combo.setCurrentIndex(class_index)
self.class_selection = items[class_index]
else:
self.cbox.setVisible(False)
def _on_target_class_changed(self):
self._update_stats_model()
def _invalidate(self, which=None):
# Invalidate learner results for `which` input keys
# (if None then all learner results are invalidated)
if which is None:
which = self.learners.keys()
model = self.view.model()
statmodelkeys = [
model.item(row, 0).data(Qt.UserRole)
for row in range(model.rowCount())
]
for key in which:
self.learners[key] = \
self.learners[key]._replace(results=None, stats=None)
if key in statmodelkeys:
row = statmodelkeys.index(key)
for c in range(1, model.columnCount()):
item = model.item(row, c)
if item is not None:
item.setData(None, Qt.DisplayRole)
item.setData(None, Qt.ToolTipRole)
self.apply_button.setEnabled(True)
def apply(self):
self.apply_button.setEnabled(False)
self._update_header()
# Update the view to display the model names
self._update_stats_model()
self._update_results()
self._update_stats_model()
self.commit()
def commit(self):
valid = [
slot for slot in self.learners.values()
if slot.results is not None and slot.results.success
]
if valid:
# Evaluation results
combined = results_merge([slot.results.value for slot in valid])
combined.learner_names = [
learner_name(slot.learner) for slot in valid
]
# Predictions & Probabilities
predictions = combined.get_augmented_data(combined.learner_names)
else:
combined = None
predictions = None
self.send("Evaluation Results", combined)
self.send("Predictions", predictions)
def send_report(self):
if not self.data or not self.learners:
return
if self.resampling == self.KFold:
stratified = 'Stratified ' if self.cv_stratified else ''
items = [
("Sampling type",
"{}{}-fold Cross validation".format(stratified, self.k_folds))
]
elif self.resampling == self.LeaveOneOut:
items = [("Sampling type", "Leave one out")]
elif self.resampling == self.ShuffleSplit:
stratified = 'Stratified ' if self.shuffle_stratified else ''
items = [
("Sampling type",
"{}Shuffle split, {} random samples with {}% data ".format(
stratified, self.n_repeat, self.sample_p))
]
elif self.resampling == self.TestOnTrain:
items = [("Sampling type", "No sampling, test on training data")]
elif self.resampling == self.TestOnTest:
items = [("Sampling type", "No sampling, test on testing data")]
else:
items = []
if self.data.domain.has_discrete_class:
items += [("Target class", self.class_selection.strip("()"))]
if items:
self.report_items("Settings", items)
self.report_table("Scores", self.view)
class OWTestLearners(widget.OWWidget):
name = "Test Learners"
description = "Cross-validation accuracy estimation."
icon = "icons/TestLearners1.svg"
priority = 100
inputs = [("Learner", Orange.classification.Learner,
"set_learner", widget.Multiple),
("Data", Orange.data.Table, "set_train_data", widget.Default),
("Test Data", Orange.data.Table, "set_test_data")]
outputs = [("Evaluation Results", Orange.evaluation.Results)]
settingsHandler = settings.ClassValuesContextHandler()
#: Resampling/testing types
KFold, LeaveOneOut, Bootstrap, TestOnTrain, TestOnTest = 0, 1, 2, 3, 4
#: Selected resampling type
resampling = settings.Setting(0)
#: Number of folds for K-fold cross validation
k_folds = settings.Setting(10)
#: Number of repeats for bootstrap sampling
n_repeat = settings.Setting(10)
#: Bootstrap sampling p
sample_p = settings.Setting(75)
class_selection = settings.ContextSetting("(None)")
def __init__(self, parent=None):
super().__init__(parent)
self.train_data = None
self.test_data = None
#: An Ordered dictionary with current inputs and their testing
#: results.
self.learners = OrderedDict()
sbox = gui.widgetBox(self.controlArea, "Sampling")
rbox = gui.radioButtons(
sbox, self, "resampling", callback=self._param_changed
)
gui.appendRadioButton(rbox, "Cross validation")
ibox = gui.indentedBox(rbox)
gui.spin(ibox, self, "k_folds", 2, 50, label="Number of folds:",
callback=self.kfold_changed)
gui.appendRadioButton(rbox, "Leave one out")
gui.appendRadioButton(rbox, "Random sampling")
ibox = gui.indentedBox(rbox)
gui.spin(ibox, self, "n_repeat", 2, 50, label="Repeat train/test",
callback=self.bootstrap_changed)
gui.widgetLabel(ibox, "Relative training set size:")
gui.hSlider(ibox, self, "sample_p", minValue=1, maxValue=100,
ticks=20, vertical=False, labelFormat="%d %%",
callback=self.bootstrap_changed)
gui.appendRadioButton(rbox, "Test on train data")
gui.appendRadioButton(rbox, "Test on test data")
rbox.layout().addSpacing(5)
gui.button(rbox, self, "Apply", callback=self.apply)
self.cbox = gui.widgetBox(self.controlArea, "Target class")
self.class_selection_combo = gui.comboBox(self.cbox, self, "class_selection",
items=[],
callback=self._select_class,
sendSelectedValue=True, valueType=str)
gui.rubber(self.controlArea)
self.view = QTreeView(
rootIsDecorated=False,
uniformRowHeights=True,
wordWrap=True,
editTriggers=QTreeView.NoEditTriggers
)
header = self.view.header()
header.setResizeMode(QHeaderView.ResizeToContents)
header.setDefaultAlignment(Qt.AlignCenter)
header.setStretchLastSection(False)
self.result_model = QStandardItemModel()
self.view.setModel(self.result_model)
self.view.setItemDelegate(ItemDelegate())
self._update_header()
box = gui.widgetBox(self.mainArea, "Evaluation Results")
box.layout().addWidget(self.view)
def set_learner(self, learner, key):
if key in self.learners and learner is None:
del self.learners[key]
else:
self.learners[key] = Input(learner, None, ())
self._update_stats_model()
def set_train_data(self, data):
self.error(0)
if data and not data.domain.class_var:
self.error(0, "Train data input requires a class variable")
data = None
self.train_data = data
self.closeContext()
if data is not None:
self.openContext(data.domain.class_var)
self._update_header()
self._update_class_selection()
self._invalidate()
def set_test_data(self, data):
self.error(1)
if data and not data.domain.class_var:
self.error(1, "Test data input requires a class variable")
data = None
self.test_data = data
if self.resampling == OWTestLearners.TestOnTest:
self._invalidate()
def handleNewSignals(self):
self.update_results()
self.commit()
def kfold_changed(self):
self.resampling = OWTestLearners.KFold
self._param_changed()
def bootstrap_changed(self):
self.resampling = OWTestLearners.Bootstrap
self._param_changed()
def _param_changed(self):
self._invalidate()
def update_results(self):
self.warning([1, 2])
self.error(2)
if self.train_data is None:
return
if self.resampling == OWTestLearners.TestOnTest:
if self.test_data is None:
self.warning(2, "Missing separate test data input")
return
elif self.test_data.domain.class_var != \
self.train_data.domain.class_var:
self.error(2, ("Inconsistent class variable between test " +
"and train data sets"))
return
# items in need of an update
items = [(key, input) for key, input in self.learners.items()
if input.results is None]
learners = [input.learner for _, input in items]
self.setStatusMessage("Running")
if self.test_data is not None and \
self.resampling != OWTestLearners.TestOnTest:
self.warning(1, "Test data is present but unused. "
"Select 'Test on test data' to use it.")
# TODO: Test each learner individually
try:
if self.resampling == OWTestLearners.KFold:
results = Orange.evaluation.CrossValidation(
self.train_data, learners, k=self.k_folds, store_data=True
)
elif self.resampling == OWTestLearners.LeaveOneOut:
results = Orange.evaluation.LeaveOneOut(
self.train_data, learners, store_data=True
)
elif self.resampling == OWTestLearners.Bootstrap:
p = self.sample_p / 100.0
results = Orange.evaluation.Bootstrap(
self.train_data, learners, n_resamples=self.n_repeat, p=p,
store_data=True
)
elif self.resampling == OWTestLearners.TestOnTrain:
results = Orange.evaluation.TestOnTrainingData(
self.train_data, learners, store_data=True
)
elif self.resampling == OWTestLearners.TestOnTest:
if self.test_data is None:
return
results = Orange.evaluation.TestOnTestData(
self.train_data, self.test_data, learners, store_data=True
)
else:
assert False
except Exception as e:
self.error(2, str(e))
return
self.results = results
results = list(split_by_model(results))
class_var = self.train_data.domain.class_var
if class_var.is_discrete:
stats = [classification_stats(self.one_vs_rest(res)) for res in results]
else:
stats = [regression_stats(res) for res in results]
self._update_header()
for (key, input), res, stat in zip(items, results, stats):
self.learners[key] = input._replace(results=res, stats=stat)
self.setStatusMessage("")
self._update_stats_model()
def _update_header(self):
headers = ["Method"]
if self.train_data is not None:
if self.train_data.domain.class_var.is_discrete:
headers.extend(classification_stats.headers)
else:
headers.extend(regression_stats.headers)
for i in reversed(range(len(headers),
self.result_model.columnCount())):
self.result_model.takeColumn(i)
self.result_model.setHorizontalHeaderLabels(headers)
def _update_stats_model(self):
model = self.view.model()
for r in reversed(range(model.rowCount())):
model.takeRow(r)
for input in self.learners.values():
name = learner_name(input.learner)
row = []
head = QStandardItem()
head.setData(name, Qt.DisplayRole)
row.append(head)
for stat in input.stats:
item = QStandardItem()
item.setData(" {:.3f} ".format(stat[0]), Qt.DisplayRole)
row.append(item)
model.appendRow(row)
def _update_class_selection(self):
self.class_selection_combo.clear()
if not self.train_data:
return
if self.train_data.domain.class_var.is_discrete:
self.cbox.setVisible(True)
values = self.train_data.domain.class_var.values
self.class_selection_combo.addItem("(None)")
self.class_selection_combo.addItems(values)
class_index = 0
if self.class_selection in self.train_data.domain.class_var.values:
class_index = self.train_data.domain.class_var.values.index(self.class_selection)+1
else:
self.class_selection = '(None)'
self.class_selection_combo.setCurrentIndex(class_index)
self.previous_class_selection = "(None)"
else:
self.cbox.setVisible(False)
def one_vs_rest(self, res):
if self.class_selection != '(None)' and self.class_selection != 0:
class_ = self.train_data.domain.class_var.values.index(self.class_selection)
actual = res.actual == class_
predicted = res.predicted == class_
return Results(
nmethods=1, domain=self.train_data.domain,
actual=actual, predicted=predicted)
else:
return res
def _select_class(self):
if self.previous_class_selection == self.class_selection:
return
results = list(split_by_model(self.results))
items = [(key, input) for key, input in self.learners.items()]
learners = [input.learner for _, input in items]
class_var = self.train_data.domain.class_var
if class_var.is_discrete:
stats = [classification_stats(self.one_vs_rest(res)) for res in results]
else:
stats = [regression_stats(res) for res in results]
for (key, input), res, stat in zip(items, results, stats):
self.learners[key] = input._replace(results=res, stats=stat)
self.setStatusMessage("")
self._update_stats_model()
self.previous_class_selection = self.class_selection
def _invalidate(self, which=None):
if which is None:
which = self.learners.keys()
all_keys = list(self.learners.keys())
model = self.view.model()
for key in which:
self.learners[key] = \
self.learners[key]._replace(results=None, stats=None)
if key in self.learners:
row = all_keys.index(key)
for c in range(1, model.columnCount()):
item = model.item(row, c)
if item is not None:
item.setData(None, Qt.DisplayRole)
def apply(self):
self.update_results()
self.commit()
def commit(self):
results = [val.results for val in self.learners.values()
if val.results is not None]
if results:
combined = results_merge(results)
combined.learner_names = [learner_name(val.learner)
for val in self.learners.values()]
else:
combined = None
self.send("Evaluation Results", combined)
class VariableTreeBox(QGroupBox):
class VariableTreeButton(QToolButton):
def __init__(self, *args, **kwargs):
QToolButton.__init__(self, *args, **kwargs)
baseIcon = QIcon(":go-next.svg")
secondIcon = QIcon(":go-previous.svg")
self.__icons__ = [baseIcon, secondIcon]
self.setIcon(baseIcon)
def switchIcon(self):
self.__icons__.reverse()
self.setIcon(self.__icons__[0])
def __init__(self, id, name="Choose Variables", model=None):
QGroupBox.__init__(self)
if model is None:
model = TreeModel()
self.setTitle(name)
self.setToolTip("<p>Select variables for analysis</p>")
self.id = id
self.pairs = {}
layout = HBoxLayout()
self.variableTreeView = QTreeView()
self.variableTreeView.setModel(model)
self.variableTreeView.setToolTip("Select variables from here")
self.variableTreeView.setSelectionMode(QAbstractItemView.ExtendedSelection)
self.variableTreeView.installEventFilter(self)
layout.addWidget(self.variableTreeView)
self.widgetsLayout = VBoxLayout()
layout.addLayout(self.widgetsLayout)
self.setLayout(layout)
def addItem(self, widget):
hbox = HBoxLayout()
button = self.VariableTreeButton()
button.setToolTip("Specify variable")
self.connect(button, SIGNAL("clicked()"), self.move)
widget.widget.installEventFilter(self)
hbox.addWidget(button)
hbox.addWidget(widget)
self.widgetsLayout.addLayout(hbox)
self.widgetsLayout.addStretch()
self.pairs[button] = widget
def eventFilter(self, object, event):
if event.type() == QEvent.FocusIn:
self.switchButton(object)
return False
def move(self):
sender = self.sender()
receiver = self.pairs[sender]
path = QString()
if isinstance(receiver, VariableLineEdit):
if receiver.widget.text().isEmpty():
indexes = self.variableTreeView.selectedIndexes()
if len(indexes) < 1:
return
path = self.variableTreeView.model().parentTree(indexes[0])
sender.switchIcon()
receiver.widget.setText(path)
elif isinstance(receiver, VariableListBox):
add = self.variableTreeView.hasFocus()
if add:
indexes = self.variableTreeView.selectedIndexes()
paths = [self.variableTreeView.model().parentTree(index) for index in indexes if index.column() == 0]
receiver.widget.addItems(paths)
else:
indexes = receiver.widget.selectedItems()
for index in indexes:
item = receiver.widget.takeItem(receiver.widget.row(index))
del item
def switchButton(self, sender):
if not isinstance(sender, QLineEdit):
for key, value in self.pairs.iteritems():
if value.widget == sender:
key.setIcon(QIcon(":go-previous.svg"))
else:
key.setIcon(QIcon(":go-next.svg"))
def parameterValues(self):
params = {}
for button, widget in self.pairs.iteritems():
params.update(widget.parameterValues())
return params
class PluginRepositoriesGUI(QWidget):
PATH_COLUMN = 1
ACTIVE_COLUMN = 0
AUTO_UPDATE_COLUMN = 2
STATUS_COLUMN = 3
addRepository = pyqtSignal()
checkForUpdates = pyqtSignal()
def __init__(self, logger, parent):
super(PluginRepositoriesGUI, self).__init__(parent)
self.logger = logger
self._gitHandler = GitHandler(logger)
layout = QVBoxLayout(self)
self._reposTable = QTreeView(self)
self._reposTable.setIndentation(0)
self._reposTable.header().setStretchLastSection(False)
self._reposModel = QStandardItemModel(self._reposTable)
self._initModel()
self._reposTable.setModel(self._reposModel)
self._reposTable.setSelectionMode(QTreeView.ExtendedSelection)
self._reposTable.selectionModel().selectionChanged.connect(self._selectionChanged)
layout.addWidget(self._reposTable)
buttonLayout = QHBoxLayout()
addButton = QPushButton("Add...")
addButton.clicked.connect(self.addRepository)
self._removeButton = QPushButton("Remove")
self._removeButton.setEnabled(False)
self._removeButton.clicked.connect(self._removeSelected)
refreshButton = QPushButton("Check Status")
refreshButton.clicked.connect(self.checkForUpdates)
buttonLayout.addWidget(addButton)
buttonLayout.addWidget(self._removeButton)
buttonLayout.addWidget(refreshButton)
layout.addLayout(buttonLayout)
self._statusWidget = QWidget(self)
self._statusWidget.setVisible(False)
statusLayout = QHBoxLayout(self._statusWidget)
statusLayout.setContentsMargins(0, 0, 0, 0)
self._statusLabel = QLabel(self)
statusLayout.addWidget(self._statusLabel)
layout.addWidget(self._statusWidget)
def clear(self):
self._initModel()
def _updateStatusItem(self, item, path, outdated=None, upToDate=None):
# first check fresh results, then the ones from repositories
if upToDate and path in upToDate:
item.setText(upToDate[path])
if upToDate[path] == GitHandler.UP_TO_DATE_REASON:
item.setData(QColor(0, 255, 0), Qt.DecorationRole)
else:
item.setData(QColor(255, 0, 0), Qt.DecorationRole)
elif outdated and path in outdated:
item.setText("Repository can be updated")
item.setData(QColor(255, 215, 0), Qt.DecorationRole)
elif get_settings().get_plugin_repositories().isUpToDate(path):
item.setText("No updates (for details, check status)")
item.setData(QColor(0, 255, 0), Qt.DecorationRole)
elif get_settings().get_plugin_repositories().isOutdated(path):
item.setText("Repository can be updated")
item.setData(QColor(255, 215, 0), Qt.DecorationRole)
else:
item.setData(None, Qt.DecorationRole)
def updateStatusItems(self, outdated=None, upToDate=None):
for row in xrange(self._reposModel.rowCount()):
path = convert_string(self._reposModel.item(row, self.PATH_COLUMN).data(Qt.DisplayRole).toString())
self._updateStatusItem(self._reposModel.item(row, self.STATUS_COLUMN), path, outdated, upToDate)
def _initModel(self):
from PyQt4.QtCore import QStringList
self._reposModel.clear()
stringList = QStringList([u"Active", u"Path", u"Auto Update", u"Status"])
self._reposModel.setColumnCount(stringList.count())
self._reposModel.setHorizontalHeaderLabels(stringList)
def appendRepository(self, path, active, autoUpdate, canAutoUpdate = None):
activeItem = QStandardItem()
activeItem.setEditable(False)
activeItem.setCheckState(Qt.Checked if active else Qt.Unchecked)
activeItem.setCheckable(True)
pathItem = QStandardItem()
pathItem.setData(path, Qt.DisplayRole)
pathItem.setEditable(False)
autoUpdateItem = QStandardItem()
autoUpdateItem.setEditable(False)
if canAutoUpdate == None:
canAutoUpdate = self._gitHandler.hasGit(path)
if canAutoUpdate:
autoUpdateItem.setCheckState(Qt.Checked if autoUpdate else Qt.Unchecked)
autoUpdateItem.setCheckable(True)
statusItem = QStandardItem()
self._updateStatusItem(statusItem, path)
self._reposModel.appendRow([activeItem, pathItem, autoUpdateItem, statusItem])
def resizeColumns(self):
self._reposTable.resizeColumnToContents(self.ACTIVE_COLUMN)
self._reposTable.resizeColumnToContents(self.AUTO_UPDATE_COLUMN)
self._reposTable.header().setResizeMode(self.PATH_COLUMN, QHeaderView.Stretch)
self._reposTable.header().setResizeMode(self.STATUS_COLUMN, QHeaderView.ResizeToContents)
def getTable(self):
return self._reposTable
@loggingSlot(QItemSelection, QItemSelection)
def _selectionChanged(self, _sel, _desel):
selection = self._reposTable.selectionModel().selectedRows()
self._removeButton.setEnabled(len(selection) > 0)
@loggingSlot()
def _removeSelected(self):
selection = self._reposTable.selectionModel().selectedRows()
for index in selection:
self._reposTable.model().removeRow(index.row())
def setStatus(self, msg, _progress=False):
if msg:
self._statusLabel.setText(msg)
self._statusWidget.setVisible(True)
else:
self._statusWidget.setVisible(False)
class OWTestLearners(widget.OWWidget):
name = "Test Learners"
description = ""
icon = "icons/TestLearners1.svg"
inputs = [("Learner", Orange.classification.Fitter,
"set_learner", widget.Multiple),
("Data", Orange.data.Table, "set_train_data", widget.Default),
("Test Data", Orange.data.Table, "set_test_data")]
outputs = [("Evaluation Results", testing.Results)]
#: Resampling/testing types
KFold, LeaveOneOut, Bootstrap, TestOnTrain, TestOnTest = 0, 1, 2, 3, 4
#: Selected resampling type
resampling = settings.Setting(0)
#: Number of folds for K-fold cross validation
k_folds = settings.Setting(10)
#: Number of repeats for bootstrap sampling
n_repeat = settings.Setting(10)
#: Bootstrap sampling p
sample_p = settings.Setting(75)
def __init__(self, parent=None):
super().__init__(parent)
self.train_data = None
self.test_data = None
#: An Ordered dictionary with current inputs and their testing
#: results.
self.learners = OrderedDict()
sbox = gui.widgetBox(self.controlArea, "Sampling")
rbox = gui.radioButtons(
sbox, self, "resampling", callback=self._param_changed
)
gui.appendRadioButton(rbox, "Cross validation")
ibox = gui.indentedBox(rbox)
gui.spin(ibox, self, "k_folds", 2, 50, label="Number of folds:",
callback=self._param_changed)
gui.appendRadioButton(rbox, "Leave one out")
gui.appendRadioButton(rbox, "Random sampling")
ibox = gui.indentedBox(rbox)
gui.spin(ibox, self, "n_repeat", 2, 50, label="Repeat train/test",
callback=self._param_changed)
gui.widgetLabel(ibox, "Relative training set size:")
gui.hSlider(ibox, self, "sample_p", minValue=1, maxValue=100,
ticks=20, vertical=False,
callback=self._param_changed)
gui.appendRadioButton(rbox, "Test on train data")
gui.appendRadioButton(rbox, "Test on test data")
rbox.layout().addSpacing(5)
gui.button(rbox, self, "Apply", callback=self.apply)
gui.rubber(self.controlArea)
self.view = QTreeView(
rootIsDecorated=False,
uniformRowHeights=True,
wordWrap=True,
editTriggers=QTreeView.NoEditTriggers
)
self.result_model = QStandardItemModel()
self.result_model.setHorizontalHeaderLabels(
["Method"] + classification_stats.headers
)
self.view.setModel(self.result_model)
box = gui.widgetBox(self.mainArea, "Evaluation Results")
box.layout().addWidget(self.view)
def set_learner(self, learner, key):
if key in self.learners and learner is None:
del self.learners[key]
else:
self.learners[key] = Input(learner, None, None)
def set_train_data(self, data):
self.train_data = data
self._invalidate()
if data is not None and is_discrete(data.domain.class_var):
headers = ["Method"] + classification_stats.headers
else:
headers = ["Method"] + regression_stats.headers
self.result_model.setHorizontalHeaderLabels(headers)
def set_test_data(self, data):
self.test_data = data
if self.resampling == OWTestLearners.TestOnTest:
self._invalidate()
def handleNewSignals(self):
self.update_results()
self.commit()
def _param_changed(self):
self._invalidate()
def update_results(self):
# items in need of an update
items = [(key, input) for key, input in self.learners.items()
if input.results is None]
learners = [input.learner for _, input in items]
self.setStatusMessage("Running")
# TODO: Test each learner individually
if self.resampling == OWTestLearners.KFold:
results = testing.CrossValidation(
self.train_data, learners, k=self.k_folds, store_data=True
)
elif self.resampling == OWTestLearners.LeaveOneOut:
results = testing.LeaveOneOut(
self.train_data, learners, store_data=True
)
elif self.resampling == OWTestLearners.Bootstrap:
p = self.sample_p / 100.0
results = testing.Bootstrap(
self.train_data, learners, n_resamples=self.n_repeat, p=p,
store_data=True
)
elif self.resampling == OWTestLearners.TestOnTrain:
results = testing.TestOnTrainingData(
self.train_data, learners, store_data=True
)
elif self.resampling == OWTestLearners.TestOnTest:
assert self.test_data is not None
results = testing.TestOnTestData(
self.train_data, self.test_data, learners, store_data=True
)
else:
assert False
results = list(split_by_model(results))
class_var = self.train_data.domain.class_var
if is_discrete(class_var):
test_stats = classification_stats
else:
test_stats = regression_stats
stats = [test_stats(res) for res in results]
for (key, input), res, stat in zip(items, results, stats):
self.learners[key] = input._replace(results=res, stats=stat)
self.setStatusMessage("")
self._update_stats_model()
def _update_stats_model(self):
model = self.view.model()
for r in reversed(range(model.rowCount())):
model.takeRow(r)
for input in self.learners.values():
name = learner_name(input.learner)
row = []
head = QStandardItem()
head.setData(name, Qt.DisplayRole)
row.append(head)
for stat in input.stats:
item = QStandardItem()
item.setData(float(stat[0]), Qt.DisplayRole)
row.append(item)
model.appendRow(row)
self.view.resizeColumnToContents(0)
def _invalidate(self, which=None):
if which is None:
which = self.learners.keys()
all_keys = list(self.learners.keys())
model = self.view.model()
for key in which:
self.learners[key] = \
self.learners[key]._replace(results=None, stats=None)
if key in self.learners:
row = all_keys.index(key)
for c in range(1, model.columnCount()):
item = model.item(row, c)
item.setData(None, Qt.DisplayRole)
def apply(self):
self.update_results()
self.commit()
def commit(self):
results = [val.results for val in self.learners.values()]
if results:
combined = results_merge(results)
combined.fitter_names = [learner_name(val.learner)
for val in self.learners.values()]
else:
combined = None
self.send("Evaluation Results", combined)
class AddToProject(QDialog):
"""Dialog to let the user choose one of the folders from the opened proj"""
def __init__(self, projects, parent=None):
super(AddToProject, self).__init__(parent)
#pathProjects must be a list
self._projects = projects
self.setWindowTitle(translations.TR_ADD_FILE_TO_PROJECT)
self.pathSelected = ''
vbox = QVBoxLayout(self)
hbox = QHBoxLayout()
self._list = QListWidget()
for project in self._projects:
self._list.addItem(project.name)
self._list.setCurrentRow(0)
self._tree = QTreeView()
#self._tree.header().setHidden(True)
self._tree.setSelectionMode(QTreeView.SingleSelection)
self._tree.setAnimated(True)
self.load_tree(self._projects[0])
hbox.addWidget(self._list)
hbox.addWidget(self._tree)
vbox.addLayout(hbox)
hbox2 = QHBoxLayout()
btnAdd = QPushButton(translations.TR_ADD_HERE)
btnCancel = QPushButton(translations.TR_CANCEL)
hbox2.addWidget(btnCancel)
hbox2.addWidget(btnAdd)
vbox.addLayout(hbox2)
self.connect(btnCancel, SIGNAL("clicked()"), self.close)
self.connect(btnAdd, SIGNAL("clicked()"), self._select_path)
def load_tree(self, project):
"""Load the tree view on the right based on the project selected."""
qfsm = QFileSystemModel()
#FIXME it's not loading the proper folder, just the root /
qfsm.setRootPath(project.path)
qfsm.setFilter(QDir.AllDirs | QDir.NoDotAndDotDot)
qfsm.setNameFilterDisables(False)
pext = ["*{0}".format(x) for x in project.extensions]
qfsm.setNameFilters(pext)
self._tree.setModel(qfsm)
t_header = self._tree.header()
t_header.setHorizontalScrollMode(QAbstractItemView.ScrollPerPixel)
t_header.setResizeMode(0, QHeaderView.Stretch)
t_header.setStretchLastSection(False)
t_header.setClickable(True)
self._tree.hideColumn(1) # Size
self._tree.hideColumn(2) # Type
self._tree.hideColumn(3) # Modification date
def _select_path(self):
"""Set pathSelected to the folder selected in the tree."""
path = self._tree.model().filePath(self._tree.currentIndex())
if path:
self.pathSelected = path
self.close()
class OWGeneInfo(widget.OWWidget):
name = "Gene Info"
description = "Displays gene information from NCBI and other sources."
icon = "../widgets/icons/GeneInfo.svg"
priority = 2010
inputs = [("Data", Orange.data.Table, "setData")]
outputs = [("Data Subset", Orange.data.Table)]
settingsHandler = settings.DomainContextHandler()
organism_index = settings.ContextSetting(0)
taxid = settings.ContextSetting("9606")
gene_attr = settings.ContextSetting(0)
auto_commit = settings.Setting(False)
search_string = settings.Setting("")
useAttr = settings.ContextSetting(False)
useAltSource = settings.ContextSetting(False)
def __init__(self, parent=None, ):
super().__init__(self, parent)
self.selectionChangedFlag = False
self.__initialized = False
self.initfuture = None
self.itemsfuture = None
self.infoLabel = gui.widgetLabel(
gui.widgetBox(self.controlArea, "Info", addSpace=True),
"Initializing\n"
)
self.organisms = None
self.organismBox = gui.widgetBox(
self.controlArea, "Organism", addSpace=True)
self.organismComboBox = gui.comboBox(
self.organismBox, self, "organism_index",
callback=self._onSelectedOrganismChanged)
# For now only support one alt source, with a checkbox
# In the future this can be extended to multiple selections
self.altSourceCheck = gui.checkBox(
self.organismBox, self, "useAltSource",
"Show information from dictyBase",
callback=self.onAltSourceChange)
self.altSourceCheck.hide()
box = gui.widgetBox(self.controlArea, "Gene names", addSpace=True)
self.geneAttrComboBox = gui.comboBox(
box, self, "gene_attr",
"Gene attribute", callback=self.updateInfoItems
)
self.geneAttrComboBox.setEnabled(not self.useAttr)
cb = gui.checkBox(box, self, "useAttr", "Use attribute names",
callback=self.updateInfoItems)
cb.toggled[bool].connect(self.geneAttrComboBox.setDisabled)
gui.auto_commit(self.controlArea, self, "auto_commit", "Commit")
# A label for dictyExpress link (Why oh god why???)
self.dictyExpressBox = gui.widgetBox(
self.controlArea, "Dicty Express")
self.linkLabel = gui.widgetLabel(self.dictyExpressBox, "")
self.linkLabel.setOpenExternalLinks(False)
self.linkLabel.linkActivated.connect(self.onDictyExpressLink)
self.dictyExpressBox.hide()
gui.rubber(self.controlArea)
gui.lineEdit(self.mainArea, self, "search_string", "Filter",
callbackOnType=True, callback=self.searchUpdate)
self.treeWidget = QTreeView(
self.mainArea,
selectionMode=QTreeView.ExtendedSelection,
rootIsDecorated=False,
uniformRowHeights=True,
sortingEnabled=True)
self.treeWidget.setItemDelegate(
gui.LinkStyledItemDelegate(self.treeWidget))
self.treeWidget.viewport().setMouseTracking(True)
self.mainArea.layout().addWidget(self.treeWidget)
box = gui.widgetBox(self.mainArea, "", orientation="horizontal")
gui.button(box, self, "Select Filtered", callback=self.selectFiltered)
gui.button(box, self, "Clear Selection",
callback=self.treeWidget.clearSelection)
self.geneinfo = []
self.cells = []
self.row2geneinfo = {}
self.data = None
# : (# input genes, # matches genes)
self.matchedInfo = 0, 0
self.setBlocking(True)
self.executor = ThreadExecutor(self)
self.progressBarInit()
task = Task(
function=partial(
taxonomy.ensure_downloaded,
callback=methodinvoke(self, "advance", ())
)
)
task.resultReady.connect(self.initialize)
task.exceptionReady.connect(self._onInitializeError)
self.initfuture = self.executor.submit(task)
def sizeHint(self):
return QSize(1024, 720)
@Slot()
def advance(self):
assert self.thread() is QThread.currentThread()
self.progressBarSet(self.progressBarValue + 1,
processEvents=None)
def initialize(self):
if self.__initialized:
# Already initialized
return
self.__initialized = True
self.organisms = sorted(
set([name.split(".")[-2] for name in
serverfiles.listfiles("NCBI_geneinfo")] +
gene.NCBIGeneInfo.common_taxids())
)
self.organismComboBox.addItems(
[taxonomy.name(tax_id) for tax_id in self.organisms]
)
if self.taxid in self.organisms:
self.organism_index = self.organisms.index(self.taxid)
else:
self.organism_index = 0
self.taxid = self.organisms[self.organism_index]
self.altSourceCheck.setVisible(self.taxid == DICTY_TAXID)
self.dictyExpressBox.setVisible(self.taxid == DICTY_TAXID)
self.infoLabel.setText("No data on input\n")
self.initfuture = None
self.setBlocking(False)
self.progressBarFinished(processEvents=None)
def _onInitializeError(self, exc):
sys.excepthook(type(exc), exc.args, None)
self.error(0, "Could not download the necessary files.")
def _onSelectedOrganismChanged(self):
assert 0 <= self.organism_index <= len(self.organisms)
self.taxid = self.organisms[self.organism_index]
self.altSourceCheck.setVisible(self.taxid == DICTY_TAXID)
self.dictyExpressBox.setVisible(self.taxid == DICTY_TAXID)
if self.data is not None:
self.updateInfoItems()
def setData(self, data=None):
if not self.__initialized:
self.initfuture.result()
self.initialize()
if self.itemsfuture is not None:
raise Exception("Already processing")
self.closeContext()
self.data = data
if data is not None:
self.geneAttrComboBox.clear()
self.attributes = \
[attr for attr in data.domain.variables + data.domain.metas
if isinstance(attr, (Orange.data.StringVariable,
Orange.data.DiscreteVariable))]
for var in self.attributes:
self.geneAttrComboBox.addItem(*gui.attributeItem(var))
self.taxid = data_hints.get_hint(self.data, "taxid", self.taxid)
self.useAttr = data_hints.get_hint(
self.data, "genesinrows", self.useAttr)
self.openContext(data)
self.gene_attr = min(self.gene_attr, len(self.attributes) - 1)
if self.taxid in self.organisms:
self.organism_index = self.organisms.index(self.taxid)
else:
self.organism_index = 0
self.taxid = self.organisms[self.organism_index]
self.updateInfoItems()
else:
self.clear()
def infoSource(self):
""" Return the current selected info source getter function from
INFO_SOURCES
"""
org = self.organisms[min(self.organism_index, len(self.organisms) - 1)]
if org not in INFO_SOURCES:
org = "default"
sources = INFO_SOURCES[org]
name, func = sources[min(self.useAltSource, len(sources) - 1)]
return name, func
def inputGenes(self):
if self.useAttr:
genes = [attr.name for attr in self.data.domain.attributes]
elif self.attributes:
attr = self.attributes[self.gene_attr]
genes = [str(ex[attr]) for ex in self.data
if not math.isnan(ex[attr])]
else:
genes = []
return genes
def updateInfoItems(self):
self.warning(0)
if self.data is None:
return
genes = self.inputGenes()
if self.useAttr:
genes = [attr.name for attr in self.data.domain.attributes]
elif self.attributes:
attr = self.attributes[self.gene_attr]
genes = [str(ex[attr]) for ex in self.data
if not math.isnan(ex[attr])]
else:
genes = []
if not genes:
self.warning(0, "Could not extract genes from input dataset.")
self.warning(1)
org = self.organisms[min(self.organism_index, len(self.organisms) - 1)]
source_name, info_getter = self.infoSource()
self.error(0)
self.updateDictyExpressLink(genes, show=org == DICTY_TAXID)
self.altSourceCheck.setVisible(org == DICTY_TAXID)
self.progressBarInit()
self.setBlocking(True)
self.setEnabled(False)
self.infoLabel.setText("Retrieving info records.\n")
self.genes = genes
task = Task(
function=partial(
info_getter, org, genes,
advance=methodinvoke(self, "advance", ()))
)
self.itemsfuture = self.executor.submit(task)
task.finished.connect(self._onItemsCompleted)
def _onItemsCompleted(self):
self.setBlocking(False)
self.progressBarFinished()
self.setEnabled(True)
try:
schema, geneinfo = self.itemsfuture.result()
finally:
self.itemsfuture = None
self.geneinfo = geneinfo = list(zip(self.genes, geneinfo))
self.cells = cells = []
self.row2geneinfo = {}
links = []
for i, (_, gi) in enumerate(geneinfo):
if gi:
row = []
for _, item in zip(schema, gi):
if isinstance(item, Link):
# TODO: This should be handled by delegates
row.append(item.text)
links.append(item.link)
else:
row.append(item)
cells.append(row)
self.row2geneinfo[len(cells) - 1] = i
model = TreeModel(cells, [str(col) for col in schema], None)
model.setColumnLinks(0, links)
proxyModel = QSortFilterProxyModel(self)
proxyModel.setSourceModel(model)
self.treeWidget.setModel(proxyModel)
self.treeWidget.selectionModel().selectionChanged.connect(self.commit)
for i in range(7):
self.treeWidget.resizeColumnToContents(i)
self.treeWidget.setColumnWidth(
i, min(self.treeWidget.columnWidth(i), 200)
)
self.infoLabel.setText("%i genes\n%i matched NCBI's IDs" %
(len(self.genes), len(cells)))
self.matchedInfo = len(self.genes), len(cells)
def clear(self):
self.infoLabel.setText("No data on input\n")
self.treeWidget.setModel(
TreeModel([], ["NCBI ID", "Symbol", "Locus Tag",
"Chromosome", "Description", "Synonyms",
"Nomenclature"], self.treeWidget))
self.geneAttrComboBox.clear()
self.send("Data Subset", None)
def commit(self):
if self.data is None:
self.send("Data Subset", None)
return
model = self.treeWidget.model()
selection = self.treeWidget.selectionModel().selection()
selection = model.mapSelectionToSource(selection)
selectedRows = list(
chain(*(range(r.top(), r.bottom() + 1) for r in selection))
)
model = model.sourceModel()
selectedGeneids = [self.row2geneinfo[row] for row in selectedRows]
selectedIds = [self.geneinfo[i][0] for i in selectedGeneids]
selectedIds = set(selectedIds)
gene2row = dict((self.geneinfo[self.row2geneinfo[row]][0], row)
for row in selectedRows)
isselected = selectedIds.__contains__
if self.useAttr:
def is_selected(attr):
return attr.name in selectedIds
attrs = [attr for attr in self.data.domain.attributes
if isselected(attr.name)]
domain = Orange.data.Domain(
attrs, self.data.domain.class_vars, self.data.domain.metas)
newdata = self.data.from_table(domain, self.data)
self.send("Data Subset", newdata)
elif self.attributes:
attr = self.attributes[self.gene_attr]
gene_col = [attr.str_val(v)
for v in self.data.get_column_view(attr)[0]]
gene_col = [(i, name) for i, name in enumerate(gene_col)
if isselected(name)]
indices = [i for i, _ in gene_col]
# Add a gene info columns to the output
headers = [str(model.headerData(i, Qt.Horizontal, Qt.DisplayRole))
for i in range(model.columnCount())]
metas = [Orange.data.StringVariable(name) for name in headers]
domain = Orange.data.Domain(
self.data.domain.attributes, self.data.domain.class_vars,
self.data.domain.metas + tuple(metas))
newdata = self.data.from_table(domain, self.data)[indices]
model_rows = [gene2row[gene] for _, gene in gene_col]
for col, meta in zip(range(model.columnCount()), metas):
col_data = [str(model.index(row, col).data(Qt.DisplayRole))
for row in model_rows]
col_data = np.array(col_data, dtype=object, ndmin=2).T
newdata[:, meta] = col_data
if not len(newdata):
newdata = None
self.send("Data Subset", newdata)
else:
self.send("Data Subset", None)
def rowFiltered(self, row):
searchStrings = self.search_string.lower().split()
row = " ".join(self.cells[row]).lower()
return not all([s in row for s in searchStrings])
def searchUpdate(self):
if not self.data:
return
searchStrings = self.search_string.lower().split()
index = self.treeWidget.model().sourceModel().index
mapFromSource = self.treeWidget.model().mapFromSource
for i, row in enumerate(self.cells):
row = " ".join(row).lower()
self.treeWidget.setRowHidden(
mapFromSource(index(i, 0)).row(),
QModelIndex(),
not all([s in row for s in searchStrings]))
def selectFiltered(self):
if not self.data:
return
itemSelection = QItemSelection()
index = self.treeWidget.model().sourceModel().index
mapFromSource = self.treeWidget.model().mapFromSource
for i, row in enumerate(self.cells):
if not self.rowFiltered(i):
itemSelection.select(mapFromSource(index(i, 0)),
mapFromSource(index(i, 0)))
self.treeWidget.selectionModel().select(
itemSelection,
QItemSelectionModel.Select | QItemSelectionModel.Rows)
def updateDictyExpressLink(self, genes, show=False):
def fix(ddb):
if ddb.startswith("DDB"):
if not ddb.startswith("DDB_G"):
ddb = ddb.replace("DDB", "DDB_G")
return ddb
return None
if show:
genes = [fix(gene) for gene in genes if fix(gene)]
link1 = '<a href="http://dictyexpress.biolab.si/run/index.php?gene=%s">Microarray profile</a>'
link2 = '<a href="http://dictyexpress.biolab.si/run/index.php?gene=%s&db=rnaseq">RNA-Seq profile</a>'
self.linkLabel.setText(link1 + "<br/>" + link2)
show = any(genes)
if show:
self.dictyExpressBox.show()
else:
self.dictyExpressBox.hide()
def onDictyExpressLink(self, link):
if not self.data:
return
selectedIndexes = self.treeWidget.selectedIndexes()
if not len(selectedIndexes):
QMessageBox.information(
self, "No gene ids selected",
"Please select some genes and try again."
)
return
model = self.treeWidget.model()
mapToSource = model.mapToSource
selectedRows = self.treeWidget.selectedIndexes()
selectedRows = [mapToSource(index).row() for index in selectedRows]
model = model.sourceModel()
selectedGeneids = [self.row2geneinfo[row] for row in selectedRows]
selectedIds = [self.geneinfo[i][0] for i in selectedGeneids]
selectedIds = set(selectedIds)
def fix(ddb):
if ddb.startswith("DDB"):
if not ddb.startswith("DDB_G"):
ddb = ddb.replace("DDB", "DDB_G")
return ddb
return None
genes = [fix(gene) for gene in selectedIds if fix(gene)]
url = str(link) % " ".join(genes)
QDesktopServices.openUrl(QUrl(url))
def onAltSourceChange(self):
self.updateInfoItems()
def onDeleteWidget(self):
# try to cancel pending tasks
if self.initfuture:
self.initfuture.cancel()
if self.itemsfuture:
self.itemsfuture.cancel()
self.executor.shutdown(wait=False)
super().onDeleteWidget()
class Widget(QWidget):
def __init__(self, panel):
super(Widget, self).__init__(panel)
layout = QVBoxLayout()
self.setLayout(layout)
layout.setSpacing(0)
self.searchEntry = SearchLineEdit()
self.treeView = QTreeView(contextMenuPolicy=Qt.CustomContextMenu)
self.textView = QTextBrowser()
applyButton = QToolButton(autoRaise=True)
editButton = QToolButton(autoRaise=True)
addButton = QToolButton(autoRaise=True)
self.menuButton = QPushButton(flat=True)
menu = QMenu(self.menuButton)
self.menuButton.setMenu(menu)
splitter = QSplitter(Qt.Vertical)
top = QHBoxLayout()
layout.addLayout(top)
splitter.addWidget(self.treeView)
splitter.addWidget(self.textView)
layout.addWidget(splitter)
splitter.setSizes([200, 100])
splitter.setCollapsible(0, False)
top.addWidget(self.searchEntry)
top.addWidget(applyButton)
top.addSpacing(10)
top.addWidget(addButton)
top.addWidget(editButton)
top.addWidget(self.menuButton)
# action generator for actions added to search entry
def act(slot, icon=None):
a = QAction(self, triggered=slot)
self.addAction(a)
a.setShortcutContext(Qt.WidgetWithChildrenShortcut)
icon and a.setIcon(icons.get(icon))
return a
# hide if ESC pressed in lineedit
a = act(self.slotEscapePressed)
a.setShortcut(QKeySequence(Qt.Key_Escape))
# import action
a = self.importAction = act(self.slotImport, 'document-open')
menu.addAction(a)
# export action
a = self.exportAction = act(self.slotExport, 'document-save-as')
menu.addAction(a)
# apply button
a = self.applyAction = act(self.slotApply, 'edit-paste')
applyButton.setDefaultAction(a)
menu.addSeparator()
menu.addAction(a)
# add button
a = self.addAction_ = act(self.slotAdd, 'list-add')
a.setShortcut(QKeySequence(Qt.Key_Insert))
addButton.setDefaultAction(a)
menu.addSeparator()
menu.addAction(a)
# edit button
a = self.editAction = act(self.slotEdit, 'document-edit')
a.setShortcut(QKeySequence(Qt.Key_F2))
editButton.setDefaultAction(a)
menu.addAction(a)
# set shortcut action
a = self.shortcutAction = act(self.slotShortcut, 'preferences-desktop-keyboard-shortcuts')
menu.addAction(a)
# delete action
a = self.deleteAction = act(self.slotDelete, 'list-remove')
a.setShortcut(QKeySequence(Qt.CTRL + Qt.Key_Delete))
menu.addAction(a)
# restore action
a = self.restoreAction = act(self.slotRestore)
menu.addSeparator()
menu.addAction(a)
# help button
a = self.helpAction = act(self.slotHelp, 'help-contents')
menu.addSeparator()
menu.addAction(a)
self.treeView.setSelectionBehavior(QTreeView.SelectRows)
self.treeView.setSelectionMode(QTreeView.ExtendedSelection)
self.treeView.setRootIsDecorated(False)
self.treeView.setAllColumnsShowFocus(True)
self.treeView.setModel(model.model())
self.treeView.setCurrentIndex(QModelIndex())
# signals
self.searchEntry.returnPressed.connect(self.slotReturnPressed)
self.searchEntry.textChanged.connect(self.updateFilter)
self.treeView.doubleClicked.connect(self.slotDoubleClicked)
self.treeView.customContextMenuRequested.connect(self.showContextMenu)
self.treeView.selectionModel().currentChanged.connect(self.updateText)
self.treeView.model().dataChanged.connect(self.updateFilter)
# highlight text
self.highlighter = highlight.Highlighter(self.textView.document())
# complete on snippet variables
self.searchEntry.setCompleter(QCompleter([
':icon', ':indent', ':menu', ':name', ':python', ':selection',
':set', ':symbol', ':template', ':template-run'], self.searchEntry))
self.readSettings()
app.settingsChanged.connect(self.readSettings)
app.translateUI(self)
self.updateColumnSizes()
self.setAcceptDrops(True)
def dropEvent(self, ev):
if not ev.source() and ev.mimeData().hasUrls():
filename = ev.mimeData().urls()[0].toLocalFile()
if filename:
ev.accept()
from . import import_export
import_export.load(filename, self)
def dragEnterEvent(self, ev):
if not ev.source() and ev.mimeData().hasUrls():
ev.accept()
def translateUI(self):
try:
self.searchEntry.setPlaceholderText(_("Search..."))
except AttributeError:
pass # not in Qt 4.6
shortcut = lambda a: a.shortcut().toString(QKeySequence.NativeText)
self.menuButton.setText(_("&Menu"))
self.addAction_.setText(_("&Add..."))
self.addAction_.setToolTip(
_("Add a new snippet. ({key})").format(key=shortcut(self.addAction_)))
self.editAction.setText(_("&Edit..."))
self.editAction.setToolTip(
_("Edit the current snippet. ({key})").format(key=shortcut(self.editAction)))
self.shortcutAction.setText(_("Configure Keyboard &Shortcut..."))
self.deleteAction.setText(_("&Remove"))
self.deleteAction.setToolTip(_("Remove the selected snippets."))
self.applyAction.setText(_("A&pply"))
self.applyAction.setToolTip(_("Apply the current snippet."))
self.importAction.setText(_("&Import..."))
self.importAction.setToolTip(_("Import snippets from a file."))
self.exportAction.setText(_("E&xport..."))
self.exportAction.setToolTip(_("Export snippets to a file."))
self.restoreAction.setText(_("Restore &Built-in Snippets..."))
self.restoreAction.setToolTip(
_("Restore deleted or changed built-in snippets."))
self.helpAction.setText(_("&Help"))
self.searchEntry.setToolTip(_(
"Enter text to search in the snippets list.\n"
"See \"What's This\" for more information."))
self.searchEntry.setWhatsThis(''.join(map("<p>{0}</p>\n".format, (
_("Enter text to search in the snippets list, and "
"press Enter to apply the currently selected snippet."),
_("If the search text fully matches the value of the '{name}' variable "
"of a snippet, that snippet is selected.").format(name="name"),
_("If the search text starts with a colon ':', the rest of the "
"search text filters snippets that define the given variable. "
"After a space a value can also be entered, snippets will then "
"match if the value of the given variable contains the text after "
"the space."),
_("E.g. entering {menu} will show all snippets that are displayed "
"in the insert menu.").format(menu="<code>:menu</code>"),
))))
def sizeHint(self):
return self.parent().mainwindow().size() / 4
def readSettings(self):
data = textformats.formatData('editor')
self.textView.setFont(data.font)
self.textView.setPalette(data.palette())
def showContextMenu(self, pos):
"""Called when the user right-clicks the tree view."""
self.menuButton.menu().popup(self.treeView.viewport().mapToGlobal(pos))
def slotReturnPressed(self):
"""Called when the user presses Return in the search entry. Applies current snippet."""
name = self.currentSnippet()
if name:
view = self.parent().mainwindow().currentView()
insert.insert(name, view)
self.parent().hide() # make configurable?
view.setFocus()
def slotEscapePressed(self):
"""Called when the user presses ESC in the search entry. Hides the panel."""
self.parent().hide()
self.parent().mainwindow().currentView().setFocus()
def slotDoubleClicked(self, index):
name = self.treeView.model().name(index)
view = self.parent().mainwindow().currentView()
insert.insert(name, view)
def slotAdd(self):
"""Called when the user wants to add a new snippet."""
edit.Edit(self, None)
def slotEdit(self):
"""Called when the user wants to edit a snippet."""
name = self.currentSnippet()
if name:
edit.Edit(self, name)
def slotShortcut(self):
"""Called when the user selects the Configure Shortcut action."""
from widgets import shortcuteditdialog
name = self.currentSnippet()
if name:
collection = self.parent().snippetActions
action = actions.action(name, None, collection)
default = collection.defaults().get(name)
mgr = actioncollectionmanager.manager(self.parent().mainwindow())
cb = mgr.findShortcutConflict
dlg = shortcuteditdialog.ShortcutEditDialog(self, cb, (collection, name))
if dlg.editAction(action, default):
mgr.removeShortcuts(action.shortcuts())
collection.setShortcuts(name, action.shortcuts())
self.treeView.update()
def slotDelete(self):
"""Called when the user wants to delete the selected rows."""
rows = sorted(set(i.row() for i in self.treeView.selectedIndexes()), reverse=True)
if rows:
for row in rows:
name = self.treeView.model().names()[row]
self.parent().snippetActions.setShortcuts(name, [])
self.treeView.model().removeRow(row)
self.updateFilter()
def slotApply(self):
"""Called when the user clicks the apply button. Applies current snippet."""
name = self.currentSnippet()
if name:
view = self.parent().mainwindow().currentView()
insert.insert(name, view)
def slotImport(self):
"""Called when the user activates the import action."""
filetypes = "{0} (*.xml);;{1} (*)".format(_("XML Files"), _("All Files"))
caption = app.caption(_("dialog title", "Import Snippets"))
filename = None
filename = QFileDialog.getOpenFileName(self, caption, filename, filetypes)
if filename:
from . import import_export
import_export.load(filename, self)
def slotExport(self):
"""Called when the user activates the export action."""
allrows = [row for row in range(model.model().rowCount())
if not self.treeView.isRowHidden(row, QModelIndex())]
selectedrows = [i.row() for i in self.treeView.selectedIndexes()
if i.column() == 0 and i.row() in allrows]
names = self.treeView.model().names()
names = [names[row] for row in selectedrows or allrows]
filetypes = "{0} (*.xml);;{1} (*)".format(_("XML Files"), _("All Files"))
n = len(names)
caption = app.caption(_("dialog title",
"Export {num} Snippet", "Export {num} Snippets", n).format(num=n))
filename = QFileDialog.getSaveFileName(self, caption, None, filetypes)
if filename:
from . import import_export
try:
import_export.save(names, filename)
except (IOError, OSError) as e:
QMessageBox.critical(self, _("Error"), _(
"Can't write to destination:\n\n{url}\n\n{error}").format(
url=filename, error=e.strerror))
def slotRestore(self):
"""Called when the user activates the Restore action."""
from . import restore
dlg = restore.RestoreDialog(self)
dlg.setWindowModality(Qt.WindowModal)
dlg.populate()
dlg.show()
dlg.finished.connect(dlg.deleteLater)
def slotHelp(self):
"""Called when the user clicks the small help button."""
userguide.show("snippets")
def currentSnippet(self):
"""Returns the name of the current snippet if it is visible."""
row = self.treeView.currentIndex().row()
if row != -1 and not self.treeView.isRowHidden(row, QModelIndex()):
return self.treeView.model().names()[row]
def updateFilter(self):
"""Called when the text in the entry changes, updates search results."""
text = self.searchEntry.text()
ltext = text.lower()
filterVars = text.startswith(':')
if filterVars:
try:
fvar, fval = text[1:].split(None, 1)
fhide = lambda v: v.get(fvar) in (True, None) or fval not in v.get(fvar)
except ValueError:
fvar = text[1:].strip()
fhide = lambda v: not v.get(fvar)
for row in range(self.treeView.model().rowCount()):
name = self.treeView.model().names()[row]
nameid = snippets.get(name).variables.get('name', '')
if filterVars:
hide = fhide(snippets.get(name).variables)
elif nameid == text:
i = self.treeView.model().createIndex(row, 0)
self.treeView.selectionModel().setCurrentIndex(i, QItemSelectionModel.SelectCurrent | QItemSelectionModel.Rows)
hide = False
elif nameid.lower().startswith(ltext):
hide = False
elif ltext in snippets.title(name).lower():
hide = False
else:
hide = True
self.treeView.setRowHidden(row, QModelIndex(), hide)
self.updateText()
def updateText(self):
"""Called when the current snippet changes."""
name = self.currentSnippet()
self.textView.clear()
if name:
s = snippets.get(name)
self.highlighter.setPython('python' in s.variables)
self.textView.setPlainText(s.text)
def updateColumnSizes(self):
self.treeView.resizeColumnToContents(0)
self.treeView.resizeColumnToContents(1)
