def startDrag(self, index):
"""start a drag operation with a PandasCellPayload on defined index.
Args:
index (QModelIndex): model index you want to start the drag operation.
"""
if not index.isValid():
return
dataFrame = self.model().dataFrame()
# get all infos from dataFrame
dfindex = dataFrame.iloc[[index.row()]].index
columnName = dataFrame.columns[index.column()]
dtype = dataFrame[columnName].dtype
value = dataFrame[columnName][dfindex]
# create the mime data
mimePayload = PandasCellPayload(dfindex, columnName, value, dtype,
hex(id(self.model())))
mimeData = MimeData()
mimeData.setData(mimePayload)
# create the drag icon and start drag operation
drag = QtGui.QDrag(self)
drag.setMimeData(mimeData)
pixmap = QtGui.QPixmap(":/icons/insert-table.png")
drag.setHotSpot(QtCore.QPoint(pixmap.width() / 3, pixmap.height() / 3))
drag.setPixmap(pixmap)
def removeDataFrameColumns(self, columns):
"""
Removes columns from the dataframe.
:param columns: [(int, str)]
:return: (bool)
True on success, False on failure.
"""
if not self.editable:
return False
if columns:
deleted = 0
errored = False
for (position, name) in columns:
position = position - deleted
if position < 0:
position = 0
self.beginRemoveColumns(QtCore.QModelIndex(), position,
position)
try:
self._dataFrame.drop(name, axis=1, inplace=True)
except ValueError as e:
errored = True
continue
self.endRemoveColumns()
deleted += 1
self.dataChanged.emit()
if errored:
return False
else:
return True
return False
def removeDataFrameRows(self, rows):
"""
Removes rows from the dataframe.
:param rows: (list)
of row indexes to removes.
:return: (bool)
True on success, False on failure.
"""
if not self.editable:
return False
if rows:
position = min(rows)
count = len(rows)
self.beginRemoveRows(QtCore.QModelIndex(), position,
position + count - 1)
removedAny = False
for idx, line in self._dataFrame.iterrows():
if idx in rows:
removedAny = True
self._dataFrame.drop(idx, inplace=True)
if not removedAny:
return False
self._dataFrame.reset_index(inplace=True, drop=True)
self.endRemoveRows()
return True
return False
def test_setDelegates(self, qtbot, tableView, index, value, singleStep):
dlg = createDelegate(numpy.dtype(value), 0, tableView)
assert dlg is not None
data = pandas.DataFrame([value], columns=['A'])
data['A'] = data['A'].astype(value.dtype)
model = tableView.model()
model.setDataFrame(data)
for i, delegate in enumerate([dlg]):
assert tableView.itemDelegateForColumn(i) == delegate
option = QtGui.QStyleOptionViewItem()
option.rect = QtCore.QRect(0, 0, 100, 100)
editor = delegate.createEditor(tableView, option, index)
delegate.setEditorData(editor, index)
assert editor.value() == index.data()
delegate.setModelData(editor, model, index)
delegate.updateEditorGeometry(editor, option, index)
dtype = value.dtype
if dtype in DataFrameModel._intDtypes:
info = numpy.iinfo(dtype)
assert isinstance(delegate, BigIntSpinboxDelegate)
elif dtype in DataFrameModel._floatDtypes:
info = numpy.finfo(dtype)
assert isinstance(delegate, CustomDoubleSpinboxDelegate)
assert delegate.decimals == DataFrameModel._float_precisions[
str(value.dtype)]
assert delegate.maximum == info.max
assert editor.maximum() == info.max
assert delegate.minimum == info.min
assert editor.minimum() == info.min
assert delegate.singleStep == singleStep
assert editor.singleStep() == singleStep
def clickEvent(index):
assert index.isValid()
tableView.clicked.connect(clickEvent)
with qtbot.waitSignal(tableView.clicked) as blocker:
qtbot.mouseClick(tableView.viewport(),
QtCore.Qt.LeftButton,
pos=QtCore.QPoint(10, 10))
assert blocker.signal_triggered
def columnCount(self, index=QtCore.QModelIndex()):
"""returns number of columns
Args:
index (QtCore.QModelIndex, optional): Index to define column and row. defaults to empty QModelIndex
Returns:
number of columns
"""
return len(self.headers)
def rowCount(self, index=QtCore.QModelIndex()):
"""returns number of rows
Args:
index (QtCore.QModelIndex, optional): Index to define column and row. defaults to empty QModelIndex
Returns:
number of rows
"""
return len(self._dataFrame.columns)
def __init__(self, parent=None):
"""Constructs the object with the given parent.
Args:
parent (QObject, optional): Causes the objected to be owned
by `parent` instead of Qt. Defaults to `None`.
"""
super(DelimiterValidator, self).__init__(parent)
re = QtCore.QRegExp('\S{1}')
self.setRegExp(re)
def __init__(self, parent=None, iconSize=QtCore.QSize(36, 36)):
"""Constructs the object with the given parent.
Args:
parent (QObject, optional): Causes the objected to be owned
by `parent` instead of Qt. Defaults to `None`.
iconSize (QSize, optional): Size of edit buttons. Defaults to QSize(36, 36).
"""
super(DataTableWidget, self).__init__(parent)
self._iconSize = iconSize
self.initUi()
def columnCount(self, index=QtCore.QModelIndex()):
"""returns number of columns
Args:
index (QtCore.QModelIndex, optional): Index to define column and row. defaults to empty QModelIndex
Returns:
number of columns
"""
# speed comparison:
# In [23]: %timeit len(df.columns)
# 10000000 loops, best of 3: 108 ns per loop
# In [24]: %timeit df.shape[1]
# 1000000 loops, best of 3: 440 ns per loop
return len(self._dataFrame.columns)
def addDataFrameRows(self, count=1):
"""
Adds rows to the dataframe.
:param count: (int)
The number of rows to add to the dataframe.
:return: (bool)
True on success, False on failure.
"""
# don't allow any gaps in the data rows.
# and always append at the end
if not self.editable:
return False
position = self.rowCount()
if count < 1:
return False
if len(self.dataFrame().columns) == 0:
# log an error message or warning
return False
# Note: This function emits the rowsAboutToBeInserted() signal which
# connected views (or proxies) must handle before the data is
# inserted. Otherwise, the views may end up in an invalid state.
self.beginInsertRows(QtCore.QModelIndex(), position,
position + count - 1)
defaultValues = []
for dtype in self._dataFrame.dtypes:
if dtype.type == numpy.dtype('<M8[ns]'):
val = pandas.Timestamp('')
elif dtype.type == numpy.dtype(object):
val = ''
else:
val = dtype.type()
defaultValues.append(val)
for i in range(count):
self._dataFrame.loc[position + i] = defaultValues
self._dataFrame.reset_index()
self.endInsertRows()
return True
def rowCount(self, index=QtCore.QModelIndex()):
"""returns number of rows
Args:
index (QtCore.QModelIndex, optional): Index to define column and row. defaults to empty QModelIndex
Returns:
number of rows
"""
# len(df.index) is faster, so use it:
# In [12]: %timeit df.shape[0]
# 1000000 loops, best of 3: 437 ns per loop
# In [13]: %timeit len(df.index)
# 10000000 loops, best of 3: 110 ns per loop
# %timeit df.__len__()
# 1000000 loops, best of 3: 215 ns per loop
return len(self._dataFrame.index)
def createThread(parent, worker, deleteWorkerLater=False):
"""Create a new thread for given worker.
Args:
parent (QObject): parent of thread and worker.
worker (ProgressWorker): worker to use in thread.
deleteWorkerLater (bool, optional): delete the worker if thread finishes.
Returns:
QThread
"""
thread = QtCore.QThread(parent)
thread.started.connect(worker.doWork)
worker.finished.connect(thread.quit)
if deleteWorkerLater:
thread.finished.connect(worker.deleteLater)
worker.moveToThread(thread)
worker.setParent(parent)
return thread
def addDataFrameColumn(self, columnName, dtype=str, defaultValue=None):
"""
Adds a column to the dataframe as long as
the model's editable property is set to True and the
dtype is supported.
:param columnName: str
name of the column.
:param dtype: qtpandas.models.SupportedDtypes option
:param defaultValue: (object)
to default the column's value to, should be the same as the dtype or None
:return: (bool)
True on success, False otherwise.
"""
if not self.editable or dtype not in SupportedDtypes.allTypes():
return False
elements = self.rowCount()
columnPosition = self.columnCount()
newColumn = pandas.Series([defaultValue] * elements,
index=self._dataFrame.index,
dtype=dtype)
self.beginInsertColumns(QtCore.QModelIndex(), columnPosition - 1,
columnPosition - 1)
try:
self._dataFrame.insert(columnPosition,
columnName,
newColumn,
allow_duplicates=False)
except ValueError as e:
# columnName does already exist
return False
self.endInsertColumns()
self.propagateDtypeChanges(columnPosition, newColumn.dtype)
return True
def __init__(self, parent=None):
"""the __init__ method.
Args:
parent (QObject): defaults to None. If parent is 0, the new widget becomes a window.
If parent is another widget, this widget becomes a child window inside parent.
The new widget is deleted when its parent is deleted.
"""
super(BigIntSpinbox, self).__init__(parent)
self._singleStep = 1
self._minimum = -18446744073709551616
self._maximum = 18446744073709551615
rx = QtCore.QRegExp("[0-9]\\d{0,20}")
validator = QtGui.QRegExpValidator(rx, self)
self._lineEdit = QtGui.QLineEdit(self)
self._lineEdit.setText('0')
self._lineEdit.setValidator(validator)
self.setLineEdit(self._lineEdit)
def test_data(self, dataframe):
model = ColumnDtypeModel(dataFrame=dataframe)
index = model.index(0, 0)
# get data for display role
ret = index.data()
assert ret == 'Foo'
# edit role does the same as display role
ret = index.data(Qt.EditRole)
assert ret == 'Foo'
# datatype only defined for column 1
ret = index.data(DTYPE_ROLE)
assert ret == None
# datatype column
index = index.sibling(0, 1)
ret = index.data(DTYPE_ROLE)
assert ret == numpy.dtype(numpy.int64)
# check translation / display text
assert index.data(
) == 'integer (64 bit)' == SupportedDtypes.description(ret)
# column not defined
index = index.sibling(0, 2)
assert index.data(DTYPE_ROLE) == None
# invalid index
index = QtCore.QModelIndex()
assert model.data(index) == None
index = model.index(2, 0)
# get data for display role
ret = index.data()
assert ret == 'Spam'
def test_invalidIndex(self, model):
assert model.setData(QtCore.QModelIndex(), None) == False
def test_invalidIndex(self, model):
assert model.data(QtCore.QModelIndex()) is None
class DataFrameModelManager(QtCore.QObject):
"""
A central storage unit for managing
DataFrameModels.
"""
signalNewModelRead = QtCore.Signal(str)
signalModelDestroyed = QtCore.Signal(str)
def __init__(self):
QtCore.QObject.__init__(self)
self._models = {}
self._updates = defaultdict(list)
self._paths_read = []
self._paths_updated = []
@property
def file_paths(self):
"""Returns a list of the currently stored file paths"""
return list(self._models.keys())
@property
def models(self):
"""Returns a list of all currently stored DataFrameModels"""
return list(self._models.values())
@property
def last_path_read(self):
"""Returns the last path read (via the DataFrameModelManager.read_file method)"""
if self._paths_read:
return self._paths_read[-1]
else:
return None
@property
def last_path_updated(self):
"""Returns the last path to register an update. (or None)"""
if self._paths_updated:
return self._paths_updated[-1]
else:
return None
def save_file(self, filepath, save_as=None, keep_orig=False, **kwargs):
"""
Saves a DataFrameModel to a file.
:param filepath: (str)
The filepath of the DataFrameModel to save.
:param save_as: (str, default None)
The new filepath to save as.
:param keep_orig: (bool, default False)
True keeps the original filepath/DataFrameModel if save_as is specified.
:param kwargs:
pandas.DataFrame.to_excel(**kwargs) if .xlsx
pandas.DataFrame.to_csv(**kwargs) otherwise.
:return: None
"""
df = self._models[filepath].dataFrame()
kwargs['index'] = kwargs.get('index', False)
if save_as is not None:
to_path = save_as
else:
to_path = filepath
ext = os.path.splitext(to_path)[1].lower()
if ext == ".xlsx":
kwargs.pop('sep', None)
df.to_excel(to_path, **kwargs)
elif ext in ['.csv', '.txt']:
df.to_csv(to_path, **kwargs)
else:
raise NotImplementedError(
"Cannot save file of type {}".format(ext))
if save_as is not None:
if keep_orig is False:
# Re-purpose the original model
# Todo - capture the DataFrameModelManager._updates too
model = self._models.pop(filepath)
model._filePath = to_path
else:
# Create a new model.
model = DataFrameModel()
model.setDataFrame(df, copyDataFrame=True, filePath=to_path)
self._models[to_path] = model
def set_model(self, df_model, file_path):
"""
Sets a DataFrameModel and registers it to the given file_path.
:param df_model: (DataFrameModel)
The DataFrameModel to register.
:param file_path:
The file path to associate with the DataFrameModel.
*Overrides the current filePath on the DataFrameModel (if any)
:return: None
"""
assert isinstance(
df_model,
DataFrameModel), "df_model argument must be a DataFrameModel!"
df_model._filePath = file_path
try:
self._models[file_path]
except KeyError:
self.signalNewModelRead.emit(file_path)
self._models[file_path] = df_model
def get_model(self, filepath):
"""
Returns the DataFrameModel registered to filepath
"""
return self._models[filepath]
def get_frame(self, filepath):
"""Returns the DataFrameModel.dataFrame() registered to filepath """
return self._models[filepath].dataFrame()
def update_file(self, filepath, df, notes=None):
"""
Sets a new DataFrame for the DataFrameModel registered to filepath.
:param filepath (str)
The filepath to the DataFrameModel to be updated
:param df (pandas.DataFrame)
The new DataFrame to register to the model.
:param notes (str, default None)
Optional notes to register along with the update.
"""
assert isinstance(
df,
pd.DataFrame), "Cannot update file with type '{}'".format(type(df))
self._models[filepath].setDataFrame(df, copyDataFrame=False)
if notes:
update = dict(date=pd.Timestamp(datetime.datetime.now()),
notes=notes)
self._updates[filepath].append(update)
self._paths_updated.append(filepath)
def remove_file(self, filepath):
"""
Removes the DataFrameModel from being registered.
:param filepath: (str)
The filepath to delete from the DataFrameModelManager.
:return: None
"""
self._models.pop(filepath)
self._updates.pop(filepath, default=None)
self.signalModelDestroyed.emit(filepath)
def read_file(self, filepath, **kwargs):
"""
Reads a filepath into a DataFrameModel and registers
it.
Example use:
dfmm = DataFrameModelManger()
dfmm.read_file(path_to_file)
dfm = dfmm.get_model(path_to_file)
df = dfm.get_frame(path_to_file)
:param filepath: (str)
The filepath to read
:param kwargs:
.xlsx files: pandas.read_excel(**kwargs)
.csv files: pandas.read_csv(**kwargs)
:return: DataFrameModel
"""
try:
model = self._models[filepath]
except KeyError:
model = read_file(filepath, **kwargs)
self._models[filepath] = model
self.signalNewModelRead.emit(filepath)
finally:
self._paths_read.append(filepath)
return self._models[filepath]
class DataFrameExportDialog(CSVExportDialog):
"""
Extends the CSVExportDialog with support for
exporting to .txt and .xlsx
"""
signalExportFilenames = QtCore.Signal(str, str)
signalModelChanged = QtCore.Signal(DataFrameModel)
def __init__(self, model=None, parent=None):
CSVExportDialog.__init__(self, model=None, parent=None)
if model is not None:
self._filename = model.filePath
else:
self._filename = None
self._windowTitle = "Export Data"
self.setWindowTitle(self._windowTitle)
@Slot(DataFrameModel)
def swapModel(self, model):
good = self.setExportModel(model)
if good:
self.signalModelChanged.emit(model)
@Slot()
def accepted(self):
"""Successfully close the widget and emit an export signal.
This method is also a `SLOT`.
The dialog will be closed, when the `Export Data` button is
pressed. If errors occur during the export, the status bar
will show the error message and the dialog will not be closed.
"""
#return super(DataFrameExportDialog, self).accepted
try:
self._saveModel()
except Exception as err:
self._statusBar.showMessage(str(err))
raise
else:
self._resetWidgets()
self.exported.emit(True)
self.accept()
@Slot()
def rejected(self):
"""Close the widget and reset its inital state.
This method is also a `SLOT`.
The dialog will be closed and all changes reverted, when the
`cancel` button is pressed.
"""
self._resetWidgets()
self.exported.emit(False)
self.reject()
def _saveModel(self):
"""
Reimplements _saveModel to utilize all of the
Pandas export options based on file extension.
:return: None
"""
delimiter = self._delimiterBox.currentSelected()
header = self._headerCheckBox.isChecked() # column labels
if self._filename is None:
filename = self._filenameLineEdit.text()
else:
filename = self._filename
ext = os.path.splitext(filename)[1].lower()
index = False # row labels
encodingIndex = self._encodingComboBox.currentIndex()
encoding = self._encodingComboBox.itemText(encodingIndex)
encoding = _calculateEncodingKey(encoding.lower())
try:
dataFrame = self._model.dataFrame()
except AttributeError as err:
raise AttributeError('No data loaded to export.')
else:
print("Identifying export type for {}".format(filename))
try:
if ext in ['.txt', '.csv']:
dataFrame.to_csv(filename,
encoding=encoding,
header=header,
index=index,
sep=delimiter)
elif ext == '.tsv':
sep = '\t'
dataFrame.to_csv(filename,
encoding=encoding,
header=header,
index=index,
sep=delimiter)
elif ext in ['.xlsx', '.xls']:
dataFrame.to_excel(filename,
encoding=encoding,
header=header,
index=index,
sep=delimiter)
except IOError as err:
raise IOError('No filename given')
except UnicodeError as err:
raise UnicodeError(
'Could not encode all data. Choose a different encoding')
except Exception:
raise
self.signalExportFilenames.emit(self._model._filePath, filename)