def validateLabels(self):
"""
This is run at the end of the label combining process (see
scripts/combine_labels.py) to validate the resulting ground truth windows,
specifically that they are distinct (unique, non-overlapping).
"""
with open(os.path.join(self.path)) as windowFile:
windows = json.load(windowFile)
self.windows = {}
for relativePath in windows.keys():
self.windows[relativePath] = deepmap(strp, windows[relativePath])
if len(self.windows[relativePath]) == 0:
continue
num_windows = len(self.windows[relativePath])
if num_windows > 1:
if not all(
[(self.windows[relativePath][i + 1][0] -
self.windows[relativePath][i][1]).total_seconds() >= 0
for i in xrange(num_windows - 1)]):
raise ValueError("In the label file %s, windows overlap." %
self.path)
def getWindows(self):
"""
Get windows as dictionaries with key value pairs of a relative path and its
corresponding list of windows.
"""
def found(t, data):
f = data["timestamp"][data["timestamp"] == pandas.tslib.Timestamp(t)]
exists = (len(f) == 1)
if not exists:
print t, "doesn't exist"
return exists
with open(os.path.join(self.path)) as windowFile:
windows = json.load(windowFile)
self.windows = {}
for relativePath in windows.keys():
self.windows[relativePath] = deepmap(strp, windows[relativePath])
if len(self.windows[relativePath]) == 0:
continue
data = self.corpus.dataFiles[relativePath].data
timestamps = list(itertools.chain(windows[relativePath]))[0]
if not all(map((lambda t: found(t, data)), timestamps)):
raise ValueError("timestamp listed in labels doesn't exist in file")
def getWindows(self):
"""
Read JSON label file. Get timestamps as dictionaries with key:value pairs of
a relative path and its corresponding list of windows.
"""
def found(t, data):
f = data["timestamp"][data["timestamp"] == pandas.tslib.Timestamp(t)]
exists = (len(f) == 1)
return exists
with open(os.path.join(self.path)) as windowFile:
windows = json.load(windowFile)
self.windows = {}
for relativePath in windows.keys():
self.windows[relativePath] = deepmap(strp, windows[relativePath])
if len(self.windows[relativePath]) == 0:
continue
data = self.corpus.dataFiles[relativePath].data
if "raw" in self.path:
timestamps = windows[relativePath]
else:
timestamps = list(itertools.chain.from_iterable(windows[relativePath]))
def getWindows(self):
"""
Get windows as dictionaries with key value pairs of a relative path and its
corresponding list of windows.
"""
with open(os.path.join(self.labelDir, "corpus_windows.json")) as windowFile:
windows = json.load(windowFile)
self.rawWindows = windows
self.windows = {}
for relativePath in windows.keys():
self.windows[relativePath] = deepmap(strp, windows[relativePath])
def getWindows(self):
"""
Read JSON label file. Get timestamps as dictionaries with key:value pairs of
a relative path and its corresponding list of windows.
"""
def found(t, data):
f = data["timestamp"][data["timestamp"] == pandas.tslib.Timestamp(
t)]
exists = (len(f) == 1)
return exists
with open(os.path.join(self.path)) as windowFile:
windows = json.load(windowFile)
print(windows)
self.windows = {}
for relativePath in windows.keys():
self.windows[relativePath] = deepmap(strp, windows[relativePath])
if len(self.windows[relativePath]) == 0:
continue
data = self.corpus.dataFiles[relativePath].data
if "raw" in self.path:
timestamps = windows[relativePath]
else:
timestamps = list(
itertools.chain.from_iterable(windows[relativePath]))
# Check that timestamps are present in dataset
if not all([found(t, data) for t in timestamps]):
raise ValueError(
"In the label file %s, one of the timestamps used for "
"the datafile %s doesn't match; it does not exist in "
"the file. Timestamps in json label files have to "
"exactly match timestamps in corresponding datafiles." %
(self.path, relativePath))
def getWindows(self):
"""
Read JSON label file. Get windows as dictionaries with key value pairs of a
relative path and its
corresponding list of windows.
"""
def found(t, data):
f = data["timestamp"][data["timestamp"] == pandas.tslib.Timestamp(t)]
exists = (len(f) == 1)
if not exists:
print t, "doesn't exist"
return exists
with open(os.path.join(self.path)) as windowFile:
windows = json.load(windowFile)
self.windows = {}
for relativePath in windows.keys():
self.windows[relativePath] = deepmap(strp, windows[relativePath])
if len(self.windows[relativePath]) == 0:
continue
data = self.corpus.dataFiles[relativePath].data
timestamps = list(itertools.chain(windows[relativePath]))[0]
if not all(map((lambda t: found(t, data)), timestamps)):
raise ValueError("In the label file %s, one of the timestamps used for "
"the datafile %s doesn't exist in the file itself. "
"Timestamps in json label files have to exactly match "
"timestamps in corresponding datafiles." %
(self.path,relativePath) )
def getWindows(self):
"""
Read JSON label file. Get timestamps as dictionaries with key:value pairs of
a relative path and its corresponding list of windows.
"""
def found(t, data):
f = data["timestamp"][data["timestamp"] == pandas.tslib.Timestamp(
t)]
exists = (len(f) == 1)
return exists
with open(os.path.join(self.path)) as windowFile:
windows = json.load(windowFile)
self.windows = {}
for relativePath in windows.keys():
self.windows[relativePath] = deepmap(strp, windows[relativePath])
if len(self.windows[relativePath]) == 0:
continue
def getWindows(self):
"""
Read JSON label file. Get timestamps as dictionaries with key:value pairs of
a relative path and its corresponding list of windows.
"""
def found(t, data):
f = data["timestamp"][data["timestamp"] == pandas.tslib.Timestamp(t)]
exists = (len(f) == 1)
return exists
with open(os.path.join(self.path)) as windowFile:
windows = json.load(windowFile)
self.windows = {}
for relativePath in windows.keys():
self.windows[relativePath] = deepmap(strp, windows[relativePath])
if len(self.windows[relativePath]) == 0:
continue
data = self.corpus.dataFiles[relativePath].data
if "raw" in self.path:
timestamps = windows[relativePath]
else:
timestamps = list(itertools.chain.from_iterable(windows[relativePath]))
# Check that timestamps are present in dataset
if not all([found(t,data) for t in timestamps]):
raise ValueError("In the label file %s, one of the timestamps used for "
"the datafile %s doesn't match; it does not exist in "
"the file. Timestamps in json label files have to "
"exactly match timestamps in corresponding datafiles."
% (self.path, relativePath))
def validateLabels(self):
"""
This is run at the end of the label combining process (see
scripts/combine_labels.py) to validate the resulting ground truth windows,
specifically that they are distinct (unique, non-overlapping).
"""
with open(os.path.join(self.path)) as windowFile:
windows = json.load(windowFile)
self.windows = {}
for relativePath in windows.keys():
self.windows[relativePath] = deepmap(strp, windows[relativePath])
if len(self.windows[relativePath]) == 0:
continue
num_windows = len(self.windows[relativePath])
if num_windows > 1:
if not all([(self.windows[relativePath][i+1][0]
- self.windows[relativePath][i][1]).total_seconds() >= 0
for i in xrange(num_windows-1)]):
raise ValueError("In the label file %s, windows overlap." % self.path)
