def setUp(self):
self.timeseries = NamedTimeseries(csvPath=TEST_DATA_PATH)
self.model = te.loada(ANTIMONY_MODEL)
def testMissingData(self):
if IGNORE_TEST:
return
with self.assertRaises(ValueError):
timeseries = NamedTimeseries(csvPath=TEST_BAD_DATA_PATH)
class TestNamedTimeseries(unittest.TestCase):
def setUp(self):
self.timeseries = NamedTimeseries(csvPath=TEST_DATA_PATH)
self.model = te.loada(ANTIMONY_MODEL)
def tearDown(self):
if os.path.isfile(TEMP_FILE):
os.remove(TEMP_FILE)
def testConstructor1(self):
if IGNORE_TEST:
return
self.assertGreater(len(self.timeseries.values), 0)
# colnames doesn't include TIME
self.assertEqual(len(self.timeseries.colnames),
np.shape(self.timeseries.values)[1] - 1)
#
newTS = self.timeseries.copy(isInitialize=True)
self.assertEqual(np.sum(newTS[self.timeseries.colnames[0]]), 0)
def testConstructor2(self):
if IGNORE_TEST:
return
COLNAMES = [TIME, "S1", "S2"]
def test(timeseries, colnames=COLNAMES):
for name in colnames:
self.assertTrue(
np.isclose(sum(timeseries[name] - self.timeseries[name]),
0))
#
newTS = NamedTimeseries(colnames=COLNAMES,
array=self.timeseries[COLNAMES])
test(newTS)
# Check can use different cases for TIME
newTS = NamedTimeseries(colnames=["Time", "S1", "S2"],
array=self.timeseries[COLNAMES])
test(newTS)
def testConstructorNamedArray(self):
if IGNORE_TEST:
return
namedArray = self.model.simulate(0, 100, 30)
ts = NamedTimeseries(namedArray=namedArray)
self.assertTrue(
namedTimeseries.arrayEquals(namedArray.flatten(),
ts.values.flatten()))
def testSizeof(self):
if IGNORE_TEST:
return
self.assertEqual(len(self.timeseries), LENGTH)
def testGetitem(self):
if IGNORE_TEST:
return
times = self.timeseries[TIME]
# Access time column with different case
refs = ["TiMe", "S1"]
self.assertTrue(
namedTimeseries.arrayEquals(self.timeseries[refs],
self.timeseries[refs]))
self.assertTrue(
namedTimeseries.arrayEquals(self.timeseries[TIME],
self.timeseries["TimE"]))
self.assertTrue(
namedTimeseries.arrayEquals(self.timeseries[TIME],
self.timeseries["TimE"]))
self.assertEqual(len(times), len(self.timeseries))
self.assertEqual(min(times), self.timeseries.start)
self.assertEqual(max(times), self.timeseries.end)
# Get multiple values at once
values = self.timeseries[self.timeseries.colnames]
trues = np.array([
v1 == v2 for v1, v2 in zip(values, self.timeseries.values[:, 1:])
])
self.assertTrue(all(trues.flatten()))
def testMissingData(self):
if IGNORE_TEST:
return
with self.assertRaises(ValueError):
timeseries = NamedTimeseries(csvPath=TEST_BAD_DATA_PATH)
def testCopyExisting(self):
if IGNORE_TEST:
return
timeseries = NamedTimeseries(timeseries=self.timeseries)
#
def checkVector(attribute):
length = len(self.timeseries.__getattribute__(attribute))
trues = [
timeseries.__getattribute__(attribute)[k] ==
self.timeseries.__getattribute__(attribute)[k]
for k in range(length)
]
self.assertTrue(all(trues))
def checkMatrix(attribute):
trues = []
for rowIdx, row in enumerate(
timeseries.__getattribute__(attribute)):
for colIdx, val in enumerate(row):
trues.append(val == self.timeseries.__getattribute__(
attribute)[rowIdx, colIdx])
self.assertTrue(all(trues))
#
for variable in ["start", "end"]:
self.assertEqual(timeseries.__getattribute__(variable),
self.timeseries.__getattribute__(variable))
for variable in ["colnames"]:
checkVector(variable)
for variable in ["values"]:
checkMatrix(variable)
def testFlattenValues(self):
if IGNORE_TEST:
return
values = self.timeseries.flatten()
self.assertTrue(
np.isclose(sum(values - self.timeseries.values[:, 1:].flatten()),
0))
def testSelectTimes(self):
if IGNORE_TEST:
return
selectorFunction = lambda t: t > 2
array = self.timeseries.selectTimes(selectorFunction)
self.assertLess(len(array), len(self.timeseries))
def testMkNamedTimeseries(self):
if IGNORE_TEST:
return
# Create a new time series that subsets the old one
colnames = ["time", "S1", "S2"]
newTS = namedTimeseries.mkNamedTimeseries(colnames,
self.timeseries[colnames])
self.assertEqual(len(self.timeseries), len(newTS))
# Create a new timeseries with a subset of times
array = self.timeseries.selectTimes(lambda t: t > 2)
newTS = namedTimeseries.mkNamedTimeseries(self.timeseries.allColnames,
array)
self.assertGreater(len(self.timeseries), len(newTS))
#
ts = mkNamedTimeseries(self.timeseries)
self.assertTrue(self.timeseries.equals(ts))
#
ts = mkNamedTimeseries(TEST_DATA_PATH)
self.assertTrue(self.timeseries.equals(ts))
#
with self.assertRaises(ValueError):
ts = mkNamedTimeseries(3)
def testToPandas(self):
if IGNORE_TEST:
return
df = self.timeseries.to_dataframe()
timeseries = NamedTimeseries(dataframe=df)
diff = set(df.columns).symmetric_difference(timeseries.colnames)
self.assertEqual(len(diff), 0)
total = sum(timeseries.values.flatten() -
self.timeseries.values.flatten())
self.assertTrue(np.isclose(total, 0))
def testArrayEquals(self):
if IGNORE_TEST:
return
arr1 = np.array([1, 2, 3, 4])
arr1 = np.reshape(arr1, (2, 2))
self.assertTrue(namedTimeseries.arrayEquals(arr1, arr1))
arr2 = 1.0001 * arr1
self.assertFalse(namedTimeseries.arrayEquals(arr1, arr2))
def testEquals(self):
if IGNORE_TEST:
return
self.assertTrue(self.timeseries.equals(self.timeseries))
newTS = self.timeseries.copy()
newTS["S1"] = -1
self.assertFalse(self.timeseries.equals(newTS))
def testCopy(self):
if IGNORE_TEST:
return
ts2 = self.timeseries.copy()
self.assertTrue(self.timeseries.equals(ts2))
def testSetitem(self):
if IGNORE_TEST:
return
self.timeseries["S1"] = self.timeseries["S2"]
self.assertTrue(
namedTimeseries.arrayEquals(self.timeseries["S1"],
self.timeseries["S2"]))
value = -20
self.timeseries["S19"] = value
self.assertEqual(self.timeseries["S19"].sum(),
len(self.timeseries) * value)
def testGetitemRows(self):
if IGNORE_TEST:
return
start = 1
stop = 3
ts1 = self.timeseries[start:stop]
self.assertTrue(isinstance(ts1, NamedTimeseries))
self.assertEqual(len(ts1), stop - start)
#
ts2 = self.timeseries[[1, 2]]
self.assertTrue(ts1.equals(ts2))
#
ts3 = self.timeseries[1]
self.assertEqual(np.shape(ts3.values), (1, len(ts2.allColnames)))
def testExamples(self):
if IGNORE_TEST:
return
# Create from file
timeseries = NamedTimeseries(csvPath=TEST_DATA_PATH)
# NamedTimeseries can use len function
length = len(timeseries) # number of rows
# Extract the numpy array values using indexing
timeValues = timeseries["time"]
s1Values = timeseries["S1"]
# Get the start and end times
startTime = timeseries.start
endTime = timeseries.end
# Create a new time series that subsets the variables of the old one
colnames = ["time", "S1", "S2"]
newTS = mkNamedTimeseries(colnames, timeseries[colnames])
# Create a new timeseries that excludes time 0
ts2 = timeseries[1:]
# Create a new column variable
timeseries["S8"] = timeseries["time"]**2 + 3 * timeseries["S1"]
timeseries["S9"] = 10 # Assign a constant to all rows
def testDelitem(self):
if IGNORE_TEST:
return
ts1 = self.timeseries.copy()
del ts1["S1"]
stg = str(ts1)
self.assertEqual(len(ts1), len(self.timeseries))
self.assertEqual(len(ts1.colnames) + 1, len(self.timeseries.colnames))
def testToCsv(self):
if IGNORE_TEST:
return
self.timeseries.to_csv(TEMP_FILE)
self.assertTrue(os.path.isfile(TEMP_FILE))
def testConcatenateColumns(self):
if IGNORE_TEST:
return
ts = self.timeseries.concatenateColumns(self.timeseries)
newNames = ["%s_" % c for c in self.timeseries.colnames]
self.assertTrue(
namedTimeseries.arrayEquals(
ts[newNames], self.timeseries[self.timeseries.colnames]))
self.assertEqual(len(ts), len(self.timeseries))
self.assertTrue(
namedTimeseries.arrayEquals(ts[TIME], self.timeseries[TIME]))
#
ts = self.timeseries.concatenateColumns(
[self.timeseries, self.timeseries])
self.assertEqual(3 * len(self.timeseries.colnames), len(ts.colnames))
def testConcatenateRows(self):
if IGNORE_TEST:
return
ts = self.timeseries.concatenateRows(self.timeseries)
diff = set(ts.colnames).symmetric_difference(self.timeseries.colnames)
self.assertEqual(len(diff), 0)
length = len(self.timeseries)
ts1 = ts[length:]
self.assertTrue(self.timeseries.equals(ts1))
#
ts = self.timeseries.concatenateRows(
[self.timeseries, self.timeseries])
self.assertEqual(3 * len(self.timeseries), len(ts))
def testSubsetColumns(self):
if IGNORE_TEST:
return
ts = self.timeseries.concatenateColumns(self.timeseries)
ts1 = ts.subsetColumns(self.timeseries.colnames)
self.assertTrue(self.timeseries.equals(ts1))
def testGetTimes(self):
if IGNORE_TEST:
return
SIZE = 10
VALUE = "values"
TIMES = np.array(range(SIZE))
def test(values, reference):
df = pd.DataFrame({TIME: TIMES, VALUE: values})
ts = NamedTimeseries(dataframe=df)
results = ts.getTimesForValue(VALUE, reference)
for time in results:
idx1 = int(time)
idx2 = idx1 + 1
small = min(ts[VALUE][idx1], ts[VALUE][idx2])
large = max(ts[VALUE][idx1], ts[VALUE][idx2])
self.assertLessEqual(small, reference)
self.assertGreaterEqual(large, reference)
#
values = (TIMES - 5)**2
test(values, 10) # 2 times
test(-values, 5) # Single maxk
def testRpickleInterface(self):
if IGNORE_TEST:
return
serialization = rpickle.Serialization(self.timeseries)
timeseries = serialization.deserialize()
self.assertTrue(timeseries.equals(self.timeseries))
def testRename(self):
if IGNORE_TEST:
return
NEW_NAME = "T1"
OLD_NAME = "S1"
newTimeseries = self.timeseries.rename(OLD_NAME, NEW_NAME)
self.assertTrue(NEW_NAME in newTimeseries.colnames)
self.assertFalse(OLD_NAME in newTimeseries.colnames)
del newTimeseries[NEW_NAME]
del self.timeseries[OLD_NAME]
self.assertTrue(newTimeseries.equals(self.timeseries))
def setUp(self):
self.timeseries = NamedTimeseries(csvPath=TEST_DATA_PATH)
self.plotter = TimeseriesPlotter(isPlot=IS_PLOT)
def getTS(data):
if isinstance(data, pd.DataFrame):
return NamedTimeseries(dataframe=data)
return data
def plotTimeSingle(self, timeseries1:NamedTimeseries,
meanTS:NamedTimeseries=None, stdTS:NamedTimeseries=None,
bandLowTS:NamedTimeseries=None, bandHighTS:NamedTimeseries=None,
ax_spec=None,
position=None, **kwargs):
"""
Constructs plots of single columns, possibly with a second
timeseries.
Parameters
---------
timeseries1: timeseries to plot
meanTS: mean values of timeseries to plot
stdTS: standard deviations of meanTS (same times)
bandLowTS: timeseries that describes the lower band for timeseries1
bandhighTS: timeseries that describes the higher band for timeseries1
ax_spec: Optionally specified axis for all lines
position: (int, int) - position of ax_spec
#@expand
Example
-------
plotter = TimeseriesPlotter()
plotter.plotTimeSingle(timeseries)
"""
options = self._mkPlotOptionsMatrix(timeseries1, **kwargs)
# Adjust rows and columns
numPlot = len(options.columns) # Number of plots
if po.NUM_COL in kwargs.keys():
options.numRow = int(np.ceil(numPlot/options.numCol))
else:
options.numCol = int(np.ceil(numPlot/options.numRow))
options.set(po.XLABEL, TIME)
# Create the LayoutManager
if ax_spec is None:
layout = self._mkManager(options, numPlot)
else:
layout = None
#
def mkStatement(ax, statement:StatementManager,
timeseries:NamedTimeseries, variable:str):
"""
Creates a plotting statement.
Parameters
----------
ax: plotting axes
initialStatement: statement if initialized
timeseries: what to plot
variable: variable to plot
Returns
-------
StatementManager
"""
times, values = self._adjustSeriesForNan(
timeseries[TIME], timeseries[variable])
statement.addPosarg(times)
statement.addPosarg(values)
return statement
#
def isFirstColumn(plotIdx):
if layout is not None:
return layout.isFirstColumn(plotIdx)
else:
if position is not None:
return position[1] == 0
else:
return True
#
def isLastRow(plotIdx):
if layout is not None:
return layout.isLastRow(plotIdx)
else:
if po.NUM_ROW in kwargs.keys():
numRow = kwargs[po.NUM_ROW]
else:
return True
if position is None:
return True
return position[0] + 1 == numRow
#
def mkBand(ts, variable, plotIdx, lineIdx):
initialStatement = StatementManager(ax.fill_between)
statement = mkStatement(ax, initialStatement, timeseries1, variable)
statement.addPosarg(ts[variable])
statement.addKwargs(alpha=0.2)
options.do(ax, statement=statement, plotIdx=plotIdx, lineIdx=lineIdx)
#
# Construct the plots
baseOptions = copy.deepcopy(options)
for plotIdx, variable in enumerate(options.columns):
if ax_spec is None:
ax = layout.getAxis(plotIdx)
else:
ax = ax_spec
options = copy.deepcopy(baseOptions)
#ax = axes[row, col]
options.set(po.YLABEL, "concentration")
options.set(po.TITLE, variable)
if not isFirstColumn(plotIdx):
options.ylabel = NULL_STR
options.set(po.YLABEL, "", isOverride=True)
if not isLastRow(plotIdx):
options.set(po.XLABEL, "", isOverride=True)
# Construct the plot
lineIdx = 0
initialStatement = StatementManager(ax.plot)
statement = mkStatement(ax, initialStatement, timeseries1, variable)
options.do(ax, statement=statement, plotIdx=plotIdx, lineIdx=lineIdx)
legends = []
if options.timeseries2 is not None:
lineIdx = 1
initialStatement = StatementManager(ax.plot)
if options.marker is not None:
if len(options.marker) > 1:
if options.marker[lineIdx] is not None:
initialStatement = StatementManager(ax.scatter)
elif options.marker is not None:
initialStatement = StatementManager(ax.scatter)
statement = mkStatement(ax, initialStatement,
options.timeseries2, variable)
legends = [LABEL1, LABEL2]
options.lengends = legends
options.do(ax, statement=statement, plotIdx=plotIdx, lineIdx=lineIdx)
if meanTS is not None:
if stdTS is None:
stdTS = meanTS.copy(isInitialize=True)
lineIdx = 2
initialStatement = StatementManager(ax.scatter)
statement = mkStatement(ax, initialStatement, meanTS, variable)
options.marker = "^"
statement.addKwargs(facecolors="none")
options.do(ax, statement=statement, plotIdx=plotIdx, lineIdx=lineIdx)
#
initialStatement = StatementManager(ax.errorbar)
statement = mkStatement(ax, initialStatement, meanTS, variable)
statement.addKwargs(yerr=stdTS[variable])
statement.addKwargs(linestyle="none")
legends.append("Bootstrap mean")
options.lengends = legends
options.do(ax, statement=statement, plotIdx=plotIdx, lineIdx=lineIdx)
if bandLowTS is not None:
lineIdx = 0
mkBand(bandLowTS, variable, plotIdx, lineIdx)
if bandHighTS is not None:
lineIdx = 0
mkBand(bandHighTS, variable, plotIdx, lineIdx)
if self.isPlot:
plt.show()
class TestTimeseriesPlotter(unittest.TestCase):
def setUp(self):
self.timeseries = NamedTimeseries(csvPath=TEST_DATA_PATH)
self.plotter = TimeseriesPlotter(isPlot=IS_PLOT)
def testConstructor1(self):
if IGNORE_TEST:
return
self.assertTrue(isinstance(self.plotter.isPlot, bool))
def testInitializeRowColumn(self):
if IGNORE_TEST:
return
def test(maxCol, **kwargs):
options = self.plotter._mkPlotOptionsMatrix(self.timeseries,
maxCol=maxCol,
**kwargs)
if po.NUM_ROW in kwargs:
self.assertGreaterEqual(options.numRow, kwargs[po.NUM_ROW])
if po.NUM_COL in kwargs:
self.assertEqual(options.numCol, kwargs[po.NUM_COL])
#
test(3, **{})
test(3, **{po.NUM_COL: 3})
test(4, **{po.NUM_ROW: 2})
test(5, **{po.NUM_ROW: 2})
def testPlotSingle1(self):
if IGNORE_TEST:
return
self.plotter.plotTimeSingle(self.timeseries,
timeseries2=self.timeseries,
numCol=4,
marker=[None, '*'],
alpha=[0.1, 0.8],
color=["red", "g"],
titlePosition=[0.8, 0.5],
titleFontsize=10)
self.plotter.plotTimeSingle(self.timeseries,
numCol=4,
marker=[None, '*'])
self.plotter.plotTimeSingle(self.timeseries,
numCol=4,
subplotWidthSpace=0.2,
yticklabels=[])
self.plotter.plotTimeSingle(self.timeseries,
columns=["S1", "S2", "S3"],
numRow=2)
self.plotter.plotTimeSingle(self.timeseries, numCol=4)
self.plotter.plotTimeSingle(self.timeseries, numCol=2)
self.plotter.plotTimeSingle(self.timeseries,
numRow=2,
numCol=3,
ylabel="xxx")
self.plotter.plotTimeSingle(self.timeseries, columns=["S1", "S2"])
def testPlotSingle5(self):
if IGNORE_TEST:
return
timeseries = self.timeseries.subsetColumns(["S1"])
dct = {}
indices = [i for i in range(len(timeseries)) if i % 4 == 0]
for col in timeseries.allColnames:
dct[col] = timeseries[col][indices]
df = pd.DataFrame(dct)
meanTS = NamedTimeseries(dataframe=df)
meanTS[meanTS.colnames] = 1.1 * meanTS[meanTS.colnames]
stdTS = meanTS.copy()
for col in meanTS.colnames:
stdTS[col] = 1
#
self.plotter.plotTimeSingle(timeseries,
timeseries2=self.timeseries,
meanTS=meanTS,
stdTS=stdTS,
marker=[None, 'o', "^"],
color=["b", "r", "g"])
#
self.plotter.plotTimeSingle(timeseries, meanTS=meanTS, stdTS=stdTS)
#
self.plotter.plotTimeSingle(timeseries,
timeseries2=self.timeseries,
marker='*')
def testPlotSingle6(self):
if IGNORE_TEST:
return
numCol = 3
numRow = 2
fig, axes = plt.subplots(numRow, numCol)
self.plotter.isPlot = False
for idx in range(numCol * numRow):
if idx < numCol:
row = 0
col = idx
else:
row = 1
col = idx - numCol
position = [row, col]
ax = axes[row, col]
ts = self.timeseries.subsetColumns(self.timeseries.colnames[idx])
self.plotter.plotTimeSingle(ts,
ax_spec=ax,
position=position,
numRow=2)
if IS_PLOT:
plt.show()
def testPlotSingle7(self):
if IGNORE_TEST:
return
def setTS(ts, frac):
ts = self.timeseries.copy()
for col in ts.colnames:
ts[col] = frac * ts[col]
return ts
#
numCol = 3
numRow = 2
fig, axes = plt.subplots(numRow, numCol)
self.plotter.isPlot = False
tsLower = setTS(self.timeseries, 0.7)
tsUpper = setTS(self.timeseries, 1.5)
for idx in range(numCol * numRow):
if idx < numCol:
row = 0
col = idx
else:
row = 1
col = idx - numCol
position = [row, col]
ax = axes[row, col]
ts = self.timeseries.subsetColumns(self.timeseries.colnames[idx])
self.plotter.plotTimeSingle(ts,
ax_spec=ax,
position=position,
bandLowTS=tsLower,
bandHighTS=tsUpper,
numRow=2)
if IS_PLOT:
plt.show()
def testPlotSingle8(self):
# Plot with nan values
if IGNORE_TEST:
return
def setTS(ts, mult, numNan):
ts = self.timeseries.copy()
for col in ts.colnames:
ts[col] = mult * ts[col]
ts[col][:numNan] = np.nan
return ts
#
numCol = 3
numRow = 2
timeseries2 = setTS(self.timeseries, 2, 3)
self.plotter.plotTimeSingle(self.timeseries,
timeseries2=timeseries2,
columns=["S1"],
numRow=numRow,
numCol=numCol)
if IS_PLOT:
plt.show()
def mkTimeseries(self):
ts2 = self.timeseries.copy()
ts2[ts2.colnames] = ts2[ts2.colnames] + np.multiply(
ts2[ts2.colnames], ts2[ts2.colnames])
return ts2
def testPlotSingle2(self):
if IGNORE_TEST:
return
ts2 = self.mkTimeseries()
self.plotter.plotTimeSingle(self.timeseries,
timeseries2=ts2,
columns=["S1", "S2"])
self.plotter.plotTimeSingle(self.timeseries, timeseries2=ts2)
self.plotter.plotTimeSingle(self.timeseries,
timeseries2=ts2,
numRow=2,
numCol=3)
def testPlotSingle3(self):
if IGNORE_TEST:
return
self.plotter.plotTimeSingle(self.timeseries, ylabel="MISSING")
def testPlotSingle4(self):
if IGNORE_TEST:
return
ts2 = self.mkTimeseries()
self.plotter.plotTimeSingle(self.timeseries,
markersize=[2, 5],
timeseries2=ts2,
numRow=2,
numCol=3,
marker=[None, "o"])
self.plotter.plotTimeSingle(self.timeseries,
timeseries2=ts2,
numRow=2,
numCol=3,
marker=[None, "o"],
alpha=0.1)
def testPlotMultiple1(self):
if IGNORE_TEST:
return
ts2 = self.mkTimeseries()
self.plotter.plotTimeMultiple(
self.timeseries,
timeseries2=ts2,
suptitle="Testing",
marker=[None, 'o', None, None, None, None],
color=['r', 'g', 'b', 'brown', 'g', 'pink'],
alpha=0.3)
self.plotter.plotTimeMultiple(self.timeseries,
timeseries2=ts2,
suptitle="Testing",
numRow=1,
numCol=1,
marker="o")
self.plotter.plotTimeMultiple(self.timeseries,
timeseries2=ts2,
suptitle="Testing",
numRow=2,
marker="o")
self.plotter.plotTimeMultiple(self.timeseries, suptitle="Testing")
def testValuePairs(self):
if IGNORE_TEST:
return
ts2 = self.mkTimeseries()
self.plotter.plotValuePairs(self.timeseries,
[("S1", "S2"), ("S2", "S3"), ("S4", "S5")],
numCol=2,
numRow=2,
alpha=0.3)
self.plotter.plotValuePairs(self.timeseries, [("S1", "S2"),
("S2", "S3")],
numRow=2)
self.plotter.plotValuePairs(self.timeseries, [("S1", "S2")])
def testPlotHistograms(self):
if IGNORE_TEST:
return
self.plotter.plotHistograms(self.timeseries, numCol=2, alpha=0.3)
self.plotter.plotHistograms(self.timeseries,
numCol=2,
alpha=0.3,
bins=100)
def testPlotValuePairsBug(self):
if IGNORE_TEST:
return
self.plotter.plotValuePairs(self.timeseries,
pairs=[("S1", "S2"), ("S1", "S6"),
("S2", "S3")],
numCol=3)
def testPlotCompare(self):
if IGNORE_TEST:
return
self.plotter.plotCompare(self.timeseries, self.timeseries, numCol=3)
def testPlotAutoCorrelations(self):
if IGNORE_TEST:
return
self.plotter.plotAutoCorrelations(self.timeseries,
numCol=3,
color=["black", "grey", "grey"],
linestyle=[None, "dashed", "dashed"],
alpha=[None, 0.5, 0.5])
def testPlotCrossCorrelations(self):
if IGNORE_TEST:
return
self.plotter.plotCrossCorrelations(self.timeseries,
titleFontsize=8,
titlePosition=(0.8, 0.8),
suptitle="Cross Correlations",
color=["black", "g", "g"],
figsize=(12, 10))
def _mkParameterDF(self, parameters=None):
df = pd.DataFrame(self.bootstrapResult.parameterDct)
if parameters is not None:
df = df[parameters]
df.index.name = TIME
return NamedTimeseries(dataframe=df)
def mkTimeSeries(self, values, name):
numPoint = len(values)
arr = np.array([range(numPoint), values])
arr = np.resize(arr, (2, numPoint))
arr = arr.transpose()
return NamedTimeseries(array=arr, colnames=["time", name])
def copy(self, isKeepLogger=False, isKeepOptimizer=False, **kwargs):
"""
Creates a copy of the model fitter, overridding any argument
that is not None.
Preserves the user-specified settings and the results
of bootstrapping.
Parameters
----------
isKeepLogger: bool
isKeepOptimizer: bool
kwargs: dict
arguments to override in copy
Returns
-------
ModelFitter
"""
def setValues(names):
"""
Sets the value for a list of names.
Parameters
----------
names: list-str
Returns
-------
list-object
"""
results = []
for name in names:
altName = "_%s" % name
if name in kwargs.keys():
results.append(kwargs[name])
elif name in self.__dict__.keys():
results.append(self.__dict__[name])
elif altName in self.__dict__.keys():
results.append(self.__dict__[altName])
else:
raise RuntimeError("%s: not found" % name)
return results
#
# Get the positional and keyword arguments
inspectResult = inspect.getfullargspec(ModelFitterCore.__init__)
allArgNames = inspectResult.args[1:] # Ignore 'self'
if inspectResult.defaults is None:
numKwarg = 0
else:
numKwarg = len(inspectResult.defaults)
numParg = len(allArgNames) - numKwarg # positional arguments
pargNames = allArgNames[:numParg]
kwargNames = allArgNames[numParg:]
# Construct the arguments
callPargs = setValues(pargNames)
callKwargValues = setValues(kwargNames)
callKwargs = {n: v for n, v in zip(kwargNames, callKwargValues)}
if numKwarg > 0:
# Adjust model specification
modelSpecificationIdx = pargNames.index("modelSpecification")
observedDataIdx = pargNames.index("observedData")
modelSpecification = callPargs[modelSpecificationIdx]
observedTS = NamedTimeseries(callPargs[observedDataIdx])
selectedColumns = callKwargs["selectedColumns"]
if not isinstance(modelSpecification, str):
try:
modelSpecification = self.modelSpecification.getAntimony()
callPargs[modelSpecificationIdx] = modelSpecification
observedTS, selectedColumns = self._adjustNames(
modelSpecification, observedTS)
callPargs[observedDataIdx] = observedTS
callKwargs["selectedColumns"] = selectedColumns
except Exception as err:
self.logger.error(
"Problem wth conversion to Antimony. Details:", err)
raise ValueError("Cannot proceed.")
#
if isKeepLogger:
callKwargs["logger"] = self.logger
if numParg < 2:
callPargs = [None, None]
newModelFitter = self.__class__(*callPargs, **callKwargs)
if self.optimizer is not None:
if isKeepOptimizer:
newModelFitter.optimizer = self.optimizer.copyResults()
if self.bootstrapResult is not None:
newModelFitter.bootstrapResult = self.bootstrapResult.copy()
return newModelFitter
def simulate(self,
params=None,
startTime=None,
endTime=None,
numPoint=None):
"""
Runs a simulation. Defaults to parameter values in the simulation.
Parameters
----------
params: lmfit.Parameters
startTime: float
endTime: float
numPoint: int
Return
------
NamedTimeseries
"""
def set(default, parameter):
# Sets to default if parameter unspecified
if parameter is None:
return default
else:
return parameter
##V
block = Logger.join(self._loggerPrefix, "fitModel.simulate")
guid = self.logger.startBlock(block)
## V
sub1Block = Logger.join(block, "sub1")
sub1Guid = self.logger.startBlock(sub1Block)
startTime = set(self.observedTS.start, startTime)
endTime = set(self.observedTS.end, endTime)
numPoint = set(len(self.observedTS), numPoint)
## V
sub1aBlock = Logger.join(sub1Block, "sub1a")
sub1aGuid = self.logger.startBlock(sub1aBlock)
if self.roadrunnerModel is None:
self._initializeRoadrunnerModel()
self.roadrunnerModel.reset()
## ^
self.logger.endBlock(sub1aGuid)
## V
sub1bBlock = Logger.join(sub1Block, "sub1b")
sub1bGuid = self.logger.startBlock(sub1bBlock)
if params is not None:
# Parameters have been specified
self._setupModel(params)
## ^
self.logger.endBlock(sub1bGuid)
# Do the simulation
selectedColumns = list(self.selectedColumns)
if not TIME in selectedColumns:
selectedColumns.insert(0, TIME)
## ^
self.logger.endBlock(sub1Guid)
## V
roadrunnerBlock = Logger.join(block, "roadrunner")
roadrunnerGuid = self.logger.startBlock(roadrunnerBlock)
data = self.roadrunnerModel.simulate(startTime, endTime, numPoint,
selectedColumns)
self.logger.endBlock(roadrunnerGuid)
## ^
# Select the required columns
## V
sub2Block = Logger.join(block, "sub2")
sub2Guid = self.logger.startBlock(sub2Block)
fittedTS = NamedTimeseries(namedArray=data)
self.logger.endBlock(sub2Guid)
## ^
self.logger.endBlock(guid)
##^
return fittedTS
def evaluate(self,
stdResiduals: float = 0.1,
relError: float = 0.1,
endTime: float = 10.0,
numPoint: int = 30,
fractionParameterDeviation: float = 0.5,
numIteration=NUM_BOOTSTRAP_ITERATION):
"""
Evaluates model fitting accuracy and bootstrapping for model
Parameters
----------
stdResiduals: Standard deviations of variable used in constructing reiduals
relError: relative error of parameter used in evaluation
endTime: ending time of the simulation
numPoint: number of points in the simulatin
fractionParameterDeviation: fractional amount that the parameter can vary
"""
# Construct synthetic observations
if self.selectedColumns is None:
data = self.roadRunner.simulate(0, endTime, numPoint)
else:
allColumns = list(self.selectedColumns)
if TIME not in allColumns:
allColumns.append(TIME)
data = self.roadRunner.simulate(0, endTime, numPoint, allColumns)
bracketTime = "[%s]" % TIME
if bracketTime in data.colnames:
# Exclude any column named '[time]'
idx = data.colnames.index(bracketTime)
dataArr = np.delete(data, idx, axis=1)
colnames = list(data.colnames)
colnames.remove(bracketTime)
colnames = [s[1:-1] if s != TIME else s for s in colnames]
simTS = NamedTimeseries(array=dataArr, colnames=colnames)
else:
simTS = NamedTimeseries(namedArray=data)
synthesizer = ObservationSynthesizerRandomErrors(fittedTS=simTS,
std=stdResiduals)
observedTS = synthesizer.calculate()
# Construct the parameter ranges
parametersToFit = []
for name in self.parameterValueDct.keys():
lower = self.parameterValueDct[name] * (1 -
fractionParameterDeviation)
upper = self.parameterValueDct[name] * (1 +
fractionParameterDeviation)
value = np.random.uniform(lower, upper)
parametersToFit.append(
SBstoat.Parameter(name, lower=lower, upper=upper, value=value))
# Create the fitter
fitter = ModelFitter(self.roadRunner,
observedTS,
selectedColumns=self.selectedColumns,
parametersToFit=parametersToFit,
**self.kwargs)
msg = "Fitting the parameters %s" % str(self.parameterValueDct.keys())
self.logger.result(msg)
# Evaluate the fit
fitter.fitModel()
self._recordResult(fitter.params, relError, self.fitModelResult)
# Evaluate bootstrap
fitter.bootstrap(numIteration=numIteration)
if fitter.bootstrapResult is not None:
if fitter.bootstrapResult.numSimulation > 0:
self._recordResult(fitter.bootstrapResult.params, relError,
self.bootstrapResult)
def runSimulation(
cls,
parameters=None,
roadrunner=None,
startTime=0,
endTime=5,
numPoint=30,
selectedColumns=None,
returnDataFrame=True,
_logger=Logger(),
_loggerPrefix="",
):
"""
Runs a simulation. Defaults to parameter values in the simulation.
Parameters
----------
roadrunner: ExtendedRoadRunner/str
Roadrunner model
parameters: lmfit.Parameters
lmfit parameters
startTime: float
start time for the simulation
endTime: float
end time for the simulation
numPoint: int
number of points in the simulation
selectedColumns: list-str
output columns in simulation
returnDataFrame: bool
return a DataFrame
_logger: Logger
_loggerPrefix: str
Return
------
NamedTimeseries (or None if fail to converge)
"""
if isinstance(roadrunner, str):
roadrunner = cls.initializeRoadrunnerModel(roadrunner)
else:
roadrunner.reset()
if parameters is not None:
# Parameters have been specified
cls.setupModel(roadrunner, parameters, logger=_logger)
# Do the simulation
if selectedColumns is not None:
newSelectedColumns = list(selectedColumns)
if TIME not in newSelectedColumns:
newSelectedColumns.insert(0, TIME)
try:
data = roadrunner.simulate(startTime, endTime, numPoint,
newSelectedColumns)
except Exception as err:
_logger.error("Roadrunner exception: ", err)
data = None
else:
try:
data = roadrunner.simulate(startTime, endTime, numPoint)
except Exception as err:
_logger.exception("Roadrunner exception: %s", err)
data = None
if data is None:
return data
fittedTS = NamedTimeseries(namedArray=data)
if returnDataFrame:
result = fittedTS.to_dataframe()
else:
result = fittedTS
return result
def getTimeseries():
return NamedTimeseries(csvPath=TEST_DATA_PATH)