def test_histogram(self):
###TEST 1 HISTOGRAM###
# if the ouput file already exists, remove it
if os.path.exists(testFolder + 'test_histogram.png'):
os.remove(testFolder + 'test_histogram.png')
# reading in a csv file, seperated by tabs into a matrix
csvData = rFunctions.readCsvFile(testFolder + 'feature.csv',
sep='\t',
head=True,
na='N/A')
# get only the rows with unique ids and put it in a new matrix
csvUniqID = rFunctions.getRowsWithUniqColumn(csvData, 'id')
# get a vector of all intensities using the index function from R_functions
intensityVector = csvData[rFunctions.index(csvUniqID, 'intensity')]
logIntensityVector = rFunctions.takeLog(intensityVector, 10)
# using all possible **kwargs arguments to test if they are all parsed correctly
self.plots.histogram(testFolder + 'test_histogram.png',
logIntensityVector,
plotArgs={'labels': True},
width=400,
height=400,
title='test #features per intensity',
ylab='# of test features')
# if after this the ouput does not exist, fail the test
if not os.path.exists(testFolder + 'test_histogram.png'):
self.fail(
testFolder +
'test_histogram.png does not exist. File not written out correctly'
)
else:
os.remove(testFolder + 'test_histogram.png')
###TEST 3 HISTOGRAMS
# if the test doesn't give an error it succeeded
if os.path.exists(testFolder + 'testOverlapHistogram.png'):
os.remove(
testFolder + 'testOverlapHistogram.png'
) # to make sure that the test isn't passing when the method doesn't work, but the file already exists
outpng = testFolder + 'testOverlapHistogram.png'
vector1 = R.IntVector((0, 2, 2, 3, 3, 3, 4, 4, 5))
vector2 = R.IntVector((2, 4, 4, 5, 5, 5, 6, 6, 7))
vector3 = R.IntVector((4, 6, 6, 7, 7, 7, 8, 8, 9))
plots = rPlots.Plots()
plots.histogram(outpng, vector1, vector2, vector3)
R.r['dev.off']()
if os.path.exists(testFolder + 'testOverlapHistogram.png'):
os.remove(testFolder + 'testOverlapHistogram.png')
def test_takeLog(self):
# because of rounding issues after 7 numbers after the comma I round both expected and actual to an int
expectedLogVector = R.IntVector((5.0, 5.0, 4.0, 5.0, 5.0, 5.0, 3.0, 5.0))
expectedLogList = []
# you can't compare vectors directly because this part >> Python:0x12241f80 << is always different, I transform them to lists first
for value in expectedLogVector:
expectedLogList.append(value)
vector = R.IntVector((59843, 34982, 12425, 90534, 34532, 54642, 1239, 43534))
actualLogVector = R.r['round'](rFunctions.takeLog(vector, 10))
actualLogList = []
for value in actualLogVector:
actualLogList.append(value)
self.assertEqual(expectedLogList, actualLogList)
def test_takeLog(self):
# because of rounding issues after 7 numbers after the comma I round both expected and actual to an int
expectedLogVector = R.IntVector(
(5.0, 5.0, 4.0, 5.0, 5.0, 5.0, 3.0, 5.0))
expectedLogList = []
# you can't compare vectors directly because this part >> Python:0x12241f80 << is always different, I transform them to lists first
for value in expectedLogVector:
expectedLogList.append(value)
vector = R.IntVector(
(59843, 34982, 12425, 90534, 34532, 54642, 1239, 43534))
actualLogVector = R.r['round'](rFunctions.takeLog(vector, 10))
actualLogList = []
for value in actualLogVector:
actualLogList.append(value)
self.assertEqual(expectedLogList, actualLogList)
def test_boxplotFormulae(self):
# if the ouput file already exists, remove it
if os.path.exists(testFolder + 'boxplotFormulae.png'):
os.remove(testFolder + 'boxplotFormulae.png')
featDataframe = rFunctions.readCsvFile(testFolder + 'feature.csv')
featDataframeUniq = rFunctions.getRowsWithUniqColumn(
featDataframe, 'id')
precursorPerFeatureDataframe = rFunctions.readCsvFile(
testFolder + 'feature_precursor.csv', head=True, sep='\t')
mergedFeatureDataframe = R.r['merge'](featDataframeUniq,
precursorPerFeatureDataframe)
mergedFeatureDataframe[rFunctions.index(
mergedFeatureDataframe,
'intensity')] = R.r['round'](rFunctions.takeLog(
featDataframeUniq[rFunctions.index(featDataframeUniq,
'intensity')], 10))
vector1 = mergedFeatureDataframe[rFunctions.index(
mergedFeatureDataframe, 'X..precursors')]
vector2 = mergedFeatureDataframe[rFunctions.index(
mergedFeatureDataframe, 'intensity')]
self.plots.boxplotFormulae(testFolder + 'boxplotFormulae.png',
vector1,
vector2,
mergedFeatureDataframe,
title='MS/MS per feature per intensity',
ylab='# of MS/MS per feature',
xlab='Rounded log10 of intensity')
R.r['dev.off']()
# if after this the ouput does not exist, fail the test
if not os.path.exists(testFolder + 'boxplotFormulae.png'):
self.fail(
testFolder +
'boxplotFormulae.png does not exist. File not written out correctly'
)
# remove the plot
if os.path.exists(testFolder + 'boxplotFormulae.png'):
os.remove(testFolder + 'boxplotFormulae.png')
def test_histogram(self):
###TEST 1 HISTOGRAM###
# if the ouput file already exists, remove it
if os.path.exists(testFolder+'test_histogram.png'):
os.remove(testFolder+'test_histogram.png')
# reading in a csv file, seperated by tabs into a matrix
csvData = rFunctions.readCsvFile(testFolder+'feature.csv', sep = '\t', head=True, na='N/A')
# get only the rows with unique ids and put it in a new matrix
csvUniqID = rFunctions.getRowsWithUniqColumn(csvData, 'id')
# get a vector of all intensities using the index function from R_functions
intensityVector = csvData[rFunctions.index(csvUniqID, 'intensity')]
logIntensityVector = rFunctions.takeLog(intensityVector, 10)
# using all possible **kwargs arguments to test if they are all parsed correctly
self.plots.histogram(testFolder+'test_histogram.png', logIntensityVector, plotArgs={'labels':True}, width=400, height=400, title='test #features per intensity', ylab = '# of test features')
# if after this the ouput does not exist, fail the test
if not os.path.exists(testFolder+'test_histogram.png'):
self.fail(testFolder+'test_histogram.png does not exist. File not written out correctly')
else:
os.remove(testFolder+'test_histogram.png')
###TEST 3 HISTOGRAMS
# if the test doesn't give an error it succeeded
if os.path.exists(testFolder+'testOverlapHistogram.png'):
os.remove(testFolder+'testOverlapHistogram.png') # to make sure that the test isn't passing when the method doesn't work, but the file already exists
outpng = testFolder+'testOverlapHistogram.png'
vector1 = R.IntVector((0,2,2,3,3,3,4,4,5))
vector2 = R.IntVector((2,4,4,5,5,5,6,6,7))
vector3 = R.IntVector((4,6,6,7,7,7,8,8,9))
plots = rPlots.Plots()
plots.histogram(outpng,vector1,vector2,vector3)
R.r['dev.off']()
if os.path.exists(testFolder+'testOverlapHistogram.png'):
os.remove(testFolder+'testOverlapHistogram.png')
def test_boxplotFormulae(self):
# if the ouput file already exists, remove it
if os.path.exists(testFolder+'boxplotFormulae.png'):
os.remove(testFolder+'boxplotFormulae.png')
featDataframe = rFunctions.readCsvFile(testFolder+'feature.csv')
featDataframeUniq = rFunctions.getRowsWithUniqColumn(featDataframe, 'id')
precursorPerFeatureDataframe = rFunctions.readCsvFile(testFolder+'feature_precursor.csv', head=True, sep='\t')
mergedFeatureDataframe = R.r['merge'](featDataframeUniq, precursorPerFeatureDataframe)
mergedFeatureDataframe[rFunctions.index(mergedFeatureDataframe, 'intensity')] = R.r['round'](rFunctions.takeLog(featDataframeUniq[rFunctions.index(featDataframeUniq, 'intensity')], 10))
vector1 = mergedFeatureDataframe[rFunctions.index(mergedFeatureDataframe, 'X..precursors')]
vector2 = mergedFeatureDataframe[rFunctions.index(mergedFeatureDataframe,'intensity')]
self.plots.boxplotFormulae(testFolder+'boxplotFormulae.png', vector1, vector2, mergedFeatureDataframe,
title = 'MS/MS per feature per intensity', ylab = '# of MS/MS per feature', xlab = 'Rounded log10 of intensity')
R.r['dev.off']()
# if after this the ouput does not exist, fail the test
if not os.path.exists(testFolder+'boxplotFormulae.png'):
self.fail(testFolder+'boxplotFormulae.png does not exist. File not written out correctly')
# remove the plot
if os.path.exists(testFolder+'boxplotFormulae.png'):
os.remove(testFolder+'boxplotFormulae.png')
