def test_HDF_Datastore_Build_with_fiducialtracks():
"""The datastore build is performed successfully.
"""
dbName = testDataRoot / Path('database_test_files/myDB_Build_Avg.h5')
if dbName.exists():
remove(str(dbName))
parser = parsers.PositionParser(positionIDs={
1: 'prefix',
3: 'channelID',
4: 'acqID'
})
readerDict = {
'FiducialTracks': readers.CSVReader(),
'AverageFiducial': readers.CSVReader()
}
# Directory to traverse for acquisition files
searchDirectory = testDataRoot / Path('test_experiment_2')
# Build datastore
with db.HDFDatastore(dbName) as myDB:
myDB.build(parser,
searchDirectory,
filenameStrings={
'FiducialTracks': '_Fids.dat',
'AverageFiducial': '_AvgFid.dat'
},
readers=readerDict,
dryRun=False)
# Test for existence of the data
with h5py.File(str(dbName), mode='r') as hdf:
key1 = 'Control/Control_1/'
name1 = 'FiducialTracks_ChannelA647'
name2 = 'AverageFiducial_ChannelA647'
ok_(key1 + name1 in hdf)
ok_(key1 + name2 in hdf)
ok_(hdf[key1 + name1].attrs.__contains__('SMLM_prefix'))
ok_(hdf[key1 + name1].attrs.__contains__('SMLM_acqID'))
ok_(hdf[key1 + name1].attrs.__contains__('SMLM_datasetType'))
ok_(hdf[key1 + name1].attrs.__contains__('SMLM_channelID'))
ok_(hdf[key1 + name1].attrs.__contains__('SMLM_dateID'))
ok_(hdf[key1 + name1].attrs.__contains__('SMLM_posID'))
ok_(hdf[key1 + name1].attrs.__contains__('SMLM_sliceID'))
key2 = 'Control/Control_2/'
ok_(key2 + name1 in hdf)
ok_(key2 + name2 in hdf)
key3 = 'shTRF2/shTRF2_1/'
ok_(key3 + name1 in hdf)
ok_(key3 + name2 in hdf)
key4 = 'shTRF2/shTRF2_2/'
ok_(key4 + name1 in hdf)
ok_(key4 + name2 in hdf)
# Remove test datastore file
remove(str(dbName))
def test_CSVReader_Comma_Delimited_Data():
"""CSVReader reads comma delimited files.
"""
filePath = testDataRoot / Path('readers_test_files/csv/comma_delimited/')
filename = filePath / Path('HeLaL_Control_1.csv')
reader = readers.CSVReader()
# Read the data from file
data = reader(filename)
# Verify data was read correctly
assert_equal(len(data.columns), 9)
assert_equal(len(data), 11)
def test_CSVReader_Kwargs():
"""CSVReader passes keyword arguments to Pandas read_csv() function.
"""
filePath = testDataRoot / Path('readers_test_files/csv/comma_delimited/')
filename = filePath / Path('HeLaL_Control_1.csv')
reader = readers.CSVReader()
# Read the data from file
# 'usecols' and 'nrows' are keywords of the Pandas read_csv() function
data = reader(filename, usecols = ['x', 'y'], nrows = 5)
# Verify data was read correctly
assert_equal(len(data.columns), 2)
assert_equal(len(data), 5)
def test_CSVReader_Tab_Delimited_Data():
"""CSVReader reads tab-delimited files.
"""
filePath = testDataRoot / Path('readers_test_files/csv/tab_delimited/')
filename = filePath / Path('HeLaL_Control_1.csv')
reader = readers.CSVReader()
# Read the data from file
# sep is a keyword argument to Pandas read_csv()
data = reader(filename, sep = '\t')
# Verify data was read correctly
assert_equal(len(data.columns), 9)
assert_equal(len(data), 11)
def test_CSVReader_Works_With_Parser():
"""CSVReader is correctly passed to readFromFile() from SimpleParser.
"""
filePath = testDataRoot / Path('readers_test_files/csv/tab_delimited/')
filename = filePath / Path('HeLaL_Control_1.csv')
# Initialize the Parser and Reader
parser = parsers.SimpleParser()
reader = readers.CSVReader()
# reader keyword argument passes the CSVReader instance;
# all other keyword arguments are passed to CSVReader's __call__ function.
parser.parseFilename(
filename, datasetType = 'Localizations', reader = reader, sep = '\t')
# Test a couple of the localization results
assert_equal(parser.dataset.data['x'].iloc[0], 6770)
assert_equal(parser.dataset.data['intensity'].iloc[0],4386.6)
assert_equal(parser.dataset.data['x'].iloc[1], 7958.1)
assert_equal(len(parser.dataset.data.columns), 9)
assert_equal(len(parser.dataset.data), 11)
def test_HDFDatastore_Build_With_Reader():
"""HDFDatastore.build() works when Reader objects are specified.
"""
dsName = testDataRoot / Path(('parsers_test_files/SimpleParser/'
'test_id_collection_temp.h5'))
if dsName.exists():
remove(str(dsName))
temp = config.__Registered_DatasetTypes__.copy()
config.__Registered_DatasetTypes__ = [
'Localizations', 'LocMetadata', 'WidefieldImage'
]
parser = parsers.SimpleParser()
filenameStrings = {
'Localizations': '.csv',
'LocMetadata': '.txt',
'WidefieldImage': '.tif'
}
readersDict = {'Localizations': readers.CSVReader()}
# Note sep and skiprows are keyword arguments of CSVReader; readTiffTags is
# a keyword argument for the WidefieldImage readfromFile() method
with database.HDFDatastore(dsName) as myDS:
res = myDS.build(parser,
dsName.parent,
filenameStrings,
readers=readersDict,
sep=',',
skiprows=2,
readTiffTags=False)
config.__Registered_DatasetTypes__ = temp
if dsName.exists():
remove(str(dsName))
assert_equal(len(res), 6)