def testMakeGeneGroupDF(self):
if IGNORE_TEST:
return
self.grouper._makeGeneGroupDF()
helpers.isValidDataFrame(self.grouper.df_gene_group, [cn.GROUP])
df = copy.deepcopy(self.grouper.df_gene_group)
self.grouper._makeGeneGroupDF(is_include_0_group=True)
helpers.isValidDataFrame(self.grouper.df_gene_group, [cn.GROUP])
self.assertGreater(len(self.grouper.df_gene_group), len(df))
def testGroupTrinaryValueRows(self):
if IGNORE_TEST:
return
self.grouper._makeGroupDF()
expecteds = set([cn.CNT_GROUP, cn.CNT_UP, cn.CNT_DOWN, cn.GENE_IDS])
difference = expecteds.symmetric_difference(self.grouper.df_group)
helpers.isValidDataFrame(
self.grouper.df_group,
[cn.CNT_GROUP, cn.CNT_UP, cn.CNT_DOWN, cn.GENE_IDS])
def testMakeTrinaryData(self):
if IGNORE_TEST:
return
df = transform_data.makeTrinaryData(
df=self.provider.df_normalized)
columns = self.provider.df_normalized.columns
self.assertTrue(helpers.isValidDataFrame(df, columns))
def testAggregateGenes(self):
if IGNORE_TEST:
return
provider = DataProvider()
provider.do()
df = transform_data.aggregateGenes(provider=provider)
self.assertTrue(helpers.isValidDataFrame(df,
provider.df_normalized.columns))
def testMakeTimeAggregationMatrix(self):
if IGNORE_TEST:
return
return
df = self.matrix.makeTimeAggregationMatrix()
self.assertTrue(helpers.isValidDataFrame(df,
self.matrix.df_matrix.columns))
self.assertEqual(len(df), cn.NUM_TIMES)
def testWriteFitResultCSV(self):
if IGNORE_TEST:
return
main.run(PERSISTER_PATH,
True,
max_iter=1,
is_report=False,
mcfo_kwargs=MCFO_KWARGS)
df = main.makeFitResultCSV(path=PERSISTER_PATH, csv_path=None)
self.assertTrue(helpers.isValidDataFrame(df, cn.FIT_RESULT_COLUMNS))
def testNormalizeReadsDF(self):
if IGNORE_TEST:
return
provider = data_provider.DataProvider(is_only_qgenes=False,
is_display_errors=False)
provider.do()
df = provider.dfs_read_count[0]
df_normalized = provider.normalizeReadsDF(df)
columns = ["T%d" % n for n in range(len(df.columns))]
self.assertTrue(helpers.isValidDataFrame(df_normalized, columns))
self.assertEqual(len(df), len(df_normalized))
def testConstructor(self):
for cls in [TrinaryData, NormalizedData]:
data = cls()
self.assertTrue(isinstance(data.df_X, pd.DataFrame))
self.assertTrue(isinstance(data.ser_y, pd.Series))
self.assertTrue(isinstance(data.features, list))
self.assertTrue(isinstance(data.state_dict, dict))
self.assertTrue(
helpers.isValidDataFrame(data.df_X, data.df_X.columns))
self.assertEqual(len(data.df_X.columns), len(data.features))
self.assertEqual(len(data.df_X), len(data.ser_y))
def testNormalizeReadsDF(self):
if IGNORE_TEST:
return
provider = data_provider.DataProvider(
is_only_qgenes=False, is_display_errors=False)
provider.do()
df = provider.dfs_read_count[0]
df_normalized = provider.normalizeReadsDF(df)
self.assertTrue(helpers.isValidDataFrame(df_normalized,
df.columns))
self.assertEqual(len(df), len(df_normalized))
ser_length = provider.df_gene_description[cn.LENGTH]
def testRunState(self):
if IGNORE_TEST:
return
df_instance = pd.read_csv(TEST_IN_PATH)
arguments = main.Arguments(state=STATE, df=df_instance, num_fset=5)
df = main._runState(arguments)
columns = expected_columns = [
ccn.FEATURE_VECTOR, ccn.SIGLVL, cn.STATE, main.INSTANCE, ccn.FRAC,
ccn.COUNT
]
self.assertTrue(
helpers.isValidDataFrame(df,
expected_columns=columns,
nan_columns=columns))
def testConstructor(self):
if IGNORE_TEST:
return
self.assertTrue(helpers.isValidDataFrame(self.analyzer.df_term,
self.analyzer.df_term.columns))
def testMakeGeneTerm(self):
if IGNORE_TEST:
return
self.assertTrue(helpers.isValidDataFrame(self.matrix.df_gene_term,
[cn.GROUP, cn.TERM, cn.GENE_ID, cn.CNT_TERM,
cn.CNT_GENE, cn.CNT_REGULATED]))
def testConstructor(self):
if IGNORE_TEST:
return
self.assertTrue(helpers.isValidDataFrame(
self.matrix.df_matrix,
self.matrix.df_matrix.columns))