def test_load_example_datasets(self):
self.assertIsInstance(gl.get_example_dataset(name="Example_Dataset_1"),
GMQLDataset)
self.assertIsInstance(gl.get_example_dataset(name="Example_Dataset_2"),
GMQLDataset)
self.assertIsInstance(
gl.get_example_dataset(name="Example_Dataset_1", load=True),
GDataframe)
self.assertIsInstance(
gl.get_example_dataset(name="Example_Dataset_2", load=True),
GDataframe)
def test_remote_select_1(self):
querytext = """
#SELECT 1
RES = SELECT(region: (chr == chr2 OR chr == chr3) AND NOT(strand == + OR strand == -)
AND start >= 130 AND stop <= 250) Example_Dataset_2;
MATERIALIZE RES INTO select_1;
"""
logging.info("Query: {}".format(querytext))
logging.info("Executing REMOTE TEXTUAL query")
respaths = self.rm.query(querytext, self.remote_output_path)
dataset_name = respaths.iloc[0].dataset
respaths = os.path.join(self.remote_output_path, dataset_name)
logging.info("Deleting remote dataset {}".format(dataset_name))
self.rm.delete_dataset(dataset_name)
res_query = gl.load_from_path(respaths).materialize()
logging.info("Executing LOCAL PYTHON query")
d = gl.get_example_dataset("Example_Dataset_2")
d = d.select(region_predicate=(d.chr.isin(['chr2', 'chr3']))
& (~d.strand.isin(['+', '-'])) & (d.start >= 130)
& (d.stop <= 250))
res_local = d.materialize()
self.gdataframe_equality(res_query, res_local)
logging.info("Executing REMOTE PYTHON query")
gl.set_mode("remote")
res_remote = d.materialize()
self.gdataframe_equality(res_local, res_remote)
def test_difference_1(self):
""" # difference_1
D1 = SELECT(region: chr == chr2) Example_Dataset_1;
D2 = SELECT(cell_karyotype == "cancer"; region: chr == chr2) Example_Dataset_2;
RES = DIFFERENCE() D1 D2;
MATERIALIZE RES INTO difference_1;
"""
d1 = gl.get_example_dataset("Example_Dataset_1")
d1 = d1.reg_select(d1.chr == 'chr2')
d2 = gl.get_example_dataset("Example_Dataset_2")
d2 = d2.select(meta_predicate=d2['cell_karyotype'] == 'cancer',
region_predicate=d2.chr == 'chr2')
res = d1.difference(d2)
res = res.materialize()
self.gdataframe_equality(res, self.get_query_results("difference_1"))
def test_project_1(self):
""" # project_1
D = SELECT() Example_Dataset_1;
RES = PROJECT(region_update: length AS right - left) D;
MATERIALIZE RES INTO project_1;
"""
res = gl.get_example_dataset("Example_Dataset_1")
res = res.project(new_field_dict={'length': res.right - res.left})
res = res.materialize()
self.gdataframe_equality(res, self.get_query_results("project_1"))
def test_merge_1(self):
""" # merge_1
D = SELECT(region: chr == chr1) Example_Dataset_1;
RES = MERGE() D;
MATERIALIZE RES INTO merge_1;
"""
res = gl.get_example_dataset("Example_Dataset_1")
res = res.reg_select(res.chr == 'chr1')
res = res.merge()
res = res.materialize()
self.gdataframe_equality(res, self.get_query_results("merge_1"))
def test_map_1(self):
""" # map_1
D1 = SELECT(region: chr == chr2) Example_Dataset_1;
D2 = SELECT(region: chr == chr2) Example_Dataset_2;
RES = MAP(avg_score AS AVG(score)) D1 D2;
MATERIALIZE RES INTO map_1;
"""
d1 = gl.get_example_dataset("Example_Dataset_1")
d1 = d1.reg_select(d1.chr == 'chr2')
d2 = gl.get_example_dataset("Example_Dataset_2")
d2 = d2.reg_select(d2.chr == 'chr2')
res = d1.map(d2,
new_reg_fields={'avg_score': gl.AVG("score")},
refName="D1",
expName="D2")
res = res.materialize("./tmp")
shutil.rmtree("./tmp")
self.gdataframe_equality(res, self.get_query_results("map_1"))
def test_select_1(self):
""" #SELECT 1
RES = SELECT(region: (chr == chr2 OR chr == chr3) AND NOT(strand == + OR strand == -)
AND start >= 130 AND stop <= 250) Example_Dataset_2;
MATERIALIZE RES INTO select_1;
"""
res = gl.get_example_dataset("Example_Dataset_2")
res = res.select(region_predicate=(res.chr.isin(['chr2', 'chr3']))
& (~res.strand.isin(['+', '-'])) & (res.start >= 130)
& (res.stop <= 250))
res = res.materialize()
self.gdataframe_equality(res, self.get_query_results("select_1"))
def test_join_1(self):
""" # join_1
D1 = SELECT(region: chr == chr2) Example_Dataset_1;
D2 = SELECT(region: chr == chr2) Example_Dataset_2;
RES = JOIN(MD(1), DGE(20); output: RIGHT; joinby: cell_karyotype) D1 D2;
MATERIALIZE RES INTO join_1;
"""
d1 = gl.get_example_dataset("Example_Dataset_1")
d1 = d1.reg_select(d1.chr == 'chr2')
d2 = gl.get_example_dataset("Example_Dataset_2")
d2 = d2.reg_select(d2.chr == 'chr2')
res = d1.join(d2, [gl.MD(1), gl.DGE(20)],
output="RIGHT",
joinBy=['cell_karyotype'],
refName="D1",
expName="D2")
res = res.materialize("./tmp")
shutil.rmtree("./tmp")
self.gdataframe_equality(res, self.get_query_results("join_1"))
def test_group_1(self):
""" # group_1
D = SELECT(region: chr == chr2) Example_Dataset_2;
RES = GROUP(controlId; meta_aggregates: max_cell_tier AS MAX(cell_tier)) D;
MATERIALIZE RES INTO group_1;
"""
res = gl.get_example_dataset("Example_Dataset_2")
res = res.reg_select(res.chr == 'chr2')
res = res.group(meta=['controlId'],
meta_aggregates={'max_cell_tier': gl.MAX("cell_tier")})
res = res.materialize()
self.gdataframe_equality(res, self.get_query_results("group_1"))
def test_extend_2(self):
""" # extend_2
D = SELECT() Example_Dataset_1;
RES = EXTEND(region_count AS COUNT(), min_pvalue AS MIN(pvalue)) D;
MATERIALIZE RES INTO extend_2;
"""
res = gl.get_example_dataset("Example_Dataset_1")
res = res.extend({
'region_count': gl.COUNT(),
'min_pvalue': gl.MIN("pvalue")
})
res = res.materialize()
self.gdataframe_equality(res, self.get_query_results("extend_2"))
def test_cover_2(self):
""" # cover_2
D = SELECT(region: chr == chr2) Example_Dataset_2;
RES = COVER(2, 3; groupby: cell; aggregate: min_pvalue AS MIN(pvalue)) D;
MATERIALIZE RES INTO cover_2;
"""
d = gl.get_example_dataset("Example_Dataset_2")
d = d.reg_select(d.chr == 'chr2')
d = d.normal_cover(2,
3,
groupBy=['cell'],
new_reg_fields={'min_pvalue': gl.MIN("pvalue")})
d = d.materialize()
self.gdataframe_equality(d, self.get_query_results("cover_2"))
def test_order_1(self):
""" # order_1
D = SELECT(region: chr == chr1) Example_Dataset_1;
D1 = EXTEND(Region_count AS COUNT()) D;
RES = ORDER(Region_count DESC; meta_top: 2) D1;
MATERIALIZE RES INTO order_1;
"""
res = gl.get_example_dataset("Example_Dataset_1")
res = res.reg_select(res.chr == 'chr1')
res = res.extend({'Region_count': gl.COUNT()})
res = res.order(meta=['Region_count'],
meta_ascending=[False],
meta_top="top",
meta_k=2)
res = res.materialize()
self.gdataframe_equality(res, self.get_query_results("order_1"))