def separate(in_gct, separate_field, row_or_col):
""" Create a new GCT object for each unique value in separate_field.
Args:
in_gct (GCToo object)
separate_field (string)
row_or_col (string)
Returns:
gcts (list of GCToo objects)
unique_values_in_field (list of strings)
"""
if row_or_col == "row":
assert separate_field in in_gct.row_metadata_df.columns, (
("separate_field must be in in_gct.row_metadata_df.columns. " +
"separate_field: {}, in_gct.row_metadata_df.columns: {}").format(
separate_field, in_gct.row_metadata_df.columns.values))
unique_values_in_field = list(
in_gct.row_metadata_df.loc[:, separate_field].unique())
gcts = []
for val in unique_values_in_field:
bool_array = in_gct.row_metadata_df.loc[:,
separate_field].values == val
new_gct = slice_gct.slice_gctoo(in_gct, row_bool=bool_array)
gcts.append(new_gct)
elif row_or_col == "col":
assert separate_field in in_gct.col_metadata_df.columns, (
("separate_field must be in in_gct.col_metadata_df.columns. " +
"separate_field: {}, in_gct.col_metadata_df.columns: {}").format(
separate_field, in_gct.col_metadata_df.columns.values))
unique_values_in_field = list(
in_gct.col_metadata_df.loc[:, separate_field].unique())
gcts = []
for val in unique_values_in_field:
bool_array = in_gct.col_metadata_df.loc[:,
separate_field].values == val
new_gct = slice_gct.slice_gctoo(in_gct, col_bool=bool_array)
gcts.append(new_gct)
else:
raise (Exception("row or col must be 'row' or 'col'."))
# Make sure each gct is associated with a value from separate_field
assert len(gcts) == len(unique_values_in_field), (
"len(gcts): {}, len(unique_values_in_field): {}".format(
len(gcts), len(unique_values_in_field)))
return gcts, unique_values_in_field
def main(args):
# Import data
assert os.path.exists(
args.in_gct_path), ("in_gct_path could not be found: {}").format(
args.in_gct_path)
in_gct = parse(args.in_gct_path)
# First, check if any rows are all NaN; if so, remove them
dropped_df = in_gct.data_df.dropna(how="all")
bools_of_remaining = in_gct.data_df.index.isin(dropped_df.index.values)
in_gct = sg.slice_gctoo(in_gct, row_bool=bools_of_remaining)
if args.replace_with == "zero":
in_gct.data_df.fillna(0, inplace=True)
elif args.replace_with == "median":
probe_medians = in_gct.data_df.median(axis=1)
for row_idx, row in enumerate(in_gct.data_df.values):
this_row = in_gct.data_df.iloc[row_idx, :]
this_row[this_row.isnull()] = probe_medians[row_idx]
in_gct.data_df.iloc[row_idx, :] = this_row
elif args.replace_with == "mean":
probe_means = in_gct.data_df.mean(axis=1)
for row_idx, row in enumerate(in_gct.data_df.values):
this_row = in_gct.data_df.iloc[row_idx, :]
this_row[this_row.isnull()] = probe_means[row_idx]
in_gct.data_df.iloc[row_idx, :] = this_row
wg.write(in_gct, args.out_name, filler_null="NA")
def test_slice_cid_and_col_bool(self):
# cid and col_bool should not both be provided
with self.assertRaises(AssertionError) as e:
out_gct = slice_gct.slice_gctoo(IN_GCT,
cid=["e", "f", "g"],
col_bool=[True, True, False])
self.assertIn("cid and col_bool", str(e.exception))
def test_slice_and_exclude_rids(self):
out_gct = slice_gct.slice_gctoo(IN_GCT,
rid=["a", "c", "d"],
exclude_rid=["d"])
# Outputs should be dataframes even if there is only 1 index or column
pd.util.testing.assert_frame_equal(out_gct.data_df,
IN_GCT.data_df.iloc[[0, 2], :])
pd.util.testing.assert_frame_equal(
out_gct.row_metadata_df, IN_GCT.row_metadata_df.iloc[[0, 2], :])
pd.util.testing.assert_frame_equal(out_gct.col_metadata_df,
IN_GCT.col_metadata_df)
def test_slice_bools(self):
out_gct = slice_gct.slice_gctoo(IN_GCT,
row_bool=[True, False, True, False],
col_bool=[False, False, True])
# Outputs should be dataframes even if there is only 1 index or column
pd.util.testing.assert_frame_equal(
out_gct.data_df, pd.DataFrame(IN_GCT.data_df.iloc[[0, 2], 2]))
pd.util.testing.assert_frame_equal(
out_gct.row_metadata_df, IN_GCT.row_metadata_df.iloc[[0, 2], :])
pd.util.testing.assert_frame_equal(
out_gct.col_metadata_df,
pd.DataFrame(IN_GCT.col_metadata_df.iloc[2, :]).T)
def test_parse(self):
# parse whole thing
mg1 = mini_gctoo_for_testing.make()
mg2 = parse_gctx.parse("functional_tests/mini_gctoo_for_testing.gctx")
assert_frame_equal(mg1.data_df, mg2.data_df)
assert_frame_equal(mg1.row_metadata_df, mg2.row_metadata_df)
assert_frame_equal(mg1.col_metadata_df, mg2.col_metadata_df)
# test with string rid/cid
test_rids = ['LJP007_MCF10A_24H:TRT_CP:BRD-K93918653:3.33','LJP007_MCF7_24H:CTL_VEHICLE:DMSO:-666']
test_cids = ['LJP007_MCF7_24H:TRT_POSCON:BRD-A61304759:10']
mg3 = slice_gct.slice_gctoo(mg1, rid=test_rids, cid=test_cids)
mg4 = parse_gctx.parse("functional_tests/mini_gctoo_for_testing.gctx",
rid = test_rids, cid = test_cids)
assert_frame_equal(mg3.data_df, mg4.data_df)
assert_frame_equal(mg3.row_metadata_df, mg4.row_metadata_df)
assert_frame_equal(mg3.col_metadata_df, mg4.col_metadata_df)
# first, make & write out temp version of mini_gctoo with int rids/cids
new_mg = mini_gctoo_for_testing.make(convert_neg_666=False)
int_indexed_data_df = new_mg.data_df.copy()
int_indexed_data_df.index = range(0,6)
int_indexed_data_df.columns = range(10,16)
int_indexed_row_meta = new_mg.row_metadata_df.copy()
int_indexed_row_meta.index = range(0,6)
int_indexed_col_meta = new_mg.col_metadata_df.copy()
int_indexed_col_meta.index = range(10,16)
int_indexed_gctoo = GCToo.GCToo(data_df = int_indexed_data_df, row_metadata_df = int_indexed_row_meta,
col_metadata_df = int_indexed_col_meta)
write_gctx.write(int_indexed_gctoo, "int_indexed_mini_gctoo.gctx")
# test with numeric (repr as string) rid/cid
mg5 = GCToo.GCToo(data_df = int_indexed_data_df, row_metadata_df = int_indexed_row_meta,
col_metadata_df = int_indexed_col_meta)
mg5 = slice_gct.slice_gctoo(mg5, row_bool = [True, False, True, False, True, False],
col_bool = [True, False, False, True, True, True])
mg5.data_df.index.name = "rid"
mg5.data_df.columns.name = "cid"
mg5.row_metadata_df.index.name = "rid"
mg5.row_metadata_df.columns.name = "rhd"
mg5.col_metadata_df.index.name = "cid"
mg5.col_metadata_df.columns.name = "chd"
mg6 = parse_gctx.parse("int_indexed_mini_gctoo.gctx", rid = [0, 2, 4],
cid = [10,13,14,15], convert_neg_666=False)
os.remove("int_indexed_mini_gctoo.gctx")
assert_frame_equal(mg5.data_df, mg6.data_df)
assert_frame_equal(mg5.row_metadata_df, mg6.row_metadata_df)
assert_frame_equal(mg5.col_metadata_df, mg6.col_metadata_df)
# test with ridx/cidx
mg7 = slice_gct.slice_gctoo(mg1, rid=['LJP007_MCF7_24H:CTL_VEHICLE:DMSO:-666'],
cid='LJP007_MCF7_24H:CTL_VEHICLE:DMSO:-666')
mg8 = parse_gctx.parse("functional_tests/mini_gctoo_for_testing.gctx", ridx=[4], cidx=[4])
assert_frame_equal(mg7.data_df, mg8.data_df)
assert_frame_equal(mg7.row_metadata_df, mg8.row_metadata_df)
assert_frame_equal(mg7.col_metadata_df, mg8.col_metadata_df)
# test with rid/cidx
mg9 = parse_gctx.parse("functional_tests/mini_gctoo_for_testing.gctx", rid=['LJP007_MCF7_24H:CTL_VEHICLE:DMSO:-666'],
cidx = [4])
assert_frame_equal(mg7.data_df, mg9.data_df)
assert_frame_equal(mg7.row_metadata_df, mg9.row_metadata_df)
assert_frame_equal(mg7.col_metadata_df, mg9.col_metadata_df)
# test with ridx/cid
mg10 = parse_gctx.parse("functional_tests/mini_gctoo_for_testing.gctx", ridx=[4],
cid = ['LJP007_MCF7_24H:CTL_VEHICLE:DMSO:-666'])
assert_frame_equal(mg7.data_df, mg10.data_df)
assert_frame_equal(mg7.row_metadata_df, mg10.row_metadata_df)
assert_frame_equal(mg7.col_metadata_df, mg10.col_metadata_df)
def test_gctx_parsing(self):
# parse in gctx, no other arguments
mg1 = mini_gctoo_for_testing.make()
mg2 = parse("functional_tests/mini_gctoo_for_testing.gctx")
pandas_testing.assert_frame_equal(mg1.data_df, mg2.data_df)
pandas_testing.assert_frame_equal(mg1.row_metadata_df,
mg2.row_metadata_df)
pandas_testing.assert_frame_equal(mg1.col_metadata_df,
mg2.col_metadata_df)
# check convert_neg_666 worked correctly
self.assertTrue(mg2.col_metadata_df["mfc_plate_id"].isnull().all())
# parse w/o convert_neg_666
mg2_alt = parse("functional_tests/mini_gctoo_for_testing.gctx",
convert_neg_666=False)
self.assertFalse(
mg2_alt.col_metadata_df["mfc_plate_id"].isnull().all())
# parsing w/rids & cids specified
test_rids = [
'LJP007_MCF10A_24H:TRT_CP:BRD-K93918653:3.33',
'LJP007_MCF7_24H:CTL_VEHICLE:DMSO:-666'
]
test_cids = ['LJP007_MCF7_24H:TRT_POSCON:BRD-A61304759:10']
mg3 = slice_gct.slice_gctoo(mg1, rid=test_rids, cid=test_cids)
mg4 = parse("functional_tests/mini_gctoo_for_testing.gctx",
rid=test_rids,
cid=test_cids)
pandas_testing.assert_frame_equal(mg3.data_df, mg4.data_df)
pandas_testing.assert_frame_equal(mg3.row_metadata_df,
mg4.row_metadata_df)
pandas_testing.assert_frame_equal(mg3.col_metadata_df,
mg4.col_metadata_df)
# parsing w/ridx & cidx specified
mg5 = slice_gct.slice_gctoo(
mg1,
rid=['LJP007_MCF7_24H:CTL_VEHICLE:DMSO:-666'],
cid='LJP007_MCF7_24H:CTL_VEHICLE:DMSO:-666')
mg6 = parse("functional_tests/mini_gctoo_for_testing.gctx",
ridx=[4],
cidx=[4])
pandas_testing.assert_frame_equal(mg5.data_df, mg6.data_df)
pandas_testing.assert_frame_equal(mg5.row_metadata_df,
mg6.row_metadata_df)
pandas_testing.assert_frame_equal(mg5.col_metadata_df,
mg6.col_metadata_df)
# parsing row metadata only
mg7 = parse("functional_tests/mini_gctoo_for_testing.gctx",
row_meta_only=True)
pandas_testing.assert_frame_equal(mg7, mg1.row_metadata_df)
# parsing col metadata only
mg8 = parse("functional_tests/mini_gctoo_for_testing.gctx",
col_meta_only=True)
pandas_testing.assert_frame_equal(mg8, mg1.col_metadata_df)
# parsing w/multiindex
mg9 = parse("functional_tests/mini_gctoo_for_testing.gctx",
make_multiindex=True)
self.assertTrue(mg9.multi_index_df is not None)