Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

WIP: use identical column names as sourmash gather #259

Closed
wants to merge 1 commit into from
Closed

WIP: use identical column names as sourmash gather #259

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions src/mastiff_manygather.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,9 +85,9 @@ pub fn mastiff_manygather(
average_abund: match_.average_abund(),
median_abund: match_.median_abund(),
std_abund: match_.std_abund(),
match_filename: match_.filename().clone(),
match_name: match_.name().clone(),
match_md5: match_.md5().clone(),
filename: match_.filename().clone(),
name: match_.name().clone(),
md5: match_.md5().clone(),
f_match_orig: match_.f_match_orig(),
unique_intersect_bp: match_.unique_intersect_bp(),
gather_result_rank: match_.gather_result_rank(),
Expand Down
56 changes: 24 additions & 32 deletions src/python/tests/test_multigather.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,7 +71,6 @@ def test_simple(runtmp, zip_against):
p_output = runtmp.output('SRR606249.prefetch.csv')
assert os.path.exists(p_output)

# check prefetch output (only non-indexed gather)
df = pandas.read_csv(p_output)
assert len(df) == 3
keys = set(df.keys())
Expand Down Expand Up @@ -145,7 +144,6 @@ def test_simple_zip_query(runtmp):
g_output = runtmp.output('SRR606249.gather.csv')
p_output = runtmp.output('SRR606249.prefetch.csv')

# check prefetch output (only non-indexed gather)
assert os.path.exists(p_output)
df = pandas.read_csv(p_output)
assert len(df) == 3
Expand Down Expand Up @@ -188,7 +186,6 @@ def test_simple_read_manifests(runtmp):
g_output = runtmp.output('SRR606249.gather.csv')
p_output = runtmp.output('SRR606249.prefetch.csv')

# check prefetch output (only non-indexed gather)
assert os.path.exists(p_output)
df = pandas.read_csv(p_output)
assert len(df) == 3
Expand Down Expand Up @@ -229,12 +226,12 @@ def test_simple_indexed(runtmp, zip_query):
df = pandas.read_csv(g_output)
assert len(df) == 3
keys = set(df.keys())
expected_keys = {'match_name', 'query_filename', 'query_n_hashes', 'match_filename', 'f_match_orig',
expected_keys = {'name', 'query_filename', 'query_n_hashes', 'filename', 'f_match_orig',
'query_bp', 'query_abundance', 'match_containment_ani', 'intersect_bp', 'total_weighted_hashes',
'n_unique_weighted_found', 'query_name', 'gather_result_rank', 'moltype',
'query_containment_ani', 'sum_weighted_found', 'f_orig_query', 'ksize', 'max_containment_ani',
'std_abund', 'scaled', 'average_containment_ani', 'f_match', 'f_unique_to_query',
'average_abund', 'unique_intersect_bp', 'median_abund', 'query_md5', 'match_md5', 'remaining_bp',
'average_abund', 'unique_intersect_bp', 'median_abund', 'query_md5', 'md5', 'remaining_bp',
'f_unique_weighted'}
assert keys == expected_keys

Expand Down Expand Up @@ -262,12 +259,12 @@ def test_simple_indexed_query_manifest(runtmp):
df = pandas.read_csv(g_output)
assert len(df) == 3
keys = set(df.keys())
expected_keys = {'match_name', 'query_filename', 'query_n_hashes', 'match_filename', 'f_match_orig',
expected_keys = {'name', 'query_filename', 'query_n_hashes', 'filename', 'f_match_orig',
'query_bp', 'query_abundance', 'match_containment_ani', 'intersect_bp', 'total_weighted_hashes',
'n_unique_weighted_found', 'query_name', 'gather_result_rank', 'moltype',
'query_containment_ani', 'sum_weighted_found', 'f_orig_query', 'ksize', 'max_containment_ani',
'std_abund', 'scaled', 'average_containment_ani', 'f_match', 'f_unique_to_query',
'average_abund', 'unique_intersect_bp', 'median_abund', 'query_md5', 'match_md5', 'remaining_bp',
'average_abund', 'unique_intersect_bp', 'median_abund', 'query_md5', 'md5', 'remaining_bp',
'f_unique_weighted'}
assert keys == expected_keys

Expand Down Expand Up @@ -339,7 +336,7 @@ def test_sig_query(runtmp, capfd, indexed):
assert len(df) == 3
keys = set(df.keys())
if indexed:
assert {'query_name', 'query_md5', 'match_name', 'match_md5', 'f_match', 'intersect_bp'}.issubset(keys)
assert {'query_name', 'query_md5', 'name', 'md5', 'f_match', 'intersect_bp'}.issubset(keys)
else:
assert {'query_filename', 'query_name', 'query_md5', 'match_name', 'match_md5', 'rank', 'intersect_bp'}.issubset(keys)

Expand Down Expand Up @@ -470,7 +467,6 @@ def test_sig_against(runtmp, capfd):
captured = capfd.readouterr()
print(captured.err)

# check prefetch output (only non-indexed gather)
assert os.path.exists(p_output)
df = pandas.read_csv(p_output)
assert len(df) == 1
Expand Down Expand Up @@ -608,7 +604,6 @@ def test_md5(runtmp, zip_query):
g_output = runtmp.output('SRR606249.gather.csv')
p_output = runtmp.output('SRR606249.prefetch.csv')

# check prefetch output (only non-indexed gather)
assert os.path.exists(p_output)
df = pandas.read_csv(p_output)
assert len(df) == 3
Expand All @@ -620,7 +615,6 @@ def test_md5(runtmp, zip_query):
for ss in sourmash.load_file_as_signatures(against_file, ksize=31):
assert ss.md5sum() in md5s

# check gather output (mostly same for indexed vs non-indexed version)
assert os.path.exists(g_output)
df = pandas.read_csv(g_output)
assert len(df) == 3
Expand Down Expand Up @@ -661,16 +655,16 @@ def test_md5_indexed(runtmp, zip_query):
df = pandas.read_csv(g_output)
assert len(df) == 3
keys = set(df.keys())
expected_keys = {'match_name', 'query_filename', 'query_n_hashes', 'match_filename', 'f_match_orig',
expected_keys = {'name', 'query_filename', 'query_n_hashes', 'filename', 'f_match_orig',
'query_bp', 'query_abundance', 'match_containment_ani', 'intersect_bp', 'total_weighted_hashes',
'n_unique_weighted_found', 'query_name', 'gather_result_rank', 'moltype',
'query_containment_ani', 'sum_weighted_found', 'f_orig_query', 'ksize', 'max_containment_ani',
'std_abund', 'scaled', 'average_containment_ani', 'f_match', 'f_unique_to_query',
'average_abund', 'unique_intersect_bp', 'median_abund', 'query_md5', 'match_md5', 'remaining_bp',
'average_abund', 'unique_intersect_bp', 'median_abund', 'query_md5', 'md5', 'remaining_bp',
'f_unique_weighted'}
assert keys == expected_keys

md5s = set(df['match_md5'])
md5s = set(df['md5'])
for against_file in (sig2, sig47, sig63):
for ss in sourmash.load_file_as_signatures(against_file, ksize=31):
assert ss.md5sum() in md5s
Expand Down Expand Up @@ -752,20 +746,18 @@ def test_csv_columns_vs_sourmash_gather_indexed(runtmp):

gather_df = pandas.read_csv(g_output)
g_keys = set(gather_df.keys())
expected_keys = {'match_name', 'query_filename', 'query_n_hashes', 'match_filename', 'f_match_orig',
expected_keys = {'name', 'query_filename', 'query_n_hashes', 'filename', 'f_match_orig',
'query_bp', 'query_abundance', 'match_containment_ani', 'intersect_bp', 'total_weighted_hashes',
'n_unique_weighted_found', 'query_name', 'gather_result_rank', 'moltype',
'query_containment_ani', 'sum_weighted_found', 'f_orig_query', 'ksize', 'max_containment_ani',
'std_abund', 'scaled', 'average_containment_ani', 'f_match', 'f_unique_to_query',
'average_abund', 'unique_intersect_bp', 'median_abund', 'query_md5', 'match_md5', 'remaining_bp',
'average_abund', 'unique_intersect_bp', 'median_abund', 'query_md5', 'md5', 'remaining_bp',
'f_unique_weighted'}
assert g_keys == expected_keys

sourmash_gather_df = pandas.read_csv(sg_output)
sg_keys = set(sourmash_gather_df.keys())
print(sg_keys)
modified_keys = ["match_md5", "match_name", "match_filename"]
sg_keys.update(modified_keys) # fastmultigather is more explicit (match_md5 instead of md5, etc)
print('g_keys - sg_keys:', g_keys - sg_keys)
assert not g_keys - sg_keys, g_keys - sg_keys

Expand Down Expand Up @@ -861,18 +853,18 @@ def test_simple_protein_indexed(runtmp):
df = pandas.read_csv(out_csv)
assert len(df) == 2
keys = set(df.keys())
expected_keys = {'match_name', 'query_filename', 'query_n_hashes', 'match_filename', 'f_match_orig',
expected_keys = {'name', 'query_filename', 'query_n_hashes', 'filename', 'f_match_orig',
'query_bp', 'query_abundance', 'match_containment_ani', 'intersect_bp', 'total_weighted_hashes',
'n_unique_weighted_found', 'query_name', 'gather_result_rank', 'moltype',
'query_containment_ani', 'sum_weighted_found', 'f_orig_query', 'ksize', 'max_containment_ani',
'std_abund', 'scaled', 'average_containment_ani', 'f_match', 'f_unique_to_query',
'average_abund', 'unique_intersect_bp', 'median_abund', 'query_md5', 'match_md5', 'remaining_bp',
'average_abund', 'unique_intersect_bp', 'median_abund', 'query_md5', 'md5', 'remaining_bp',
'f_unique_weighted'}
assert keys == expected_keys
print(df)
# since we're just matching to identical sigs, the md5s should be the same
assert df['query_md5'][0] == df['match_md5'][0]
assert df['query_md5'][1] == df['match_md5'][1]
assert df['query_md5'][0] == df['md5'][0]
assert df['query_md5'][1] == df['md5'][1]


def test_simple_dayhoff_indexed(runtmp):
Expand All @@ -891,18 +883,18 @@ def test_simple_dayhoff_indexed(runtmp):
df = pandas.read_csv(out_csv)
assert len(df) == 2
keys = set(df.keys())
expected_keys = {'match_name', 'query_filename', 'query_n_hashes', 'match_filename', 'f_match_orig',
expected_keys = {'name', 'query_filename', 'query_n_hashes', 'filename', 'f_match_orig',
'query_bp', 'query_abundance', 'match_containment_ani', 'intersect_bp', 'total_weighted_hashes',
'n_unique_weighted_found', 'query_name', 'gather_result_rank', 'moltype',
'query_containment_ani', 'sum_weighted_found', 'f_orig_query', 'ksize', 'max_containment_ani',
'std_abund', 'scaled', 'average_containment_ani', 'f_match', 'f_unique_to_query',
'average_abund', 'unique_intersect_bp', 'median_abund', 'query_md5', 'match_md5', 'remaining_bp',
'average_abund', 'unique_intersect_bp', 'median_abund', 'query_md5', 'md5', 'remaining_bp',
'f_unique_weighted'}
assert keys == expected_keys
print(df)
# since we're just matching to identical sigs, the md5s should be the same
assert df['query_md5'][0] == df['match_md5'][0]
assert df['query_md5'][1] == df['match_md5'][1]
assert df['query_md5'][0] == df['md5'][0]
assert df['query_md5'][1] == df['md5'][1]


def test_simple_hp_indexed(runtmp):
Expand All @@ -921,18 +913,18 @@ def test_simple_hp_indexed(runtmp):
df = pandas.read_csv(out_csv)
assert len(df) == 2
keys = set(df.keys())
expected_keys = {'match_name', 'query_filename', 'query_n_hashes', 'match_filename', 'f_match_orig',
expected_keys = {'name', 'query_filename', 'query_n_hashes', 'filename', 'f_match_orig',
'query_bp', 'query_abundance', 'match_containment_ani', 'intersect_bp', 'total_weighted_hashes',
'n_unique_weighted_found', 'query_name', 'gather_result_rank', 'moltype',
'query_containment_ani', 'sum_weighted_found', 'f_orig_query', 'ksize', 'max_containment_ani',
'std_abund', 'scaled', 'average_containment_ani', 'f_match', 'f_unique_to_query',
'average_abund', 'unique_intersect_bp', 'median_abund', 'query_md5', 'match_md5', 'remaining_bp',
'average_abund', 'unique_intersect_bp', 'median_abund', 'query_md5', 'md5', 'remaining_bp',
'f_unique_weighted'}
assert keys == expected_keys
print(df)
# since we're just matching to identical sigs, the md5s should be the same
assert df['query_md5'][0] == df['match_md5'][0]
assert df['query_md5'][1] == df['match_md5'][1]
assert df['query_md5'][0] == df['md5'][0]
assert df['query_md5'][1] == df['md5'][1]


def test_indexed_full_output(runtmp):
Expand All @@ -959,12 +951,12 @@ def test_indexed_full_output(runtmp):
df = pandas.read_csv(g_output)
assert len(df) == 3
keys = set(df.keys())
expected_keys = {'match_name', 'query_filename', 'query_n_hashes', 'match_filename', 'f_match_orig',
expected_keys = {'name', 'query_filename', 'query_n_hashes', 'filename', 'f_match_orig',
'query_bp', 'query_abundance', 'match_containment_ani', 'intersect_bp', 'total_weighted_hashes',
'n_unique_weighted_found', 'query_name', 'gather_result_rank', 'moltype',
'query_containment_ani', 'sum_weighted_found', 'f_orig_query', 'ksize', 'max_containment_ani',
'std_abund', 'scaled', 'average_containment_ani', 'f_match', 'f_unique_to_query',
'average_abund', 'unique_intersect_bp', 'median_abund', 'query_md5', 'match_md5', 'remaining_bp',
'average_abund', 'unique_intersect_bp', 'median_abund', 'query_md5', 'md5', 'remaining_bp',
'f_unique_weighted'}
assert keys == expected_keys
results = df.values.tolist()
Expand Down
6 changes: 3 additions & 3 deletions src/utils.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -812,9 +812,9 @@ pub struct BranchwaterGatherResult {
pub average_abund: f64,
pub median_abund: f64,
pub std_abund: f64,
pub match_filename: String,
pub match_name: String,
pub match_md5: String,
pub filename: String,
pub name: String,
pub md5: String,
pub f_match_orig: f64,
pub unique_intersect_bp: usize,
pub gather_result_rank: usize,
Expand Down
Loading