snplib 1.0.7__py3-none-any.whl → 1.0.9__py3-none-any.whl

snplib/format/tests/test_plink_map.py

@@ -1,42 +0,0 @@
-#!/usr/bin/env python
-# coding: utf-8
-__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
-
-from . import DIR_FILES
-from .. import make_map
-
-import pytest
-import pandas as pd
-
-
-@pytest.fixture
-def data_map() -> pd.DataFrame:
-	return pd.read_csv(DIR_FILES / "fplink/map/file_bovinesnp50.csv")
-
-
-class TestPlinkFormatMap(object):
-
-	def test_map_true(self, data_map) -> None:
-
-		res = make_map(data_map)
-		assert not res.empty
-
-	def test_map_raise(self, data_map) -> None:
-		with pytest.raises(
-				KeyError, match="Manifest has no data to build map format!"
-		):
-			make_map(data_map)
-			make_map(pd.DataFrame())
-			make_map(
-				pd.DataFrame(columns=['Chr', 'Name', 'MapInfo', 'morgans'])
-			)
-
-		with pytest.raises(
-				KeyError, match="Manifest has no data to build map format!"
-		):
-			make_map(pd.DataFrame())
-
-	def test_map_empty(self) -> None:
-		assert make_map(
-				pd.DataFrame(columns=['Chr', 'Name', 'MapInfo', 'morgans'])
-			).empty

snplib/format/tests/test_plink_ped.py

@@ -1,136 +0,0 @@
-#!/usr/bin/env python
-# coding: utf-8
-__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
-
-from . import DIR_FILES
-from .. import make_ped
-
-import pytest
-import pandas as pd
-
-
-@pytest.fixture
-def data_ped(request) -> pd.DataFrame | None:
-	return pd.read_pickle(DIR_FILES / f"fplink/ped/{request.param}")
-
-
-class TestPlinkFormatPed(object):
-
-	@pytest.mark.parametrize("data_ped", ["file.pl"], indirect=True)
-	def test_ped_true(self, data_ped: pd.DataFrame) -> None:
-		assert not make_ped(
-			data_ped,
-			"SAMPLE_ID",
-			"SNP",
-			fid_col="SAMPLE_ID"
-		).empty
-
-		assert not make_ped(
-			data_ped,
-			"SAMPLE_ID",
-			"SNP"
-		).empty
-
-	def test_ped_empty(self) -> None:
-		assert make_ped(
-			pd.DataFrame(columns=["SAMPLE_ID", "SNP"]),
-			"SAMPLE_ID",
-			"SNP"
-		).empty
-
-		assert make_ped(
-			pd.DataFrame(columns=["SAMPLE_ID", "SNP"]),
-			"SAMPLE_ID",
-			"SNP",
-			fid_col="SAMPLE_ID"
-		).empty
-
-	@pytest.mark.parametrize("data_ped", ["file.pl"], indirect=True)
-	def test_ped_raise_columns(self, data_ped: pd.DataFrame) -> None:
-		# SID_COL
-		with pytest.raises(
-				KeyError, match="Data has not in name columns!"
-		):
-			make_ped(
-				data=data_ped,
-				sid_col="SAMPLE_ID1",
-				fid_col="SAMPLE_ID",
-				snp_col="SNP"
-			)
-
-		# SNP_COL
-		with pytest.raises(
-				KeyError, match="Data has not in name columns!"
-		):
-			make_ped(
-				data_ped,
-				"SAMPLE_ID",
-				"SNP1",
-				fid_col="SAMPLE_ID"
-			)
-
-		# FID_COL
-		with pytest.raises(
-				KeyError, match="Data has not in name columns SAMPLE_ID1!"
-		):
-			make_ped(
-				data_ped,
-				"SAMPLE_ID",
-				"SNP",
-				fid_col="SAMPLE_ID1"
-			)
-
-	@pytest.mark.parametrize("data_ped", ["file2.pl"], indirect=True)
-	def test_ped_raises_underscope_sid(self, data_ped: pd.DataFrame) -> None:
-
-		# SID_COL
-		with pytest.raises(
-				Exception,
-				match="Replace in 'Sample ID' columns '_' on another a simbols"
-		):
-			res = make_ped(
-				data_ped,
-				"SAMPLE_ID",
-				"SNP"
-			)
-
-	@pytest.mark.parametrize("data_ped", ["file3.pl"], indirect=True)
-	def test_ped_raises_underscope_fid(self, data_ped: pd.DataFrame) -> None:
-
-		# FID_COL
-		with pytest.raises(
-				Exception,
-				match="Replace in 'Family ID' columns '_' on another a simbols"
-		):
-			res = make_ped(
-				data_ped,
-				"SAMPLE_ID",
-				"SNP",
-				fid_col="FAMILY_ID"
-			)
-
-	@pytest.mark.parametrize("data_ped", ["file4.pl"], indirect=True)
-	def test_ped_check_data(self, data_ped: pd.DataFrame) -> None:
-		res = make_ped(
-			data_ped,
-			"SAMPLE_ID",
-			"SNP",
-			fid_col="FAMILY_ID",
-			father_col="father",
-			mother_col="mother",
-			sex_col="sex"
-		)
-
-		res2 = make_ped(
-			data_ped,
-			"SAMPLE_ID",
-			"SNP",
-			fid_col="FAMILY_ID",
-		)
-
-		assert all(res.father.values == list('1234'))
-		assert all(res.mother.values == list('5678'))
-		assert all(res.sex.values == list('1210'))
-		assert all(res2.father.values == list('0000'))
-		assert all(res2.mother.values == list('0000'))
-		assert all(res2.sex.values == list('0000'))

snplib/format/tests/test_snp.py

@@ -1,128 +0,0 @@
-#!/usr/bin/env python
-# coding: utf-8
-__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
-
-from . import DIR_FILES
-from .. import Snp
-
-import pytest
-import pandas as pd
-
-
-@pytest.fixture
-def data_fr(request) -> pd.DataFrame:
-	return pd.read_csv(DIR_FILES / f"fsnp/{request.param}", sep="\t")
-
-
-@pytest.fixture
-def obj_snp(request) -> Snp:
-	return Snp(fmt=request.param)
-
-
-class TestSNP(object):
-
-	@pytest.mark.parametrize(
-		"obj_snp, data_fr", [("uga", 'file1.txt')], indirect=True
-	)
-	def test_snp_process_uga_true(
-			self, obj_snp: Snp, data_fr: pd.DataFrame
-	) -> None:
-
-		obj_snp.process(data_fr)
-		assert obj_snp.data is not None and not obj_snp.data.empty
-		assert obj_snp.data.SNP.isin([
-			'02011015010000500', '01110152120222512'
-		]).all()
-
-	@pytest.mark.parametrize("obj_snp", ["uga"], indirect=True)
-	def test_snp_process_uga_empty(self, obj_snp: Snp) -> None:
-
-		obj_snp.process(pd.DataFrame(columns=[
-			'SNP Name', 'Sample ID', 'Allele1 - AB', 'Allele2 - AB',
-			'GC Score', 'GT Score'
-		]))
-		assert obj_snp.data is not None and obj_snp.data.empty
-
-	@pytest.mark.parametrize(
-		"obj_snp, data_fr",
-		[("uga", 'file1.txt'), (None, 'file1.txt')],
-		indirect=True
-	)
-	def test_snp_process_raises(
-			self, obj_snp: Snp, data_fr: pd.DataFrame
-	) -> None:
-
-		with pytest.raises(KeyError):
-			obj_snp.process(pd.DataFrame(columns=[
-				'SNP Name1', 'Sample ID1', 'Allele1 - AB', 'Allele2 - AB',
-				'GC Score', 'GT Score'
-			]))
-
-		assert obj_snp.data is None
-
-	@pytest.mark.parametrize(
-		"obj_snp, data_fr", [(None, 'file1.txt')], indirect=True
-	)
-	def test_snp_process_df(
-			self, obj_snp: Snp, data_fr: pd.DataFrame
-	) -> None:
-
-		obj_snp.process(data_fr)
-		assert obj_snp.data is not None and not obj_snp.data.empty
-
-	@pytest.mark.parametrize("obj_snp", [None], indirect=True)
-	def test_snp_process_df_empty(self, obj_snp: Snp) -> None:
-
-		obj_snp.process(pd.DataFrame(columns=[
-			'SNP Name', 'Sample ID', 'Allele1 - AB', 'Allele2 - AB',
-			'GC Score', 'GT Score'
-		]))
-		assert obj_snp.data is not None and obj_snp.data.empty
-
-	@pytest.mark.parametrize(
-		"obj_snp, data_fr", [("uga", 'file1.txt')], indirect=True
-	)
-	def test_snp_to_file_uga1(
-			self, obj_snp: Snp, data_fr: pd.DataFrame, tmp_path
-	) -> None:
-		"""
-		The name sample_id is one length
-		"""
-
-		_dir_sub = tmp_path / "sub"
-		_dir_sub.mkdir()
-		_file_save = _dir_sub / "data_snp.csv"
-
-		obj_snp.process(data_fr)
-		assert obj_snp.data is not None and not obj_snp.data.empty
-
-		obj_snp.to_file(_file_save)
-		assert _file_save.is_file() and _file_save.exists()
-		assert (
-			_file_save.read_text() ==
-			"14814 02011015010000500\n14815 01110152120222512\n"
-		)
-
-	@pytest.mark.parametrize(
-		"obj_snp, data_fr", [("uga", 'file2.txt')], indirect=True
-	)
-	def test_snp_to_file_uga2(
-			self, obj_snp: Snp, data_fr: pd.DataFrame, tmp_path
-	) -> None:
-		"""
-		The name sample_id of different length
-		"""
-
-		_dir_sub = tmp_path / "sub"
-		_dir_sub.mkdir()
-		_file_save = _dir_sub / "data_snp.csv"
-
-		obj_snp.process(data_fr)
-		assert obj_snp.data is not None and not obj_snp.data.empty
-
-		obj_snp.to_file(_file_save)
-		assert _file_save.is_file() and _file_save.exists()
-		assert (
-			_file_save.read_text() ==
-			"14814qwert 02011015010000500\n14815      01110152120222512\n"
-		)

snplib/parentage/tests/__init__.py

@@ -1,7 +0,0 @@
-#!/usr/bin/env python
-# coding: utf-8
-__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
-
-from pathlib import Path
-
-DIR_DATA = Path(__file__).parent.joinpath("data")

snplib/parentage/tests/test_discov.py

@@ -1,164 +0,0 @@
-#!/usr/bin/env python
-# coding: utf-8
-__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
-
-from . import DIR_DATA
-from .. import Discovery, isag_disc
-
-import pytest
-import pandas as pd
-
-
-@pytest.fixture
-def data() -> pd.DataFrame:
-	return pd.read_csv(DIR_DATA / "parentage_test_disc.csv", sep=" ")
-
-
-@pytest.fixture
-def obj_discovery() -> Discovery:
-	return Discovery(isag_markers=isag_disc().markers)
-
-
-class TestDiscovery(object):
-
-	def test_search_parent_successfully(
-		self, data: pd.DataFrame, obj_discovery: Discovery
-	) -> None:
-
-		assert obj_discovery.search_parent(
-			data=data,
-			descendant="BY000041988163",
-			parents="EE10512586",
-			snp_name_col="SNP_Name"
-		) is None
-		assert obj_discovery.num_conflicts == 77
-		assert obj_discovery.status == "Excluded"
-		assert obj_discovery.perc_conflicts == 14.86
-
-	def test_search_parent_1(self, data: pd.DataFrame) -> None:
-		"""
-		An exception is thrown for the absence of data with isag markers
-		"""
-		obj_discovery = Discovery()
-
-		with pytest.raises(
-			ValueError, match="Error. No array of snp names to verify"
-		):
-			obj_discovery.search_parent(
-				data=data,
-				descendant="BY000041988163",
-				parents="EE10512586",
-				snp_name_col="SNP_Name"
-			)
-		assert obj_discovery.status is None
-		assert obj_discovery.num_conflicts is None
-		assert obj_discovery.perc_conflicts is None
-
-	def test_search_parent_2(
-		self, data: pd.DataFrame, obj_discovery: Discovery
-	) -> None:
-		"""
-		Exception when the number of markers required to confirm paternity is
-		less than the established value.
-		"""
-
-		with pytest.raises(
-			Exception, match="Calf call rate is low."
-		):
-			obj_discovery.search_parent(
-				data=data[:-100],
-				descendant="BY000041988163",
-				parents="EE10512586",
-				snp_name_col="SNP_Name"
-			)
-		assert obj_discovery.status is None
-		assert obj_discovery.num_conflicts is None
-		assert obj_discovery.perc_conflicts is None
-
-	def test_search_parent_3(
-		self, data: pd.DataFrame, obj_discovery: Discovery
-	) -> None:
-		"""
-		Test if the transmitted animal names are not in the dataframe.
-		"""
-
-		# For descendant
-		with pytest.raises(KeyError):
-			obj_discovery.search_parent(
-				data=data,
-				descendant="BY00004198816",
-				parents="EE10512586",
-				snp_name_col="SNP_Name"
-			)
-		assert obj_discovery.status is None
-		assert obj_discovery.num_conflicts is None
-		assert obj_discovery.perc_conflicts is None
-
-		# For parents
-		with pytest.raises(KeyError):
-			obj_discovery.search_parent(
-				data=data,
-				descendant="BY000041988163",
-				parents="EE105125864",
-				snp_name_col="SNP_Name"
-			)
-		assert obj_discovery.status is None
-		assert obj_discovery.num_conflicts is None
-		assert obj_discovery.perc_conflicts is None
-
-	def test_search_parent_4(
-		self, data: pd.DataFrame, obj_discovery: Discovery
-	) -> None:
-		"""
-		Test when all snp data is not read - equal to 5.
-		"""
-		data[["BY000041988163", "EE10512586"]] = 5
-
-		with pytest.raises(
-			Exception, match="Calf call rate is low."
-		):
-			obj_discovery.search_parent(
-				data=data,
-				descendant="BY000041988163",
-				parents="EE10512586",
-				snp_name_col="SNP_Name"
-			)
-		assert obj_discovery.status is None
-		assert obj_discovery.num_conflicts is None
-		assert obj_discovery.perc_conflicts is None
-
-	def test_search_parent_5(
-			self, data: pd.DataFrame, obj_discovery: Discovery
-	) -> None:
-		"""
-		Test when there is a complete match.
-		"""
-		data[["BY000041988163", "EE10512586"]] = 2
-
-		obj_discovery.search_parent(
-			data=data,
-			descendant="BY000041988163",
-			parents="EE10512586",
-			snp_name_col="SNP_Name"
-		)
-		assert obj_discovery.status == "Discovered"
-		assert obj_discovery.num_conflicts == 0
-		assert obj_discovery.perc_conflicts == 0.0
-
-	def test_search_parent_6(
-			self, data: pd.DataFrame, obj_discovery: Discovery
-	) -> None:
-		"""
-		Partial match test.
-		"""
-		data.loc[202:, "EE10512586"] = 1
-
-		obj_discovery.search_parent(
-			data=data,
-			descendant="BY000041988163",
-			parents="EE10512586",
-			snp_name_col="SNP_Name"
-		)
-		assert obj_discovery.status == "Doubtful"
-		assert obj_discovery.num_conflicts == 14
-		assert obj_discovery.perc_conflicts == 2.70

snplib/parentage/tests/test_verif.py

@@ -1,160 +0,0 @@
-#!/usr/bin/env python
-# coding: utf-8
-__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
-
-from . import DIR_DATA
-from .. import Verification, isag_verif
-
-import pytest
-import pandas as pd
-
-
-@pytest.fixture
-def data() -> pd.DataFrame:
-	return pd.read_csv(DIR_DATA / "parentage_test_verf.csv", sep=" ")
-
-
-@pytest.fixture
-def obj_verification() -> Verification:
-	return Verification(isag_marks=isag_verif().markers)
-
-
-class TestVerification(object):
-
-	def test_check_on_successfully(
-		self, data: pd.DataFrame, obj_verification: Verification
-	) -> None:
-
-		assert obj_verification.check_on(
-			data=data,
-			descendant="BY000041988163",
-			parent="EE10512586",
-			snp_name_col="SNP_Name"
-		) is None
-		assert obj_verification.num_conflicts == 31
-		assert obj_verification.status == "Excluded"
-
-	def test_check_on_1(self, data: pd.DataFrame) -> None:
-		"""
-		The test checks the exception for missing token data for verification.
-		"""
-		obj_verification = Verification()
-
-		with pytest.raises(
-			ValueError, match="Error. No array of snp names to verify"
-		):
-			obj_verification.check_on(
-				data=data,
-				descendant="BY000041988163",
-				parent="EE10512586",
-				snp_name_col="SNP_Name"
-			)
-		assert obj_verification.status is None
-		assert obj_verification.num_conflicts is None
-
-	def test_check_on_2(
-		self, data: pd.DataFrame, obj_verification: Verification
-	) -> None:
-		"""
-		Exception for low call rate in both animals.
-		"""
-
-		with pytest.raises(
-			Exception, match="Calf and parent have low call rate"
-		):
-			obj_verification.check_on(
-				data=data[:-100],
-				descendant="BY000041988163",
-				parent="EE10512586",
-				snp_name_col="SNP_Name"
-			)
-		assert obj_verification.status is None
-		assert obj_verification.num_conflicts is None
-
-	def test_check_on_3(
-		self, data: pd.DataFrame, obj_verification: Verification
-	) -> None:
-		"""
-		Exception when paired call rate is below threshold.
-		"""
-
-		data.loc[228:, 'BY000041988163'] = 5
-		data.loc[239:, 'EE10512586'] = 5
-
-		with pytest.raises(
-			Exception, match="Pair call rate is low"
-		):
-			obj_verification.check_on(
-				data=data,
-				descendant="BY000041988163",
-				parent="EE10512586",
-				snp_name_col="SNP_Name"
-			)
-		assert obj_verification.status is None
-		assert obj_verification.num_conflicts is None
-
-	def test_search_parent_4(
-		self, data: pd.DataFrame, obj_verification: Verification
-	) -> None:
-		"""
-		Test if the transmitted animal names are not in the dataframe.
-		"""
-
-		# For descendant
-		with pytest.raises(KeyError):
-			obj_verification.check_on(
-				data=data,
-				descendant="BY00004198816",
-				parent="EE10512586",
-				snp_name_col="SNP_Name"
-			)
-		assert obj_verification.status is None
-		assert obj_verification.num_conflicts is None
-
-		# For parents
-		with pytest.raises(KeyError):
-			obj_verification.check_on(
-				data=data,
-				descendant="BY000041988163",
-				parent="EE105125864",
-				snp_name_col="SNP_Name"
-			)
-		assert obj_verification.status is None
-		assert obj_verification.num_conflicts is None
-
-	def test_search_parent_5(
-		self, data: pd.DataFrame, obj_verification: Verification
-	) -> None:
-		"""
-		Test when all snp data is not read - equal to 5
-		"""
-		data[["BY000041988163", "EE10512586"]] = 5
-
-		with pytest.raises(
-			Exception, match="Calf and parent have low call rate"
-		):
-			obj_verification.check_on(
-				data=data,
-				descendant="BY000041988163",
-				parent="EE10512586",
-				snp_name_col="SNP_Name"
-			)
-		assert obj_verification.status is None
-		assert obj_verification.num_conflicts is None
-
-	def test_search_parent_6(
-			self, data: pd.DataFrame, obj_verification: Verification
-	) -> None:
-		"""
-		Test when there is a complete match
-		"""
-		data[["BY000041988163", "EE10512586"]] = 2
-
-		obj_verification.check_on(
-			data=data,
-			descendant="BY000041988163",
-			parent="EE10512586",
-			snp_name_col="SNP_Name"
-		)
-		assert obj_verification.status == "Accept"
-		assert obj_verification.num_conflicts == 0

snplib/statistics/tests/__init__.py

@@ -1,7 +0,0 @@
-#!/usr/bin/env python
-# coding: utf-8
-__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
-
-from pathlib import Path
-
-DIR_DATA = Path(__file__).parent.joinpath("data")