snplib 1.0.7__py3-none-any.whl → 1.0.8__py3-none-any.whl

snplib/statistics/tests/test_callrate.py

@@ -1,171 +0,0 @@
-#!/usr/bin/env python
-# coding: utf-8
-__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
-
-from . import DIR_DATA
-from .. import call_rate
-
-import pytest
-import numpy as np
-import pandas as pd
-
-
-@pytest.fixture
-def data_df(request) -> pd.DataFrame:
-	match request.param:
-		case "cra":
-			return pd.read_pickle(DIR_DATA / "cr/file_cra.pl")
-
-		case "crm":
-			return pd.read_pickle(DIR_DATA / "cr/file_crm.pl")
-
-
-@pytest.fixture
-def data_str() -> list[str]:
-	return ['02011015010000500', '01110152120222512']
-
-
-class TestCallRateAnimal(object):
-
-	@pytest.mark.parametrize("data_df", ["cra"], indirect=True)
-	def test_cra_datafame_dtype_obj(self, data_df: pd.DataFrame) -> None:
-		data_df.SNP = data_df.SNP.astype(str)
-		result = call_rate(data=data_df, id_col="SAMPLE_ID", snp_col="SNP")
-
-		assert isinstance(result, pd.DataFrame) and not result.empty
-		assert result.SNP.round(6).isin([0.882353, 0.882353]).all()
-
-	@pytest.mark.parametrize("data_df", ["cra"], indirect=True)
-	def test_cra_datafame_dtype_int(self, data_df: pd.DataFrame) -> None:
-		data_df.SNP = data_df.SNP.astype("int8")
-		result = call_rate(data=data_df, id_col="SAMPLE_ID", snp_col="SNP")
-
-		assert isinstance(result, pd.DataFrame) and not result.empty
-		assert result.SNP.round(6).isin([0.882353, 0.882353]).all()
-
-	@pytest.mark.parametrize("data_df", ["cra"], indirect=True)
-	def test_cra_datafame_dtype_float(self, data_df: pd.DataFrame) -> None:
-		data_df.SNP = data_df.SNP.astype("float32")
-		result = call_rate(data=data_df, id_col="SAMPLE_ID", snp_col="SNP")
-
-		assert isinstance(result, pd.DataFrame) and not result.empty
-		assert result.SNP.round(6).isin([0.882353, 0.882353]).all()
-
-	@pytest.mark.parametrize("data_df", ["cra"], indirect=True)
-	def test_cra_datafame_dtype_random_simbols(
-		self, data_df: pd.DataFrame
-	) -> None:
-		data_df.SNP = [
-			np.random.choice(["A", "C", "G", "T"])
-			for _ in range(data_df.SNP.shape[0])
-		]
-		result = call_rate(data=data_df, id_col="SAMPLE_ID", snp_col="SNP")
-
-		assert result is None
-
-	def test_cra_datafame_empty1(self) -> None:
-		with pytest.raises(KeyError):
-			call_rate(data=pd.DataFrame(), id_col="SAMPLE_ID", snp_col="SNP")
-
-	def test_cra_datafame_empty2(self) -> None:
-		result = call_rate(
-			data=pd.DataFrame(columns=["SAMPLE_ID", "SNP"]),
-			id_col="SAMPLE_ID",
-			snp_col="SNP"
-		)
-
-		assert isinstance(result, pd.DataFrame) and result.empty
-
-	@pytest.mark.parametrize("data_df", ["cra"], indirect=True)
-	def test_cra_datafame_fail(self, data_df: pd.DataFrame) -> None:
-		with pytest.raises(KeyError):
-			call_rate(data=data_df, id_col="SAMPLE_ID")
-			call_rate(data=data_df, snp_col="SNP")
-			call_rate(data=data_df)
-
-	def test_cra_str_int(self, data_str: list[str]) -> None:
-		for sequence in data_str:
-			assert call_rate(data=sequence) == 0.882353
-
-	def test_cra_str_simbols(self) -> None:
-		data_str = ['GCATGAGGTATACTCTA', 'CGCCATGCTGTATATCC']
-
-		for sequence in data_str:
-			assert call_rate(data=sequence) is None
-
-	def test_cra_str_empty(self) -> None:
-		assert call_rate(data="") is None
-
-	def test_cra_str_mixid(self) -> None:
-		assert call_rate(data="GCATGAG3G4T6A67TACTCTA") is None
-
-
-class TestCallRateMarker(object):
-
-	@pytest.mark.parametrize("data_df", ["crm"], indirect=True)
-	def test_crm_datafame_dtype_obj(self, data_df: pd.DataFrame) -> None:
-		data_df.SNP = data_df.SNP.astype(str)
-		result = call_rate(data=data_df, id_col="SNP_NAME", snp_col="SNP")
-
-		assert isinstance(result, pd.DataFrame) and not result.empty
-		assert result.SNP.round(6).isin([0.727273, 0.909091, 0.818182]).all()
-
-	@pytest.mark.parametrize("data_df", ["crm"], indirect=True)
-	def test_crm_datafame_dtype_int(self, data_df: pd.DataFrame) -> None:
-		data_df.SNP = data_df.SNP.astype("int8")
-		result = call_rate(data=data_df, id_col="SNP_NAME", snp_col="SNP")
-
-		assert isinstance(result, pd.DataFrame) and not result.empty
-		assert result.SNP.round(6).isin([0.727273, 0.909091, 0.818182]).all()
-
-	@pytest.mark.parametrize("data_df", ["crm"], indirect=True)
-	def test_crm_datafame_dtype_float(self, data_df: pd.DataFrame) -> None:
-		data_df.SNP = data_df.SNP.astype("float32")
-		result = call_rate(data=data_df, id_col="SNP_NAME", snp_col="SNP")
-
-		assert isinstance(result, pd.DataFrame) and not result.empty
-		assert result.SNP.round(6).isin([0.727273, 0.909091, 0.818182]).all()
-
-	@pytest.mark.parametrize("data_df", ["crm"], indirect=True)
-	def test_crm_datafame_dtype_random_simbols(
-		self, data_df: pd.DataFrame
-	) -> None:
-		data_df.SNP = [
-			np.random.choice(["A", "C", "G", "T"])
-			for _ in range(data_df.SNP.shape[0])
-		]
-		result = call_rate(data=data_df, id_col="SNP_NAME", snp_col="SNP")
-
-		assert result is None
-
-	def test_crm_datafame_empty1(self) -> None:
-		with pytest.raises(KeyError):
-			call_rate(data=pd.DataFrame(), id_col="SNP_NAME", snp_col="SNP")
-
-	def test_crm_datafame_empty2(self) -> None:
-		result = call_rate(
-			data=pd.DataFrame(columns=["SNP_NAME", "SNP"]),
-			id_col="SNP_NAME",
-			snp_col="SNP"
-		)
-
-		assert isinstance(result, pd.DataFrame) and result.empty
-
-	@pytest.mark.parametrize("data_df", ["crm"], indirect=True)
-	def test_crm_datafame_fail(self, data_df: pd.DataFrame) -> None:
-		with pytest.raises(KeyError):
-			call_rate(data=data_df, id_col="SNP_NAME")
-			call_rate(data=data_df, snp_col="SNP")
-			call_rate(data=data_df)
-
-	def test_crm_str_simbols(self) -> None:
-		data_str = ['GCATGAGGTATACTCTA', 'CGCCATGCTGTATATCC']
-
-		for sequence in data_str:
-			assert call_rate(data=sequence) is None
-
-	def test_crm_str_empty(self) -> None:
-		assert call_rate(data="") is None
-
-	def test_crm_str_mixid(self) -> None:
-		assert call_rate(data="GCATGAG3G4T6A67TACTCTA") is None

snplib/statistics/tests/test_freq_allele.py

@@ -1,87 +0,0 @@
-#!/usr/bin/env python
-# coding: utf-8
-__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
-
-from . import DIR_DATA
-from .. import allele_freq
-
-import pytest
-import numpy as np
-import pandas as pd
-
-
-@pytest.fixture
-def data_df() -> pd.DataFrame:
-	return pd.read_pickle(DIR_DATA / "freq/file.pl")
-	# [0.   , 0.9  , 0.889]
-
-
-def data_str() -> list[tuple]:
-	return [
-		('2212120', 0.714),
-		('02011015010000500', 0.2),
-		('01110152120222512', 0.6)
-	]
-
-
-class TestAlleleFreq(object):
-
-	def test_allele_freq_df_dtype_obj(self, data_df: pd.DataFrame) -> None:
-		data_df.SNP = data_df.SNP.astype(str)
-		result = allele_freq(data=data_df, id_col="SNP_NAME", seq_col="SNP")
-
-		assert isinstance(result, pd.DataFrame) and not result.empty
-		assert result.SNP.round(6).isin([0.000, 0.900, 0.889]).all()
-
-	def test_allele_freq_df_dtype_int(self, data_df: pd.DataFrame) -> None:
-		data_df.SNP = data_df.SNP.astype("int8")
-		result = allele_freq(data=data_df, id_col="SNP_NAME", seq_col="SNP")
-
-		assert isinstance(result, pd.DataFrame) and not result.empty
-		assert result.SNP.round(6).isin([0.000, 0.900, 0.889]).all()
-
-	def test_allele_freq_df_dtype_float(self, data_df: pd.DataFrame) -> None:
-		data_df.SNP = data_df.SNP.astype("float32")
-		result = allele_freq(data=data_df, id_col="SNP_NAME", seq_col="SNP")
-
-		assert isinstance(result, pd.DataFrame) and not result.empty
-		assert result.SNP.round(6).isin([0.000, 0.900, 0.889]).all()
-
-	def test_allele_freq_df_data_rand_simbols(
-			self, data_df: pd.DataFrame
-	) -> None:
-		data_df.SNP = [
-			np.random.choice(["A", "C", "G", "T"])
-			for _ in range(data_df.SNP.shape[0])
-		]
-		assert allele_freq(
-			data=data_df, id_col="SNP_NAME", seq_col="SNP"
-		) is None
-
-	def test_allele_freq_df_empty(self) -> None:
-		with pytest.raises(KeyError):
-			allele_freq(
-				data=pd.DataFrame(), id_col="SNP_NAME", seq_col="SNP"
-			)
-
-	def test_allele_freq_df_empty_only_columns(self) -> None:
-		result = allele_freq(
-			data=pd.DataFrame(columns=["SNP_NAME", "SNP"]),
-			id_col="SNP_NAME",
-			seq_col="SNP"
-		)
-
-		assert isinstance(result, pd.DataFrame) and result.empty
-
-	def test_allele_freq_df_raises(self, data_df: pd.DataFrame) -> None:
-		with pytest.raises(KeyError):
-			allele_freq(data=data_df, id_col="SNP_NAME")
-			allele_freq(data=data_df, seq_col="SNP")
-			allele_freq(data=data_df)
-
-	@pytest.mark.parametrize("data, obs_value", data_str())
-	def test_allele_freq_str(self, data: str, obs_value: float) -> None:
-		assert allele_freq(data=data) == obs_value
-
-	def test_allele_freq_non_type(self) -> None:
-		assert allele_freq(data=1423) is None

snplib/statistics/tests/test_freq_maf.py

@@ -1,17 +0,0 @@
-#!/usr/bin/env python
-# coding: utf-8
-__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
-
-from .. import minor_allele_freq as maf
-
-import pytest
-
-
-class TestMinorAlleleFreq(object):
-
-	@pytest.mark.parametrize("value, res", [
-		(0.0, 0.0), (0.9, 0.1), (0.889, 0.111),
-		(0.714, 0.286), (0.22, 0.22), (0.45, 0.45), (0.6, 0.4)
-	])
-	def test_minor_allele_freq(self, value: float, res: float) -> None:
-		assert maf(value) == res

snplib/statistics/tests/test_hwe_t.py

@@ -1,41 +0,0 @@
-#!/usr/bin/env python
-# coding: utf-8
-__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
-
-from .. import hwe_test
-
-import pytest
-import pandas as pd
-
-
-class TestHWE(object):
-
-	@pytest.mark.parametrize(
-		"seq, freq",
-		[
-			('2212120', 0.714),
-			('02011015010000500', 0.2),
-			('01110152120222512', 0.6),
-			('00005005005', 0.0),
-			('22521212222', 0.9),
-			('52221521222', 0.889)
-		]
-	)
-	def test_hweT_true(self, seq: str, freq: float) -> None:
-		"""
-		 check snphwe gives expected p-values
-		"""
-
-		_seq_snp = pd.Series(list(map(int, seq)))
-
-		assert hwe_test(_seq_snp, freq)
-
-	@pytest.mark.parametrize("seq, freq", [('000000000102', 0.125)])
-	def test_hweT_false(self, seq: str, freq: float) -> None:
-		"""
-		 check snphwe gives expected p-values
-		"""
-
-		_seq_snp = pd.Series(list(map(int, seq)))
-
-		assert not hwe_test(_seq_snp, freq)

snplib/statistics/tests/test_snphwe.py

@@ -1,41 +0,0 @@
-#!/usr/bin/env python
-# coding: utf-8
-__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
-
-from .. import hwe
-
-import pytest
-
-
-class TestHWE(object):
-
-	def test_snphwe(self) -> None:
-		"""
-		 check snphwe gives expected p-values
-		"""
-		assert hwe(500, 10, 5000) == 0.6515718999145375
-		assert hwe(1000, 20, 5000) == 1.2659849194317374e-05
-
-	def test_snphwe_odd_inputs(self) -> None:
-		"""
-		check snphwe with odd inputs
-		"""
-		# should raise errors with odd inputs
-
-		with pytest.raises(ValueError, match="snphwe: zero genotypes"):
-			hwe(0, 0, 0)
-
-		with pytest.raises(ValueError, match="snphwe: negative allele count"):
-			hwe(-5, 10, 1000)
-
-	def test_snphwe_large_input(self) -> None:
-		"""
-		check snphwe doesn't give errors with large sample sizes
-		"""
-		assert hwe(200000, 200000, 200000) == 0.0
-
-	def test_snphwe_uncertain_genotypes(self) -> None:
-		"""
-		check uncertain genotypes give correct p-values
-		"""
-		assert hwe(4989.99999, 494999.999, 9.9999999) == 0.5702231983054381

snplib-1.0.7.dist-info/RECORD

@@ -1,37 +0,0 @@
-snplib/__init__.py,sha256=xw0VDA6vCABCOwfQHF2L2paFnc4Q_ss7OvFLJYjeU-U,204
-snplib/finalreport/__init__.py,sha256=yF48v321n31WqnzzX3F_vZ41t0NkeWruJVIOnM1yLj0,168
-snplib/finalreport/_finalreport.py,sha256=mhggK7IlcwfAywAFKTxqKnmErduyWzPbgA-uPGKkBYA,6127
-snplib/finalreport/tests/__init__.py,sha256=px8I01mwlI8cLhKIroJus5ga7PDXGI7T0QL7G3bJLSc,181
-snplib/finalreport/tests/test_finalreport.py,sha256=OASntKSCbLGfS9JX4z4Q4cnivKkVk6YQlsuDgLy5gZ0,6713
-snplib/format/__init__.py,sha256=nA7SIUSKZumP62yWvstew8ASLsC4Uz__Ywr8roGdc18,280
-snplib/format/__settings.py,sha256=UUK1kc3Fnzl9S3U7MQEbGrumyzogKNW0nllys41ymfk,296
-snplib/format/_plink.py,sha256=Haqd28yTdGMYwBaWaE9qf9TKMRtY12KvBygljZz6CWM,10834
-snplib/format/_snp.py,sha256=vKUhsNHjfRCXPxNV0wP1xcPM831SOGIu4RPmuLYh-g4,3285
-snplib/format/tests/__init__.py,sha256=px8I01mwlI8cLhKIroJus5ga7PDXGI7T0QL7G3bJLSc,181
-snplib/format/tests/test_plink_fam.py,sha256=TulkoH1OIATa2sJRKXx2DvOcF0Y7vESJCQ1LKC9aa5E,2878
-snplib/format/tests/test_plink_lgen.py,sha256=P1id3isYbiL7jqaC_-hKrw_-H_zbrX2_OopyDN54ueI,2311
-snplib/format/tests/test_plink_map.py,sha256=mNErvrP3gfE19-UunsO-miEjURyjj226L4UiZ3tqMnE,989
-snplib/format/tests/test_plink_ped.py,sha256=0QtejE_V70jaATTp5mDrDvEvqehV2pTMM4MRU9j3lAE,3074
-snplib/format/tests/test_snp.py,sha256=LL61fAy2U4pybv_eua85XfvAPGTW3lgi475aL1lyRd4,3391
-snplib/parentage/__init__.py,sha256=9wgWZxDJA0FfXs8MT-VVF3O7LfZhDh9y-jEV4_wE4-c,295
-snplib/parentage/_discov.py,sha256=YHM83V92uIc8wBtKySU3cschikCCg1vc4wY2fWkg5Xc,3282
-snplib/parentage/_isagmark.py,sha256=djEKEHn15vEzcovIh2t_r9PLJOztEM40enWZJf1Un44,371
-snplib/parentage/_verif.py,sha256=lcfFMZrNC6ymIMU2cel9Dudgqc3OZ6CIASjDUhnos7E,3110
-snplib/parentage/tests/__init__.py,sha256=-mLPBAje75GqCilX0dkqw9KQj_HPnxjm5R6_xHVe6k0,179
-snplib/parentage/tests/test_discov.py,sha256=u2vdAYSoiB6PRHlys07LWetQb-rEwT_8p_5Ajm5Jneg,4314
-snplib/parentage/tests/test_verif.py,sha256=FgZ_MRpGa2WbEC0S6sYiElkDzt3JZ4ENVza68eJFRtQ,4111
-snplib/statistics/__init__.py,sha256=2xN_dUTProTBUzPW3oKi_CZ0QlqjIUlxbtGfsBqLD2c,318
-snplib/statistics/_callrate.py,sha256=r0cn5s1RHSBVDG6GrcmN210zeMTpHCOiOjdgkETV7Yg,1924
-snplib/statistics/_freq.py,sha256=ZxuZLm8vFS60YKMcrTZDNuj1Y22FkqfaFp76R4hivLY,1690
-snplib/statistics/_snphwe.py,sha256=lvIuRYYs625tduNa_DU5OfqWUB7fHnXnh5VoSkNQe_Q,3485
-snplib/statistics/tests/__init__.py,sha256=-mLPBAje75GqCilX0dkqw9KQj_HPnxjm5R6_xHVe6k0,179
-snplib/statistics/tests/test_callrate.py,sha256=-PK_VFWx76MWFXMOPLwlzEb570fKXt1nK4gjYe4bNAQ,5824
-snplib/statistics/tests/test_freq_allele.py,sha256=5ik_2sdupTcf4cCnEflyH5aPJ0k8tk68mih2faeF-ZY,2673
-snplib/statistics/tests/test_freq_maf.py,sha256=DIqpl52fMKyHTL4YEP1ZZ9_QNV91T-QgjTrA4lQeGPw,447
-snplib/statistics/tests/test_hwe_t.py,sha256=34wr6EE1ZVqL2zXgSNgBwsGplt0YtbyVFJ7c0uiYBZw,888
-snplib/statistics/tests/test_snphwe.py,sha256=dB62NvmrSrZPXXgJu6ni1xSxJxRqeLBkVp9ZXpfAV8s,1036
-snplib-1.0.7.dist-info/LICENSE,sha256=IwGE9guuL-ryRPEKi6wFPI_zOhg7zDZbTYuHbSt_SAk,35823
-snplib-1.0.7.dist-info/METADATA,sha256=iR0uXLWtZ_T_ztUacJ4TeYhXI_mbFxvEDY61lDO7vpU,2521
-snplib-1.0.7.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-snplib-1.0.7.dist-info/top_level.txt,sha256=CGCrLXuCSyXPCTwMFQjPxQR7b93FFFft56sAPPun_2g,7
-snplib-1.0.7.dist-info/RECORD,,