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

snplib/parentage/_verif.py

@@ -1,91 +1,91 @@
-#!/usr/bin/env python
-# coding: utf-8
-__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
-
-import numpy as np
-import pandas as pd
-
-
-"""
-https://www.icar.org/Documents/GenoEx/ICAR%20Guidelines%20for%20Parentage%20Verification%20and%20Parentage%20Discovery%20based%20on%20SNP.pdf    
-"""
-
-
-class Verification(object):
-    """
-    Verification of paternity according to ICAR recommendations.
-
-    :argument isag_marks: Fixed sample of markers to confirm paternity.
-    """
-
-    def __init__(
-            self, isag_marks: pd.Series | list | set | None = None
-    ) -> None:
-        self.__isag_marks = isag_marks
-
-        # The minimum number of SNP available in the profile
-        # of each animal and potential parent must be scaled (i.e.: 95%
-        # truncated down)
-        self.__min_num_snp = 0.95
-        self.__num_conflicts = None  # Number of conflicts
-
-    @property
-    def status(self) -> None | str:
-        if self.__num_conflicts is not None:
-            if self.__num_conflicts <= 2:
-                return 'Accept'
-            elif 3 <= self.__num_conflicts <= 5:
-                return 'Doubtful'
-            elif self.__num_conflicts > 5:
-                return 'Excluded'
-            else:
-                return None
-
-    @property
-    def num_conflicts(self) -> None | int:
-        return self.__num_conflicts
-
-    def check_on(
-            self,
-            data: pd.DataFrame,
-            descendant: str,
-            parent: str,
-            snp_name_col: str
-    ) -> None:
-        """ Verification of paternity according to ICAR recommendations.
-
-        :param data: SNP data for descendant and parent.
-        :param descendant: Columns name of the descendant in the data.
-        :param parent: Columns name of the parent in the data.
-        :param snp_name_col: SNP column name in data.
-        """
-
-        if self.__isag_marks is None:
-            raise ValueError('Error. No array of snp names to verify')
-
-        num_isag_mark = len(self.__isag_marks)
-        min_num_comm_snp = int(num_isag_mark - (2 * (num_isag_mark * 0.05)))
-
-        sample_mark = data.loc[
-            data[snp_name_col].isin(self.__isag_marks), [descendant, parent]
-        ]
-
-        # The number of markers is not 5ok
-        desc_n_markers = (sample_mark[descendant] < 5).sum()
-        parent_n_markers = (sample_mark[parent] < 5).sum()
-
-        # According to ICAR, the number of markers not 5ok should be more
-        # than 95%
-        if (desc_n_markers < num_isag_mark * self.__min_num_snp) and \
-                (parent_n_markers < num_isag_mark * self.__min_num_snp):
-            raise Exception('Calf and parent have low call rate')
-
-        comm_snp_no_missing = sample_mark.replace(5, np.nan).dropna()
-        num_comm_markers = len(comm_snp_no_missing)
-
-        if num_comm_markers < min_num_comm_snp:
-            raise Exception('Pair call rate is low')
-
-        self.__num_conflicts = (abs(
-            comm_snp_no_missing[descendant] - comm_snp_no_missing[parent]
-        ) == 2).sum()
+#!/usr/bin/env python
+# coding: utf-8
+__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
+
+import numpy as np
+import pandas as pd
+
+
+"""
+https://www.icar.org/Documents/GenoEx/ICAR%20Guidelines%20for%20Parentage%20Verification%20and%20Parentage%20Discovery%20based%20on%20SNP.pdf    
+"""
+
+
+class Verification(object):
+    """
+    Verification of paternity according to ICAR recommendations.
+
+    :argument isag_marks: Fixed sample of markers to confirm paternity.
+    """
+
+    def __init__(
+            self, isag_marks: pd.Series | list | set | None = None
+    ) -> None:
+        self.__isag_marks = isag_marks
+
+        # The minimum number of SNP available in the profile
+        # of each animal and potential parent must be scaled (i.e.: 95%
+        # truncated down)
+        self.__min_num_snp = 0.95
+        self.__num_conflicts = None  # Number of conflicts
+
+    @property
+    def status(self) -> None | str:
+        if self.__num_conflicts is not None:
+            if self.__num_conflicts <= 2:
+                return 'Accept'
+            elif 3 <= self.__num_conflicts <= 5:
+                return 'Doubtful'
+            elif self.__num_conflicts > 5:
+                return 'Excluded'
+            else:
+                return None
+
+    @property
+    def num_conflicts(self) -> None | int:
+        return self.__num_conflicts
+
+    def check_on(
+            self,
+            data: pd.DataFrame,
+            descendant: str,
+            parent: str,
+            snp_name_col: str
+    ) -> None:
+        """ Verification of paternity according to ICAR recommendations.
+
+        :param data: SNP data for descendant and parent.
+        :param descendant: Columns name of the descendant in the data.
+        :param parent: Columns name of the parent in the data.
+        :param snp_name_col: SNP column name in data.
+        """
+
+        if self.__isag_marks is None:
+            raise ValueError('Error. No array of snp names to verify')
+
+        num_isag_mark = len(self.__isag_marks)
+        min_num_comm_snp = int(num_isag_mark - (2 * (num_isag_mark * 0.05)))
+
+        sample_mark = data.loc[
+            data[snp_name_col].isin(self.__isag_marks), [descendant, parent]
+        ]
+
+        # The number of markers is not 5ok
+        desc_n_markers = (sample_mark[descendant] < 5).sum()
+        parent_n_markers = (sample_mark[parent] < 5).sum()
+
+        # According to ICAR, the number of markers not 5ok should be more
+        # than 95%
+        if (desc_n_markers < num_isag_mark * self.__min_num_snp) and \
+                (parent_n_markers < num_isag_mark * self.__min_num_snp):
+            raise Exception('Calf and parent have low call rate')
+
+        comm_snp_no_missing = sample_mark.replace(5, np.nan).dropna()
+        num_comm_markers = len(comm_snp_no_missing)
+
+        if num_comm_markers < min_num_comm_snp:
+            raise Exception('Pair call rate is low')
+
+        self.__num_conflicts = (abs(
+            comm_snp_no_missing[descendant] - comm_snp_no_missing[parent]
+        ) == 2).sum()

snplib/statistics/__init__.py

@@ -1,16 +1,16 @@
-#!/usr/bin/env python
-# coding: utf-8
-__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
-
-from ._snphwe import hwe, hwe_test
-from ._callrate import call_rate
-from ._freq import allele_freq, minor_allele_freq
-
-
-__all__ = [
-	"call_rate",
-	"allele_freq",
-	"minor_allele_freq",
-	"hwe",
-	"hwe_test"
-]
+#!/usr/bin/env python
+# coding: utf-8
+__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
+
+from ._snphwe import hwe, hwe_test
+from ._callrate import call_rate
+from ._freq import allele_freq, minor_allele_freq
+
+
+__all__ = [
+	"call_rate",
+	"allele_freq",
+	"minor_allele_freq",
+	"hwe",
+	"hwe_test"
+]

snplib/statistics/_callrate.py

@@ -1,59 +1,59 @@
-#!/usr/bin/env python
-# coding: utf-8
-__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
-
-import pandas as pd
-
-
-def call_rate(
-		data: pd.DataFrame | str,
-		id_col: str = None,
-		snp_col: str = None
-) -> pd.DataFrame | float | None:
-	""" The call rate for a given SNP is defined as the proportion of
-	individuals in the study for which the corresponding SNP information is
-	not missing. In the following example, we filter using a call rate of 95%,
-	meaning we retain SNPs for which there is less than 5% missing data.
-
-		Of the say, 54K markers in the chip, 50K have been genotyped for a
-	particular animal, the “call rate animal” is 50K/54K=93%
-		Of the say, 900 animals genotyped for marker CL635944_160.1, how many
-	have actually been successfully read? Assume that 600 have been read, then
-	the “call rate marker” is 600/900 = 67%
-
-	:param data: Pre-processed data on which the call rate is calculated.
-	:param id_col: The name of the column with the id of the animals or
-		markers.
-	:param snp_col: The name of the column with the snp sequence.
-	:return: Return dataframe with call rates for each animal if a dataframe
-		is transmitted. The number if the snp sequence is passed as a string.
-		None if there were errors.
-	"""
-
-	if isinstance(data, pd.DataFrame):
-		try:
-			if data[snp_col].dtype.hasobject:
-				if not data[snp_col].str.isdigit().all():
-					return None
-
-				return data[[id_col, snp_col]].\
-					groupby(by=id_col)[snp_col].\
-					apply(lambda x: 1 - ((x == "5").sum() / len(x))).\
-					reset_index()
-
-			return data[[id_col, snp_col]]. \
-				groupby(by=id_col)[snp_col]. \
-				apply(lambda x: 1 - ((x == 5).sum() / len(x))). \
-				reset_index()
-
-		except Exception as e:
-			raise e
-
-	elif isinstance(data, str):
-		if not data.isdigit():
-			return None
-
-		return round(1 - (data.count('5') / len(data)), 6)
-
-	else:
-		return None
+#!/usr/bin/env python
+# coding: utf-8
+__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
+
+import pandas as pd
+
+
+def call_rate(
+		data: pd.DataFrame | str,
+		id_col: str = None,
+		snp_col: str = None
+) -> pd.DataFrame | float | None:
+	""" The call rate for a given SNP is defined as the proportion of
+	individuals in the study for which the corresponding SNP information is
+	not missing. In the following example, we filter using a call rate of 95%,
+	meaning we retain SNPs for which there is less than 5% missing data.
+
+		Of the say, 54K markers in the chip, 50K have been genotyped for a
+	particular animal, the “call rate animal” is 50K/54K=93%
+		Of the say, 900 animals genotyped for marker CL635944_160.1, how many
+	have actually been successfully read? Assume that 600 have been read, then
+	the “call rate marker” is 600/900 = 67%
+
+	:param data: Pre-processed data on which the call rate is calculated.
+	:param id_col: The name of the column with the id of the animals or
+		markers.
+	:param snp_col: The name of the column with the snp sequence.
+	:return: Return dataframe with call rates for each animal if a dataframe
+		is transmitted. The number if the snp sequence is passed as a string.
+		None if there were errors.
+	"""
+
+	if isinstance(data, pd.DataFrame):
+		try:
+			if data[snp_col].dtype.hasobject:
+				if not data[snp_col].str.isdigit().all():
+					return None
+
+				return data[[id_col, snp_col]].\
+					groupby(by=id_col)[snp_col].\
+					apply(lambda x: 1 - ((x == "5").sum() / len(x))).\
+					reset_index()
+
+			return data[[id_col, snp_col]]. \
+				groupby(by=id_col)[snp_col]. \
+				apply(lambda x: 1 - ((x == 5).sum() / len(x))). \
+				reset_index()
+
+		except Exception as e:
+			raise e
+
+	elif isinstance(data, str):
+		if not data.isdigit():
+			return None
+
+		return round(1 - (data.count('5') / len(data)), 6)
+
+	else:
+		return None

snplib/statistics/_freq.py

@@ -1,67 +1,67 @@
-#!/usr/bin/env python
-# coding: utf-8
-__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
-
-import pandas as pd
-
-
-def allele_freq(
-		data: pd.DataFrame | str, id_col: str = None, seq_col: str = None
-) -> pd.DataFrame | float | None:
-	""" The allele frequency represents the incidence of a gene variant in a
-	population.
-
-	:param data: Data array.
-	:param id_col: Columns with snp names.
-	:param seq_col: Columns with value snp in format ucg - 0, 1, 2, 5.
-	:return: Return the alleles frequency.
-	"""
-
-	if isinstance(data, pd.DataFrame):
-		try:
-			if data[seq_col].dtype.hasobject:
-				if not data[seq_col].str.isdigit().all():
-					return None
-
-				return data.\
-					loc[data[seq_col] != "5", [id_col, seq_col]]. \
-					groupby(by=id_col)[seq_col]. \
-					apply(lambda x: x.astype("int8").sum() / (2 * x.count())).\
-					reset_index().\
-					round(3)
-
-			return data.\
-				loc[data[seq_col] != 5, [id_col, seq_col]].\
-				groupby(by=id_col)[seq_col].\
-				apply(lambda x: x.sum() / (2 * x.count())).\
-				reset_index().\
-				round(3)
-
-		except Exception as e:
-			raise e
-
-	elif isinstance(data, str):
-		if not data.isdigit():
-			return None
-
-		sam_seq = tuple(
-			map(int, filter(lambda x: x if x != "5" else None, data))
-		)
-		return round(sum(sam_seq) / (2 * len(sam_seq)), 3)
-
-	else:
-		return None
-
-
-def minor_allele_freq(value: float) -> float:
-	""" The minor allele frequency is therefore the frequency at which the
-	minor allele occurs within a population.
-
-	:param value: Allele frequency
-	:return: Return the minor alleles frequency
-	"""
-
-	if value > 0.5:
-		return round(1 - value, 3)
-
-	return round(value, 3)
+#!/usr/bin/env python
+# coding: utf-8
+__author__ = "Igor Loschinin (igor.loschinin@gmail.com)"
+
+import pandas as pd
+
+
+def allele_freq(
+		data: pd.DataFrame | str, id_col: str = None, seq_col: str = None
+) -> pd.DataFrame | float | None:
+	""" The allele frequency represents the incidence of a gene variant in a
+	population.
+
+	:param data: Data array.
+	:param id_col: Columns with snp names.
+	:param seq_col: Columns with value snp in format ucg - 0, 1, 2, 5.
+	:return: Return the alleles frequency.
+	"""
+
+	if isinstance(data, pd.DataFrame):
+		try:
+			if data[seq_col].dtype.hasobject:
+				if not data[seq_col].str.isdigit().all():
+					return None
+
+				return data.\
+					loc[data[seq_col] != "5", [id_col, seq_col]]. \
+					groupby(by=id_col)[seq_col]. \
+					apply(lambda x: x.astype("int8").sum() / (2 * x.count())).\
+					reset_index().\
+					round(3)
+
+			return data.\
+				loc[data[seq_col] != 5, [id_col, seq_col]].\
+				groupby(by=id_col)[seq_col].\
+				apply(lambda x: x.sum() / (2 * x.count())).\
+				reset_index().\
+				round(3)
+
+		except Exception as e:
+			raise e
+
+	elif isinstance(data, str):
+		if not data.isdigit():
+			return None
+
+		sam_seq = tuple(
+			map(int, filter(lambda x: x if x != "5" else None, data))
+		)
+		return round(sum(sam_seq) / (2 * len(sam_seq)), 3)
+
+	else:
+		return None
+
+
+def minor_allele_freq(value: float) -> float:
+	""" The minor allele frequency is therefore the frequency at which the
+	minor allele occurs within a population.
+
+	:param value: Allele frequency
+	:return: Return the minor alleles frequency
+	"""
+
+	if value > 0.5:
+		return round(1 - value, 3)
+
+	return round(value, 3)