Merge pull request #45 from sanogenetics/feature/23andme-missings

handle unusual 23andme files with missing values

Author: afaulconbridge

src/snps/io/reader.py

@@ -68,7 +68,7 @@
 
 
 def get_empty_snps_dataframe():
-    """ Get empty dataframe normalized for usage with ``snps``.
+    """Get empty dataframe normalized for usage with ``snps``.
 
     Returns
     -------
@@ -81,7 +81,7 @@ def get_empty_snps_dataframe():
 
 
 class Reader:
-    """ Class for reading and parsing raw data / genotype files. """
+    """Class for reading and parsing raw data / genotype files."""
 
     def __init__(self, file="", only_detect_source=False, resources=None, rsids=()):
         """Initialize a `Reader`.
@@ -104,7 +104,7 @@ def __init__(self, file="", only_detect_source=False, resources=None, rsids=()):
         self._rsids = frozenset(rsids)
 
     def read(self):
-        """ Read and parse a raw data / genotype file.
+        """Read and parse a raw data / genotype file.
 
         Returns
         -------
@@ -447,18 +447,70 @@ def read_23andme(self, file, compression):
         """
 
         def parser():
-            return (
-                pd.read_csv(
-                    file,
-                    comment="#",
-                    sep="\t",
-                    na_values="--",
-                    names=["rsid", "chrom", "pos", "genotype"],
-                    index_col=0,
-                    dtype=NORMALIZED_DTYPES,
-                    compression=compression,
-                ),
+            df = pd.read_csv(
+                file,
+                comment="#",
+                sep="\t",
+                na_values="--",
+                names=["rsid", "chrom", "pos", "genotype"],
+                compression=compression,
             )
+            df = df.dropna(subset=["rsid", "chrom", "pos"])
+            # turn number numbers into string numbers
+            df["chrom"] = df["chrom"].map(
+                {
+                    "1": "1",
+                    "2": "2",
+                    "3": "3",
+                    "4": "4",
+                    "5": "5",
+                    "6": "6",
+                    "7": "7",
+                    "8": "8",
+                    "9": "9",
+                    "10": "10",
+                    "11": "11",
+                    "12": "12",
+                    "13": "13",
+                    "14": "14",
+                    "15": "15",
+                    "16": "16",
+                    "17": "17",
+                    "18": "18",
+                    "19": "19",
+                    "20": "20",
+                    "21": "21",
+                    "22": "22",
+                    1: "1",
+                    2: "2",
+                    3: "3",
+                    4: "4",
+                    5: "5",
+                    6: "6",
+                    7: "7",
+                    8: "8",
+                    9: "9",
+                    10: "10",
+                    11: "11",
+                    12: "12",
+                    13: "13",
+                    14: "14",
+                    15: "15",
+                    16: "16",
+                    17: "17",
+                    18: "18",
+                    19: "19",
+                    20: "20",
+                    21: "21",
+                    22: "22",
+                    "X": "X",
+                    "Y": "Y",
+                    "MT": "MT",
+                }
+            )
+            df = df.astype(dtype=NORMALIZED_DTYPES)
+            df = df.set_index("rsid")
+            return (df,)
 
         return self.read_helper("23andMe", parser)
 
@@ -725,7 +777,7 @@ def parser():
         return self.read_helper("LivingDNA", parser)
 
     def read_mapmygenome(self, file, compression, header):
-        """ Read and parse Mapmygenome file.
+        """Read and parse Mapmygenome file.
 
         https://mapmygenome.in
 
@@ -1065,7 +1117,7 @@ def parser():
         return self.read_helper("DNA.Land", parser)
 
     def read_snps_csv(self, file, comments, compression):
-        """ Read and parse CSV file generated by ``snps``.
+        """Read and parse CSV file generated by ``snps``.
 
         https://pypi.org/project/snps/
 

src/snps/io/writer.py

@@ -48,10 +48,10 @@
 
 
 class Writer:
-    """ Class for writing SNPs to files. """
+    """Class for writing SNPs to files."""
 
     def __init__(self, snps=None, filename="", vcf=False, atomic=True, **kwargs):
-        """ Initialize a `Writer`.
+        """Initialize a `Writer`.
 
         Parameters
         ----------
@@ -80,7 +80,7 @@ def write(self):
 
     @classmethod
     def write_file(cls, snps=None, filename="", vcf=False, atomic=True, **kwargs):
-        """ Save SNPs to file.
+        """Save SNPs to file.
 
         Parameters
         ----------
@@ -106,7 +106,7 @@ def write_file(cls, snps=None, filename="", vcf=False, atomic=True, **kwargs):
         return w.write()
 
     def _write_csv(self):
-        """ Write SNPs to a CSV file.
+        """Write SNPs to a CSV file.
 
         Returns
         -------
@@ -147,7 +147,7 @@ def _write_csv(self):
         )
 
     def _write_vcf(self):
-        """ Write SNPs to a VCF file.
+        """Write SNPs to a VCF file.
 
         References
         ----------