Added support to pass filetype and rt unit

CHANGELOG.md

@@ -6,7 +6,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 ### Added
+- __main__.py + cli/LoadDataAction.py: Added required passing of filetype and rt unit. [#64](https://github.com/RECETOX/RIAssigner/issues/64) [#67](https://github.com/RECETOX/RIAssigner/issues/67) [#68](https://github.com/RECETOX/RIAssigner/pull/68)
 ### Changed
+- utils.py: `get_extension` function now returns extension without `.` [#68](https://github.com/RECETOX/RIAssigner/pull/68)
+- data/Data.py: Added `filetype` to constructor and made `rt_unit` non-optional. [#67](https://github.com/RECETOX/RIAssigner/issues/67) [#68](https://github.com/RECETOX/RIAssigner/pull/68)
+- data/MatchMSData.py: Added `filetype` to constructor and made `rt_unit` non-optional. [#67](https://github.com/RECETOX/RIAssigner/issues/67) [#68](https://github.com/RECETOX/RIAssigner/pull/68)
+- data/PandasData.py: Added `filetype` to constructor and made `rt_unit` non-optional. [#67](https://github.com/RECETOX/RIAssigner/issues/67) [#68](https://github.com/RECETOX/RIAssigner/pull/68)
 ### Removed
 
 ## [0.2.0] - 2021-08-18

README.md

@@ -2,6 +2,7 @@
 [![Python package](https://github.com/RECETOX/RIAssigner/actions/workflows/python-package.yml/badge.svg)](https://github.com/RECETOX/RIAssigner/actions/workflows/python-package.yml)
 [![Python Package using Conda](https://github.com/RECETOX/RIAssigner/actions/workflows/python-package-conda.yml/badge.svg?branch=main)](https://github.com/RECETOX/RIAssigner/actions/workflows/python-package-conda.yml)
 [![Anaconda Build](https://github.com/RECETOX/RIAssigner/actions/workflows/anaconda.yml/badge.svg?branch=main)](https://github.com/RECETOX/RIAssigner/actions/workflows/anaconda.yml)
+[![Quality Gate Status](https://sonarcloud.io/api/project_badges/measure?project=hechth_RIAssigner&metric=alert_status)](https://sonarcloud.io/dashboard?id=hechth_RIAssigner)
 ## Overview
 RIAssigner is a python tool for retention index (RI) computation for GC-MS data developed at [RECETOX](https://www.recetox.muni.cz/en).
 

RIAssigner/__main__.py

@@ -1,3 +1,5 @@
+import sys
+from typing import Tuple
 from RIAssigner.compute.ComputationMethod import ComputationMethod
 import argparse
 
@@ -14,12 +16,16 @@ def create_parser():
                           required=True,
                           type=str,
                           action=LoadDataAction,
-                          help="Reference dataset containing retention times and indices. Path to CSV or MSP.")
+                          nargs=3,
+                          help="""Reference dataset containing retention times and indices.
+                          Path to CSV or MSP, filetype and retention time unit.""")
     required.add_argument("--query",
                           required=True,
                           type=str,
                           action=LoadDataAction,
-                          help="Query dataset for which to compute retention indices. Path to CSV or MSP.")
+                          nargs=3,
+                          help="""Query dataset for which to compute retention indices.
+                          Path to CSV or MSP, filetype and retention time unit.""")
     required.add_argument("--method",
                           required=True,
                           type=str,
@@ -33,14 +39,14 @@ def create_parser():
     return parser
 
 
-def main():
+def main(argv):
     """Command line interface for the RIAssigner library.
 
     Args:
         argv (List[string]): Arguments passed to the program
     """
     parser = create_parser()
-    args = parser.parse_args()
+    args = parser.parse_args(argv)
 
     query: Data = args.query
     reference: Data = args.reference
@@ -54,4 +60,4 @@ def main():
 
 
 if __name__ == "__main__":
-    main()
+    main(sys.argv[1:])

RIAssigner/cli/LoadDataAction.py

@@ -1,6 +1,5 @@
 import argparse
 
-from RIAssigner.utils import get_extension
 from RIAssigner.data import MatchMSData, PandasData
 
 
@@ -9,10 +8,12 @@ def __init__(self, option_strings, dest, **kwargs):
         super().__init__(option_strings, dest, **kwargs)
 
     def __call__(self, parser, namespace, values, option_string=None):
-        filetype = get_extension(values)
-        if filetype == '.msp':
-            data = MatchMSData(values)
-        elif filetype in ['.csv', '.tsv']:
-            data = PandasData(values)
+        filename = values[0]
+        filetype = values[1]
+        rt_unit = values[2]
+        if filetype == 'msp':
+            data = MatchMSData(filename, filetype, rt_unit)
+        elif filetype in ['csv', 'tsv']:
+            data = PandasData(filename, filetype, rt_unit)
 
         setattr(namespace, self.dest, data)

RIAssigner/data/Data.py

@@ -15,8 +15,9 @@ class Data(ABC):
     def is_valid(rt: RetentionTimeType) -> bool:
         return rt is not None and rt >= 0.0
 
-    def __init__(self, filename: str, rt_unit: str = 'seconds'):
+    def __init__(self, filename: str, filetype: str, rt_unit: str):
         self._filename = filename
+        self._filetype = filetype
         self._rt_unit = rt_unit
         self._unit = Data.Unit(self._rt_unit)
         self.read()

RIAssigner/data/MatchMSData.py

@@ -14,7 +14,7 @@ class MatchMSData(Data):
     def read(self):
         """Load data into object and initialize properties.
         """
-        self._read_spectra(self._filename)
+        self._read_spectra(self._filename, self._filetype)
 
         self._sort_spectra_by_rt()
 
@@ -29,7 +29,7 @@ def write(self, filename: str):
         """
         save_as_msp(self._spectra, filename)
 
-    def _read_spectra(self, filename: str):
+    def _read_spectra(self, filename: str, filetype: str):
         """Read spectra from 'msp' file into data.
 
         Args:
@@ -38,7 +38,7 @@ def _read_spectra(self, filename: str):
         Raises:
             NotImplementedError: For filetypes other tahn 'msp'.
         """
-        if filename.endswith('.msp'):
+        if filetype == 'msp':
             self._spectra = list(load_from_msp(filename))
         else:
             raise NotImplementedError("Currently only supports 'msp'.")

RIAssigner/data/PandasData.py

@@ -24,7 +24,7 @@ def read(self):
 
     def _read_into_dataframe(self):
         """ Read the data from file into dataframe. """
-        if(self._filename.endswith('.csv') or self._filename.endswith('.tsv')):
+        if(self._filetype in ['csv', 'tsv']):
             separator = define_separator(self._filename)
             self._data = read_csv(self._filename, sep=separator)
         else:

RIAssigner/utils.py

@@ -31,4 +31,4 @@ def get_extension(filename: str):
     Returns:
         str: Filename extension.
     """
-    return splitext(filename)[1]
+    return splitext(filename)[1][1:]

tests/builders/MatchMSDataBuilder.py

@@ -6,6 +6,7 @@ class MatchMSDataBuilder:
     def __init__(self):
         self.filename = None
         self._rt_unit = 'seconds'
+        self._filetype = "msp"
 
     def with_filename(self, filename: str):
         self.filename = filename
@@ -15,5 +16,9 @@ def with_rt_unit(self, rt_unit: str):
         self._rt_unit = rt_unit
         return self
 
+    def with_filetype(self, filetype: str):
+        self._filetype = filetype
+        return self
+
     def build(self) -> MatchMSData:
-        return MatchMSData(self.filename, self._rt_unit)
+        return MatchMSData(self.filename, self._filetype, self._rt_unit)

tests/builders/PandasDataBuilder.py

@@ -6,6 +6,7 @@ class PandasDataBuilder:
     def __init__(self):
         self._filename = None
         self._rt_unit = 'seconds'
+        self._filetype = 'csv'
 
     def with_filename(self, filename: str):
         self._filename = filename
@@ -15,6 +16,10 @@ def with_rt_unit(self, rt_unit: str):
         self._rt_unit = rt_unit
         return self
 
+    def with_filetype(self, filetype: str):
+        self._filetype = filetype
+        return self
+
     def build(self) -> PandasData:
-        data = PandasData(self._filename, self._rt_unit)
+        data = PandasData(self._filename, self._filetype, self._rt_unit)
         return data

tests/builders/__init__.py

@@ -0,0 +1,21 @@
+import logging
+from typing import Optional, Union
+
+from .MatchMSDataBuilder import MatchMSDataBuilder
+from .PandasDataBuilder import PandasDataBuilder
+
+logging.getLogger(__name__).addHandler(logging.NullHandler())
+
+
+def get_builder(filetype) -> Optional[Union[PandasDataBuilder, MatchMSDataBuilder]]:
+    if (filetype in ['csv', 'tsv']):
+        return PandasDataBuilder().with_filetype(filetype)
+    if (filetype in ['msp']):
+        return MatchMSDataBuilder().with_filetype(filetype)
+    return None
+
+
+__all__ = [
+    "MatchMSDataBuilder",
+    "PandasDataBuilder",
+]

tests/data/dat/Alkanes_20210325.dat

@@ -0,0 +1,161 @@
+NAME: Undecane
+SCANNUMBER: -1
+RETENTIONTIME: 2.08
+RETENTIONINDEX: 1100
+FORMULA: C11H24
+Num Peaks: 2
+57	1
+56  0.2
+
+Name: DODECANE
+Synon: $:00in-source
+DB#: JP005756
+InChIKey: SNRUBQQJIBEYMU-UHFFFAOYSA-N
+Spectrum_type: MS1
+Instrument_type: EI-B
+Instrument: HITACHI M-80
+Ion_mode: P
+Formula: C12H26
+MW: 170
+ExactMass: 170.203450832
+RETENTIONINDEX: 1200
+RETENTIONTIME: 2.43
+Comments: "SMILES=CCCCCCCCCCCC" "cas=112-40-3" "InChI=InChI=1S/C12H26/c1-3-5-7-9-11-12-10-8-6-4-2/h3-12H2,1-2H3" "computed SMILES=CCCCCCCCCCCC" "accession=JP005756" "date=2016.01.19 (Created 2008.10.21, modified 2011.05.06)" "author=MASS SPECTROSCOPY SOC. OF JAPAN (MSSJ)" "license=CC BY-NC-SA" "exact mass=170.20345" "ionization energy=70 eV" "ion type=[M]+*" "SPLASH=splash10-052f-9000000000-e297100d4245d91a3893" "submitter=University of Tokyo Team (Faculty of Engineering, University of Tokyo)" "MoNA Rating=3.75"
+Num Peaks: 36
+39 8.15
+40 1.49
+41 41.51
+42 11.33
+43 98.66
+44 3.45
+53 2.13
+54 2.05
+55 17.07
+56 14.21
+57 99.99
+58 4.93
+67 1.24
+68 1.11
+69 6.35
+70 11.79
+71 52.2
+72 2.82
+82 0.73
+83 2.35
+84 7.03
+85 29.3
+86 0.94
+97 0.92
+98 5.46
+99 5.66
+100 0.4
+112 3.05
+113 4.38
+126 1.38
+127 3.05
+128 0.77
+140 0.71
+141 1.58
+170 5.13
+171 0.65
+
+Name: TRIDECANE
+Synon: $:00in-source
+DB#: JP005755
+InChIKey: IIYFAKIEWZDVMP-UHFFFAOYSA-N
+Spectrum_type: MS1
+Instrument_type: EI-B
+Instrument: HITACHI M-80
+Ion_mode: P
+Formula: C13H28
+MW: 184
+ExactMass: 184.219100896
+RETENTIONTIME: 2.75
+RETENTIONINDEX: 1300
+Comments: "SMILES=CCCCCCCCCCCCC" "cas=629-50-5" "InChI=InChI=1S/C13H28/c1-3-5-7-9-11-13-12-10-8-6-4-2/h3-13H2,1-2H3" "computed SMILES=CCCCCCCCCCCCC" "accession=JP005755" "date=2016.01.19 (Created 2008.10.21, modified 2011.05.06)" "author=MASS SPECTROSCOPY SOC. OF JAPAN (MSSJ)" "license=CC BY-NC-SA" "exact mass=184.2191" "ionization energy=70 eV" "ion type=[M]+*" "SPLASH=splash10-0596-9000000000-562483fea4bbcff9f5aa" "submitter=University of Tokyo Team (Faculty of Engineering, University of Tokyo)" "MoNA Rating=3.75"
+Num Peaks: 36
+39 4.82
+40 1.46
+41 40.61
+42 9.32
+43 99.99
+44 3.74
+53 2.05
+54 2.26
+55 19.09
+56 10.29
+57 96.92
+58 4.17
+67 1.52
+68 1.32
+69 8.09
+70 12.2
+71 58.38
+72 3.39
+82 0.97
+83 3.05
+84 7.07
+85 33.34
+97 1.48
+98 4.91
+99 6.54
+111 0.33
+112 3.23
+113 4.77
+126 1.94
+127 3.63
+140 0.91
+141 2.16
+154 0.58
+155 1.08
+184 4.66
+185 0.73
+
+Name: Tetradecane
+Synon: tetradecane
+Synon: $:00in-source
+DB#: HMDB0059907_c_ms_1094
+InChIKey: BGHCVCJVXZWKCC-UHFFFAOYSA-N
+Instrument_type: GC-MS
+Retentionindex: 1393.41
+RETENTIONTIME: 3.08
+Formula: C14H30
+MW: 198
+ExactMass: 198.23475095999999
+Comments: "SMILES=CCCCCCCCCCCCCC" "cas number=" "InChI=InChI=1S/C14H30/c1-3-5-7-9-11-13-14-12-10-8-6-4-2/h3-14H2,1-2H3" "computed SMILES=CCCCCCCCCCCCCC" "column=5%-phenyl-95%-dimethylpolysiloxane capillary column" "retention index type=based on 9 n-alkanes (C10–C36)" "chromatography type=GC" "SPLASH=splash10-00di-9100000000-8774faafa64b5f45d039" "submitter=David Wishart (University of Alberta)" "MoNA Rating=3.333333333333333"
+Num Peaks: 35
+70.0 0.208
+71.0 1.0
+72.0 0.053
+77.0 0.003
+79.0 0.005
+81.0 0.005
+82.0 0.03
+83.0 0.078
+84.0 0.105
+85.0 0.543
+86.0 0.033
+96.0 0.01
+97.0 0.045
+98.0 0.078
+99.0 0.141
+100.0 0.008
+110.0 0.002
+111.0 0.013
+112.0 0.055
+113.0 0.063
+114.0 0.005
+124.0 0.002
+125.0 0.003
+126.0 0.033
+127.0 0.04
+128.0 0.002
+140.0 0.02
+141.0 0.028
+142.0 0.002
+154.0 0.007
+155.0 0.015
+168.0 0.002
+169.0 0.007
+198.0 0.028
+199.0 0.003