id field in json better interpretable. Closes #125

proteobench/modules/dda_quant/module.py

@@ -126,12 +126,16 @@ def generate_datapoint(
         self, intermediate: pd.DataFrame, input_format: str, user_input: dict
     ) -> Datapoint:
         """Method used to compute metadata for the provided result."""
+        current_datetime = datetime.datetime.now()
+        formatted_datetime = current_datetime.strftime("%Y%m%d_%H%M%S_%f")
+
+
         result_datapoint = Datapoint(
             id=input_format
             + "_"
             + user_input["version"]
             + "_"
-            + str(datetime.datetime.now()),
+            + formatted_datetime,
             search_engine=input_format,
             software_version=user_input["version"],
             fdr_psm=user_input["fdr_psm"],

test/test_module_dda_quant.py

@@ -1,3 +1,4 @@
+import datetime
 import os
 import unittest
 
@@ -8,15 +9,19 @@
 from proteobench.modules.dda_quant.module import Module
 from proteobench.modules.dda_quant.parse import ParseInputs
 from proteobench.modules.dda_quant.parse_settings import (
-    DDA_QUANT_RESULTS_REPO, INPUT_FORMATS, ParseSettings)
+    DDA_QUANT_RESULTS_REPO,
+    INPUT_FORMATS,
+    ParseSettings,
+)
 from proteobench.modules.dda_quant.plot import PlotDataPoint
+from proteobench.modules.dda_quant.module import Datapoint
 
 # genereate_input_field
 
 
 TESTDATA_DIR = os.path.join(os.path.dirname(__file__), "data")
 TESTDATA_FILES = {
-    #"WOMBAT": os.path.join(TESTDATA_DIR, "WOMBAT_stand_pep_quant_mergedproline.csv"),
+    # "WOMBAT": os.path.join(TESTDATA_DIR, "WOMBAT_stand_pep_quant_mergedproline.csv"),
     "MaxQuant": os.path.join(TESTDATA_DIR, "MaxQuant_evidence_sample.txt"),
     "MSFragger": os.path.join(TESTDATA_DIR, "MSFragger_combined_ion.tsv"),
     "AlphaPept": os.path.join(TESTDATA_DIR, "AlphaPept_subset.csv"),
@@ -59,12 +64,18 @@ def process_file(format_name: str):
 
 
 class TestOutputFileReading(unittest.TestCase):
-    supported_formats = ("MaxQuant", "MSFragger", "AlphaPept", "Sage") #"WOMBAT", 
+    supported_formats = ("MaxQuant", "MSFragger", "AlphaPept", "Sage")  # "WOMBAT",
     """ Simple tests for reading csv input files."""
 
     def test_search_engines_supported(self):
         """Test whether the expected formats are supported."""
-        for format_name in ("MaxQuant", "AlphaPept", "MSFragger", "Proline", "Sage"): #, "WOMBAT"
+        for format_name in (
+            "MaxQuant",
+            "AlphaPept",
+            "MSFragger",
+            "Proline",
+            "Sage",
+        ):  # , "WOMBAT"
             self.assertTrue(format_name in INPUT_FORMATS)
 
     def test_input_file_loading(self):
@@ -128,7 +139,7 @@ class TestPlot(unittest.TestCase):
     """Test if the plots return a figure."""
 
     def test_plot_metric(self):
-        #all_datapoints = pd.read_json(DDA_QUANT_RESULTS_PATH)
+        # all_datapoints = pd.read_json(DDA_QUANT_RESULTS_PATH)
         all_datapoints = read_results_json_repo(DDA_QUANT_RESULTS_REPO)
         all_datapoints["old_new"] = "old"
         fig = PlotDataPoint().plot_metric(all_datapoints)
@@ -141,30 +152,72 @@ def test_plot_bench(self):
         Nyeast = 1000
         Necoli = 500
         Nhuman = 2000
-        
+
         yeastRatio = np.random.normal(loc=-1, scale=1, size=Nyeast)
         humanRatio = np.random.normal(loc=0, scale=1, size=Nhuman)
         ecoliRatio = np.random.normal(loc=2, scale=1, size=Necoli)
         combined_ratios = np.concatenate([yeastRatio, humanRatio, ecoliRatio])
-        
+
         human_strings = ["HUMAN"] * Nhuman
         ecoli_strings = ["ECOLI"] * Necoli
         yeast_strings = ["YEAST"] * Nyeast
 
         # Concatenate the lists to create a single list
         combined_list = human_strings + ecoli_strings + yeast_strings
 
-        combineddf = pd.DataFrame({'SPECIES': combined_list, '1|2_ratio': combined_ratios})
-        combineddf['HUMAN'] = combineddf['SPECIES'] == 'HUMAN'
-        combineddf['ECOLI'] = combineddf['SPECIES'] == 'ECOLI'
-        combineddf['YEAST'] = combineddf['SPECIES'] == 'YEAST'
-
-
+        combineddf = pd.DataFrame(
+            {"SPECIES": combined_list, "1|2_ratio": combined_ratios}
+        )
+        combineddf["HUMAN"] = combineddf["SPECIES"] == "HUMAN"
+        combineddf["ECOLI"] = combineddf["SPECIES"] == "ECOLI"
+        combineddf["YEAST"] = combineddf["SPECIES"] == "YEAST"
 
         fig = PlotDataPoint().plot_bench(combineddf)
-        #fig.write_html("dummy.html")
+        # fig.write_html("dummy.html")
         self.assertIsNotNone(fig)
 
 
+class TestDatapoint(unittest.TestCase):
+    """Test if the plots return a figure."""
+
+    def test_Datapoint_constructor(self):
+        input_format = "MaxQuant"
+        user_input = {
+            "version": "1.0",
+            "fdr_psm": 0.01,
+            "fdr_peptide": 0.05,
+            "fdr_protein": 0.1,
+            "mbr": 1,
+            "precursor_mass_tolerance": 0.02,
+            "precursor_mass_tolerance_unit": "Da",
+            "fragment_mass_tolerance": 0.02,
+            "fragment_mass_tolerance_unit": "Da",
+            "search_enzyme_name": "Trypsin",
+            "allowed_missed_cleavage": 1,
+            "min_peptide_length": 6,
+            "max_peptide_length": 30,
+        }
+        current_datetime = datetime.datetime.now()
+        formatted_datetime = current_datetime.strftime("%Y%m%d_%H%M%S_%f")
+
+        result_datapoint = Datapoint(
+            id=input_format + "_" + user_input["version"] + "_" + formatted_datetime,
+            search_engine=input_format,
+            software_version=user_input["version"],
+            fdr_psm=user_input["fdr_psm"],
+            fdr_peptide=user_input["fdr_peptide"],
+            fdr_protein=user_input["fdr_protein"],
+            MBR=user_input["mbr"],
+            precursor_tol=user_input["precursor_mass_tolerance"],
+            precursor_tol_unit=user_input["precursor_mass_tolerance_unit"],
+            fragmnent_tol=user_input["fragment_mass_tolerance"],
+            fragment_tol_unit=user_input["fragment_mass_tolerance_unit"],
+            enzyme_name=user_input["search_enzyme_name"],
+            missed_cleavages=user_input["allowed_missed_cleavage"],
+            min_pep_length=user_input["min_peptide_length"],
+            max_pep_length=user_input["max_peptide_length"],
+        )
+
+
 if __name__ == "__main__":
     unittest.main()