Merge pull request #418 from pepkit/417-peppyprojectto_dict-creates-u…

…nwanted-nan-values

Remove creating `NaN`s in `to_dict` method

docs/changelog.md

@@ -1,7 +1,9 @@
 # Changelog
 
 This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html) and [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) format.
-
+## [0.35.2] -- 2022-09-13
+### Fixed
+- Returning `NaN` value within `to_dict` method was fixed and method now returns `None` instead
 ## [0.35.1] -- 2022-09-07
 ### Changed
 - Organization of test files. Separated unittests from smoketests.

peppy/_version.py

@@ -1 +1 @@
-__version__ = "0.35.1"
+__version__ = "0.35.2"

peppy/sample.py

@@ -138,7 +138,7 @@ def _obj2dict(obj, name=None):
             elif isnull(obj):
                 # Missing values as evaluated by pandas.isnull().
                 # This gets correctly written into yaml.
-                return "NaN"
+                return None
             else:
                 return obj
 

tests/conftest.py

@@ -4,6 +4,7 @@
 
 import pandas as pd
 import pytest
+import json
 
 __author__ = "Michal Stolarczyk"
 __email__ = "[email protected]"
@@ -36,6 +37,11 @@ def example_pep_csv_path(request):
     return get_path_to_example_file(EPB, request.param, "sample_table.csv")
 
 
+@pytest.fixture
+def example_pep_nextflow_csv_path():
+    return get_path_to_example_file(EPB, "nextflow_taxprofiler_pep", "samplesheet.csv")
+
+
 @pytest.fixture
 def example_pep_cfg_noname_path(request):
     return get_path_to_example_file(EPB, "noname", request.param)

tests/data/example_peps-master/example_nextflow_taxprofiler_pep/config.yaml

@@ -0,0 +1,2 @@
+pep_version: "2.1.0"
+sample_table: "https://raw.githubusercontent.com/pepkit/example_peps/master/example_nextflow_taxprofiler_pep/samplesheet.csv"

tests/data/example_peps-master/example_nextflow_taxprofiler_pep/samplesheet.csv

@@ -0,0 +1,7 @@
+sample,instrument_platform,run_accession,fastq_1,fastq_2,fasta
+2611,ILLUMINA,ERR5766174,,,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fasta/ERX5474930_ERR5766174_1.fa.gz
+2612,ILLUMINA,ERR5766176,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474932_ERR5766176_1.fastq.gz,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474932_ERR5766176_2.fastq.gz,
+2612,ILLUMINA,ERR5766176_B,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474932_ERR5766176_B_1.fastq.gz,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474932_ERR5766176_B_2.fastq.gz,
+2612,ILLUMINA,ERR5766180,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474936_ERR5766180_1.fastq.gz,,
+2613,ILLUMINA,ERR5766181,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474937_ERR5766181_1.fastq.gz,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474937_ERR5766181_2.fastq.gz,
+ERR3201952,OXFORD_NANOPORE,ERR3201952,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERR3201952.fastq.gz,,

tests/data/example_peps-master/example_nextflow_taxprofiler_pep/samplesheet_schema.yaml

@@ -0,0 +1,41 @@
+description: A schema for validation of samplesheet.csv for taxprofiler pipeline.
+imports:
+  - https://schema.databio.org/pep/2.1.0.yaml
+properties:
+  samples:
+    type: array
+    items:
+      type: object
+      properties:
+        sample:
+          type: string
+          description: "Sample identifier."
+          pattern: "^\\S*$"
+        run_accession:
+          type: string
+          description: "Run accession number."
+        instrument_platform:
+          type: string
+          description: "Name of the platform that sequenced the samples."
+          enum: ["ABI_SOLID", "BGISEQ", "CAPILLARY", "COMPLETE_GENOMICS", "DNBSEQ", "HELICOS", "ILLUMINA", "ION_TORRENT", "LS454", "OXFORD_NANOPORE", "PACBIO_SMRT"]
+        fastq1:
+          type: string
+          description: "FASTQ file for read 1."
+          pattern: "^[\\S]+.(fq\\.gz|fastq\\.gz)$"
+        fastq2:
+          type: string
+          description: "FASTQ file for read 2."
+          pattern: "^[\\S]+.(fq\\.gz|fastq\\.gz)$"
+        fasta:
+          type: string
+          description: "Path to FASTA file."
+      required:
+        - sample
+        - run_accession
+        - instrument_platform
+      files:
+        - fastq1
+        - fastq2
+        - fasta
+required:
+  - samples

tests/data/example_peps-master/example_nextflow_taxprofiler_pep/test_nextflow_original_samplesheet.csv

@@ -0,0 +1,7 @@
+sample,run_accession,instrument_platform,fastq_1,fastq_2,fasta
+2611,ERR5766174,ILLUMINA,,,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fasta/ERX5474930_ERR5766174_1.fa.gz
+2612,ERR5766176,ILLUMINA,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474932_ERR5766176_1.fastq.gz,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474932_ERR5766176_2.fastq.gz,
+2612,ERR5766176_B,ILLUMINA,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474932_ERR5766176_B_1.fastq.gz,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474932_ERR5766176_B_2.fastq.gz,
+2612,ERR5766180,ILLUMINA,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474936_ERR5766180_1.fastq.gz,,
+2613,ERR5766181,ILLUMINA,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474937_ERR5766181_1.fastq.gz,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERX5474937_ERR5766181_2.fastq.gz,
+ERR3201952,ERR3201952,OXFORD_NANOPORE,https://raw.githubusercontent.com/nf-core/test-datasets/taxprofiler/data/fastq/ERR3201952.fastq.gz,,

tests/test_Project.py

@@ -4,6 +4,7 @@
 import socket
 import tempfile
 
+import numpy as np
 import pytest
 from pandas import DataFrame
 from yaml import dump, safe_load
@@ -338,6 +339,16 @@ def test_from_dict_instatiation(self, example_pep_cfg_path):
         p2 = Project().from_dict(p1.to_dict(extended=True))
         assert p1 == p2
 
+    def test_to_dict_does_not_create_nans(self, example_pep_nextflow_csv_path):
+        wrong_values = ["NaN", np.nan, "nan"]
+
+        p1 = Project(
+            cfg=example_pep_nextflow_csv_path, sample_table_index="sample"
+        ).to_dict()
+        for sample in p1.get("_samples"):
+            for attribute, value in sample.items():
+                assert value not in wrong_values
+
     @pytest.mark.parametrize("example_pep_cfg_path", ["missing_version"], indirect=True)
     def test_missing_version(self, example_pep_cfg_path):
         """