From 1569975c75b472fc0debdb0eadd28e46b5585a14 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?M=C3=A1t=C3=A9=20Balajti?= <mate.balajti@unibas.ch>
Date: Tue, 19 Sep 2023 11:38:10 +0200
Subject: [PATCH] feat: add and update tests, ci, env
---
.gitlab-ci.yml | 6 +-
environment.yml | 24 ++++
requirements.txt | 4 +-
setup.py | 2 +-
tests/__init__.py | 1 +
tests/{input_files => inputs}/expression.csv | 0
tests/{input_files => inputs}/test.gtf | 0
tests/test_functions.py | 4 +-
tests/test_match_reptrans_explvl.py | 137 +++++--------------
9 files changed, 67 insertions(+), 111 deletions(-)
create mode 100644 environment.yml
rename tests/{input_files => inputs}/expression.csv (100%)
rename tests/{input_files => inputs}/test.gtf (100%)
diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index c4402dd..e34cd6f 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -29,6 +29,6 @@ lint-test-job: # This job also runs in the test stage.
- pip install -r requirements.txt
- pip install -r requirements_dev.txt
- pip install -e .
- # - flake8 --docstring-convention google transcript_sampler/ tests/
- # - pylint transcript_sampler/ tests/
- # - mypy transcript_sampler/
\ No newline at end of file
+ - flake8 --docstring-convention google transcript_sampler/ tests/
+ - pylint transcript_sampler/ tests/
+ - mypy transcript_sampler/ tests/
\ No newline at end of file
diff --git a/environment.yml b/environment.yml
new file mode 100644
index 0000000..bb7989a
--- /dev/null
+++ b/environment.yml
@@ -0,0 +1,24 @@
+name: scrna-seq-sim
+channels:
+ - defaults
+ - bioconda
+ - conda-forge
+dependencies:
+ - argparse
+ - biopython>=1.78
+ - black
+ - coverage
+ - flake8
+ - flake8-docstrings
+ - gtfparse
+ - polars==0.16.17
+ - mypy
+ - numpy>=1.23.3
+ - pylint
+ - pytest
+ - nextflow
+ - pandas>=1.4.4
+ - pip>=20.2.3
+ - python>=3.6, <=3.10
+ - pip:
+ - -e .
diff --git a/requirements.txt b/requirements.txt
index 98d4d62..782fb4a 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,5 +1,5 @@
argparse
biopython
gtfparse
-numpy >= 1.23.3
-pandas >= 1.4.4
\ No newline at end of file
+numpy>=1.23.3
+pandas>=1.4.4
\ No newline at end of file
diff --git a/setup.py b/setup.py
index 9542e8a..721659b 100644
--- a/setup.py
+++ b/setup.py
@@ -1,6 +1,6 @@
"""Set up project."""
from pathlib import Path
-from setuptools import setup, find_packages
+from setuptools import setup, find_packages # type: ignore
project_root_dir = Path(__file__).parent.resolve()
with open(project_root_dir / "requirements.txt",
diff --git a/tests/__init__.py b/tests/__init__.py
index e69de29..b3d9b62 100644
--- a/tests/__init__.py
+++ b/tests/__init__.py
@@ -0,0 +1 @@
+"""Initialize tests."""
diff --git a/tests/input_files/expression.csv b/tests/inputs/expression.csv
similarity index 100%
rename from tests/input_files/expression.csv
rename to tests/inputs/expression.csv
diff --git a/tests/input_files/test.gtf b/tests/inputs/test.gtf
similarity index 100%
rename from tests/input_files/test.gtf
rename to tests/inputs/test.gtf
diff --git a/tests/test_functions.py b/tests/test_functions.py
index a0f2f1a..a81b075 100644
--- a/tests/test_functions.py
+++ b/tests/test_functions.py
@@ -1,6 +1,6 @@
"""Tests functions."""
import os
-import pandas as pd
+import pandas as pd # type: ignore
import numpy as np
@@ -36,7 +36,7 @@ def find_output():
None
"""
absolute_path = os.path.dirname(__file__)
- test_file = "ReprTrans_ExpressionLevel.tsv"
+ test_file = "inputs/test_ref_output.tsv"
full_path = os.path.join(absolute_path, test_file)
return full_path
diff --git a/tests/test_match_reptrans_explvl.py b/tests/test_match_reptrans_explvl.py
index abef23b..495155d 100644
--- a/tests/test_match_reptrans_explvl.py
+++ b/tests/test_match_reptrans_explvl.py
@@ -1,19 +1,17 @@
"""Tests for match representative transcript with expression level."""
import pytest
-import pandas as pd
+import pandas as pd # type: ignore
import numpy as np
-from pandas.testing import assert_frame_equal
-import tests.test_functions as tFun
-from transcript_sampler.match_reptrans_explvl import \
+from pandas.testing import assert_frame_equal # type: ignore
+from transcript_sampler.match_reptrans_explvl import (
MatchReptransExplvl as match
+)
+import tests.test_functions as tFun
class TestMatchReptrans:
"""Tests for match_reptrans_explvl.py."""
- # def test_gtf_to_df(self):
- # TO DO
-
def test_dict_repr_trans_to_df(self):
"""Test dict_repr_trans_to_df() function.
@@ -44,7 +42,7 @@ class TestMatchReptrans:
assert tFun.duplicated_rows(data_frame).empty, \
"at least one row is duplicated"
assert tFun.na_value(data_frame) == 0, \
- "at least one row contain NA values"
+ "at least one row contains NA values"
def test_tsv_or_csv_to_df(self):
"""Test tsv_or_csv_to_df() function.
@@ -65,9 +63,9 @@ class TestMatchReptrans:
assert tFun.column_d_type(df_tsv) == datatype, \
"at least one column has the wrong datatype"
assert tFun.duplicated_rows(df_tsv).empty, \
- "at least one row are duplicated "
+ "at least one row is duplicated"
assert tFun.na_value(df_tsv) == 0, \
- "at least one row contain NA values"
+ "at least one row contains NA values"
assert assert_frame_equal(df_tsv, df_csv) is None, \
"csv and tsv import doesn't match"
@@ -75,7 +73,7 @@ class TestMatchReptrans:
"""Test expr_level_by_gene() function.
This function test if the function expr_level_by_gene can find
- the gene of each transcipt given by the expression level csv/tsv
+ the gene of each transcript given by the expression level csv/tsv
file and sum their expression level
"""
path_tsv = tFun.find_path(r"test_gene_exprL")
@@ -104,9 +102,9 @@ class TestMatchReptrans:
assert tFun.column_d_type(df_exp_lvl) == datatype, \
"at least one column has the wrong datatype"
assert tFun.duplicated_rows(df_exp_lvl).empty, \
- "at least one row are duplicated "
+ "at least one row is duplicated"
assert tFun.na_value(df_exp_lvl) == 0, \
- "at least one row contain NA values "
+ "at least one row contains NA values"
assert tFun.duplicated_index(df_exp_lvl).empty, \
"at least one index element is duplicated"
@@ -151,9 +149,9 @@ class TestMatchReptrans:
assert tFun.column_d_type(df_match) == datatype, \
"at least one column has the wrong datatype"
assert tFun.duplicated_rows(df_match).empty, \
- "at least one row are duplicated "
+ "at least one row is duplicated"
assert tFun.na_value(df_match) == 0, \
- "at least one row contain NA values "
+ "at least one row contains NA values"
assert tFun.duplicated_index(df_match).empty, \
"at least one index element is duplicated"
@@ -164,104 +162,37 @@ class TestMatchReptrans:
function match_repr_transcript_expression_level().
"""
input_path = tFun.find_path("test_gene_exprL")
- intermediate_path = tFun.find_path_intermediate_file()
+ gtf_file = tFun.find_path("test.gtf")
dict_repr_test = {
'ENSMUSG00000079415': 'ENSMUST00000112933',
"ENSMUSG00000024691": "ENSMUST00000025595",
"ENSMUSG00000063683": "ENSMUST00000119960"}
- match.match_repr_transcript_expression_level(
- self,
- exprTrans=input_path,
- dict_reprTrans=dict_repr_test,
- gtf_file=intermediate_path
- )
+ # Create an instance of MatchReptransExplvl
+ match_instance = match()
+
+ df_result = match_instance.match_repr_transcript_expression_level(
+ expr_trans=input_path,
+ dict_repr_trans=dict_repr_test,
+ gtf_file=gtf_file
+ )
ref_path = tFun.find_path("test_ref_output.tsv")
output_path = tFun.find_output()
- with open(ref_path, 'r', encoding="utf-8") as t1,\
- open(output_path, 'r', encoding="utf-8") as t2,\
- open(input_path, 'r', encoding="utf-8") as t3:
- fileRef = t1.readlines()
- fileOutput = t2.readlines()
- fileInput = t3.readlines()
+ with open(
+ ref_path, 'r', encoding="utf-8"
+ ) as test_file_1, open(
+ output_path, 'r', encoding="utf-8"
+ ) as test_file_2:
+ file_ref = test_file_1.readlines()
+ file_output = test_file_2.readlines()
assert (
- sorted(fileRef) == sorted(fileOutput)
- ), "the output does't match the expected tsv file"
+ sorted(file_ref) == sorted(file_output)
+ ), "the output doesn't match the expected tsv file"
assert (
- sorted(fileRef) != sorted(fileInput)
- ), "the output does't match the expected tsv file"
-
- def test_txt_to_dict(self):
- """This function tests if txt is convertod to dict"""
- path = tFun.find_path("test_dict_repr_trans.txt")
- dico = match.txt_to_dict(path)
- dict_test = {'ENSMUSG00000079415': 'ENSMUST00000112933',
- "ENSMUSG00000024691": "ENSMUST00000025595",
- "ENSMUSG00000063683": "ENSMUST00000119960"}
- assert dico == dict_test
-
- def test_transcripts_by_gene_inDf():
- """
- This function test if a dataframe generated from
- the intermediate file is converted in another
- dataframe without the support level column.
- """
- path = tFun.find_path_intermediate_file()
- df = repr.import_gtfSelection_to_df(path)
- df_gene = match.transcripts_by_gene_inDf(df)
- datatype = {'Gene': np.dtype('O'), 'Transcript': np.dtype('O')}
- assert tFun.column_number(df_gene) == (
- 2, "number of columns is not equal to 2")
- assert tFun.column_d_type(df_gene) == (
- datatype, "at least one column has the wrong datatype")
- assert tFun.duplicated_rows(df_gene).empty, \
- "at least one row are duplicated"
- assert tFun.na_value(df_gene) == 0, \
- "at least one row contain NA values"
-
- def test_output_tsv():
- """Test if a tsv file is generated from a df in the right format."""
- dict_repr_test = {
- 'ENSMUSG00000079415': 'ENSMUST00000112933',
- "ENSMUSG00000024691": "ENSMUST00000025595",
- "ENSMUSG00000063683": "ENSMUST00000119960"}
- df_dict_repr_trans = match.dict_repr_trans_to_df(dict_repr_test)
-
- path_tsv = tFun.find_path(r"test_gene_exprL")
- df_tsv_exp_lvl = match.tsv_or_csv_to_df(path_tsv)
- path_intermediate = tFun.find_path_intermediate_file()
- df_intermediate = repr.import_gtfSelection_to_df(path_intermediate)
- df_gene_transcript = match.transcripts_by_gene_inDf(df_intermediate)
-
- df_exp_lvl = match.expr_level_by_gene(
- df_tsv_exp_lvl, df_gene_transcript
+ sorted(file_ref) != sorted(
+ df_result.to_csv(index=False).splitlines()
)
-
- df_match = match.match_by_gene(df_dict_repr_trans, df_exp_lvl)
-
- match.output_tsv(df_match)
-
- ref_path = tFun.find_path("test_ref_output.tsv")
- output_path = tFun.find_output()
-
- with open(ref_path, 'r', encoding="utf-8") as t1, open(output_path, 'r') as t2:
- fileRef = t1.readlines()
- fileOutput = t2.readlines()
-
- assert (
- sorted(fileRef) == sorted(fileOutput)
- ), "the output does't match the expected tsv file"
-
-# test_dict_repr_trans_to_df()
-# test_txt_to_dict()
-# test_transcripts_by_gene_inDf()
-# test_tsv_or_csv_to_df()
-# test_expr_level_by_gene()
-# test_match_by_gene()
-# test_output_tsv()
-# test_match_repr_transcript_expression_level()
-
-# print("test_match is done ! No error was found")
+ ), "the output doesn't match the expected tsv file"
--
GitLab