Merge 98b9136 into 3dc5ac3

.github/workflows/run_tests.yml

@@ -0,0 +1,133 @@
+name: Unit Tests
+
+on:
+  push:
+    branches:
+      - '*'
+  pull_request:
+    branches:
+      - '*'
+
+jobs:
+  run_linter:
+    runs-on: ${{ matrix.config.os }}
+    if: "!contains(github.event.head_commit.message, 'ci skip')"
+
+    strategy:
+      fail-fast: false
+      matrix:
+        config:
+        - {name: 'current', os: ubuntu-latest, python: '3.8' }
+
+    steps:
+    - name: Cancel Previous Runs
+      uses: styfle/cancel-workflow-action@0.6.0
+      with:
+        access_token: ${{ github.token }}
+
+    - uses: actions/checkout@v2
+
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.config.python }}
+
+    - name: Install tools
+      run: |
+        python -m pip install --upgrade "pip<=21.0"
+        pip install --use-deprecated=legacy-resolver -U wheel setuptools
+        pip install --use-deprecated=legacy-resolver -U black flake8
+    - name: Lint with Black
+      run: |
+        black . --check --diff
+    - name: Lint with flake8
+      run: |
+        flake8 scprep
+
+  run_tester:
+    runs-on: ${{ matrix.config.os }}
+    if: "!contains(github.event.head_commit.message, 'ci skip')"
+    env:
+      RENV_PATHS_ROOT: ~/.local/share/renv
+
+    strategy:
+      fail-fast: false
+      matrix:
+        config:
+        - {name: 'current', os: ubuntu-latest, python: '3.8', r: 'release' }
+        - {name: 'prev', os: ubuntu-latest, python: '3.7', r: 'release' }
+        - {name: 'old', os: ubuntu-latest, python: '3.6', r: 'release' }
+
+    steps:
+    - name: Cancel Previous Runs
+      uses: styfle/cancel-workflow-action@0.6.0
+      with:
+        access_token: ${{ github.token }}
+
+    - uses: actions/checkout@v2
+      with:
+        fetch-depth: 0
+
+    - name: Install system dependencies
+      if: runner.os == 'Linux'
+      run: |
+        sudo apt-get update -qq
+        sudo apt-get install -y libhdf5-dev libhdf5-serial-dev pandoc gfortran libblas-dev liblapack-dev libedit-dev llvm-dev libcurl4-openssl-dev ffmpeg
+
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.config.python }}
+
+    - name: Set up R
+      id: setup-r
+      uses: r-lib/actions/setup-r@v1
+      with:
+        r-version: ${{ matrix.config.r }}
+
+    - name: Cache Python packages
+      uses: actions/cache@v2
+      with:
+        path: ${{ env.pythonLocation }}
+        key: ${{runner.os}}-pip-${{ env.pythonLocation }}-${{ hashFiles('setup.py') }}
+        restore-keys: ${{runner.os}}-pip-${{ env.pythonLocation }}-
+
+    - name: Cache R packages
+      uses: actions/cache@v2
+      if: startsWith(runner.os, 'Linux')
+      with:
+        path: ${{ env.RENV_PATHS_ROOT }}
+        key: ${{ runner.os }}-renv-${{ steps.setup-r.outputs.installed-r-version }}-${{ hashFiles('**/renv.lock') }}
+        restore-keys: |
+          ${{ runner.os }}-renv-${{ steps.setup-r.outputs.installed-r-version }}-
+
+    - name: Install R packages
+      run: |
+        if (!requireNamespace("renv", quietly = TRUE)) install.packages("renv")
+        renv::restore()
+        renv::install("bioc::splatter")
+        renv::install("bioc::slingshot")
+      shell: Rscript {0}
+
+    - name: Install package & dependencies
+      run: |
+        python -m pip install --upgrade "pip<=21.0"
+        pip install --use-deprecated=legacy-resolver -U wheel setuptools
+        pip install --use-deprecated=legacy-resolver -U .[test,r]
+        python -c "import scprep"
+
+    - name: Run tests
+      run: nose2 -vvv
+
+    - name: Coveralls
+      env:
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      run: |
+        coveralls
+
+    - name: Upload check results on fail
+      if: failure()
+      uses: actions/upload-artifact@master
+      with:
+        name: ${{ matrix.config.name }}_results
+        path: check

scprep/__init__.py

@@ -19,7 +19,7 @@
 
 if int(pd.__version__.split(".")[1]) < 26:
 
-    def fill_value(self):
+    def _fill_value(self):
         # Used in reindex_indexer
         try:
             return self.values.dtype.fill_value
@@ -28,4 +28,4 @@ def fill_value(self):
 
     from pandas.core.internals.blocks import ExtensionBlock
 
-    setattr(ExtensionBlock, "fill_value", property(fill_value))
+    setattr(ExtensionBlock, "fill_value", property(_fill_value))

scprep/filter.py

@@ -48,7 +48,7 @@ def remove_duplicates(data, *extra_data, sample_labels=None):
 
 
 def filter_empty_genes(data, *extra_data):
-    """Filter all genes with zero counts across all cells
+    """Filter all genes with zero counts across all cells.
 
     This is equivalent to `filter_rare_genes(data, cutoff=0, min_cells=1)`
     but should be faster.
@@ -74,7 +74,7 @@ def filter_empty_genes(data, *extra_data):
 
 
 def filter_rare_genes(data, *extra_data, cutoff=0, min_cells=5):
-    """Filter all genes with negligible counts in all but a few cells
+    """Filter all genes with negligible counts in all but a few cells.
 
     Parameters
     ----------
@@ -101,7 +101,7 @@ def filter_rare_genes(data, *extra_data, cutoff=0, min_cells=5):
 
 
 def filter_empty_cells(data, *extra_data, sample_labels=None):
-    """Remove all cells with zero library size
+    """Remove all cells with zero library size.
 
     Parameters
     ----------
@@ -142,7 +142,7 @@ def filter_values(
     sample_labels=None,
     filter_per_sample=None
 ):
-    """Remove all cells with `values` above or below a certain threshold
+    """Remove all cells with `values` above or below a certain threshold.
 
     It is recommended to use :func:`~scprep.plot.histogram` to
     choose a cutoff prior to filtering.
@@ -211,7 +211,7 @@ def filter_library_size(
     sample_labels=None,
     filter_per_sample=None
 ):
-    """Remove all cells with library size above or below a certain threshold
+    """Remove all cells with library size above or below a certain threshold.
 
     It is recommended to use :func:`~scprep.plot.plot_library_size` to
     choose a cutoff prior to filtering.
@@ -278,7 +278,7 @@ def filter_gene_set_expression(
     sample_labels=None,
     filter_per_sample=None
 ):
-    """Remove cells with total expression of a gene set above or below a certain threshold
+    """Remove cells with total expression of a gene set above or below a threshold.
 
     It is recommended to use :func:`~scprep.plot.plot_gene_set_expression` to
     choose a cutoff prior to filtering.
@@ -352,7 +352,7 @@ def filter_gene_set_expression(
 
 
 def _find_unique_cells(data):
-    """Identify unique cells
+    """Identify unique cells.
 
     Parameters
     ----------
@@ -381,7 +381,7 @@ def _find_unique_cells(data):
 
 
 def filter_duplicates(data, *extra_data, sample_labels=None):
-    """Filter all duplicate cells
+    """Filter all duplicate cells.
 
     Parameters
     ----------

scprep/io/csv.py

@@ -8,7 +8,7 @@
 
 
 def _read_csv_sparse(filename, chunksize=10000, fill_value=0.0, **kwargs):
-    """Read a csv file into a pd.DataFrame[pd.SparseArray]"""
+    """Read a csv file into a pd.DataFrame[pd.SparseArray]."""
     chunks = pd.read_csv(filename, chunksize=chunksize, **kwargs)
     data = pd.concat(
         utils.dataframe_to_sparse(chunk, fill_value=fill_value) for chunk in chunks
@@ -26,7 +26,7 @@ def load_csv(
     chunksize=10000,
     **kwargs
 ):
-    """Load a csv file
+    r"""Load a csv file.
 
     Parameters
     ----------
@@ -36,7 +36,7 @@ def load_csv(
         If your data has genes on the rows and cells on the columns, use
         cell_axis='column'
     delimiter : str, optional (default: ',')
-        Use '\\t' for tab separated values (tsv)
+        Use '\t' for tab separated values (tsv)
     gene_names : `bool`, `str`, array-like, or `None` (default: True)
         If `True`, we assume gene names are in the first row/column. Otherwise
         expects a filename or an array containing a list of gene symbols or ids
@@ -113,7 +113,7 @@ def load_tsv(
     sparse=False,
     **kwargs
 ):
-    """Load a tsv file
+    r"""Load a tsv file.
 
     Parameters
     ----------
@@ -122,7 +122,7 @@ def load_tsv(
     cell_axis : {'row', 'column'}, optional (default: 'row')
         If your data has genes on the rows and cells on the columns, use
         cell_axis='column'
-    delimiter : str, optional (default: '\\t')
+    delimiter : str, optional (default: '\t')
         Use ',' for comma separated values (csv)
     gene_names : `bool`, `str`, array-like, or `None` (default: True)
         If `True`, we assume gene names are in the first row/column. Otherwise

scprep/io/download.py

@@ -31,7 +31,7 @@ def _google_drive_confirm_token(response):
 
 @utils._with_pkg(pkg="requests")
 def _GET_google_drive(id):
-    """Post a GET request to Google Drive"""
+    """Post a GET request to Google Drive."""
     global _GOOGLE_DRIVE_URL
 
     with requests.Session() as session:
@@ -45,7 +45,7 @@ def _GET_google_drive(id):
 
 
 def download_google_drive(id, destination):
-    """Download a file from Google Drive
+    """Download a file from Google Drive.
 
     Requires the file to be available to view by anyone with the URL.
 
@@ -63,7 +63,7 @@ def download_google_drive(id, destination):
 
 
 def download_url(url, destination):
-    """Download a file from a URL
+    """Download a file from a URL.
 
     Parameters
     ----------
@@ -85,7 +85,7 @@ def download_url(url, destination):
 
 
 def unzip(filename, destination=None, delete=True):
-    """Extract a .zip file and optionally remove the archived version
+    """Extract a .zip file and optionally remove the archived version.
 
     Parameters
     ----------
@@ -109,7 +109,7 @@ def unzip(filename, destination=None, delete=True):
 
 
 def download_and_extract_zip(url, destination):
-    """Download a .zip file from a URL and extract it
+    """Download a .zip file from a URL and extract it.
 
     Parameters
     ----------