unit-test-and-ci-updates

Author: Philip Adenekan

.editorconfig

@@ -0,0 +1,23 @@
+# EditorConfig is awesome: https://EditorConfig.org
+
+# top-most EditorConfig file
+root = true
+
+# Unix-style newlines with a newline ending every file
+[*]
+end_of_line = lf
+insert_final_newline = true
+
+# Matches multiple files with brace expansion notation
+# Set default charset
+[*.{js,py}]
+charset = utf-8
+
+# 4 space indentation
+[*.py]
+indent_style = space
+indent_size = 4
+
+# Tab indentation (no size specified)
+[Makefile]
+indent_style = tab

.github/workflows/pylint.yml

@@ -0,0 +1,23 @@
+name: Pylint
+
+on: [push]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.6"]
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install pylint
+    - name: Analysing the code with pylint
+      run: |
+        pylint rec_to_binaries/

.github/workflows/unit_test.yml

@@ -0,0 +1,26 @@
+name: Project Tests
+
+on: [push]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        shell: bash -l {0}
+    strategy:
+      matrix:
+        python-version: ["3.6"]
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+      - uses: conda-incubator/setup-miniconda@v2
+        with:
+          miniconda-version: "latest"
+          activate-environment: rec_to_binaries
+          environment-file: environment.yml
+        run: |
+          pytest -vv

.pylintrc

@@ -0,0 +1,44 @@
+#options - https://github.com/Qiskit/openqasm/blob/master/.pylintrc
+#          https://pylint.pycqa.org/en/latest/technical_reference/features.html
+
+
+[MESSAGES CONTROL]
+disable=
+    missing-docstring,
+    too-few-public-methods,
+    too-many-instance-attributes,
+    line-too-long,
+    too-many-arguments,
+    logging-fstring-interpolation,
+    consider-using-f-string, # consider removing in the future
+    import-error, # consider removing after finding a better solution
+
+
+[TYPECHECK]
+ignored-modules = numpy, pandas, scipy.stats
+
+
+[BASIC]
+# Good variable names which should always be accepted, separated by a comma
+good-names=_, id
+
+# Bad variable names which should always be refused, separated by a comma
+bad-names=foo,bar,baz,toto,tutu,tata
+
+# Regular expression matching correct attribute names
+attr-rgx=[A-Za-z_][A-Za-z0-9_]{0,30}$
+
+# Naming hint for attribute names
+attr-name-hint=[A-Za-z_][A-Za-z0-9_]{0,30}$
+
+# Regular expression matching correct argument names
+argument-rgx=[A-Za-z_][A-Za-z0-9_]{0,30}$
+
+# Naming hint for argument names
+argument-name-hint=[A-Za-z_][A-Za-z0-9_]{0,30}$
+
+# Regular expression matching correct variable names
+variable-rgx=[A-Za-z_][A-Za-z0-9_]{0,30}$
+
+# Naming hint for variable names
+variable-name-hint=[A-Za-z_][A-Za-z0-9_]{0,30}$

.vscode/settings.json

@@ -0,0 +1,5 @@
+{
+    "python.linting.pylintEnabled": true,
+    "python.linting.enabled": true,
+    "python.linting.flake8Enabled": false
+}

environment.yml

@@ -14,6 +14,7 @@ dependencies:
 - pytest
 - pytest-cov
 - coveralls
+- Faker
 - pip
 - pip:
   - mountainlab-pytools

rec_to_binaries/adjust_timestamps.py

@@ -10,10 +10,10 @@
 
 import numpy as np
 import pandas as pd
+from scipy.stats import linregress
 from rec_to_binaries.create_system_time import infer_systime
 from rec_to_binaries.read_binaries import (readTrodesExtractedDataFile,
                                            write_trodes_extracted_datafile)
-from scipy.stats import linregress
 
 logger = getLogger(__name__)
 
@@ -53,28 +53,28 @@ def _regress_timestamps(trodestime, systime):
         Unix time
 
     """
-    NANOSECONDS_TO_SECONDS = 1E9
+    nanoseconds_to_seconds = 1E9
 
     # Convert
     systime_seconds = np.asarray(systime).astype(
-        np.float64) / NANOSECONDS_TO_SECONDS
+        np.float64) / nanoseconds_to_seconds
     trodestime_index = np.asarray(trodestime).astype(np.float64)
 
-    slope, intercept, r_value, p_value, std_err = linregress(
+    slope, intercept = linregress(
         trodestime_index, systime_seconds)
     adjusted_timestamps = intercept + slope * trodestime_index
-    return (adjusted_timestamps * NANOSECONDS_TO_SECONDS).astype(np.int64)
+    return (adjusted_timestamps * nanoseconds_to_seconds).astype(np.int64)
 
 
-def _insert_new_data(data_file, df):
+def _insert_new_data(data_file, data_frame):
     """
     Replaces the `data` in the extracted data file with a new one.
 
     Parameters
     ----------
     data_file : dict
         Original data file as read in by `readTrodesExtractedDataFile`
-    df : pandas.DataFrame
+    data_frame : pandas.DataFrame
         New data
 
     Returns
@@ -84,7 +84,7 @@ def _insert_new_data(data_file, df):
 
     """
     new_data_file = data_file.copy()
-    new_data_file['data'] = np.asarray(df.to_records(index=False))
+    new_data_file['data'] = np.asarray(data_frame.to_records(index=False))
     new_data_file['fields'] = ''.join(
         [f'<{name} {dtype}>'
          for name, (dtype, _) in new_data_file['data'].dtype.fields.items()])
@@ -113,7 +113,7 @@ def fix_timestamp_lag(continuoustime_filename):
     data_file = readTrodesExtractedDataFile(continuoustime_filename)
 
     if 'systime' not in data_file['data'].dtype.names:
-        logger.warn("No `systime`. Inferring from `system_time_at_creation` timestamp"
+        logger.warning("No `systime`. Inferring from `system_time_at_creation` timestamp"
                     " as a function of the `clockrate` and `trodestime`")
         new_data = infer_systime(data_file)
     else:

rec_to_binaries/core.py

@@ -34,6 +34,7 @@ def extract_trodes_rec_file(data_dir,
                             parallel_instances=1,
                             use_day_config=True,
                             trodes_version=None):
+    # pylint: disable=too-many-branches, too-many-locals, too-many-statements
     """Extracting Trodes rec files.
 
     Following the Frank Lab directory structure for raw ephys data, will
@@ -205,11 +206,11 @@ def extract_trodes_rec_file(data_dir,
             use_day_config=use_day_config)
 
     if adjust_timestamps_for_mcu_lag:
-        ''''There is some jitter in the arrival times of packets from the MCU (as
-            reflected in the sysclock records in the .rec file. If we assume that
-            the Trodes clock is actually regular, and that any episodes of lag are
-            fairly sporadic, we can recover the correspondence between trodestime
-            and system (wall) time.'''
+        # There is some jitter in the arrival times of packets from the MCU (as
+        # reflected in the sysclock records in the .rec file. If we assume that
+        # the Trodes clock is actually regular, and that any episodes of lag are
+        # fairly sporadic, we can recover the correspondence between trodestime
+        # and system (wall) time.
         preprocessing_dir = animal_info.get_preprocessing_dir()
         filenames = glob.glob(os.path.join(
             preprocessing_dir, '**', '*.continuoustime.dat'), recursive=True)
@@ -243,9 +244,7 @@ def convert_binaries_to_hdf5(data_dir, animal, out_dir=None, dates=None,
                              convert_lfp=True,
                              convert_pos=True,
                              convert_spike=True):
-    animal_info = td.TrodesAnimalInfo(
-        data_dir, animal, out_dir=out_dir, dates=dates)
-    """Converting preprocessed binaries into HDF5 files.
+    '''Converting preprocessed binaries into HDF5 files.
 
     Assume that preprocessing has already been completed using (for example)
     extract_trodes_rec_file.
@@ -266,7 +265,9 @@ def convert_binaries_to_hdf5(data_dir, animal, out_dir=None, dates=None,
     convert_lfps : bool, optional
     convert_dio : bool, optional
     convert_mda : bool, optional
-    """
+    '''
+    animal_info = td.TrodesAnimalInfo(
+        data_dir, animal, out_dir=out_dir, dates=dates)
 
     importer = td.TrodesPreprocessingToAnalysis(animal_info)
 

rec_to_binaries/create_system_time.py

@@ -41,14 +41,14 @@ def create_systime(clockrate, data, system_time_at_creation):
     millisecond
 
     """
-    NANOSECONDS_TO_SECONDS = 1e9
+    nanoseconds_to_seconds = 1e9
 
     clockrate = int(clockrate)
     n_time = data.shape[0]
     system_time_at_creation = pd.to_datetime(
         int(system_time_at_creation), unit='ms').value
     end = (system_time_at_creation +
-           int((n_time - 1) * NANOSECONDS_TO_SECONDS / clockrate))
+           int((n_time - 1) * nanoseconds_to_seconds / clockrate))
 
     systime = pd.date_range(
         start=system_time_at_creation,

rec_to_binaries/read_binaries.py

@@ -4,7 +4,7 @@
 import numpy as np
 
 
-def readTrodesExtractedDataFile(filename):
+def readTrodesExtractedDataFile(filename): # pylint: disable=invalid-name
     '''Read extracted trodes binary.
 
     Parameters
@@ -20,24 +20,24 @@ def readTrodesExtractedDataFile(filename):
         # Check if first line is start of settings block
         if file.readline().decode().strip() != '<Start settings>':
             raise Exception("Settings format not supported")
-        fieldsText = dict()
+        fields_text = {}
         for line in file:
             # Read through block of settings
             line = line.decode().strip()
             # filling in fields dict
             if line != '<End settings>':
                 settings_name, setting = line.split(': ')
-                fieldsText[settings_name.lower()] = setting
+                fields_text[settings_name.lower()] = setting
             # End of settings block, signal end of fields
             else:
                 break
         # Reads rest of file at once, using dtype format generated by parse_dtype()
         try:
-            fieldsText['data'] = np.fromfile(
-                file, dtype=parse_dtype(fieldsText['fields']))
+            fields_text['data'] = np.fromfile(
+                file, dtype=parse_dtype(fields_text['fields']))
         except KeyError:
-            fieldsText['data'] = np.fromfile(file)
-        return fieldsText
+            fields_text['data'] = np.fromfile(file)
+        return fields_text
 
 
 def parse_dtype(fieldstr):
@@ -46,7 +46,7 @@ def parse_dtype(fieldstr):
     Returns: np.dtype
     '''
     # Returns np.dtype from field string
-    sep = re.split('\s', re.sub(r"\>\<|\>|\<", ' ', fieldstr).strip())
+    sep = re.split('\s', re.sub(r"\>\<|\>|\<", ' ', fieldstr).strip()) # pylint: disable=anomalous-backslash-in-string
     typearr = []
 
     # Every two elemets is fieldname followed by datatype
@@ -56,7 +56,7 @@ def parse_dtype(fieldstr):
         ftype = 'uint32'
         # Finds if a <num>* is included in datatype
         if '*' in sep[i + 1]:
-            temptypes = re.split('\*', sep[i + 1])
+            temptypes = re.split('\*', sep[i + 1]) # pylint: disable=anomalous-backslash-in-string
             # Results in the correct assignment, whether str is num*dtype or dtype*num
             ftype = temptypes[temptypes[0].isdigit()]
             repeats = int(temptypes[temptypes[1].isdigit()])