fix unit-tests

.gitignore

@@ -6,3 +6,80 @@ tests/data/test_bigwig.bw.dir/
 **/__pycache__/**
 genomelake.egg-info/
 .pytest_cache/
+
+
+#gitignore from kipoi
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+docs/site/*
+docs/sources/*
+docs/theme_dir/img/ipynb/*
+
+# emacs
+*~
+.venv
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+.pytest_cache/
+coverage.xml
+*,cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# pycharm
+.idea
+.ipynb_checkpoints
+logfile.txt
+/genomelake/util.c

genomelake/backend.py

@@ -28,7 +28,7 @@ def extract_fasta_to_file(fasta, output_dir, mode='bcolz', overwrite=False):
     fasta_file = Fasta(fasta, as_raw=True)
     file_shapes = {}
     for chrom in fasta_file.keys():
-        data = np.empty((len(fasta_file[chrom]), NUM_SEQ_CHARS), dtype=np.float32)
+        data = np.zeros((len(fasta_file[chrom]), NUM_SEQ_CHARS), dtype=np.float32)
         seq = str(fasta_file[chrom][:])
         one_hot_encode_sequence(seq, data)
         file_shapes[chrom] = data.shape

genomelake/extractors.py

@@ -104,7 +104,7 @@ def __init__(self, datafile, use_strand=False, **kwargs):
         self.use_strand = use_strand
         from pyfaidx import Fasta
 
-        self.fasta = Fasta(self._datafile, as_raw=True)
+        self.fasta = Fasta(self._datafile)
 
     def _extract(self, intervals, out, **kwargs):
         for index, interval in enumerate(intervals):