Draft: Count gene

Issue #11 Before writing the CLI, I wanted to ask wether the method for counting the reads for each gene would work fine like I scripted it. In addition, I wanted to ask you wether you think there would be a more efficient way to do this. As of now, the function reads through the entire bam file, and it could take long for a high number of reads. Thank you!

src/sample_from_input.py

@@ -71,3 +71,30 @@ def sample_from_input(
         myfile.write(line + '\n')
     myfile.close()
     LOG.info('output written.')
+
+
+def main():
+    """CLI interface for the transcripts sampler.
+
+    Accepts arguments from the command line and
+    runs the transcript sampler.
+    """
+    import argparse
+    parser = argparse.ArgumentParser(description='Read functions argument')
+    parser.add_argument('input', action='store',
+                        type=Path, help='path of the input file')
+    parser.add_argument('-o', action='store',
+                        type=Path, default=Path.cwd() / 'sampled_cell.csv',
+                        help='path of the output file')
+    parser.add_argument('-n', action='store',
+                        type=int, default=10000,
+                        help='number of total reads to be simulated')
+    parser.add_argument('-sep', action='store',
+                        type=str, default=',',
+                        help='separator of the input file')
+    args = parser.parse_args()
+    sample_from_input(args.input, args.o, args.n, args.sep)
+
+
+if __name__ == '__main__':
+    main()