small fixes, update env

env.yaml

@@ -14,4 +14,6 @@ dependencies:
   - hyperopt=0.2.5
   - seaborn=0.11.1
   - numpy=1.19.5
-  - pytables=3.6.1
\ No newline at end of file
+  - pytables=3.6.1
+  - kmer-jellyfish=2.3.0
+  - scikit-learn=0.24.2

validation/validate_16S.py

-import os
+import os, sys
 import pandas as pd
 from os.path import basename
 from shutil import copy
@@ -6,6 +6,11 @@ from pathlib import Path
 from distutils.dir_util import copy_tree
 from sklearn.model_selection import StratifiedKFold
 from jinja2 import Template
+
+__location__ = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))
+baseless_location = os.path.realpath(f'{__location__}/..')
+sys.path.append(baseless_location)
+
 from argparse_dicts import get_validate_parser
 from helper_functions import parse_input_path, parse_output_path
 from snakemake import snakemake
@@ -17,8 +22,7 @@ args = parser.parse_args()
 
 nn_target_list = [pth.name for pth in Path(args.primed_nn_dir).iterdir() if pth.is_dir()]
 
-__location__ = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))
-baseless_location = os.path.realpath(f'{__location__}/..')
+
 with open(args.parameter_file, 'r') as pf: params = yaml.load(pf, Loader=yaml.FullLoader)
 primed_nn_dir = args.primed_nn_dir
 if primed_nn_dir[-1] != '/': primed_nn_dir += '/'
@@ -44,7 +48,7 @@ fast5_basename_list = [basename(f) for f in fast5_list]
 
 fast5_df = pd.DataFrame({'read_id': fast5_basename_list,
                          'fn': fast5_list,
-                         'species': [gt_df.species_short.get(ff) for ff in fast5_basename_list]}
+                         'species': [gt_df.species_short.get(ff, 'unknown') for ff in fast5_basename_list]}
                         ).set_index('read_id')
 fast5_df.drop(fast5_df.query('species == "unknown"').index, axis=0, inplace=True)