minor fix

.gitignore

@@ -3,4 +3,5 @@
 /whokaryote_scripts/test_prediction.py
 /whokaryote_scripts/train_classifier.py
 /whokaryote_scripts/train_kmers_only.py
-/whokaryote/scripts/test_kmer_predictions.py
\ No newline at end of file
+/whokaryote/scripts/test_kmer_predictions.py
+/Whokaryote.egg-info/

bin/whokaryote.py

@@ -15,7 +15,7 @@ parser.add_argument("--f", action='store_true', help="If you want new multifasta
                                                      "prokaryotes. This can take a long time.")
 parser.add_argument("--test", action='store_true', help="If you want to test it on a known dataset.")
 parser.add_argument("--train", help="For training an RF on your own dataset. Provide name of RF output file.")
-parser.add_argument("--minsize", default=5000, help="Select a minimum contig size in bp, default = 5000. Accuracy on\
+parser.add_argument("--minsize", default=5000, help="Select a minimum contig size in bp, default = 5000. Accuracy on \
 contigs below 5000 is lower.")
 #  parser.add_argument("--log", action='store_true', help="If you want a log file.")
 parser.add_argument("--model", default="T", help="Choose the stand-alone model or the tiara-integrated model: S or T.\
@@ -107,7 +107,7 @@ if args.train:
 
 if args.f:
     print("Writing eukaryotic and prokaryotic contigs to separate fasta files. This can take very long...")
-    script_path = os.path.join(str(Path(__file__).parents[1]), "whokaryote_scripts", "get_euk_prok_fasta.sh")
+    script_path = os.path.join(str(Path(__file__).parents[2]), "whokaryote_scripts/data", "get_euk_prok_fasta.sh")
     input_file = args.contigs
     output_file = os.path.join(args.outdir, "lin_contigs.fasta")
     euk_headers = os.path.join(args.outdir, "eukaryote_contig_headers.txt")

whokaryote_scripts/calculate_features.py

@@ -134,7 +134,7 @@ def calc_features(contig_file, outfile):
                 if gene_list != "empty":   # This is the gene list from the previous contig
                     if len(rbs_list) == 0:
                         rbs_ratio = np.nan
-                        print("RBS_list = 0", rbs_ratio)
+                        #  print("RBS_list = 0", rbs_ratio)
                     if len(rbs_list) > 0:
                         rbs_ratio = 1 - (rbs_list.count("None") / len(rbs_list))
 

whokaryote_scripts/predict_class.py

@@ -4,6 +4,9 @@ import joblib
 from pathlib import Path
 import os
 
+import warnings
+warnings.filterwarnings('ignore')
+
 
 def add_tiara(dataframe, outdir):
     tiara_list = []
@@ -78,9 +81,9 @@ def predict_class(feature_path, outdir, model):
     #  features = pd.get_dummies(feature_df)
     features = feature_df.dropna()
     #  features = np.array(features)
-    print("Used features:\n", features.describe())
-    print(features.shape)
-    print("Used model: ", model_file)
+    #  print("Used features:\n", features.describe())
+    #  print(features.shape)
+    #  print("Used model: ", model_file)
     loaded_rf = joblib.load(os.path.join(str(Path(__file__).parents[1]), "whokaryote_scripts/data", model_file))
 
     predictions = loaded_rf.predict(features)