Bug Fix - 367 (#35)

* - Fixed references to ref_names_for_pe

* removed extra tabs

* trying to match empty line, no tabs

* - changed references to ref_names[0]

* Mckay/pd warnings (#45)

* refactor errors='ignore' to try except

* refactored integer slice to iloc[]

* moved to_numeric try except to function

* Refactor to_numeric_ignore_errors to to_numeric_ignore_columns

This change is slightly cleaner because it addresses the root issue that some
columns are strings (and can therefore not be converted to numeric types). Now
if an error does occur when converting the dfs to numeric types it won't be
swallowed up.

* Add documentation to to_numeric_ignore_columns

---------

Co-authored-by: Cole Lyman <[email protected]>

---------

Co-authored-by: Cole Lyman <[email protected]>

CRISPResso2/CRISPRessoCORE.py

@@ -4791,14 +4791,14 @@ def get_scaffold_len(row, scaffold_start_loc, scaffold_seq):
                     mod_pcts.append(np.concatenate(([ref_name, 'Deletions'], np.array(ref1_all_deletion_count_vectors[ref_name]).astype(float)/tot)))
                     mod_pcts.append(np.concatenate(([ref_name, 'Substitutions'], np.array(ref1_all_substitution_count_vectors[ref_name]).astype(float)/tot)))
                     mod_pcts.append(np.concatenate(([ref_name, 'All_modifications'], np.array(ref1_all_indelsub_count_vectors[ref_name]).astype(float)/tot)))
-                    mod_pcts.append(np.concatenate(([ref_name, 'Total'], [counts_total[ref_name]]*refs[ref_names_for_pe[0]]['sequence_length'])))
-                colnames = ['Batch', 'Modification']+list(refs[ref_names_for_pe[0]]['sequence'])
+                    mod_pcts.append(np.concatenate(([ref_name, 'Total'], [counts_total[ref_name]]*refs[ref_names[0]]['sequence_length'])))
+                colnames = ['Batch', 'Modification']+list(refs[ref_names[0]]['sequence'])
                 pe_modification_percentage_summary_df = to_numeric_ignore_columns(pd.DataFrame(mod_pcts, columns=colnames), {'Batch', 'Modification'})
 
-                sgRNA_intervals = refs[ref_names_for_pe[0]]['sgRNA_intervals']
-                sgRNA_names = refs[ref_names_for_pe[0]]['sgRNA_names']
-                sgRNA_mismatches = refs[ref_names_for_pe[0]]['sgRNA_mismatches']
-                include_idxs_list = refs[ref_names_for_pe[0]]['include_idxs']
+                sgRNA_intervals = refs[ref_names[0]]['sgRNA_intervals']
+                sgRNA_names = refs[ref_names[0]]['sgRNA_names']
+                sgRNA_mismatches = refs[ref_names[0]]['sgRNA_mismatches']
+                include_idxs_list = refs[ref_names[0]]['include_idxs']
 
                 plot_root = _jp('11a.Prime_editing_nucleotide_percentage_quilt')
                 pro_output_name = f'plot_{os.path.basename(plot_root)}.json'