diff --git a/CRISPResso2/CRISPResso2Align.pyx b/CRISPResso2/CRISPResso2Align.pyx index eb0f7d8c..21c959c4 100644 --- a/CRISPResso2/CRISPResso2Align.pyx +++ b/CRISPResso2/CRISPResso2Align.pyx @@ -166,14 +166,14 @@ def global_align(str pystr_seqj, str pystr_seqi, np.ndarray[DTYPE_INT, ndim=2] m #init i matrix for i in range(1,max_j+1): iScore[0,i] = gap_extend * i + gap_incentive[0] -# iScore[0,1:] = [gap_extend * np.arange(1, max_j+1, dtype=np.int)] +# iScore[0,1:] = [gap_extend * np.arange(1, max_j+1, dtype=int)] iScore[0:,0] = min_score iPointer[0,1:] = IARRAY #init j matrix for i in range(1,max_i+1): jScore[i,0] = gap_extend * i + gap_incentive[0] - #jScore[1:,0] = np.vectorize(gap_extend * np.arange(1, max_i+1, dtype=np.int)) + #jScore[1:,0] = np.vectorize(gap_extend * np.arange(1, max_i+1, dtype=int)) jScore[0,0:] = min_score jPointer[1:,0] = JARRAY diff --git a/CRISPResso2/CRISPRessoBatchCORE.py b/CRISPResso2/CRISPRessoBatchCORE.py index 6ec08cbc..c802bb9f 100644 --- a/CRISPResso2/CRISPRessoBatchCORE.py +++ b/CRISPResso2/CRISPRessoBatchCORE.py @@ -451,7 +451,7 @@ def main(): mod_pcts = {} for key in mod_freqs: - mod_pcts[key] = np.array(mod_freqs[key]).astype(np.float)/float(mod_freqs['Total'][0]) + mod_pcts[key] = np.array(mod_freqs[key]).astype(float)/float(mod_freqs['Total'][0]) amp_found_count += 1 diff --git a/CRISPResso2/CRISPRessoCORE.py b/CRISPResso2/CRISPRessoCORE.py index cbd64816..b70799d8 100644 --- a/CRISPResso2/CRISPRessoCORE.py +++ b/CRISPResso2/CRISPRessoCORE.py @@ -3514,11 +3514,11 @@ def count_alternate_alleles(sub_base_vectors, ref_name, ref_sequence, ref_total_ if not args.suppress_plots: mod_pcts = [] tot = float(counts_total[ref_name]) - mod_pcts.append(np.concatenate((['Insertions'], np.array(all_insertion_count_vectors[ref_name]).astype(np.float)/tot))) - mod_pcts.append(np.concatenate((['Insertions_Left'], np.array(all_insertion_left_count_vectors[ref_name]).astype(np.float)/tot))) - mod_pcts.append(np.concatenate((['Deletions'], np.array(all_deletion_count_vectors[ref_name]).astype(np.float)/tot))) - mod_pcts.append(np.concatenate((['Substitutions'], np.array(all_substitution_count_vectors[ref_name]).astype(np.float)/tot))) - mod_pcts.append(np.concatenate((['All_modifications'], np.array(all_indelsub_count_vectors[ref_name]).astype(np.float)/tot))) + mod_pcts.append(np.concatenate((['Insertions'], np.array(all_insertion_count_vectors[ref_name]).astype(float)/tot))) + mod_pcts.append(np.concatenate((['Insertions_Left'], np.array(all_insertion_left_count_vectors[ref_name]).astype(float)/tot))) + mod_pcts.append(np.concatenate((['Deletions'], np.array(all_deletion_count_vectors[ref_name]).astype(float)/tot))) + mod_pcts.append(np.concatenate((['Substitutions'], np.array(all_substitution_count_vectors[ref_name]).astype(float)/tot))) + mod_pcts.append(np.concatenate((['All_modifications'], np.array(all_indelsub_count_vectors[ref_name]).astype(float)/tot))) mod_pcts.append(np.concatenate((['Total'], [counts_total[ref_name]]*refs[ref_name]['sequence_length']))) colnames = ['Modification']+list(ref_seq) modification_percentage_summary_df = pd.DataFrame(mod_pcts, columns=colnames).apply(pd.to_numeric, errors='ignore') @@ -3897,18 +3897,18 @@ def count_alternate_alleles(sub_base_vectors, ref_name, ref_sequence, ref_total_ for ref_name_for_hdr in ref_names_for_hdr: tot = float(counts_total[ref_name_for_hdr]) for nuc in ['A', 'C', 'G', 'T', 'N', '-']: - nuc_pcts.append(np.concatenate(([ref_name_for_hdr, nuc], np.array(ref1_all_base_count_vectors[ref_name_for_hdr+"_"+nuc]).astype(np.float)/tot))) + nuc_pcts.append(np.concatenate(([ref_name_for_hdr, nuc], np.array(ref1_all_base_count_vectors[ref_name_for_hdr+"_"+nuc]).astype(float)/tot))) colnames = ['Batch', 'Nucleotide']+list(refs[ref_names_for_hdr[0]]['sequence']) hdr_nucleotide_percentage_summary_df = pd.DataFrame(nuc_pcts, columns=colnames).apply(pd.to_numeric, errors='ignore') mod_pcts = [] for ref_name_for_hdr in ref_names_for_hdr: tot = float(counts_total[ref_name_for_hdr]) - mod_pcts.append(np.concatenate(([ref_name_for_hdr, 'Insertions'], np.array(ref1_all_insertion_count_vectors[ref_name_for_hdr]).astype(np.float)/tot))) - mod_pcts.append(np.concatenate(([ref_name_for_hdr, 'Insertions_Left'], np.array(ref1_all_insertion_left_count_vectors[ref_name_for_hdr]).astype(np.float)/tot))) - mod_pcts.append(np.concatenate(([ref_name_for_hdr, 'Deletions'], np.array(ref1_all_deletion_count_vectors[ref_name_for_hdr]).astype(np.float)/tot))) - mod_pcts.append(np.concatenate(([ref_name_for_hdr, 'Substitutions'], np.array(ref1_all_substitution_count_vectors[ref_name_for_hdr]).astype(np.float)/tot))) - mod_pcts.append(np.concatenate(([ref_name_for_hdr, 'All_modifications'], np.array(ref1_all_indelsub_count_vectors[ref_name_for_hdr]).astype(np.float)/tot))) + mod_pcts.append(np.concatenate(([ref_name_for_hdr, 'Insertions'], np.array(ref1_all_insertion_count_vectors[ref_name_for_hdr]).astype(float)/tot))) + mod_pcts.append(np.concatenate(([ref_name_for_hdr, 'Insertions_Left'], np.array(ref1_all_insertion_left_count_vectors[ref_name_for_hdr]).astype(float)/tot))) + mod_pcts.append(np.concatenate(([ref_name_for_hdr, 'Deletions'], np.array(ref1_all_deletion_count_vectors[ref_name_for_hdr]).astype(float)/tot))) + mod_pcts.append(np.concatenate(([ref_name_for_hdr, 'Substitutions'], np.array(ref1_all_substitution_count_vectors[ref_name_for_hdr]).astype(float)/tot))) + mod_pcts.append(np.concatenate(([ref_name_for_hdr, 'All_modifications'], np.array(ref1_all_indelsub_count_vectors[ref_name_for_hdr]).astype(float)/tot))) mod_pcts.append(np.concatenate(([ref_name_for_hdr, 'Total'], [counts_total[ref_name_for_hdr]]*refs[ref_names_for_hdr[0]]['sequence_length']))) colnames = ['Batch', 'Modification']+list(refs[ref_names_for_hdr[0]]['sequence']) hdr_modification_percentage_summary_df = pd.DataFrame(mod_pcts, columns=colnames).apply(pd.to_numeric, errors='ignore') @@ -4465,18 +4465,18 @@ def get_scaffold_len(row, scaffold_start_loc, scaffold_seq): for ref_name in ref_names_for_pe: tot = float(counts_total[ref_name]) for nuc in ['A', 'C', 'G', 'T', 'N', '-']: - nuc_pcts.append(np.concatenate(([ref_name, nuc], np.array(ref1_all_base_count_vectors[ref_name+"_"+nuc]).astype(np.float)/tot))) + nuc_pcts.append(np.concatenate(([ref_name, nuc], np.array(ref1_all_base_count_vectors[ref_name+"_"+nuc]).astype(float)/tot))) colnames = ['Batch', 'Nucleotide']+list(refs[ref_names[0]]['sequence']) pe_nucleotide_percentage_summary_df = pd.DataFrame(nuc_pcts, columns=colnames).apply(pd.to_numeric,errors='ignore') mod_pcts = [] for ref_name in ref_names_for_pe: tot = float(counts_total[ref_name]) - mod_pcts.append(np.concatenate(([ref_name, 'Insertions'], np.array(ref1_all_insertion_count_vectors[ref_name]).astype(np.float)/tot))) - mod_pcts.append(np.concatenate(([ref_name, 'Insertions_Left'], np.array(ref1_all_insertion_left_count_vectors[ref_name]).astype(np.float)/tot))) - mod_pcts.append(np.concatenate(([ref_name, 'Deletions'], np.array(ref1_all_deletion_count_vectors[ref_name]).astype(np.float)/tot))) - mod_pcts.append(np.concatenate(([ref_name, 'Substitutions'], np.array(ref1_all_substitution_count_vectors[ref_name]).astype(np.float)/tot))) - mod_pcts.append(np.concatenate(([ref_name, 'All_modifications'], np.array(ref1_all_indelsub_count_vectors[ref_name]).astype(np.float)/tot))) + mod_pcts.append(np.concatenate(([ref_name, 'Insertions'], np.array(ref1_all_insertion_count_vectors[ref_name]).astype(float)/tot))) + mod_pcts.append(np.concatenate(([ref_name, 'Insertions_Left'], np.array(ref1_all_insertion_left_count_vectors[ref_name]).astype(float)/tot))) + 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']) pe_modification_percentage_summary_df = pd.DataFrame(mod_pcts, columns=colnames).apply(pd.to_numeric,errors='ignore') diff --git a/CRISPResso2/CRISPRessoPlot.py b/CRISPResso2/CRISPRessoPlot.py index e11fd9d6..caa896c1 100644 --- a/CRISPResso2/CRISPRessoPlot.py +++ b/CRISPResso2/CRISPRessoPlot.py @@ -2507,7 +2507,7 @@ def __init__(self, data, vmin, vmax, cmap, center, robust, annot, fmt, if annot is not None: if per_element_annot_kws is None: - self.per_element_annot_kws=np.empty_like(annot, dtype=np.object) + self.per_element_annot_kws=np.empty_like(annot, dtype=object) self.per_element_annot_kws[:]=dict() else: self.per_element_annot_kws=per_element_annot_kws @@ -2641,7 +2641,7 @@ def prep_alleles_table(df_alleles, reference_seq, MAX_N_ROWS, MIN_FREQUENCY): (row['Reference_Sequence'][i_sub]!=idx[i_sub]) and \ (row['Reference_Sequence'][i_sub]!='-') and\ (idx[i_sub]!='-')] - to_append=np.array([{}]*len(idx), dtype=np.object) + to_append=np.array([{}]*len(idx), dtype=object) to_append[ idxs_sub]={'weight':'bold', 'color':'black','size':16} per_element_annot_kws.append(to_append) @@ -2693,7 +2693,7 @@ def prep_alleles_table_compare(df_alleles, sample_name_1, sample_name_2, MAX_N_R (row['Reference_Sequence'][i_sub]!=idx[i_sub]) and \ (row['Reference_Sequence'][i_sub]!='-') and\ (idx[i_sub]!='-')] - to_append=np.array([{}]*len(idx), dtype=np.object) + to_append=np.array([{}]*len(idx), dtype=object) to_append[ idxs_sub]={'weight':'bold', 'color':'black','size':16} per_element_annot_kws.append(to_append) @@ -3198,7 +3198,7 @@ def plot_nucleotide_quilt_from_folder(crispresso_output_folder,fig_filename_root mod_pcts = {} for key in mod_counts: - mod_pcts[key] = np.array(mod_counts[key]).astype(np.float)/float(mod_counts['Total'][0]) + mod_pcts[key] = np.array(mod_counts[key]).astype(float)/float(mod_counts['Total'][0]) modification_percentage_summary = [] for mod in ['Insertions', 'Insertions_Left', 'Deletions', 'Substitutions', 'All_modifications']: