From 291bb13563557dab8a32d1ae355b10a2cf3dc057 Mon Sep 17 00:00:00 2001 From: blankkirigaya Date: Sat, 28 Feb 2026 20:14:11 +0530 Subject: [PATCH 1/2] added astype(bool) --- malariagen_data/anoph/hap_frq.py | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/malariagen_data/anoph/hap_frq.py b/malariagen_data/anoph/hap_frq.py index 9178f8d3e..66b9d66fd 100644 --- a/malariagen_data/anoph/hap_frq.py +++ b/malariagen_data/anoph/hap_frq.py @@ -261,19 +261,22 @@ def haplotypes_frequencies_advanced( ds_out[f"cohort_{coh_col}"] = "cohorts", df_cohorts[coh_col] # Label the haplotypes - ds_out["variant_label"] = "variants", df_haps_sorted["label"] + ds_out["variant_label"] = "variants", df_haps_sorted["label"].values # Event variables. + freq_cols = [c for c in df_haps_sorted.columns if c.startswith("frq_")] + count_cols = [c for c in df_haps_sorted.columns if c.startswith("count_")] + nobs_cols = [c for c in df_haps_sorted.columns if c.startswith("nobs_")] ds_out["event_frequency"] = ( ("variants", "cohorts"), - df_haps_sorted.to_numpy()[:, : len(df_cohorts)], + df_haps_sorted[freq_cols].to_numpy(), ) ds_out["event_count"] = ( ("variants", "cohorts"), - df_haps_sorted.to_numpy()[:, len(df_cohorts) : 2 * len(df_cohorts)], + df_haps_sorted[count_cols].to_numpy(), ) ds_out["event_nobs"] = ( ("variants", "cohorts"), - df_haps_sorted.to_numpy()[:, 2 * len(df_cohorts) : -2], + df_haps_sorted[nobs_cols].to_numpy(), ) # Add confidence intervals. From 0ca2ab21e2a13010f4015272835c4a6fccd4ba0f Mon Sep 17 00:00:00 2001 From: blankkirigaya Date: Sat, 28 Feb 2026 20:22:59 +0530 Subject: [PATCH 2/2] fixed repeated variable issue --- malariagen_data/anoph/hap_frq.py | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/malariagen_data/anoph/hap_frq.py b/malariagen_data/anoph/hap_frq.py index 66b9d66fd..e9d18a607 100644 --- a/malariagen_data/anoph/hap_frq.py +++ b/malariagen_data/anoph/hap_frq.py @@ -263,20 +263,20 @@ def haplotypes_frequencies_advanced( # Label the haplotypes ds_out["variant_label"] = "variants", df_haps_sorted["label"].values # Event variables. - freq_cols = [c for c in df_haps_sorted.columns if c.startswith("frq_")] - count_cols = [c for c in df_haps_sorted.columns if c.startswith("count_")] - nobs_cols = [c for c in df_haps_sorted.columns if c.startswith("nobs_")] + freq_cols_name = [c for c in df_haps_sorted.columns if c.startswith("frq_")] + count_cols_name = [c for c in df_haps_sorted.columns if c.startswith("count_")] + nobs_cols_name = [c for c in df_haps_sorted.columns if c.startswith("nobs_")] ds_out["event_frequency"] = ( ("variants", "cohorts"), - df_haps_sorted[freq_cols].to_numpy(), + df_haps_sorted[freq_cols_name].to_numpy(), ) ds_out["event_count"] = ( ("variants", "cohorts"), - df_haps_sorted[count_cols].to_numpy(), + df_haps_sorted[count_cols_name].to_numpy(), ) ds_out["event_nobs"] = ( ("variants", "cohorts"), - df_haps_sorted[nobs_cols].to_numpy(), + df_haps_sorted[nobs_cols_name].to_numpy(), ) # Add confidence intervals.