框式打印中列的前十个值

Question

我有一个大的dataframe，在这里我使用t检验计算每一行的p值。我现在想要一个包含前十个最低p值的行的箱线图

LeadSNPs = pd.unique(candidate_genes.LeadSNP) #rs3184504 rs531612
gene_counts_per_snp_df = pd.DataFrame.empty
save_path = "../figures/SM5_gene_counts/"
for LeadSNP_cnt, LeadSNP in enumerate(LeadSNPs):
    print(LeadSNP)
    candidate_genes_per_SNP = candidate_genes.Target[np.where(candidate_genes.LeadSNP==LeadSNP)[0]]
    region = pd.unique(candidate_genes.Region[np.where(candidate_genes.LeadSNP==LeadSNP)[0]])
    first_gene_flag = 1
    for gene_cnt, target_gene in enumerate(candidate_genes_per_SNP):
        gene_indexes = candidate_genes_per_SNP.index
        PRE = candidate_genes['sumOfWeightedWeights (PRE)'][gene_indexes[gene_cnt]]
        print(target_gene)
        ensembl_id = get_ensembl_id(target_gene)
        print(ensembl_id)
        if pd.isnull(ensembl_id):
            pass
        else:
            gene_counts_df = get_gene_counts_df(ensembl_id)
            if gene_counts_df.shape[0]==0:
                print('no ensemble id found in gene counts!')
            else:
                gene_counts_df = gene_counts_df.melt(id_vars=["Gene"], var_name='compartment', value_name='count')
                gene_counts_df = reshape_gene_counts_df(gene_counts_df)
                gene_counts_df['target_gene'] = target_gene
                gene_counts_df['PRE'] = PRE
                gene_counts_df['pval_ftest']= np.nan
                pop3= gene_counts_df.loc[(gene_counts_df['target_gene']==target_gene) & (gene_counts_df['compartment']=='CSF_N')]['count']
                pop4 = gene_counts_df.loc[(gene_counts_df['target_gene']==target_gene) & (gene_counts_df['compartment']=='PB_N')]['count']
                pval1 = stats.ttest_ind(pop3, pop4)[1]
                gene_counts_df.loc[(gene_counts_df['target_gene']==target_gene) & (gene_counts_df['compartment'].isin(['CSF_N','PB_N'])),"pval_ftest"]= pval_ftest
                if first_gene_flag == 1:
                    gene_counts_per_snp_df = gene_counts_df
                    first_gene_flag = 0
                else:
                    gene_counts_per_snp_df = pd.concat([gene_counts_per_snp_df, gene_counts_df])
    gene_counts_per_snp_df['LeadSNP'] = LeadSNP
    if LeadSNP_cnt == 0:
        all_gene_counts = gene_counts_per_snp_df
    else:
        all_gene_counts = pd.concat([all_gene_counts, gene_counts_per_snp_df])
all_gene_counts = pd.DataFrame.reset_index(all_gene_counts)
plot_top_genes_snps(all_gene_counts_per_comp, 'target_gene')

绘图代码如下所示：

def plot_top_genes_snps(all_gene_counts_per_comp, x_label):
    
    sns.set(style="white")
    sns.set_context("poster")
    palette = sns.color_palette("colorblind", 10)
    
    fig, ax = plt.subplots(figsize=(25,4))
    g = sns.boxplot(ax=ax, y='count', x=x_label, data=all_gene_counts_per_comp, hue = 'compartment', showfliers=False, palette=palette, hue_order=comp_order)
    ax.set_xticklabels(ax.get_xticklabels(), rotation=45, horizontalalignment='right')
    handles, _ = ax.get_legend_handles_labels()
    current_legends = []
    for str_ind in range(len(handles)):
        current_legends.append(comp_dict[handles[str_ind].get_label()])
    ax.legend(handles, current_legends, bbox_to_anchor=(1, 1), loc=2)
    ax.yaxis.grid()
    sns.set(font_scale = 2)
    plt.xlabel('')
    plt.ylabel('Gene count')
    # plt.savefig(save_path+str(LeadSNP)+'.pdf', bbox_inches='tight')
    plt.show()

对于上下文，我想要具有最低p值的前十个target_gene。然而，这是我得到的情节：

allgenesandpvalues

如何仅提取十个最低的p值并进行箱线图绘制

更新：数据框如下所示，该表从不同的SNP重复：

dataframe

文本格式的dataframe

Gene compartment  count patient_id target_gene  PRE  \
1   ENSG00000157870       CSF_N      0          1     FAM213B  7.5   
11  ENSG00000157870       CSF_N      0          2     FAM213B  7.5   
21  ENSG00000157870       CSF_N      0          3     FAM213B  7.5   
31  ENSG00000157870       CSF_N      0          4     FAM213B  7.5   
41  ENSG00000157870       CSF_N      0          5     FAM213B  7.5   
..              ...         ...    ...        ...         ...  ...   
21  ENSG00000182866       CSF_N     18          3         LCK  2.0   
31  ENSG00000182866       CSF_N     45          4         LCK  2.0   
41  ENSG00000182866       CSF_N      0          5         LCK  2.0   
51  ENSG00000182866       CSF_N      9          6         LCK  2.0   
61  ENSG00000182866       CSF_N      0          7         LCK  2.0   

    pval_ftest        LeadSNP  
1     0.222523      rs6670198  
11    0.222523      rs6670198  
21    0.222523      rs6670198  
31    0.222523      rs6670198  
41    0.222523      rs6670198  

Answer 1

all_gene_counts_per_comp.sort_values(by="pval_ftest").loc[:10, :]

将为您提供具有最小"pval_ftest"值的前10行

也许这个玩具示例会让我们更清楚地了解如何排序和选择数据帧的子集

>>> df = pd.DataFrame({"a": [1, 2, 3, 4], "b": [4, 3, 2, 1]})
>>> print(df)
   a  b
0  1  4
1  2  3
2  3  2
3  4  1
>>> df_sorted = df.sort_values(by="b")
>>> print(df_sorted)
   a  b
3  4  1
2  3  2
1  2  3
0  1  4
>>> print(df_sorted.loc[:2, :])
   a  b
3  4  1
2  3  2