Question

这是我在论坛上的第一个问题。感谢您的帮助！

我基于df.iterrows（）（sic。）编写了嵌套的for循环，执行该过程需要花费大量时间。我需要通过在描述的条件下检查所有单元格来将值从一个数据帧转换为另一个数据帧。您能帮我使它生效吗？（多重处理，应用方法，向量化还是其他？）会非常感激！：）

样本数据：

import pandas as pd
import numpy as np

d1 = {'geno_start' : [60, 1120, 1660], 'geno_end' : [90, 1150, 1690], 'original_subseq' : ['AAATGCCTGAACCTTGGAATTGGA',  'AAATGCCTGAACCTTGGAATTGGA', 'AAATGCCTGAACCTTGGAATTGGA']}

d2 = {'most_left_coordinate_genome' : [56, 1120, 1655], 'most_right_coordinate_genome' : [88, 1150, 1690], 'protein_ID' : ['XYZ_1', 'XYZ_2', 'XYZ_3']}

df_1 = pd.DataFrame(data=d1)
df_2 = pd.DataFrame(data=d2)

df_1['protein_ID'] = np.nan


def match_ranges(df1: pd.DataFrame, df2: pd.DataFrame):

for index, row_2 in df2.iterrows():
    for index_1, row_1 in df1.iterrows():
        if (row_1['geno_start'] >= row_2['most_left_coordinate_genome']) & (row_1['geno_end'] <= row_2['most_right_coordinate_genome']):
            df1['protein_ID'].iloc[index_1] = row_2['protein_ID']
                
        elif (abs(row_1['geno_start'] - row_2['most_left_coordinate_genome']) < 30) & (row_1['geno_end'] <= row_2['most_right_coordinate_genome']):
            df1['protein_ID'].iloc[index_1] = row_2['protein_ID']
                
        elif (row_1['geno_start'] >= row_2['most_left_coordinate_genome']) & (abs(row_1['geno_end'] - row_2['most_right_coordinate_genome']) < 30):
            df1['protein_ID'].iloc[index_1] = row_2['protein_ID']

match_ranges(df_1, df_2)

Desired output:

Answer 1

这是从2个for循环到1个循环的一种方式。我重命名了几列以减少行宽。

首先，创建数据框：

import pandas as pd

d1 = {'geno_start' : [60, 1120, 1660], 
      'geno_end' : [90, 1150, 1690], 
      'original_subseq' : ['AAATGCCTGAACCTTGGAATTGGA',  
                           'AAATGCCTGAACCTTGGAATTGGA', 
                           'AAATGCCTGAACCTTGGAATTGGA'],}
d2 = {'left' : [56, 1120, 1655], 
      'right' : [88, 1150, 1690], 
      'protein_ID' : ['XYZ_1', 'XYZ_2', 'XYZ_3']}
df_1 = pd.DataFrame(data=d1)
df_1['protein_ID'] = '?'
df_1['rule'] = '?'
df_2 = pd.DataFrame(data=d2)

第二，在第一个数据框中填充protein_ID列（即，以基因组开始，基因组结束）：

for g in df_1.itertuples():
    
    # Rule A: left most <= geno start < geno end <= right-most
    # LM-----------------------RM   left- and right-most
    #     GS-----------GE           genome start, end
    if ((df_2['left'] <= g.geno_start) & (g.geno_end <= df_2['right'])).any():
        mask = (df_2['left'] <= g.geno_start) & (g.geno_end <= df_2['right'])
        df_1.at[g.Index, 'protein_ID'] = df_2.loc[mask, 'protein_ID'].values[0]
        df_1.at[g.Index, 'rule'] = 'Rule A'
        
        
    # Rule B: geno start before left-most
    #      LM-----------------RM
    #  GS-----------------GE
    elif ((df_2['left'] - g.geno_start < 30) & (g.geno_end <= df_2['right'])).any():
        mask = (df_2['left'] - g.geno_start < 30) & (g.geno_end <= df_2['right'])
        df_1.at[g.Index, 'protein_ID'] = df_2.loc[mask, 'protein_ID'].values[0]
        df_1.at[g.Index, 'rule'] = 'Rule B'

    # Rule C: geno end after right-most 
    #      LM-----------------RM
    #          GS-----------------GE

    elif ((df_2['left'] <= g.geno_start) & (g.geno_end - df_2['right'] < 30)).any():
        mask = (df_2['left'] <= g.geno_start) & (g.geno_end - df_2['right'] < 30)
        df_1.at[g.Index, 'protein_ID'] = df_2.loc[mask, 'protein_ID'].values[0]
        df_1.at[g.Index, 'rule'] = 'Rule C'
        
    else:
        pass

print(df_1)
   geno_start  geno_end           original_subseq protein_ID    rule
0          60        90  AAATGCCTGAACCTTGGAATTGGA      XYZ_1  Rule C
1        1120      1150  AAATGCCTGAACCTTGGAATTGGA      XYZ_2  Rule A
2        1660      1690  AAATGCCTGAACCTTGGAATTGGA      XYZ_3  Rule A

在大熊猫中使用行列的有效方法（另一种方法）

1 个答案: