Pandas groupby 应用执行缓慢

Question

我正在开发一个涉及大量数据的程序。我正在使用 python pandas 模块来查找我的数据中的错误。这通常工作得非常快。然而，我写的这段代码似乎比它应该的要慢得多，我正在寻找一种方法来加快它。

为了让你们正确测试它，我上传了一段相当大的代码。您应该能够按原样运行它。代码中的 cmets 应该解释我在这里尝试做什么。任何帮助将不胜感激。

# -*- coding: utf-8 -*-

import pandas as pd
import numpy as np

# Filling dataframe with data
# Just ignore this part for now, real data comes from csv files, this is an example of how it looks
TimeOfDay_options = ['Day','Evening','Night']
TypeOfCargo_options = ['Goods','Passengers']
np.random.seed(1234)
n = 10000

df = pd.DataFrame()
df['ID_number'] = np.random.randint(3, size=n)
df['TimeOfDay'] = np.random.choice(TimeOfDay_options, size=n)
df['TypeOfCargo'] = np.random.choice(TypeOfCargo_options, size=n)
df['TrackStart'] = np.random.randint(400, size=n) * 900
df['SectionStart'] = np.nan
df['SectionStop'] = np.nan

grouped_df = df.groupby(['ID_number','TimeOfDay','TypeOfCargo','TrackStart'])
for index, group in grouped_df:
    if len(group) == 1:
        df.loc[group.index,['SectionStart']] = group['TrackStart']
        df.loc[group.index,['SectionStop']] = group['TrackStart'] + 899

    if len(group) > 1:
        track_start = group.loc[group.index[0],'TrackStart']
        track_end = track_start + 899
        section_stops = np.random.randint(track_start, track_end, size=len(group))
        section_stops[-1] = track_end
        section_stops = np.sort(section_stops)
        section_starts = np.insert(section_stops, 0, track_start)

        for i,start,stop in zip(group.index,section_starts,section_stops):
            df.loc[i,['SectionStart']] = start
            df.loc[i,['SectionStop']] = stop

#%% This is what a random group looks like without errors
#Note that each section neatly starts where the previous section ended
#There are no gaps (The whole track is defined)
grouped_df.get_group((2, 'Night', 'Passengers', 323100))

#%% Introducing errors to the data
df.loc[2640,'SectionStart'] += 100
df.loc[5390,'SectionStart'] += 7

#%% This is what the same group looks like after introducing errors 
#Note that the 'SectionStop' of row 1525 is no longer similar to the 'SectionStart' of row 2640
#This track now has a gap of 100, it is not completely defined from start to end
grouped_df.get_group((2, 'Night', 'Passengers', 323100))

#%% Try to locate the errors
#This is the part of the code I need to speed up

def Full_coverage(group):
    if len(group) > 1:
        #Sort the grouped data by column 'SectionStart' from low to high

        #Updated for newer pandas version
        #group.sort('SectionStart', ascending=True, inplace=True)
        group.sort_values('SectionStart', ascending=True, inplace=True)

        #Some initial values, overwritten at the end of each loop  
        #These variables correspond to the first row of the group
        start_km = group.iloc[0,4]
        end_km = group.iloc[0,5]
        end_km_index = group.index[0]

        #Loop through all the rows in the group
        #index is the index of the row
        #i is the 'SectionStart' of the row
        #j is the 'SectionStop' of the row
        #The loop starts from the 2nd row in the group
        for index, (i, j) in group.iloc[1:,[4,5]].iterrows():

            #The start of the next row must be equal to the end of the previous row in the group
            if i != end_km: 

                #Add the faulty data to the error list
                incomplete_coverage.append(('Expected startpoint: '+str(end_km)+' (row '+str(end_km_index)+')', \
                                    'Found startpoint: '+str(i)+' (row '+str(index)+')'))                

            #Overwrite these values for the next loop
            start_km = i
            end_km = j
            end_km_index = index

    return group

#Check if the complete track is completely defined (from start to end) for each combination of:
    #'ID_number','TimeOfDay','TypeOfCargo','TrackStart'
incomplete_coverage = [] #Create empty list for storing the error messages
df_grouped = df.groupby(['ID_number','TimeOfDay','TypeOfCargo','TrackStart']).apply(lambda x: Full_coverage(x))

#Print the error list
print('\nFound incomplete coverage in the following rows:')
for i,j in incomplete_coverage:
    print(i)
    print(j)
    print() 

#%%Time the procedure -- It is very slow, taking about 6.6 seconds on my pc
%timeit df.groupby(['ID_number','TimeOfDay','TypeOfCargo','TrackStart']).apply(lambda x: Full_coverage(x))

Answer 1

我认为，问题在于您的数据有 5300 个不同的组。因此，您的功能中的任何缓慢都会被放大。您可能可以在函数中使用矢量化操作而不是 for 循环来节省时间，但更简单的节省时间的方法是使用 return 0 而不是 return group。当您return group 时，pandas 实际上会创建一个新的数据对象，并结合您的排序组，而您似乎没有使用它。当你return 0 时，pandas 会合并 5300 个零，这样更快。

例如：

cols = ['ID_number','TimeOfDay','TypeOfCargo','TrackStart']
groups = df.groupby(cols)
print(len(groups))
# 5353

%timeit df.groupby(cols).apply(lambda group: group)
# 1 loops, best of 3: 2.41 s per loop

%timeit df.groupby(cols).apply(lambda group: 0)
# 10 loops, best of 3: 64.3 ms per loop

仅结合您不使用的结果大约需要 2.4 秒；其余时间是循环中的实际计算，您应该尝试对其进行矢量化。

---

编辑：

通过在 for 循环之前进行快速的额外矢量化检查并返回 0 而不是 group，我将时间缩短到大约 2 秒，这基本上是对每个组进行排序的成本。试试这个功能：

def Full_coverage(group):
    if len(group) > 1:
        group = group.sort('SectionStart', ascending=True)

        # this condition is sufficient to find when the loop
        # will add to the list
        if np.any(group.values[1:, 4] != group.values[:-1, 5]):
            start_km = group.iloc[0,4]
            end_km = group.iloc[0,5]
            end_km_index = group.index[0]

            for index, (i, j) in group.iloc[1:,[4,5]].iterrows():
                if i != end_km:
                    incomplete_coverage.append(('Expected startpoint: '+str(end_km)+' (row '+str(end_km_index)+')', \
                                        'Found startpoint: '+str(i)+' (row '+str(index)+')'))                
                start_km = i
                end_km = j
                end_km_index = index

    return 0

cols = ['ID_number','TimeOfDay','TypeOfCargo','TrackStart']
%timeit df.groupby(cols).apply(Full_coverage)
# 1 loops, best of 3: 1.74 s per loop

---

编辑 2：这是一个示例，其中包含我的建议，将排序移到 groupby 之外并删除不必要的循环。对于给定的示例，删除循环并没有快多少，但如果有很多不完整的，会更快：

def Full_coverage_new(group):
    if len(group) > 1:
        mask = group.values[1:, 4] != group.values[:-1, 5]
        if np.any(mask):
            err = ('Expected startpoint: {0} (row {1}) '
                   'Found startpoint: {2} (row {3})')
            incomplete_coverage.extend([err.format(group.iloc[i, 5],
                                                   group.index[i],
                                                   group.iloc[i + 1, 4],
                                                   group.index[i + 1])
                                        for i in np.where(mask)[0]])
    return 0

incomplete_coverage = []
cols = ['ID_number','TimeOfDay','TypeOfCargo','TrackStart']
df_s = df.sort_values(['SectionStart','SectionStop'])
df_s.groupby(cols).apply(Full_coverage_nosort)

Answer 2

我发现 pandas 的定位命令（.loc 或 .iloc）也减慢了进度。通过将排序移出循环并在函数开始时将数据转换为 numpy 数组，我得到了更快的结果。我知道数据不再是数据框，但列表中返回的索引可用于查找原始 df 中的数据。

如果有任何方法可以进一步加快进程，我将不胜感激。到目前为止我所拥有的：

def Full_coverage(group):

    if len(group) > 1:
        group_index = group.index.values
        group = group.values

        # this condition is sufficient to find when the loop will add to the list
        if np.any(group[1:, 4] != group[:-1, 5]):
            start_km = group[0,4]
            end_km = group[0,5]
            end_km_index = group_index[0]

            for index, (i, j) in zip(group_index, group[1:,[4,5]]):

                if i != end_km:
                    incomplete_coverage.append(('Expected startpoint: '+str(end_km)+' (row '+str(end_km_index)+')', \
                                        'Found startpoint: '+str(i)+' (row '+str(index)+')'))               
                start_km = i
                end_km = j
                end_km_index = index

    return 0

incomplete_coverage = []
df.sort(['SectionStart','SectionStop'], ascending=True, inplace=True)
cols = ['ID_number','TimeOfDay','TypeOfCargo','TrackStart']
%timeit df.groupby(cols).apply(Full_coverage)
# 1 loops, best of 3: 272 ms per loop