Я работаю над программой, которая включает в себя большие объемы данных. Я использую модуль Python Pandas для поиска ошибок в моих данных. Это обычно работает очень быстро. Однако этот фрагмент кода, который я написал, кажется намного медленнее, чем должен быть, и я ищу способ ускорить его.
Чтобы вы, ребята, правильно его протестировали, я загрузил довольно большой кусок кода. Вы должны быть в состоянии запустить его как есть. Комментарии в коде должны объяснить, что я пытаюсь сделать здесь. Любая помощь будет принята с благодарностью.
# -*- 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))