我需要从大约6000万行的数据集中创建一个2000列，大约30-50百万行的数据透视表。我曾尝试过旋转100,000行的数据块，但这种方法行得通，但是当我尝试通过先执行.append（）然后再执行.groupby（’someKey’）。sum（）来重组DataFrame时，我的所有内存都被占用了和python最终崩溃。

如何在有限的RAM量下处理如此大的数据？

编辑：添加示例代码

下面的代码在此过程中包括各种测试输出，但是最后打印的是我们真正感兴趣的内容。请注意，如果将segMax更改为3（而不是4），则该代码将为正确的输出产生误报。主要的问题是，如果sum（wawa）所查看的每个块中都不存在shipmentid条目，则该条目不会显示在输出中。

import pandas as pd
import numpy as np
import random
from pandas.io.pytables import *
import os

pd.set_option('io.hdf.default_format','table')

# create a small dataframe to simulate the real data.
def loadFrame():
    frame = pd.DataFrame()
    frame['shipmentid']=[1,2,3,1,2,3,1,2,3] #evenly distributing shipmentid values for testing purposes
    frame['qty']= np.random.randint(1,5,9) #random quantity is ok for this test
    frame['catid'] = np.random.randint(1,5,9) #random category is ok for this test
    return frame

def pivotSegment(segmentNumber,passedFrame):
    segmentSize = 3 #take 3 rows at a time
    frame = passedFrame[(segmentNumber*segmentSize):(segmentNumber*segmentSize + segmentSize)] #slice the input DF

    # ensure that all chunks are identically formatted after the pivot by appending a dummy DF with all possible category values
    span = pd.DataFrame() 
    span['catid'] = range(1,5+1)
    span['shipmentid']=1
    span['qty']=0

    frame = frame.append(span)

    return frame.pivot_table(['qty'],index=['shipmentid'],columns='catid', \
                             aggfunc='sum',fill_value=0).reset_index()

def createStore():

    store = pd.HDFStore('testdata.h5')
    return store

segMin = 0
segMax = 4

store = createStore()
frame = loadFrame()

print('Printing Frame')
print(frame)
print(frame.info())

for i in range(segMin,segMax):
    segment = pivotSegment(i,frame)
    store.append('data',frame[(i*3):(i*3 + 3)])
    store.append('pivotedData',segment)

print('\nPrinting Store')   
print(store)
print('\nPrinting Store: data') 
print(store['data'])
print('\nPrinting Store: pivotedData') 
print(store['pivotedData'])

print('**************')
print(store['pivotedData'].set_index('shipmentid').groupby('shipmentid',level=0).sum())
print('**************')
print('$$$')
for df in store.select('pivotedData',chunksize=3):
    print(df.set_index('shipmentid').groupby('shipmentid',level=0).sum())

print('$$$')
store['pivotedAndSummed'] = sum((df.set_index('shipmentid').groupby('shipmentid',level=0).sum() for df in store.select('pivotedData',chunksize=3)))
print('\nPrinting Store: pivotedAndSummed') 
print(store['pivotedAndSummed'])

store.close()
os.remove('testdata.h5')
print('closed')