Python 数据分析之逐块读取文本的实现

from pandas import DataFrame,Series
import pandas as pd
 
path='D:/AStudy2018/pydata-book-2nd-edition/examples/ex6.csv'
# chunksize return TextParser
chunker=pd.read_csv(path,chunksize=1000)
 
# an array of Series
tot=Series([])
chunkercount=0
for piece in chunker:
	print '------------piece[key] value_counts start-----------'
	#piece is a DataFrame,lenth is chunksize=1000,and piece[key] is a Series ,key is int ,value is the key column
	print piece['key'].value_counts()
	print '------------piece[key] value_counts end-------------'
	#piece[key] value_counts is a Series ,key is the key column, and value is the key count
	tot=tot.add(piece['key'].value_counts(),fill_value=0)
	chunkercount+=1
 
#last order the series
tot=tot.order(ascending=False)
print chunkercount
print '--------------'