Question

import pandas as pd
from pandas import DataFrame
import tables as pytb

with pytb.open_file('debug_counts.h5', mode='r') as h5file:

    table = h5file.get_node('/tbl_main') 

    print("number of rows in table =", table.nrows) 

    i = 0 
    j = 0
    for row in table:
        j += 1
        if row['symbol'] == b"foo":           
            i += 1  

    print("table all records count =", j)  
    print("table foo records count =", i)  

    df = pd.DataFrame.from_records(table.read_where('(symbol == b"foo")')) 

    print("dataframe size =", df.size)    

    i = 0
    for index, row in df.iterrows():
        i += 1

    print("dataframe records count =", i)    

    i = 0 
    for record in table.where('(symbol == b"foo")'):
        i += 1

    print("table.where records count =", i)

    h5file.close()

输出：

runfile('G:/$HDF5/debug_counts.py', wdir='G:/$HDF5')
number of rows in table = 2826254
table all records count = 2826254
table foo records count = 37920
dataframe size = 985920
dataframe records count = 37920
table.where records count = 37920

较大的数字都是正确的。 37920数字不正确，或者至少不是我想要的数字。如何获取我要查找的输出（985920，而不是37920），以及37920来自何处？

Answer 1

这是我将如何编码以获得行数和大小计数的方法。我无法测试您的例子。抱歉，如果有误输入。

import tables as pytb
with pytb.open_file('debug_counts.h5', mode='r') as h5file:
    table = h5file.get_node('/tbl_main')

    sym_list = table.get_where_list('(symbol == b"foo")')
    print("table.get_where_list retrieved =", len(sym_list), "rows" )

    sym_array = table.read_where('(symbol == b"foo")')
    print("table.read_where array dtype=" , sym_array.dtype)     
    print("table.read_where array shape=" , sym_array.shape)
    print("table.read_where array size =" , sym_array.size)

遍历数据帧或pytable中的记录的正确语法是什么？

1 个答案: