我尝试查询pandas HDF存储中的多索引表,但是当同时对index和data_columns使用查询时,它会失败。这仅在data_columns=True
时发生。知道这是否是预期的,或者如果我不想明确指定data_columns,如何避免?
请参阅以下示例,它似乎无法将索引识别为有效引用:
import pandas as pd
import numpy as np
file_path = 'D:\\test_store.h5'
np.random.seed(1234)
pd.set_option('display.max_rows',4)
# simulate some data
index = pd.MultiIndex.from_product([np.arange(10000,10200),
pd.date_range('19800101',periods=500)],
names=['id','date'])
df = pd.DataFrame(dict(id2=np.random.randint(0, 1000, size=len(index)),
w=np.random.randn(len(index))),
index=index).reset_index().set_index(['id', 'date'])
# store the data
store = pd.HDFStore(file_path,mode='a',complib='blosc', complevel=9)
store.append('df_dc_None', df, data_columns=None)
store.append('df_dc_explicit', df, data_columns=['id2', 'w'])
store.append('df_dc_True', df, data_columns=True)
store.close()
# query the data
start = '19810201'
print(pd.read_hdf(file_path,'df_dc_None', where='date>start & id=10000'))
print(pd.read_hdf(file_path,'df_dc_True', where='id2>500'))
print(pd.read_hdf(file_path,'df_dc_explicit', where='date>start & id2>500'))
try:
print(pd.read_hdf(file_path,'df_dc_True', where='date>start & id2>500'))
except ValueError as err:
print(err)
答案 0 :(得分:2)
这确实是一个有趣的问题!
我无法解释以下差异(为什么我们在使用data_columns=None
时将索引列编入索引(默认由于docstring
方法的HDFStore.append
)而我们没有使用data_columns=True
时将它们编入索引:
In [114]: store.get_storer('df_dc_None').table
Out[114]:
/df_dc_None/table (Table(100000,), shuffle, blosc(9)) ''
description := {
"index": Int64Col(shape=(), dflt=0, pos=0),
"values_block_0": Int32Col(shape=(1,), dflt=0, pos=1),
"values_block_1": Float64Col(shape=(1,), dflt=0.0, pos=2),
"date": Int64Col(shape=(), dflt=0, pos=3),
"id": Int64Col(shape=(), dflt=0, pos=4)}
byteorder := 'little'
chunkshape := (1820,)
autoindex := True
colindexes := {
"date": Index(6, medium, shuffle, zlib(1)).is_csi=False,
"id": Index(6, medium, shuffle, zlib(1)).is_csi=False,
"index": Index(6, medium, shuffle, zlib(1)).is_csi=False}
In [115]: store.get_storer('df_dc_True').table
Out[115]:
/df_dc_True/table (Table(100000,), shuffle, blosc(9)) ''
description := {
"index": Int64Col(shape=(), dflt=0, pos=0),
"values_block_0": Int64Col(shape=(1,), dflt=0, pos=1),
"values_block_1": Int64Col(shape=(1,), dflt=0, pos=2),
"id2": Int32Col(shape=(), dflt=0, pos=3),
"w": Float64Col(shape=(), dflt=0.0, pos=4)}
byteorder := 'little'
chunkshape := (1820,)
autoindex := True
colindexes := {
"w": Index(6, medium, shuffle, zlib(1)).is_csi=False,
"index": Index(6, medium, shuffle, zlib(1)).is_csi=False,
"id2": Index(6, medium, shuffle, zlib(1)).is_csi=False}
注意:请注意上面输出中的colindexes
。
但是使用以下简单的黑客,我们可以“修复”这个:
In [116]: store.append('df_dc_all', df, data_columns=df.head(1).reset_index().columns)
In [118]: store.get_storer('df_dc_all').table
Out[118]:
/df_dc_all/table (Table(100000,), shuffle, blosc(9)) ''
description := {
"index": Int64Col(shape=(), dflt=0, pos=0),
"id": Int64Col(shape=(), dflt=0, pos=1),
"date": Int64Col(shape=(), dflt=0, pos=2),
"id2": Int32Col(shape=(), dflt=0, pos=3),
"w": Float64Col(shape=(), dflt=0.0, pos=4)}
byteorder := 'little'
chunkshape := (1820,)
autoindex := True
colindexes := {
"w": Index(6, medium, shuffle, zlib(1)).is_csi=False,
"date": Index(6, medium, shuffle, zlib(1)).is_csi=False,
"id": Index(6, medium, shuffle, zlib(1)).is_csi=False,
"index": Index(6, medium, shuffle, zlib(1)).is_csi=False,
"id2": Index(6, medium, shuffle, zlib(1)).is_csi=False}
检查:
In [119]: pd.read_hdf(file_path,'df_dc_all', where='date>start & id2>500')
Out[119]:
id2 w
id date
10000 1981-02-02 935 0.245637
1981-02-04 994 0.291287
... ... ...
10199 1981-05-11 680 -0.370745
1981-05-12 812 -0.880742
[10121 rows x 2 columns]