#!/usr/bin/python
# -*- coding: UTF-8 -*-
#
# Created by WW on Jan. 26, 2020
# All rights reserved.
#
import h5py
import numpy as np
def main():
#===========================================================================
# Create a HDF5 file.
f = h5py.File("h5py_example.hdf5", "w") # mode = {'w', 'r', 'a'}
# Create two groups under root '/'.
g1 = f.create_group("bar1")
g2 = f.create_group("bar2")
# Create a dataset under root '/'.
d = f.create_dataset("dset", data=np.arange(16).reshape([4, 4]))
# Add two attributes to dataset 'dset'
d.attrs["myAttr1"] = [100, 200]
d.attrs["myAttr2"] = "Hello, world!"
# Create a group and a dataset under group "bar1".
c1 = g1.create_group("car1")
d1 = g1.create_dataset("dset1", data=np.arange(10))
# Create a group and a dataset under group "bar2".
c2 = g2.create_group("car2")
d2 = g2.create_dataset("dset2", data=np.arange(10))
# Save and exit the file.
f.close()
''' h5py_example.hdf5 file structure
+-- '/'
| +-- group "bar1"
| | +-- group "car1"
| | | +-- None
| | |
| | +-- dataset "dset1"
| |
| +-- group "bar2"
| | +-- group "car2"
| | | +-- None
| | |
| | +-- dataset "dset2"
| |
| +-- dataset "dset"
| | +-- attribute "myAttr1"
| | +-- attribute "myAttr2"
| |
|
'''
#===========================================================================
# Read HDF5 file.
f = h5py.File("h5py_example.hdf5", "r") # mode = {'w', 'r', 'a'}
# Print the keys of groups and datasets under '/'.
print(f.filename, ":")
print([key for key in f.keys()], "\n")
#===================================================
# Read dataset 'dset' under '/'.
d = f["dset"]
# Print the data of 'dset'.
print(d.name, ":")
print(d[:])
# Print the attributes of dataset 'dset'.
for key in d.attrs.keys():
print(key, ":", d.attrs[key])
print()
#===================================================
# Read group 'bar1'.
g = f["bar1"]
# Print the keys of groups and datasets under group 'bar1'.
print([key for key in g.keys()])
# Three methods to print the data of 'dset1'.
print(f["/bar1/dset1"][:]) # 1. absolute path
print(f["bar1"]["dset1"][:]) # 2. relative path: file[][]
print(g['dset1'][:]) # 3. relative path: group[]
# Delete a database.
# Notice: the mode should be 'a' when you read a file.
'''
del g["dset1"]
'''
# Save and exit the file
f.close()
if __name__ == "__main__":
main()
import h5py
f=h5py.File("myh5py.hdf5","w")
import h5py
f=h5py.File("myh5py.hdf5","w")
#deset1是数据集的name，（20,）代表数据集的shape，i代表的是数据集的元素类型
d1=f.create_dataset("dset1", (20,), 'i')
for key in f.keys():
print(key)
print(f[key].name)
print(f[key].shape)
print(f[key].value)
输出：
dset1
/dset1
(20,)
[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0]
import h5py
import numpy as np
f=h5py.File("myh5py.hdf5","w")
d1=f.create_dataset("dset1",(20,),'i')
#赋值
d1[...]=np.arange(20)
#或者我们可以直接按照下面的方式创建数据集并赋值
f["dset2"]=np.arange(15)
for key in f.keys():
print(f[key].name)
print(f[key].value)
输出：
/dset1
[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19]
/dset2
[ 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14]
import h5py
import numpy as np
f=h5py.File("myh5py.hdf5","w")
#创建一个名字为bar的组
g1=f.create_group("bar")
#在bar这个组里面分别创建name为dset1,dset2的数据集并赋值。
g1["dset1"]=np.arange(10)
g1["dset2"]=np.arange(12).reshape((3,4))
for key in g1.keys():
print(g1[key].name)
print(g1[key].value)
输出：
/bar/dset1
[0 1 2 3 4 5 6 7 8 9]
/bar/dset2
[[ 0 1 2 3]
[ 4 5 6 7]
[ 8 9 10 11]]
# 删除某个key，调用remove
f.remove("bar")
import pandas as pd
import numpy as np
# 将mode改成r即可
hdf5 = pd.HDFStore("hello.h5", mode="r")
# 或者
"""
hdfs = pd.read_hdf("hello.h5", key="xxx")
"""
發表於 2020-11-22 18:15:00