文本文件

利用savetxt(),loadtxt()和genfromtxt()函数可以存储读取txt、csv等文本文件。
其中genfromtxt()比loadtxt更加强大，可对缺失值进行处理。

savetxt()

numpy.savetxt(fname, X, fmt='%.18e', delimiter=' ', newline='\n', header='', footer='', comments='# ', encoding=None)
fname:文件路径
X:存入文件的数组
fmt：写入文件中每个元素的字符串格式
delimiter:分割字符串，默认以空格分割

loadtxt()

numpy.loadtxt(fname, dtype=float, comments='#', delimiter=None, converters=None, skiprows=0, usecols=None, unpack=False, ndmin=0, encoding='bytes', max_rows=None)
fname:文件路径
dtype：文件类型，默认为float
comments：字符串或字符组成的列表
skiprows：跳读，表示跳过多少行，一般跳过表头
usecols：元组。用来指定要读取数据的列
unpack：当加载多列数据时是否需要将数据列进行解耦赋值给不用的变量

例子

import numpy as np

outfile = r'.\test.txt'
x = np.arange(0, 10).reshape(2, -1)
np.savetxt(outfile, x)
y = np.loadtxt(outfile)
print(y)

import numpy as np

outfile = r'.\test.csv'
x = np.arange(0, 10, 0.5).reshape(4, -1)
np.savetxt(outfile, x, fmt='%.3f', delimiter=',')
y = np.loadtxt(outfile, delimiter=',')
print(y)

genfromtxt()是面向结构数组和缺失数据处理的

numpy.genfromtxt(fname, dtype=float, comments='#', delimiter=None, skip_header=0, skip_footer=0, converters=None, missing_values=None, filling_values=None, usecols=None, names=None, excludelist=None, deletechars=''.join(sorted(NameValidator.defaultdeletechars)), replace_space='_', autostrip=False, case_sensitive=True, defaultfmt="f%i", unpack=None, usemask=False, loose=True, invalid_raise=True, max_rows=None, encoding='bytes')
names：设置为True时，程序将把第一行作为列名称。

import numpy as np

outfile = r'.\data.csv'
x = np.loadtxt(outfile, delimiter=',', skiprows=1)
print(x)
# [[  1.  123.    1.4  23. ]
#  [  2.  110.    0.5  18. ]
#  [  3.  164.    2.1  19. ]]

x = np.loadtxt(outfile, delimiter=',', skiprows=1, usecols=(1, 2))
print(x)
# [[123.    1.4]
#  [110.    0.5]
#  [164.    2.1]]

val1, val2 = np.loadtxt(outfile, delimiter=',', skiprows=1, usecols=(1, 2), unpack=True)
print(val1)  # [123. 110. 164.]
print(val2)  # [1.4 0.5 2.1]

import numpy as np

outfile = r'.\data.csv'
x = np.genfromtxt(outfile, delimiter=',', names=True)
print(x)
# [(1., 123., 1.4, 23.) (2., 110., 0.5, 18.) (3., 164., 2.1, 19.)]

print(type(x))  
# <class 'numpy.ndarray'>

print(x.dtype)
# [('id', '<f8'), ('value1', '<f8'), ('value2', '<f8'), ('value3', '<f8')]

print(x['id'])  # [1. 2. 3.]
print(x['value1'])  # [123. 110. 164.]
print(x['value2'])  # [1.4 0.5 2.1]
print(x['value3'])  # [23. 18. 19.]

import numpy as np

outfile = r'.\data1.csv'
x = np.genfromtxt(outfile, delimiter=',', names=True)
print(x)
# [(1., 123., 1.4, 23.) (2., 110., nan, 18.) (3.,  nan, 2.1, 19.)]

print(type(x))  
# <class 'numpy.ndarray'>

print(x.dtype)
# [('id', '<f8'), ('value1', '<f8'), ('value2', '<f8'), ('value3', '<f8')]

print(x['id'])  # [1. 2. 3.]
print(x['value1'])  # [123. 110.  nan]
print(x['value2'])  # [1.4 nan 2.1]
print(x['value3'])  # [23. 18. 19.]

文件格式选项

numpy.set_printoptions(precision=None,threshold=None, edgeitems=None,linewidth=None, suppress=None, nanstr=None, infstr=None,formatter=None, sign=None, floatmode=None, **kwarg)
precision:设置浮点精度，控制输出的小数点个数，默认是8
threshold：概略显示，超过该值则以...的形式表示，默认1000
linewidth:用于确定每行多少字符数后插入换行符，默认为75
suppress:当为True，表示小数不需要以科学计数法的形式输出，默认False
nanstr：浮点非数字的字符串表示形式，默认nan
infstr：浮点无穷大的字符串表示形式，默认inf

例子

import numpy as np

np.set_printoptions(precision=4)
x = np.array([1.123456789])
print(x)  # [1.1235]

np.set_printoptions(threshold=20)
x = np.arange(50)
print(x)  # [ 0  1  2 ... 47 48 49]

np.set_printoptions(threshold=np.iinfo(np.int).max)
print(x)
# [ 0  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
#  24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47
#  48 49]

eps = np.finfo(float).eps
x = np.arange(4.)
x = x ** 2 - (x + eps) ** 2
print(x)  
# [-4.9304e-32 -4.4409e-16  0.0000e+00  0.0000e+00]
np.set_printoptions(suppress=True)
print(x)  # [-0. -0.  0.  0.]

x = np.linspace(0, 10, 10)
print(x)
# [ 0.      1.1111  2.2222  3.3333  4.4444  5.5556  6.6667  7.7778  8.8889
#  10.    ]
np.set_printoptions(precision=2, suppress=True, threshold=5)
print(x)  # [ 0.    1.11  2.22 ...  7.78  8.89 10.  ]

x = np.get_printoptions()
print(x)
# {
# 'edgeitems': 3, 
# 'threshold': 1000, 
# 'floatmode': 'maxprec', 
# 'precision': 8, 
# 'suppress': False, 
# 'linewidth': 75, 
# 'nanstr': 'nan', 
# 'infstr': 'inf', 
# 'sign': '-', 
# 'formatter': None, 
# 'legacy': False
# }