将我的数据加载到numpy genfromtxt中会出错 [英] loading my data in numpy genfromtxt get errors
本文介绍了将我的数据加载到numpy genfromtxt中会出错的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！
问题描述
我的数据文件包含7500行，并带有:
I have my data file contain 7500 lines with :
Y1C 1.53 -0.06 0.58 0.52 0.42 0.16 0.79 -0.6 -0.3
-0.78 -0.14 0.38 0.34 0.23 0.26 -1.8 -0.1 -0.17 0.3
0.6 0.9 0.71 0.5 0.49 1.06 0.25 0.96 -0.39 0.24 0.69
0.41 0.7 -0.16 -0.39 0.6 1.04 0.4 -0.04 0.36 0.23 -0.14
-0.09 0.15 -0.46 -0.05 0.32 -0.54 -0.28 -0.15 1.34 0.29
0.59 -0.43 -0.55 -0.18 -0.01 0.68 -0.06 -0.11 -0.67
-0.25 -0.34 -0.38 0.02 -0.21 0.12 0.01 0.07 0.15 0.14
0.15 -0.11 0.07 -0.41 -0.2 0.24 0.06 0.12 0.12 0.11
0.1 0.24 -0.71 0.22 -0.02 0.15 0.84 1.39 0.13 0.48
0.19 -0.23 -0.12 0.33 0.37 0.18 0.06 0.32 0.09
-0.09 0.02 -0.01 -0.06 -0.23 0.52 0.14 0.24 -0.05 0.37
0.1 0.45 0.38 1.34 0.74 0.5 0.92 0.91 1.34 1.78 2.26
0.05 0.29 0.53 0.17 0.41 0.47 0.47 1.21 0.87 0.68
1.08 0.89 0.13 0.5 0.57 -0.5 -0.78 -0.34 -0.3 0.54
0.31 0.64 1.23 0.335 0.36 -0.65 0.39 0.39 0.31 0.73
0.54 0.3 0.26 0.47 0.13 0.24 -0.6 0.02 0.11 0.27
0.21 -0.3 -1 -0.44 -0.15 -0.51 0.3 0.14 -0.15 -0.27 -0.27
Y2W -0.01 -0.3 0.23 0.01 -0.15 0.45 -0.04 0.14 -1.16
-0.14 -0.56 -0.13 0.77 0.77 -0.57 0.48 0.22 -0.08
-1.81 -0.46 -0.17 0.2 -0.18 -0.45 -0.4 1.35 0.81 1.21
0.52 0.02 -0.06 0.37 0 -0.38 -0.02 0.48 0 0.58 0.81
0.54 0.18 -0.11 0.03 0.1 -0.38 0.17 0.37 -0.05 0.13
-0.01 -0.17 0.36 0.22 0 -1.4 -0.67 -0.45 -0.62 -0.58
-0.47 -0.86 -1.12 -0.43 0.1 0.06 -0.45 -0.14 0.68 -0.16
0.14 0.14 0.18 0.14 0.17 0.13 0.07 0.05 0.04 0.07
-0.01 0.03 0.05 0.02 0.12 0.34 -0.04 -0.75 1.68 0.23
0.49 0.38 -0.57 0.17 -0.04 0.19 0.22 0.29 -0.04 -0.3
0.18 0.04 0.3 -0.06 -0.07 -0.21 -0.01 0.51 -0.04 -0.04
-0.23 0.06 0.9 -0.14 0.19 2.5 2.84 3.27 2.13 2.5 2.66
4.16 3.52 -0.12 0.13 0.44 0.32 0.44 0.46 0.7 0.68
0.99 0.83 0.74 0.51 0.33 0.22 0.01 0.33 -0.19 0.4
0.41 0.07 0.18 -0.01 0.45 -0.37 -0.49 1.02 -0.59
-1.44 -1.53 -0.74 -1.48 0.12 0.05 0.02 -0.1 0.57
-0.36 0.1 -0.16 -0.23 -0.34 -0.61 -0.37 -0.14 -0.22 -0.27
-0.08 -0.08 -0.17 0.18 -0.74
Y3W 0.15 -0.07 -0.25 -0.3 -1.12 -0.67 -0.15 -0.43 0.63
0.92 0.25 0.33 0.81 -0.12 -0.12 0.67 0.86 0.86
1.54 -0.3 0 -0.29 -0.74 0.15 0.59 0.15 0.34 0.23
0.5 0.52 0.25 0.86 0.53 0.51 0.25 -1.29 -1.79
-0.45 -0.64 0.01 -0.58 -0.51 -0.74 -1.32 -0.47
-0.81 0.55 -0.09 0.46 -0.3 -0.2 -0.81 -1.56 -2.74 1.03
1 1.01 0.29 -0.64 -1.03 0.07 0.46 0.33 0.04 -0.6
-0.64 -0.51 -0.36 -0.1 0.13 -1.4 -1.17 -0.64 -0.16 -0.5
-0.47 0.75 0.62 0.7 1.06 0.93 0.56 -2.25 -0.94 -0.09
0.08 -0.15 -1.6 -1.43 -0.84 -0.25 -1.22 -0.92 -1.22
-0.97 -0.84 -0.89 0.24 0 -0.04 -0.64 -0.94 -1.56 -2.32
0.63 -0.17 -3.06 -2.4 -2 -1.4 -0.81 -1.6 -3.06 -1.79
0.17 0.28 -0.67 -2.82 -1.47 -1.82 -1.69 -1.38 -1.96
-1.88 -2.34 -3.06 -0.18 0.5 -0.03 -0.49 -0.61 -0.54 -0.37
0.1 -0.92 -1.79 -0.03 -0.54 0.94 -1 0.15 0.95 0.55
-0.36 0.4 -0.73 0.85 -0.26 0.55 0.14 -0.36 0.38 0.87
0.62 0.66 0.79 -0.67 0.48 0.62 0.48 0.72 0.73 0.29
-0.3 -0.81
Y4W 0.24 0.76 0.2 0.34 0.11 0.07 0.01 0.36 0.4 -0.25
-0.45 0.09 -0.97 0.19 0.28 -1.81 -0.64 -0.49 -1.27
-0.95 -0.1 0.12 -0.1 0 -0.08 0.77 1.02 0.92 0.56
0.1 0.7 0.57 0.16 1.29 0.82 0.55 0.5 1.83 1.79 0.01
0.24 -0.67 -0.85 -0.42 -0.37 0.2 0.07 -0.01 -0.17 -0.2
-0.43 -0.34 0.12 -0.21 -0.23 -0.22 -0.1 -0.07 -0.61
-0.14 -0.43 -0.97 0.27 0.7 0.54 0.11 -0.5 -0.39 0.01
0.61 0.88 1 0.35 0.67 0.6 0.78 0.46 0.09 -0.06
-0.35 0.08 -0.14 -0.32 -0.11 0 0.01 0.02 0.77 0.18
0.36 -1.15 -0.42 -0.19 0.06 -0.25 -0.81 -0.63 -1.43
-0.85 -0.88 -0.68 -0.59 -1.01 -0.68 -0.71 0.15 0.08 0.08
-0.03 -0.2 0.03 -0.18 -0.01 -0.08 -1.61 -0.67 -0.74
-0.54 -0.8 -1.02 -0.84 -1.91 -0.22 -0.02 0.05 -0.84
-0.65 -0.82 -0.4 -0.83 -0.9 -1.04 -1.23 -0.91 0.28 0.68
0.57 -0.02 0.4 -1.52 0.17 0.44 -1.18 0.04 0.17 0.16
0.04 -0.26 0.04 0.1 -0.11 -0.64 -0.09 -0.16 0.16 -0.05
0.39 0.39 -0.06 0.46 0.2 -0.45 -0.35 -1.3 -0.26 -0.29
0.02 0.16 0.18 -0.35 -0.45 -1.04 -0.69
Y5C 2.85 3.34 -1 -0.47 -0.66 -0.03 1.41
0.8 0 0.41 -0.14 -0.86 -0.79 -1.69 0 0 1.52
1.29 0.84 0.58 1.02 1.35 0.45 1.02 1.47 0.82 0.46
0.25 0.77 0.93 -0.58 -0.67 -0.18 -0.56 -0.01 0.25
-0.71 -0.49 -0.43 0 -1.06 0.44 -0.29 0.26 -0.04
-0.14 -0.1 -0.12 -1.6 0.33 0.62 0.52 0.7 -0.22 0.44
-0.6 0.86 1.19 1.58 0.93 1 0.85 1.24 1.06 0.49
0.26 0.18 0.3 -0.09 -0.42 0.05 0.54 0.24 0.37 0.86
0.9 0.49 -1.47 -0.2 -0.43 0.2 0.1 -0.81 -0.74 -1.36 -0.97
-0.94 -0.86 -1.56 -1.89 -1.89 -1.06 0.12 0.06 0.04
-0.01 -0.12 0.01 -0.15 0.76 0.89 0.71 -1.12 0.03
-0.86 0.26 0 -0.25 -0.06 0.19 0.41 0.58 -0.46 0.01
-0.15 0.04 -1.01 -0.57 -0.71 -0.3 -1.01 1.83 0.59
1.04 -1.43 0.38 0.65 -6.64 -0.42 0.24 0.46 0.96 0.24
0.7 1.21 0.6 0.12 0.77 -0.03 0.53 0.31 0.46 0.51
-0.45 0.23 0.32 -0.34 -0.1 0.1 -0.45 0.74 -0.06 0.21
0.29 0.45 0.68 0.29 0.45
Y7C -0.22 -0.12 -0.29 -0.51 -0.81 -0.47 0.28 -0.1 0.15
0.38 0.18 -0.27 0.12 -0.15 0.43 0.25 0.19 0.33 0.67
0.86 -0.56 -0.29 -0.36 -0.42 0.08 0.04 -0.04 0.15 0.38
-0.07 -0.1 -0.2 -0.03 -0.29 0.06 0.65 0.58 0.86 2.05
0.3 0.33 -0.29 -0.23 -0.15 -0.32 0.08 0.34 0.15 0
-0.01 0.28 0.36 0.25 0.46 0.4 0.7 0.49 0.97 1.04
0.36 -0.47 -0.29 0.77 0.57 0.45 0.77 0.24 -0.23 0.12
0.49 0.62 0.49 0.84 0.89 1.08 0.87 -0.18 -0.43
-0.39 -0.18 -0.02 0.01 0.2 -0.2 -0.03 0.01 0.25 0.1
-0.07 -1.43 -0.2 -0.4 0.32 0.72 -0.42 -0.3 -0.38
-0.22 -0.81 -1.15 -1.6 -1.89 -2.06 -2.4 0.08 0.34 0.1
-0.15 -0.06 -0.17 -0.47 -0.4 0.15 -1.22 -1.43 -1.03
-1.03 -1.64 -1.84 -2.64 -2 0.05 0.4 0.88 -1.54 -1.21
-1.46 -1.92 -1.52 -1.92 -1.7 -1.94 -1.86 -0.1 -0.02
-0.22 -0.34 -0.48 0.28 0 0.14 0.4 -0.29 -0.27 -0.3
-0.67 -0.09 0.23 0.33 0.23 0.1 0.38 -0.51 0.23 -0.73
0.22 -0.47 0.24 0.68 0.53 0.23 -0.1 0.11 -0.18 0.16
0.68 0.55 0.28 -0.03 0.03 0.08 0.12
缺少一个值，我想将其加载为我使用的矩阵:
There is a missing value, I wanted to load it as matrix I used :
data = np.genfromtxt("This_data.txt", delimiter='\t', missing_values=np.nan)
当我打印数据时，我得到:
When I print data I get :
Traceback (most recent call last):
File "matrix.py", line 8, in <module>
data = np.genfromtxt("This_data.txt", delimiter='\t', missing_values=np.nan ,usecols=np.arange(0,174))
File "/home/anaconda2/lib/python2.7/numpy/lib/npyio.py", line 1769, in genfromtxt
raise ValueError(errmsg)
ValueError: Some errors were detected !
Line #25 (got 172 columns instead of 174)
我以前放过:
data = np.genfromtxt("This_data.txt", delimiter='\t', missing_values=np.nan ,usecols=np.arange(0,174))
但是我有同样的错误.有什么建议吗?
But I have same errors. Any suggestion?
推荐答案
文件的简短示例字节串替代:
A short sample bytestring substitute for a file:
In [168]: txt = b"""Y7C\t-0.22\t-0.12\t-0.29\t-0.51\t-0.81
...: Y7C\t-0.22\t-0.12\t-0.29\t-0.51\t-0.81
...: Y7C\t-0.22\t-0.12\t-0.29\t-0.51\t-0.81
...: """
使用正确的定界符的最小负载.请注意，第一列是nan，因为它无法将字符串转换为浮点数.
Minimal load with correct delimiter. Note the first column is nan, because it can't convert the strings to float.
In [169]: np.genfromtxt(txt.splitlines(),delimiter='\t')
Out[169]:
array([[ nan, -0.22, -0.12, -0.29, -0.51, -0.81],
[ nan, -0.22, -0.12, -0.29, -0.51, -0.81],
[ nan, -0.22, -0.12, -0.29, -0.51, -0.81]])
with dtype = None会自动设置每列dtype，从而创建结构化数组:
with dtype=None it sets each column dtype automatically, creating a structured array:
In [170]: np.genfromtxt(txt.splitlines(),delimiter='\t',dtype=None)
Out[170]:
array([(b'Y7C', -0.22, -0.12, -0.29, -0.51, -0.81),
(b'Y7C', -0.22, -0.12, -0.29, -0.51, -0.81),
(b'Y7C', -0.22, -0.12, -0.29, -0.51, -0.81)],
dtype=[('f0', 'S3'), ('f1', '<f8'), ('f2', '<f8'), ('f3', '<f8'), ('f4', '<f8'), ('f5', '<f8')])
说明要使用的列，跳过第一列:
Spell out the columns to use, skipping the first:
In [172]: np.genfromtxt(txt.splitlines(),delimiter='\t',usecols=np.arange(1,6))
Out[172]:
array([[-0.22, -0.12, -0.29, -0.51, -0.81],
[-0.22, -0.12, -0.29, -0.51, -0.81],
[-0.22, -0.12, -0.29, -0.51, -0.81]])
但是，如果我要求找到更多列，则会收到错误消息，例如您的错误消息:
But if I ask for more columns that it finds I get an error, like yours:
In [173]: np.genfromtxt(txt.splitlines(),delimiter='\t',usecols=np.arange(1,7))
---------------------------------------------------------------------------
....
ValueError: Some errors were detected !
Line #1 (got 6 columns instead of 6)
Line #2 (got 6 columns instead of 6)
Line #3 (got 6 columns instead of 6)
您的missing_values参数没有帮助；那是错误的用途
Your missing_values parameters doesn't help; that's the wrong use for that
这是missing_values的正确用法-检测字符串值并将其替换为有效的浮点值:
This is the correct use of missing_values - to detect the string value and replace it with a valid float value:
In [177]: np.genfromtxt(txt.splitlines(),delimiter='\t',missing_values='Y7C',filling_val
...: ues=0)
Out[177]:
array([[ 0. , -0.22, -0.12, -0.29, -0.51, -0.81],
[ 0. , -0.22, -0.12, -0.29, -0.51, -0.81],
[ 0. , -0.22, -0.12, -0.29, -0.51, -0.81]])
如果文件中有足够的定界符，则可以将其视为缺失值
If the file has sufficient delimiters, it can treat those as missing values
In [178]: txt = b"""Y7C\t-0.22\t-0.12\t-0.29\t-0.51\t-0.81\t\t
...: Y7C\t-0.22\t-0.12\t-0.29\t-0.51\t-0.81\t\t
...: Y7C\t-0.22\t-0.12\t-0.29\t-0.51\t-0.81\t\t
...: """
In [179]: np.genfromtxt(txt.splitlines(),delimiter='\t')
Out[179]:
array([[ nan, -0.22, -0.12, -0.29, -0.51, -0.81, nan, nan],
[ nan, -0.22, -0.12, -0.29, -0.51, -0.81, nan, nan],
[ nan, -0.22, -0.12, -0.29, -0.51, -0.81, nan, nan]])
In [180]: np.genfromtxt(txt.splitlines(),delimiter='\t',filling_values=0)
Out[180]:
array([[ 0. , -0.22, -0.12, -0.29, -0.51, -0.81, 0. , 0. ],
[ 0. , -0.22, -0.12, -0.29, -0.51, -0.81, 0. , 0. ],
[ 0. , -0.22, -0.12, -0.29, -0.51, -0.81, 0. , 0. ]])
我相信pandas csv阅读器可以更好地处理粗糙"列和缺少值.
I believe the pandas csv reader can handle 'ragged' columns and missing values better.
这篇关于将我的数据加载到numpy genfromtxt中会出错的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
查看全文
