for中的范围是 [a, b)
for i in range(1,10):
print(i)
输出:
1
2
3
4
5
6
7
8
9
定义空的数组(numpy中的array; list)
X = np.empty(0,dtype=int)
X
output:array([], dtype=int32)
list = []
往数组里添加元素:
list:append 等等;
array:stack , vstack 等等;
去掉一行或者一列:
写CSV文件
import pandas as pd
#任意的多组列表
a = [1,2,3]
b = [4,5,6]
#字典中的key值即为csv中列名
dataframe = pd.DataFrame({'a_name':a,'b_name':b})
#将DataFrame存储为csv,index表示是否显示行名,default=True
dataframe.to_csv("test.csv",index=False,sep='')
numpy读写文件
import numpy
my_matrix = numpy.loadtxt(open("c:\\1.csv","rb"),delimiter=",",skiprows=0)
numpy.savetxt(fname, X, fmt='%.18e', delimiter=' ', newline='\n', header='', footer='', comments='# ')[source]
Save an array to a text file.
Parameters:
fname : filename or file handle
If the filename ends in .gz, the file is automatically saved in compressed gzip format. loadtxt understands gzipped files transparently.
X : array_like
Data to be saved to a text file.
fmt : str or sequence of strs, optional
A single format (%10.5f), a sequence of formats, or a multi-format string, e.g. ‘Iteration %d – %10.5f’, in which case delimiter is ignored. For complex X, the legal options for fmt are:
a single specifier, fmt=’%.4e’, resulting in numbers formatted
like ‘ (%s+%sj)’ % (fmt, fmt)
a full string specifying every real and imaginary part, e.g.
‘ %.4e %+.4j %.4e %+.4j %.4e %+.4j’ for 3 columns
a list of specifiers, one per column - in this case, the real
and imaginary part must have separate specifiers, e.g. [‘%.3e + %.3ej’, ‘(%.15e%+.15ej)’] for 2 columns
delimiter : str, optional
String or character separating columns.
newline : str, optional
String or character separating lines.
New in version 1.5.0.
header : str, optional
String that will be written at the beginning of the file.
New in version 1.7.0.
footer : str, optional
String that will be written at the end of the file.
New in version 1.7.0.
comments : str, optional
String that will be prepended to the header and footer strings, to mark them as comments. Default: ‘# ‘, as expected by e.g. numpy.loadtxt.
New in version 1.7.0.
# 画图看看数据变动
import matplotlib.pyplot as plt
%matplotlib inline
x = pro_train[:,0]
y = pro_train[:,2]
plt.plot(x,y)
将列表存储为csv文件
import pandas as pd
list_test = [ [1,2,3],[4,5,6],[7,8,9] ]
name = ['id','uid','time']
test = pd.DataFrame(columns=name,data=list_test)
test.to_csv('C:/Users/Admin/Desktop/test.csv')
[output]
id uid time
0 1 2 3
1 4 5 6
2 7 8 9
test2 = pd.DataFrame(data=list_test)
test2.to_csv('C:/Users/Admin/Desktop/test2.csv')
[output]
0 1 2
0 1 2 3
1 4 5 6
2 7 8 9
output = pd.DataFrame( data={"id":test["id"], "sentiment":xgbc_y_predict} )
output.to_csv("result/BagOfCentroids_classify_by_XGBoost.csv", index=False, quoting=3 )
numpy.argmax()
>>>a = np.array([[0, 1, 2],\
[3, 4, 5],\
[8, 3, 4]
])
>>>np.argmax(a, axis=1)
array([2, 2, 0], dtype=int64)
>>>np.argmax(a, axis=0)
array([2, 1, 1], dtype=int64)
arr
输出:
array([[ 0, 1, 2, 3, 4],
[ 5, 6, 7, 8, 9],
[10, 11, 12, 13, 14]])
arr.T
输出:
array([[ 0, 5, 10],
[ 1, 6, 11],
[ 2, 7, 12],
[ 3, 8, 13],
[ 4, 9, 14]])