简单展示如何利用python中的pandas库创建、读取、修改CSV数据文件
1 写入CSV文件
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
|
import numpy as np import pandas as pd # -----create an initial numpy array----- # data = np.zeros(( 8 , 4 )) # print(data.dtype) # print(type(data)) # print(data.shape) # -----from array to dataframe----- # df = pd.DataFrame(data) # print(type(df)) # print(df.shape) # print(df) # -----edit columns and index----- # df.columns = [ 'A' , 'B' , 'C' , 'D' ] df.index = range (data.shape[ 0 ]) df.info() # -----save dataframe as csv----- # csv_save_path = './data_.csv' df.to_csv(csv_save_path, sep = ',' , index = False , header = True ) # -----check----- # df = pd.read_csv(csv_save_path) print ( '-' * 25 ) print (df) |
输出如下:
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 8 entries, 0 to 7
Data columns (total 4 columns):
A 8 non-null float64
B 8 non-null float64
C 8 non-null float64
D 8 non-null float64
dtypes: float64(4)
memory usage: 336.0 bytes
-------------------------
A B C D
0 0.0 0.0 0.0 0.0
1 0.0 0.0 0.0 0.0
2 0.0 0.0 0.0 0.0
3 0.0 0.0 0.0 0.0
4 0.0 0.0 0.0 0.0
5 0.0 0.0 0.0 0.0
6 0.0 0.0 0.0 0.0
7 0.0 0.0 0.0 0.0
2 读取CSV文件
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
|
import pandas as pd import numpy as np csv_path = './data_.csv' # -----saved as dataframe----- # data = pd.read_csv(csv_path) # ---if index is given in csv file, you can use next line of code to replace the previous one--- # data = pd.read_csv(csv_path, index_col=0) print ( type (data)) print (data) print (data.shape) # -----saved as array----- # data_ = np.array(data) # data_ = data.values print ( type (data_)) print (data_) print (data_.shape) |
输出如下:
<class 'pandas.core.frame.DataFrame'>
A B C D
0 0.0 0.0 0.0 0.0
1 0.0 0.0 0.0 0.0
2 0.0 0.0 0.0 0.0
3 0.0 0.0 0.0 0.0
4 0.0 0.0 0.0 0.0
5 0.0 0.0 0.0 0.0
6 0.0 0.0 0.0 0.0
7 0.0 0.0 0.0 0.0
(8, 4)
<class 'numpy.ndarray'>
[[0. 0. 0. 0.]
[0. 0. 0. 0.]
[0. 0. 0. 0.]
[0. 0. 0. 0.]
[0. 0. 0. 0.]
[0. 0. 0. 0.]
[0. 0. 0. 0.]
[0. 0. 0. 0.]]
(8, 4)
3 修改CSV文件
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
|
import pandas as pd import numpy as np csv_path = './data_.csv' df = pd.read_csv(csv_path) # -----edit columns and index----- # df.columns = [ 'X1' , 'X2' , 'X3' , 'Y' ] df.index = range (df.shape[ 0 ]) # df.index = [i+1 for i in range(df.shape[0])] # -----columns operations----- # Y = df[ 'Y' ] df[ 'X4' ] = [ 4 for i in range (df.shape[ 0 ])] # add df[ 'X5' ] = [ 5 for i in range (df.shape[ 0 ])] # print(df) df.drop(columns = 'Y' , inplace = True ) # delete # print(df) df[ 'X1' ] = [i + 1 for i in range (df.shape[ 0 ])] # correct --(1) # df.iloc[:df.shape[0], 0] = [i+1 for i in range(df.shape[0])] # correct --(2) # print(df) df[ 'Y' ] = Y_temp # print(df) # -----rows operations----- # df.loc[df.shape[ 0 ]] = [i + 2 for i in range ( 6 )] # add # print(df) df.drop(index = 4 , inplace = True ) # delete # print(df) df.loc[ 0 ] = [i + 1 for i in range (df.shape[ 1 ])] # correct # print(df) # -----edit index again after rows operations!!!----- # df.index = range (df.shape[ 0 ]) # -----save dataframe as csv----- # csv_save_path = './data_copy.csv' df.to_csv(csv_save_path, sep = ',' , index = False , header = True ) print (df) |
输出如下:
X1 X2 X3 X4 X5 Y
0 1.0 2.0 3.0 4 5 6.0
1 2.0 0.0 0.0 4 5 0.0
2 3.0 0.0 0.0 4 5 0.0
3 4.0 0.0 0.0 4 5 0.0
4 6.0 0.0 0.0 4 5 0.0
5 7.0 0.0 0.0 4 5 0.0
6 8.0 0.0 0.0 4 5 0.0
7 2.0 3.0 4.0 5 6 7.0
参考资料
csv文件的读写与修改还可以通过python的csv库来实现
python中csv文件的创建、读取、修改等操作总结
总结
到此这篇关于如何利用python创建、读取和修改CSV数据文件的文章就介绍到这了,更多相关python创建读取修改CSV内容请搜索服务器之家以前的文章或继续浏览下面的相关文章希望大家以后多多支持服务器之家!
原文链接:https://blog.csdn.net/qq_41866202/article/details/121535663