代码之家 › 专栏 › 技术社区 › blue-sky

动态熊猫数据帧生成

pandas python

blue-sky · 技术社区 · 7 年前

下面是我为生成包含4列的数据帧而编写的代码

num_rows = 10

df = pd.DataFrame({ 'id_col' : [x+1 for x in range(num_rows)] , 'c1': [randint(0, 9) for x in range(num_rows)], 'c2': [randint(0, 9) for x in range(num_rows)], 'c3': [randint(0, 9) for x in range(num_rows)] })
df

print(df) 渲染:

id_col  c1  c2  c3
0       1   3   1   5
1       2   0   2   4
2       3   1   2   5
3       4   0   5   6
4       5   0   0   1
5       6   6   5   8
6       7   1   6   8
7       8   5   8   8
8       9   1   5   2
9      10   2   9   2

我已经设置了要通过 num_rows 变量。

如何动态生成1000个列,其中每个列前面都有“c”。所以列 c1,c2,c3....c1000 是否在每列包含10行的位置生成?

3 回复 | 直到 7 年前

jezrael 7 年前

DataFrame numpy.random.randint DataFrame.insert

np.random.seed(458)

N = 15
M = 10
df = pd.DataFrame(np.random.randint(10, size=(M, N)))
df.columns = ['c{}'.format(x+1) for x in df.columns]
df.insert(0, 'idcol', np.arange(M))

print (df)
   idcol  c1  c2  c3  c4  c5  c6  c7  c8  c9  c10  c11  c12  c13  c14  c15
0      0   8   2   1   6   2   1   0   9   7    8    0    5    5    6    0
1      1   0   2   5   0   0   2   5   2   9    2    1    0    0    5    0
2      2   5   1   3   5   4   5   3   0   2    1    7    8    9    5    4
3      3   8   7   7   0   1   3   6   7   5    8    8    9    8    5    5
4      4   2   8   1   7   3   7   4   6   0    7    0    9    4    0    4
5      5   9   2   1   6   1   9   5   6   7    4    6    1    7    3    7
6      6   1   9   3   9   7   7   2   7   9    8    2    7    2    5    5
7      7   7   6   6   6   4   2   9   0   6    5    7    0    0    4    9
8      8   6   4   2   1   3   1   7   0   4    3    0    5    4    7    7
9      9   1   3   5   7   2   2   1   5   6    1    9    5    9    6    3

numpy.hstack id

np.random.seed(458)

arr = np.hstack([np.arange(M)[:, None], np.random.randint(10, size=(M, N))])
df = pd.DataFrame(arr)
df.columns = ['idcol'] + ['c{}'.format(x) for x in df.columns[1:]]
print (df)
   idcol  c1  c2  c3  c4  c5  c6  c7  c8  c9  c10  c11  c12  c13  c14  c15
0      0   8   2   1   6   2   1   0   9   7    8    0    5    5    6    0
1      1   0   2   5   0   0   2   5   2   9    2    1    0    0    5    0
2      2   5   1   3   5   4   5   3   0   2    1    7    8    9    5    4
3      3   8   7   7   0   1   3   6   7   5    8    8    9    8    5    5
4      4   2   8   1   7   3   7   4   6   0    7    0    9    4    0    4
5      5   9   2   1   6   1   9   5   6   7    4    6    1    7    3    7
6      6   1   9   3   9   7   7   2   7   9    8    2    7    2    5    5
7      7   7   6   6   6   4   2   9   0   6    5    7    0    0    4    9
8      8   6   4   2   1   3   1   7   0   4    3    0    5    4    7    7
9      9   1   3   5   7   2   2   1   5   6    1    9    5    9    6    3

rafaelc 7 年前

str.format

num_rows = 10
num_cols = 15

df = pd.DataFrame({ 'c{}'.format(n):  [randint(0, 9) for x in range(num_rows)] for n in range(num_cols)}, 
                  index=[x+1 for x in range(num_rows)] , )
    c0  c1  c2  c3  c4  c5  c6  c7  c8  c9
1   1   6   2   1   3   1   8   8   2   0
2   2   6   2   2   5   7   4   1   6   2
3   1   2   6   8   7   5   5   7   2   2
4   5   5   3   3   4   7   8   1   8   6
5   7   2   8   6   5   6   2   0   0   4
6   8   2   4   4   6   3   0   1   0   2
7   5   6   8   5   1   0   4   8   4   7
8   1   5   4   5   2   4   4   6   2   7
9   5   7   7   8   5   0   2   7   3   2
10  4   8   5   3   3   7   5   1   5   1

jpp 7 年前

np.random.randint pd.DataFrame.assign np.arange

import pandas as pd, numpy as np

rows = 10
cols = 5
minval, maxval = 0, 10

df = pd.DataFrame(np.random.randint(minval, maxval, (rows, cols)),
                  columns=[f'c{i}' for i in range(1, cols+1)])\
       .assign(id_col=np.arange(1, num_rows+1))

print(df)

   c1  c2  c3  c4  c5  id_col
0   8   4   6   0   8       1
1   8   3   5   9   0       2
2   1   3   3   6   2       3
3   6   4   1   1   7       4
4   3   7   0   9   5       5
5   4   6   8   8   6       6
6   0   3   9   9   7       7
7   0   6   1   2   4       8
8   3   7   1   2   0       9
9   6   6   0   5   8      10