In [1]:
import pandas as pd
In [2]:
%%time
df = pd.read_csv('sample_data.csv')
CPU times: user 22.1 s, sys: 9.06 s, total: 31.2 s
Wall time: 35 s
In [3]:
%%time
df = pd.read_parquet('sample_data_parquet')
CPU times: user 7.31 s, sys: 9.37 s, total: 16.7 s
Wall time: 12.9 s
In [4]:
df.head()
Out[4]:
alphabet
useless_letter
Z
Y
X
W
V
U
T
S
...
J
I
H
G
F
E
D
C
B
A
index
0
ABCDEFGHIJKLMNOPQRSTUVWXYZ
U
1
66
69
4
70
64
83
55
...
36
28
33
57
23
86
48
30
91
84
1
ABCDEFGHIJKLMNOPQRSTUVWXYZ
L
25
26
36
34
0
75
60
73
...
42
91
8
24
64
13
43
47
94
11
2
ABCDEFGHIJKLMNOPQRSTUVWXYZ
N
40
67
36
54
46
5
57
50
...
82
76
24
60
3
55
64
28
26
89
3
ABCDEFGHIJKLMNOPQRSTUVWXYZ
C
91
98
8
36
17
3
29
90
...
88
24
7
51
52
87
1
6
19
48
4
ABCDEFGHIJKLMNOPQRSTUVWXYZ
J
87
68
73
78
39
67
57
24
...
9
14
0
2
51
18
95
71
28
13
5 rows × 28 columns
In [5]:
type(df)
Out[5]:
pandas.core.frame.DataFrame
In [6]:
df
Out[6]:
alphabet
useless_letter
Z
Y
X
W
V
U
T
S
...
J
I
H
G
F
E
D
C
B
A
index
0
ABCDEFGHIJKLMNOPQRSTUVWXYZ
U
1
66
69
4
70
64
83
55
...
36
28
33
57
23
86
48
30
91
84
1
ABCDEFGHIJKLMNOPQRSTUVWXYZ
L
25
26
36
34
0
75
60
73
...
42
91
8
24
64
13
43
47
94
11
2
ABCDEFGHIJKLMNOPQRSTUVWXYZ
N
40
67
36
54
46
5
57
50
...
82
76
24
60
3
55
64
28
26
89
3
ABCDEFGHIJKLMNOPQRSTUVWXYZ
C
91
98
8
36
17
3
29
90
...
88
24
7
51
52
87
1
6
19
48
4
ABCDEFGHIJKLMNOPQRSTUVWXYZ
J
87
68
73
78
39
67
57
24
...
9
14
0
2
51
18
95
71
28
13
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
8999995
ABCDEFGHIJKLMNOPQRSTUVWXYZ
F
14
6
87
54
44
93
39
5
...
25
31
72
35
31
20
38
19
92
55
8999996
ABCDEFGHIJKLMNOPQRSTUVWXYZ
F
3
86
73
6
47
72
31
75
...
55
60
72
60
85
58
34
79
40
22
8999997
ABCDEFGHIJKLMNOPQRSTUVWXYZ
U
6
88
22
17
0
18
47
16
...
41
68
56
17
15
7
29
14
86
9
8999998
ABCDEFGHIJKLMNOPQRSTUVWXYZ
V
14
97
6
5
4
55
56
29
...
71
86
38
92
4
20
0
58
96
2
8999999
ABCDEFGHIJKLMNOPQRSTUVWXYZ
N
5
76
72
99
50
42
68
43
...
30
63
68
65
84
46
46
41
52
15
9000000 rows × 28 columns
In [7]:
%%time
df['mean'] = df.mean(axis=1)
CPU times: user 36.7 s, sys: 45.7 s, total: 1min 22s
Wall time: 1min 56s
In [ ]:
Content source: CLEpy/CLEpy-MotM
Similar notebooks: