[PANDAS1] - Quelques exemples avec Pandas

pandas is another essential tool for the Scientific Python.

Objectives :

• Understand how to slice a dataset

Step 1 - A little cooking with datasets

import pandas as pd
import numpy  as np

# Get some data
a = np.arange(50).reshape(10,5)
print('Starting data: \n',a)

Starting data: 
 [[ 0  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 42 43 44]
 [45 46 47 48 49]]

# Create a DataFrame
df_all = pd.DataFrame(a, columns=['A','B','C','D','E'])
print('\nDataFrame :')
display(df_all)

DataFrame :

	A	B	C	D	E
0	0	1	2	3	4
1	5	6	7	8	9
2	10	11	12	13	14
3	15	16	17	18	19
4	20	21	22	23	24
5	25	26	27	28	29
6	30	31	32	33	34
7	35	36	37	38	39
8	40	41	42	43	44
9	45	46	47	48	49

# Shuffle data
df_all = df_all.sample(frac=1, axis=0)
print('\nDataFrame randomly shuffled :')
display(df_all)

DataFrame randomly shuffled :

	A	B	C	D	E
5	25	26	27	28	29
7	35	36	37	38	39
4	20	21	22	23	24
9	45	46	47	48	49
1	5	6	7	8	9
0	0	1	2	3	4
2	10	11	12	13	14
3	15	16	17	18	19
8	40	41	42	43	44
6	30	31	32	33	34

# Get a train part
df_train = df_all.sample(frac=0.8, axis=0)
print('\nTrain set (80%) :')
display(df_train)

Train set (80%) :

	A	B	C	D	E
3	15	16	17	18	19
1	5	6	7	8	9
7	35	36	37	38	39
2	10	11	12	13	14
6	30	31	32	33	34
8	40	41	42	43	44
5	25	26	27	28	29
4	20	21	22	23	24

# Get test set as all - train
df_test = df_all.drop(df_train.index)
print('\nTest set (all - train) :')
display(df_test)

Test set (all - train) :

	A	B	C	D	E
9	45	46	47	48	49
0	0	1	2	3	4

x_train = df_train.drop('E',  axis=1)
y_train = df_train['E']
x_test  = df_test.drop('E',   axis=1)
y_test  = df_test['E']
display(x_train)
display(y_train)

	A	B	C	D
3	15	16	17	18
1	5	6	7	8
7	35	36	37	38
2	10	11	12	13
6	30	31	32	33
8	40	41	42	43
5	25	26	27	28
4	20	21	22	23

3    19
1     9
7    39
2    14
6    34
8    44
5    29
4    24
Name: E, dtype: int64

---