这里有一个快速而肮脏的方法来达到你的目的:
我的_数据集.py在import numpy as np
import csv
from sklearn.datasets.base import Bunch
def load_my_fancy_dataset():
with open('my_fancy_dataset.csv') as csv_file:
data_file = csv.reader(csv_file)
temp = next(data_file)
n_samples = int(temp[0])
n_features = int(temp[1])
data = np.empty((n_samples, n_features))
target = np.empty((n_samples,), dtype=np.int)
for i, sample in enumerate(data_file):
data[i] = np.asarray(sample[:-1], dtype=np.float64)
target[i] = np.asarray(sample[-1], dtype=np.int)
return Bunch(data=data, target=target)
我的幻想_数据集.csv在
^{pr2}$
演示In [12]: import my_datasets
In [13]: mfd = my_datasets.load_my_fancy_dataset()
In [14]: X = mfd.data
In [15]: y = mfd.target
In [16]: X
Out[16]:
array([[ 5.90000000e+00, 1.20300000e+03, 6.90000000e-01],
[ 7.20000000e+00, 9.02000000e+02, 5.20000000e-01],
[ 6.30000000e+00, 1.43000000e+02, 4.40000000e-01],
[ -2.60000000e+00, 2.91000000e+02, 1.50000000e-01],
[ 1.80000000e+00, 4.86000000e+02, 3.70000000e-01]])
In [17]: y
Out[17]: array([2, 0, 1, 1, 0])