小编Sac*_*mar的帖子

我正在尝试将SGDRegressor放入我的数据中,然后检查准确性.拟合工作正常,但是预测与原始目标数据的数据类型(？)不同,我得到了错误

ValueError: Can't handle mix of multiclass and continuous

当调用print "Accuracy:", ms.accuracy_score(y_test,predictions).

数据看起来像这样(只有20万+行):

Product_id/Date/product_group1/Price/Net price/Purchase price/Hour/Quantity/product_group2
0   107 12/31/2012  10  300 236 220 10  1   108

代码如下:

from sklearn.preprocessing import StandardScaler
import numpy as np
from sklearn.linear_model import SGDRegressor
import numpy as np
from sklearn import metrics as ms

msk = np.random.rand(len(beers)) < 0.8

train = beers[msk]
test = beers[~msk]

X = train [['Price', 'Net price', 'Purchase price','Hour','Product_id','product_group2']]
y = train[['Quantity']]
y = y.as_matrix().ravel()

X_test = test [['Price', …

如果我打开同一个文件两次,它会给出错误,还是会创建两个不同的文件描述符？例如

a = open("teste.txt", O_RDONLY);
b = open("teste.txt", O_RDONLY);

我正在尝试创建一个数据集来检查我的 Logistic 回归算法，但我无法从字典中创建一个 Pandas DataFrame。我收到“数据必须是一维的”异常。

    x1 = np.random.random(size=(10,1))*2
    x2 = np.random.random(size=(10,1))*2

    x3 = np.random.random(size=(10,1))*2 + 2
    x4 = np.random.random(size=(10,1))*2 + 2

    y0 = np.zeros(shape=(10,1))
    y1 = np.ones(shape=(10,1))

    plt.scatter(x1,x2, color='g', marker='o')
    plt.scatter(x3,x4, color='r', marker='o')

    dict_data = { 'X1':np.concatenate((x1,x3)), 
                  'X2':np.concatenate((x2,x4)),
                   'Y':np.concatenate((y0,y1))}

    data = pd.DataFrame(dict_data, index=np.arange(20))

我得到这个作为输出，错误数据必须是 1 维。

    --------------------------------------------------------------------------
Exception                                 Traceback (most recent call last)
<ipython-input-49-fe81f079ebc6> in <module>
     13 dict_data = { 'X1':np.concatenate((x1,x3)), 'X2':np.concatenate((x2,x4)),'Y':np.concatenate((y0,y1))}
     14 #print(dict_data.shape)
---> 15 data = pd.DataFrame(dict_data, index=np.arange(20).reshape(20))

~/anaconda3/lib/python3.6/site-packages/pandas/core/frame.py in __init__(self, data, index, columns, dtype, copy)
    328                                  dtype=dtype, …