data2 = pd.DataFrame(data1['kwh'])
data2
kwh
date
2012-04-12 14:56:50 1.256400
2012-04-12 15:11:55 1.430750
2012-04-12 15:27:01 1.369910
2012-04-12 15:42:06 1.359350
2012-04-12 15:57:10 1.305680
2012-04-12 16:12:10 1.287750
2012-04-12 16:27:14 1.245970
2012-04-12 16:42:19 1.282280
2012-04-12 16:57:24 1.365710
2012-04-12 17:12:28 1.320130
2012-04-12 17:27:33 1.354890
2012-04-12 17:42:37 1.343680
2012-04-12 17:57:41 1.314220
2012-04-12 18:12:44 1.311970
2012-04-12 18:27:46 1.338980
2012-04-12 18:42:51 1.357370
2012-04-12 18:57:54 1.328700
2012-04-12 19:12:58 1.308200
2012-04-12 19:28:01 1.341770
2012-04-12 19:43:04 1.278350
2012-04-12 19:58:07 1.253170
2012-04-12 20:13:10 1.420670
2012-04-12 20:28:15 1.292740
2012-04-12 20:43:15 1.322840
2012-04-12 20:58:18 1.247410
2012-04-12 21:13:20 0.568352
2012-04-12 21:28:22 0.317865
2012-04-12 21:43:24 0.233603
2012-04-12 21:58:27 0.229524
2012-04-12 22:13:29 0.236929
2012-04-12 22:28:34 0.233806
2012-04-12 22:43:38 0.235618
2012-04-12 22:58:43 0.229858
2012-04-12 23:13:43 0.235132
2012-04-12 23:28:46 0.231863
2012-04-12 23:43:55 0.237794
2012-04-12 23:59:00 0.229634
2012-04-13 00:14:02 0.234484
2012-04-13 00:29:05 0.234189
2012-04-13 00:44:09 0.237213
2012-04-13 00:59:09 0.230483
2012-04-13 01:14:10 0.234982
2012-04-13 01:29:11 0.237121
2012-04-13 01:44:16 0.230910
2012-04-13 01:59:22 0.238406
2012-04-13 02:14:21 0.250530
2012-04-13 02:29:24 0.283575
2012-04-13 02:44:24 0.302299
2012-04-13 02:59:25 0.322093
2012-04-13 03:14:30 0.327600
2012-04-13 03:29:31 0.324368
2012-04-13 03:44:31 0.301869
2012-04-13 03:59:42 0.322019
2012-04-13 04:14:43 0.325328
2012-04-13 04:29:43 0.306727
2012-04-13 04:44:46 0.299012
2012-04-13 04:59:47 0.303288
2012-04-13 05:14:48 0.326205
2012-04-13 05:29:49 0.344230
2012-04-13 05:44:50 0.353484
...
65701 rows × 1 columns
我想使用线性回归和 sklearn 进行简单的预测。如何将数据拆分为训练/测试集，以及如何将数据目标拆分为训练/测试集。（我希望 x 值是时间和 y 值 kwh）
import matplotlib.pyplot as plt
import numpy as np
from sklearn import linear_model
from sklearn.cross_validation import train_test_split
#create x data
data2['xraw'] = data2.index
x = data2['xraw'].astype(np.int64) // 10**9
y = data2['kwh']
y = y.reshape((y.shape[0],1))
#train-test split
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.33, random_state=42)
# Create linear regression object
regr = linear_model.LinearRegression()
# Train the model using the training sets
regr.fit(x_train, y_train)
# The coefficients
print('Coefficients: n', regr.coef_)
# The mean square error
print("Residual sum of squares: %.2f" % np.mean((regr.predict(x_test) - y_test) ** 2))
# Explained variance score: 1 is perfect prediction
print('Variance score: %.2f' % regr.score(x_test, y_test))
# Plot outputs
plt.scatter(x_test, y_test, color='black')
plt.plot(x_test, regr.predict(x_test), color='blue', linewidth=3)
plt.xticks(())
plt.yticks(())
plt.show()