我正在使用来自sickit learn 的岭线性回归。在文档中，他们声明 alpha 参数必须很小。
但是，我在 6060 处获得了最好的模型性能。我做错了吗？
以下是文档中的描述：
alpha : {float, array-like} shape = [n_targets] Small positive values
of alpha improve the conditioning of the problem and reduce the
variance of the estimates.
这是我的代码：
import pandas as pd
import numpy as np
import custom_metrics as cmetric
from sklearn import preprocessing
from sklearn import cross_validation
from sklearn import linear_model
# Read data files:
df_train = pd.read_csv(path + "/input/train.csv")
df_test = pd.read_csv(path + "/input/test.csv")
#print df.shape
#(50999, 34)
#convert categorical features into integers
feature_cols_obj = [col for col in df_train.columns if df_train[col].dtypes == 'object']
le = preprocessing.LabelEncoder()
for col in feature_cols_obj:
df_train[col] = le.fit_transform(df_train[col])
df_test[col] = le.transform(df_test[col])
#Scale the data so that each feature has zero mean and unit std
feature_cols = [col for col in df_train.columns if col not in ['Hazard','Id']]
scaler = preprocessing.StandardScaler().fit(df_train[feature_cols])
df_train[feature_cols] = scaler.transform(df_train[feature_cols])
df_test[feature_cols] = scaler.transform(df_test[feature_cols])
#polynomial features/interactions
X_train = df_train[feature_cols]
X_test = df_test[feature_cols]
y = df_train['Hazard']
test_ids = df_test['Id']
poly = preprocessing.PolynomialFeatures(2)
X_train = poly.fit_transform(X_train)
X_test = poly.fit_transform(X_test)
#do grid search to find best value for alpha
#alphas = np.arange(-10,3,1)
#clf = linear_model.RidgeCV(10**alphas)
alphas = np.arange(100,10000,10)
clf = linear_model.RidgeCV(alphas)
clf.fit(X_train, y)
print clf.alpha_
#clf.alpha=6060
cv = cross_validation.KFold(df_train.shape[0], n_folds=10)
mse = []
mse_train = []
fold_count = 0
for train, test in cv:
print("Processing fold %s" % fold_count)
train_fold = df_train.ix[train]
test_fold = df_train.ix[test]
# Get training examples
X_train = train_fold[feature_cols]
y = train_fold['Hazard']
X_test = test_fold[feature_cols]
#interactions
poly = preprocessing.PolynomialFeatures(2)
X_train = poly.fit_transform(X_train)
X_test = poly.fit_transform(X_test)
# Fit Ridge linear regression
cfr = linear_model.Ridge (alpha = 6060)
cfr.fit(X_train, y)
# Check error on test set
pred = cfr.predict(X_test)
mse.append(cmetric.normalized_gini(test_fold.Hazard, pred))
# Check error on training set (Resubsitution error)
mse_train.append(cmetric.normalized_gini(y, cfr.predict(X_train)))
# Done with the fold
fold_count += 1
#print model coeff
print cfr.coef_
print pd.DataFrame(mse).mean()
#0.311794
print pd.DataFrame(mse_train).mean()
#.344775
这是我模型的参数
[ 0.00000000e+00 5.01056266e-02 3.38358145e-01 1.30415614e-01
1.96089173e-01 1.25423106e-01 -1.72319456e-02 1.02133523e-01
2.81574892e-01 8.95633136e-02 -5.88384438e-03 1.47409573e-01
1.33623390e-01 -1.23180872e-02 -1.46668969e-01 -4.92436419e-02
1.99181255e-01 -4.04964277e-03 -1.53413757e-01 -1.44825780e-01
-3.91212516e-03 3.31216145e-03 -6.26732347e-02 2.88351008e-02
-2.06225972e-03 -5.62389494e-02 -1.36303417e-01 -9.71481638e-03
-2.50177992e-02 -5.66878847e-03 5.27927411e-03 8.52720405e-02
2.06771941e-01 1.56008577e-01 6.40581708e-04 9.92281016e-03
-9.19795609e-02 3.12156134e-02 5.99317391e-03 2.97288547e-02
8.18623392e-02 2.29032549e-02 -2.73972788e-02 1.51645073e-02
3.23438207e-02 3.88545534e-02 2.09627935e-02 6.96394351e-02
-9.16980407e-03 -2.18354808e-02 5.07216880e-03 3.17494225e-02
-2.09772938e-02 7.49790681e-02 1.64625955e-02 1.62684403e-02
1.75895590e-02 -1.75381993e-02 3.30949594e-02 1.68392658e-02
-4.66582083e-02 -1.31719587e-02 2.87477287e-02 3.09746600e-02
4.02686924e-02 9.92987348e-02 6.68115596e-02 1.37739367e-02
2.59549211e-02 -2.38058399e-02 2.65402587e-02 -6.92529979e-04
1.29576451e-02 1.25610137e-02 -9.68450401e-03 -2.27944079e-03
8.09259777e-03 3.30342301e-02 -1.66721756e-02 2.23839435e-02
3.32432426e-02 -8.04561602e-04 -1.76497454e-01 3.88186056e-02
3.37774181e-02 2.17565099e-02 5.30233710e-03 -9.24771708e-03
-2.73679575e-02 1.85809743e-02 1.29401582e-02 -3.19690493e-02
6.66584177e-03 4.49614784e-02 1.54566766e-02 -7.53477425e-02
5.81757746e-02 -1.76431610e-02 2.75413678e-02 -2.55708758e-02
-1.45602981e-02 1.81886720e-02 -2.32100056e-02 -3.80762864e-02
1.23351328e-02 -1.66785206e-02 1.56719872e-02 4.68276318e-03
9.40509132e-04 3.57552385e-02 -1.58076069e-02 -5.53826979e-02
-6.65141956e-03 -2.88814865e-03 1.50011930e-02 2.13362782e-02
-2.81424369e-03 -2.31808199e-02 -7.58749682e-04 -2.14478348e-02
-2.51214499e-02 -1.79191990e-02 -4.81870440e-03 -1.46611980e-02
-4.94190983e-03 3.70234969e-02 -1.02883622e-01 2.76857570e-02
1.79941196e-02 1.32435722e-02 4.76814155e-02 3.65520203e-02
-3.40269596e-02 2.28209650e-02 2.64274614e-02 -1.27865165e-02
-2.27199591e-02 8.70615230e-02 6.13932119e-02 -1.08140405e-02
-4.25732617e-02 2.77774841e-02 2.61014304e-02 -2.11770868e-02
-3.23724937e-02 -1.89128329e-02 -1.05251080e-02 1.83862325e-02
2.23534204e-05 -1.20347566e-02 -9.01096911e-03 4.02046530e-02
1.98012305e-02 1.58194352e-02 1.12816659e-02 2.20555788e-02
3.63227509e-03 8.58770347e-03 1.02248600e-02 9.08000210e-03
-3.46537486e-03 3.12890495e-02 -1.43673284e-02 3.14534787e-02
-2.75188217e-02 -7.18691836e-03 -7.07891187e-03 2.31015874e-03
1.35687890e-03 1.19905667e-02 1.67455167e-02 -4.81069735e-02
-9.68752624e-03 1.07210195e-02 2.21967422e-02 -1.01291741e-02
5.25316073e-02 -6.66390427e-03 1.14009388e-02 -2.01902980e-02
7.12558770e-02 7.83356049e-03 2.38237767e-02 -4.15273084e-03
8.77559520e-03 -9.00060067e-03 1.60980039e-02 -1.08296154e-02
-4.42603447e-02 -1.09092326e-02 -1.44739014e-02 -8.60951329e-03
2.49086682e-02 -1.92284756e-02 -1.89749837e-02 -2.77355424e-02
9.82524416e-04 5.67031203e-03 -2.54535190e-03 4.75299754e-03
2.71211354e-02 3.27688397e-03 1.85424999e-02 -2.26283972e-03
-1.79189346e-02 1.71016295e-02 1.93496703e-02 -8.69306494e-03
-9.58453162e-03 1.20178271e-02 -2.26289764e-02 2.15726732e-03
8.10821412e-03 2.47074350e-02 2.95059846e-02 1.21555107e-03
4.98131914e-03 2.43000118e-03 1.95785508e-02 -1.57990583e-02
-1.16102797e-02 7.46115157e-03 -8.06557912e-03 2.15298282e-02
2.29129769e-03 3.25367516e-02 1.99525909e-02 -3.92835829e-05
-2.05836804e-02 5.04866199e-03 1.24307792e-02 2.53079097e-02
1.96925968e-02 -2.64611443e-02 -6.82689419e-03 -1.49852524e-02
-3.93645529e-02 9.99089648e-03 1.09631668e-02 -1.51040704e-02
1.67164079e-02 1.26766125e-02 -5.86334604e-02 2.40496926e-02
1.54186622e-02 -6.12083319e-02 2.96323772e-02 -2.44415176e-02
1.11052819e-02 -2.57457149e-02 -2.49398749e-02 3.32951848e-02
3.85385282e-02 -5.16258286e-02 9.54478785e-03 -1.72063013e-02
2.23740124e-02 -5.52438260e-03 -1.31083373e-02 4.06350280e-02
2.55388980e-02 -1.41308581e-02 -5.75406964e-03 -2.16662792e-02
1.62563844e-02 -2.24345285e-02 -3.11828721e-02 1.44461933e-02
-1.30242777e-02 5.54219131e-03 7.95690283e-03 1.76646739e-03
1.41692278e-02 1.86635350e-02 -1.97979179e-02 -4.63186884e-03
1.20542175e-02 3.20413779e-02 -4.57051394e-02 -2.36441701e-02
-3.04932172e-02 3.87911664e-02 4.78728082e-02 -1.88170992e-02
2.63657803e-03 -3.86012566e-03 3.97224532e-03 1.39442494e-02
-1.88336565e-02 -2.70551779e-02 -4.66568493e-03 -1.33610215e-03
-8.18744988e-03 8.46266586e-03 1.48045340e-02 -6.83182810e-03
4.27071232e-04 -2.06468268e-03 -4.97468097e-03 1.48996773e-02
1.07555873e-03 -9.22835391e-03 8.99547441e-03 4.82968523e-03
9.98661438e-03 -1.65016157e-02 4.92553539e-03 -1.16019345e-03
-8.61715302e-02 3.61199006e-02 -3.42490963e-02 1.90392013e-03
-2.28637135e-02 -5.21567166e-02 2.52407362e-02 -4.18485080e-02
-1.10058841e-02 1.08156107e-02 2.75855699e-02 3.42679472e-02
-2.20825398e-02 3.10296716e-02 -2.75477891e-02 -3.07610994e-04
-9.01535833e-03 1.83193047e-02 -1.62208155e-02 -3.10351309e-02
2.48818137e-02 8.18365382e-03 -1.60809925e-02 1.01836062e-02
-2.05476464e-02 6.85855700e-03 2.57900195e-02 -1.49888744e-02
-1.74511929e-03 1.24756224e-02 6.52823373e-03 -8.66673208e-03
4.31158765e-02 -3.38250310e-02 3.18997087e-02 -1.37758806e-02
-5.33139333e-03 -8.79443447e-03 -1.44610591e-02 2.52537246e-02
7.87391233e-02 1.27012172e-02 -1.56102214e-02 -2.67977090e-02
-4.62736835e-04 2.56238335e-02 -8.09176226e-03 1.91149252e-03
2.22919180e-03 -1.68315172e-02 7.52355012e-04 8.54417905e-03
4.70626447e-03 3.26721691e-02 -6.66386713e-03 -3.62252305e-02
-1.58279947e-03 9.68094966e-04 -1.48804245e-02 7.77251715e-03
3.10671736e-02 -2.88045626e-02 -4.11328551e-03 -8.85415876e-03
1.00068277e-02 -1.91264954e-02 2.67619648e-03 4.45828413e-02
3.10793047e-02 -5.73633264e-03 -1.42399778e-02 -1.64262324e-02
3.46889578e-03 -2.07657571e-02 4.23753762e-02 -1.34629372e-04
1.29942385e-02 2.76672570e-02 2.42359462e-02 -3.10531938e-02
-6.55599208e-03 -2.99614420e-02 -1.91772543e-03 -2.02543378e-02
2.21573145e-02 -1.59205200e-02 -4.01668972e-02 1.68476566e-02
2.37997259e-02 9.68827220e-03 2.31875156e-02 6.79334701e-03
8.50905759e-03 2.75432711e-02 -1.15121814e-02 -3.73346961e-02
-1.38350227e-02 1.80944227e-03 -1.99144252e-02 -4.50820362e-02
-8.51953547e-02 1.05289990e-03 -5.73683988e-02 -2.28014261e-03
8.79845471e-04 -1.78715467e-02 3.80136044e-02 5.91779029e-03
-2.78439138e-02 1.17008295e-02 -3.42645883e-02 2.34195563e-02
-4.81212125e-03 -3.66954676e-03 3.90228979e-02 -1.70824631e-02
1.26012065e-02 -6.31776451e-03 -4.50539802e-02 4.56076309e-03
1.44345103e-04 7.18085486e-03 -5.65887042e-03 -8.93522131e-03
1.10250325e-02 -7.96661764e-03 3.41027635e-03 1.22731705e-02
8.47707142e-03 -1.49932019e-02 2.66278446e-02 -1.91671698e-02
-1.26043505e-02 6.35412651e-02 -1.96684538e-02 1.54777089e-02
1.91255149e-02 5.31808863e-02 5.35289710e-04 -2.08611895e-03
-4.96139883e-05 3.58330048e-02 -4.11211604e-03 -2.71141250e-02
-3.69387375e-02 1.32678215e-02 1.03065894e-02 -1.16026233e-01
9.05902436e-03 -4.11355240e-03 -5.76609367e-03 -3.03489660e-02
-2.28466980e-02 -4.07422105e-03 -1.14981380e-02 -2.00718306e-02
2.82733363e-02 -5.85023917e-03 3.73266757e-02 -6.81585169e-02
-5.58717156e-02 -3.08019223e-02 -2.96969413e-03 -2.47161214e-02
-4.22694385e-03 -7.48483026e-03 -5.56253994e-03 7.40543585e-04
3.01216667e-02 -5.56430481e-03 5.64963486e-03 -3.23841390e-02
8.53283403e-03 1.11517051e-02 9.92444066e-03 -1.23128623e-01
9.55844602e-03 -1.99321384e-02 1.57922080e-02 1.19673131e-02
1.68849528e-02 -6.34044465e-03 1.06775644e-02 2.47265340e-02
-3.25711720e-02 -9.76594327e-03 -5.08742553e-02 5.24289526e-02
2.91111239e-02 -1.39398617e-02 2.42465106e-02 -4.15577108e-02
-2.58480889e-02 4.62777932e-02 1.20306488e-02 2.75909133e-03
-1.01712845e-02 -5.46886148e-02 -2.46527009e-02 -1.01558015e-02
1.56187669e-02 3.52148277e-03 2.19565752e-02 -8.63359919e-03
-1.76395758e-02 1.96950103e-02 1.48984342e-02 -3.16258423e-03
-5.85331096e-03 9.65977546e-03 4.50183244e-03 -2.47884005e-03
-1.69232421e-02 -5.99840290e-04 6.71455978e-04 1.08295297e-02
1.95363677e-02 9.41925140e-03 -1.81041432e-02 -1.40310535e-02
7.22752555e-04 2.96587727e-02 -3.23319552e-02 -3.06897437e-02
-1.84134215e-02 6.59667420e-02 2.65303333e-02 3.17956491e-02
1.27969978e-02 -2.03537673e-02 -2.66071290e-02 -7.43361712e-03
-2.48459980e-02 3.64371936e-03 1.64657605e-02 -4.65377776e-02
-8.32882233e-03 2.52378813e-02 2.51187743e-02 -1.62291204e-02
-1.84450879e-02 3.42146322e-02 -3.21809348e-02 -9.33033795e-03
-9.45292979e-03 -3.45051567e-02 -3.55155679e-02 -1.25766013e-01
-2.02891251e-02 5.37952007e-03 1.27094363e-02 2.36198128e-02
2.32853839e-02]
