Kaggle - House Prices

kaggle_kfold.py

from sklearn.cross_validation import KFold

from sklearn import linear_model
from sklearn import ensemble
from sklearn.metrics import mean_squared_error

xpca = PCA(100).fit_transform(df_cars_maxabs);

kf = KFold(len(df), n_folds=10, shuffle=True)

X = df.drop('SalePrice',1)
Y = df['SalePrice']
results = []
for train_index, test_index in kf:
    X_train, X_test =  xpca[train_index], xpca[test_index]
    Y_train, Y_test = Y.iloc[train_index], Y.iloc[test_index]
    
    regr = linear_model.Ridge()
    regr.fit(X_train,Y_train)
    
    predictions = regr.predict(X_test)
    error = np.sqrt(mean_squared_error(Y_test, predictions))
    RMSLE = np.sqrt(np.sum( (np.log(predictions +1) - np.log(Y_test+1))**2)/len(Y_test))
    
    results += [RMSLE]

print sum(results)/10