我的算法
filename='housing_data.xlsx'
names= ['CRIM','ZN','INDUS','CHAS','NOX','RM','AGE','DIS','RAD','TAX','PRTATIO','B','LSTAT','MEDV']
data = pd.read_excel(filename,names=names)
pd.set_option('display.width',120)
array = data.values
X = array[:,0:13]
Y = array[:,13]
validation_size=0.2
seed=7
X_train, X_validation, Y_train, Y_validation= train_test_split(X,Y,test_size=validation_size,random_state=seed )
num_folds = 10
seed = 7
scoring = 'neg_mean_squared_error'
models ={}
models['LR'] = LinearRegression()
models['Lasso'] = Lasso()
models['EN'] = ElasticNet()
models['KNN'] = KNeighborsRegressor()
models['CART'] =DecisionTreeClassifier()
models['SVM'] = SVR()
results = []
for key in models:
kfold = KFold(n_splits=num_folds,shuffle=True,random_state=seed)
cv_result = cross_val_score(models[key],X_train,Y_train,cv=kfold,scoring=scoring)
results.append(cv_result)
print('%s: %f(%f)' % (key,cv_result.mean(),cv_result.std()))
输出结果是
ValueError: Input contains NaN, infinity or a value too large for dtype('float64').
warnings.warn("Estimator fit failed. The score on this train-test"
SVM: nan(nan)