更改model_selection

Question

我试图修改此tutorial中的示例以使用我自己的数据。

在教程中，Y数据只能有3个不同的值，但在我的情况下，它可以在0到200之间。如果预测值达到+ -3，我认为这是一个成功的估计。

我怀疑我必须对评分变量进行一些修改，但我不确定如何继续。

import pandas
from pandas.tools.plotting import scatter_matrix
import matplotlib.pyplot as plt
from sklearn import model_selection
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC

url = "testdata2.csv"
dataset = pandas.read_csv(url)


# Test options and evaluation metric
seed = 7
scoring = 'accuracy'

# Split-out validation dataset
array = dataset.values
X = array[:,0:6]
Y = array[:,6]


validation_size = 0.20
seed = 7
X_train, X_validation, Y_train, Y_validation = model_selection.train_test_split(X, Y, test_size=validation_size, random_state=seed)



# Spot Check Algorithms
models = []

models.append(('LR', LogisticRegression()))
models.append(('LDA', LinearDiscriminantAnalysis()))
models.append(('KNN', KNeighborsClassifier()))
models.append(('CART', DecisionTreeClassifier()))
models.append(('NB', GaussianNB()))
models.append(('SVM', SVC()))
# evaluate each model in turn
results = []
names = []
for name, model in models:
    kfold = model_selection.KFold(n_splits=10, random_state=seed)
    cv_results = model_selection.cross_val_score(model, X_train, Y_train, cv=kfold, scoring=scoring)
    results.append(cv_results)
    names.append(name)
    msg = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
    print(cv_results)