def _ompcv(*,
train,
test,
x_predict=None,
metrics,
copy=True,
fit_intercept=True,
normalize=True,
max_iter=None,
cv=None,
n_jobs=None,
verbose=False):
"""For more info visit :
https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.OrthogonalMatchingPursuitCV.html#sklearn.linear_model.OrthogonalMatchingPursuitCV
"""
model = OrthogonalMatchingPursuitCV(fit_intercept=fit_intercept,
copy=copy,
normalize=normalize,
max_iter=max_iter,
cv=cv,
n_jobs=n_jobs,
verbose=verbose)
model.fit(train[0], train[1])
model_name = 'OrthogonalMatchingPursuitCV'
y_hat = model.predict(test[0])
if metrics == 'mse':
accuracy = _mse(test[1], y_hat)
if metrics == 'rmse':
accuracy = _rmse(test[1], y_hat)
if metrics == 'mae':
accuracy = _mae(test[1], y_hat)
if x_predict is None:
return (model_name, accuracy, None)
y_predict = model.predict(x_predict)
return (model_name, accuracy, y_predict)
class _OrthogonalMatchingPursuitCVImpl:
def __init__(self, **hyperparams):
self._hyperparams = hyperparams
self._wrapped_model = Op(**self._hyperparams)
def fit(self, X, y=None):
if y is not None:
self._wrapped_model.fit(X, y)
else:
self._wrapped_model.fit(X)
return self
def predict(self, X):
return self._wrapped_model.predict(X)
def predict(self):
"""
trains the scikit-learn python machine learning algorithm library function
https://scikit-learn.org
then passes the trained algorithm the features set and returns the
predicted y test values form, the function
then compares the y_test values from scikit-learn predicted to
y_test values passed in
then returns the accuracy
"""
n_nonzero_coefs = 17
algorithm = OrthogonalMatchingPursuitCV()
algorithm.fit(self.X_train, self.y_train)
y_pred = list(algorithm.predict(self.X_test))
self.acc = OneHotPredictor.get_accuracy(y_pred, self.y_test)
return self.acc
tss, rss, ess, r2 = xss(Y, omp.predict(X))
print "TSS(Total Sum of Squares): ", tss
print "RSS(Residual Sum of Squares): ", rss
print "ESS(Explained Sum of Squares): ", ess
print "R^2: ", r2
print "\n**********测试OrthogonalMatchingPursuitCV类**********"
ompCV = OrthogonalMatchingPursuitCV(cv=5)
# 拟合训练集
ompCV.fit(train_X, train_Y.values.ravel())
# 打印最好的n_nonzero_coefs值
print "最好的n_nonzero_coefs值: ", ompCV.n_nonzero_coefs_
# 打印模型的系数
print "系数:", ompCV.coef_
print "截距:", ompCV.intercept_
print '训练集R2: ', r2_score(train_Y, ompCV.predict(train_X))
# 对于线性回归模型, 一般使用均方误差(Mean Squared Error,MSE)或者
# 均方根误差(Root Mean Squared Error,RMSE)在测试集上的表现来评该价模型的好坏.
test_Y_pred = ompCV.predict(test_X)
print "测试集得分:", ompCV.score(test_X, test_Y)
print "测试集MSE:", mean_squared_error(test_Y, test_Y_pred)
print "测试集RMSE:", np.sqrt(mean_squared_error(test_Y, test_Y_pred))
print "测试集R2:", r2_score(test_Y, test_Y_pred)
tss, rss, ess, r2 = xss(Y, ompCV.predict(X))
print "TSS(Total Sum of Squares): ", tss
print "RSS(Residual Sum of Squares): ", rss
print "ESS(Explained Sum of Squares): ", ess
print "R^2: ", r2