def test_sk_OrthogonalMatchingPursuitCV():
print("Testing sklearn, OrthogonalMatchingPursuitCV...")
mod = linear_model.OrthogonalMatchingPursuitCV()
X, y = iris_data
mod.fit(X, y)
docs = {'name': "OrthogonalMatchingPursuitCV test"}
fv = X[0, :]
upload(mod, fv, docs)
def cross_validated_estimators_tests():
models = [
linear_model.ElasticNetCV(),
linear_model.LarsCV(),
linear_model.LassoCV(),
linear_model.LassoLarsCV(),
linear_model.LogisticRegressionCV(),
linear_model.OrthogonalMatchingPursuitCV(),
linear_model.RidgeClassifierCV(),
linear_model.RidgeCV()
]
for model in models:
cross_validated_estimators(model)
def orthogonal_matching_pursuit_cv_autoregression(df, sliding_window=1):
predictions = []
terminal_condition = False
x_start = 0
x_end = sliding_window
data = [df.ix[ind] for ind in df.index]
while x_end != len(data)-1:
Y = data[x_end+1]
X = data[x_start:x_end]
regressor = linear_model.OrthogonalMatchingPursuitCV()
regressor.fit(X,Y)
predictions.append(regressor.predict(X))
return predictions
def test_model_orthogonal_matching_pursuit_cv(self):
model, X = fit_regression_model(
linear_model.OrthogonalMatchingPursuitCV())
model_onnx = convert_sklearn(
model,
"orthogonal matching pursuit cv",
[("input", FloatTensorType([None, X.shape[1]]))],
target_opset=TARGET_OPSET)
self.assertIsNotNone(model_onnx)
dump_data_and_model(X,
model,
model_onnx,
verbose=False,
basename="SklearnOrthogonalMatchingPursuitCV-Dec4")
def test_model_orthogonal_matching_pursuit_cv(self):
model, X = fit_regression_model(
linear_model.OrthogonalMatchingPursuitCV())
model_onnx = convert_sklearn(
model, "orthogonal matching pursuit cv",
[("input", FloatTensorType([None, X.shape[1]]))])
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
verbose=False,
basename="SklearnOrthogonalMatchingPursuitCV-Dec4",
allow_failure="StrictVersion("
"onnxruntime.__version__)"
"<= StrictVersion('0.2.1')",
)
def sklearn_liner_model_regressions(xTrain, xTest, yTrain, yTest):
modelForConsideration: DataFrame = pd.DataFrame()
LinerModels = \
[
linear_model.ARDRegression(), linear_model.BayesianRidge(), linear_model.ElasticNet(),
linear_model.ElasticNetCV(),
linear_model.HuberRegressor(), linear_model.Lars(), linear_model.LarsCV(), linear_model.Lasso(),
linear_model.LassoCV(), linear_model.LassoLars(), linear_model.LassoLarsCV(), linear_model.LassoLarsIC(),
linear_model.LinearRegression(), linear_model.MultiTaskLasso(),
linear_model.MultiTaskElasticNet(), linear_model.MultiTaskLassoCV(), linear_model.MultiTaskElasticNetCV(),
linear_model.OrthogonalMatchingPursuit(),
linear_model.OrthogonalMatchingPursuitCV(), linear_model.PassiveAggressiveClassifier(),
linear_model.PassiveAggressiveRegressor(), linear_model.Perceptron(),
linear_model.RANSACRegressor(), linear_model.Ridge(), linear_model.RidgeClassifier(),
linear_model.RidgeClassifierCV(),
linear_model.RidgeCV(), linear_model.SGDClassifier(), linear_model.SGDRegressor(),
linear_model.TheilSenRegressor(),
linear_model.enet_path(xTrain, yTrain),
linear_model.lars_path(xTrain, yTrain), linear_model.lasso_path(xTrain, yTrain),
# linear_model.LogisticRegression()
# ,linear_model.LogisticRegressionCV(),linear_model.logistic_regression_path(xTrain, yTrain), linear_model.orthogonal_mp(xTrain, yTrain), linear_model.orthogonal_mp_gram(), linear_model.ridge_regression()
]
for model in LinerModels:
modelName: str = model.__class__.__name__
try:
# print(f"Preparing Model {modelName}")
if modelName == "LogisticRegression":
model = linear_model.LogisticRegression(random_state=0)
model.fit(xTrain, yTrain)
yTrainPredict = model.predict(xTrain)
yTestPredict = model.predict(xTest)
errorList = calculate_prediction_error(modelName, yTestPredict,
yTest, yTrainPredict,
yTrain)
if errorList["Test Average Error"][0] < 30 and errorList[
"Train Average Error"][0] < 30:
try:
modelForConsideration = modelForConsideration.append(
errorList)
except (Exception) as e:
print(e)
except (Exception, ArithmeticError) as e:
print(f"Error occurred while preparing Model {modelName}")
return modelForConsideration
def __init__(
self,
method,
yrange,
params,
i=0
): #TODO: yrange doesn't currently do anything. Remove or do something with it!
self.algorithm_list = [
'PLS',
'GP',
'OLS',
'OMP',
'Lasso',
'Elastic Net',
'Ridge',
'Bayesian Ridge',
'ARD',
'LARS',
'LASSO LARS',
'SVR',
'KRR',
]
self.method = method
self.outliers = None
self.ransac = False
print(params)
if self.method[i] == 'PLS':
self.model = PLSRegression(**params[i])
if self.method[i] == 'OLS':
self.model = linear.LinearRegression(**params[i])
if self.method[i] == 'OMP':
# check whether to do CV or not
self.do_cv = params[i]['CV']
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# Remove CV parameter
params_temp.pop('CV')
if self.do_cv is False:
self.model = linear.OrthogonalMatchingPursuit(**params_temp)
else:
params_temp.pop('precompute')
self.model = linear.OrthogonalMatchingPursuitCV(**params_temp)
if self.method[i] == 'LASSO':
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# check whether to do CV or not
try:
self.do_cv = params[i]['CV']
# Remove CV parameter
params_temp.pop('CV')
except:
self.do_cv = False
if self.do_cv is False:
self.model = linear.Lasso(**params_temp)
else:
params_temp.pop('alpha')
self.model = linear.LassoCV(**params_temp)
if self.method[i] == 'Elastic Net':
params_temp = copy.copy(params[i])
try:
self.do_cv = params[i]['CV']
params_temp.pop('CV')
except:
self.do_cv = False
if self.do_cv is False:
self.model = linear.ElasticNet(**params_temp)
else:
params_temp['l1_ratio'] = [.1, .5, .7, .9, .95, .99, 1]
self.model = linear.ElasticNetCV(**params_temp)
if self.method[i] == 'Ridge':
# create a temporary set of parameters
params_temp = copy.copy(params[i])
try:
# check whether to do CV or not
self.do_cv = params[i]['CV']
# Remove CV parameter
params_temp.pop('CV')
except:
self.do_cv = False
if self.do_cv:
self.model = linear.RidgeCV(**params_temp)
else:
self.model = linear.Ridge(**params_temp)
if self.method[i] == 'BRR':
self.model = linear.BayesianRidge(**params[i])
if self.method[i] == 'ARD':
self.model = linear.ARDRegression(**params[i])
if self.method[i] == 'LARS':
# create a temporary set of parameters
params_temp = copy.copy(params[i])
try:
# check whether to do CV or not
self.do_cv = params[i]['CV']
# Remove CV parameter
params_temp.pop('CV')
except:
self.do_cv = False
if self.do_cv is False:
self.model = linear.Lars(**params_temp)
else:
self.model = linear.LarsCV(**params_temp)
if self.method[i] == 'LASSO LARS':
model = params[i]['model']
params_temp = copy.copy(params[i])
params_temp.pop('model')
if model == 0:
self.model = linear.LassoLars(**params_temp)
elif model == 1:
self.model = linear.LassoLarsCV(**params_temp)
elif model == 2:
self.model = linear.LassoLarsIC(**params_temp)
else:
print("Something went wrong, \'model\' should be 0, 1, or 2")
if self.method[i] == 'SVR':
self.model = svm.SVR(**params[i])
if self.method[i] == 'KRR':
self.model = kernel_ridge.KernelRidge(**params[i])
if self.method[i] == 'GP':
# get the method for dimensionality reduction and the number of components
self.reduce_dim = params[i]['reduce_dim']
self.n_components = params[i]['n_components']
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# Remove parameters not accepted by Gaussian Process
params_temp.pop('reduce_dim')
params_temp.pop('n_components')
self.model = GaussianProcess(**params_temp)
classification(svm.NuSVC(kernel="rbf", **SVC_PARAMS)),
# Linear Regression
regression(linear_model.LinearRegression()),
regression(linear_model.HuberRegressor()),
regression(linear_model.ElasticNet(random_state=RANDOM_SEED)),
regression(linear_model.ElasticNetCV(random_state=RANDOM_SEED)),
regression(linear_model.TheilSenRegressor(random_state=RANDOM_SEED)),
regression(linear_model.Lars()),
regression(linear_model.LarsCV()),
regression(linear_model.Lasso(random_state=RANDOM_SEED)),
regression(linear_model.LassoCV(random_state=RANDOM_SEED)),
regression(linear_model.LassoLars()),
regression(linear_model.LassoLarsIC()),
regression(linear_model.OrthogonalMatchingPursuit()),
regression(linear_model.OrthogonalMatchingPursuitCV()),
regression(linear_model.Ridge(random_state=RANDOM_SEED)),
regression(linear_model.RidgeCV()),
regression(linear_model.BayesianRidge()),
regression(linear_model.ARDRegression()),
regression(linear_model.SGDRegressor(random_state=RANDOM_SEED)),
regression(
linear_model.PassiveAggressiveRegressor(random_state=RANDOM_SEED)),
# Logistic Regression
classification(
linear_model.LogisticRegression(random_state=RANDOM_SEED)),
classification(
linear_model.LogisticRegressionCV(random_state=RANDOM_SEED)),
classification(linear_model.RidgeClassifier(random_state=RANDOM_SEED)),
classification(linear_model.RidgeClassifierCV()),
# open a file to save calculated coefficients
coefs_file = open('OMP_coefs.txt', 'w')
coefs_file.write('OMP algorithm with CV to calculate %s' % X_name)
# write the predictor names to file
for pred in predictor_names:
coefs_file.write('%s\t' % pred)
# add column for R2 and fold
coefs_file.write('R2\tfold\n')
#make figure to plot predicted vs measured
plt.figure(figsize=(5 * len(cv_list), 5))
sb = 1 # subplot index
# loop over the list of cv fold values to calculate the model, plot the results, and save to file
for cv_ in cv_list:
OMP = linear_model.OrthogonalMatchingPursuitCV(cv=cv_)
OMPfit = OMP.fit(predictors, X[:, 0])
OMP_coefs = OMPfit.coef_
OMP_predicted = OMP.predict(predictors)
OMP_score = OMP.score(predictors, OMP_predicted)
D = X[:, 0] * scale_D + mean_D[0]
Dpredicted = OMP_predicted * scale_D + mean_D[0]
# calculate the R2 of the fit
R2 = 1 - sum((D - Dpredicted)**2) / sum((D - np.mean(D))**2)
print('CV fold = %d' % cv_)
print 'Number of non-zero coefficients:', OMPfit.n_nonzero_coefs_
print 'R2 :', R2
print("Set up KFolds...")
n_splits = 5
kf = KFold(n_splits=n_splits)
kf.get_n_splits(X)
predictions0 = np.zeros((test.shape[0], n_splits))
predictions1 = np.zeros((test.shape[0], n_splits))
score = 0
print("Starting ", n_splits, "-fold CV loop...")
oof_predictions = np.zeros(X.shape[0])
for fold, (train_index, test_index) in enumerate(kf.split(X)):
X_train, X_valid = X[train_index, :], X[test_index, :]
y_train, y_valid = y[train_index], y[test_index]
clf = linear_model.OrthogonalMatchingPursuitCV()
clf.fit(X_train, y_train)
pred0 = clf.predict(X)
pred1 = clf.predict(test)
oof_predictions[test_index] = clf.predict(X_valid)
predictions0[:, fold] = pred0
predictions1[:, fold] = pred1
score += r2_score(y_train, clf.predict(X_train))
print('Fold %d: Score %f' % (fold, clf.score(X_train, y_train)))
prediction0 = predictions0.mean(axis=1)
prediction1 = predictions1.mean(axis=1)
score /= n_splits
oof_score = r2_score(y, oof_predictions)
def get_regression_estimators(r, regression_models):
if r == 'ARDRegression':
regression_models[r] = linear_model.ARDRegression()
elif r == 'BayesianRidge':
regression_models[r] = linear_model.BayesianRidge()
elif r == 'ElasticNet':
regression_models[r] = linear_model.ElasticNet()
elif r == 'ElasticNetCV':
regression_models[r] = linear_model.ElasticNetCV()
elif r == 'HuberRegressor':
regression_models[r] = linear_model.HuberRegressor()
elif r == 'Lars':
regression_models[r] = linear_model.Lars()
elif r == 'LarsCV':
regression_models[r] = linear_model.LarsCV()
elif r == 'Lasso':
regression_models[r] = linear_model.Lasso()
elif r == 'LassoCV':
regression_models[r] = linear_model.LassoCV()
elif r == 'LassoLars':
regression_models[r] = linear_model.LassoLars()
elif r == 'LassoLarsCV':
regression_models[r] = linear_model.LassoLarsCV()
elif r == 'LassoLarsIC':
regression_models[r] = linear_model.LassoLarsIC()
elif r == 'LinearRegression':
regression_models[r] = linear_model.LinearRegression()
elif r == 'LogisticRegression':
regression_models[r] = linear_model.LogisticRegression()
elif r == 'LogisticRegressionCV':
regression_models[r] = linear_model.LogisticRegressionCV()
elif r == 'MultiTaskElasticNet':
regression_models[r] = linear_model.MultiTaskElasticNet()
elif r == 'MultiTaskElasticNetCV':
regression_models[r] = linear_model.MultiTaskElasticNetCV()
elif r == 'MultiTaskLasso':
regression_models[r] = linear_model.MultiTaskLasso()
elif r == 'MultiTaskLassoCV':
regression_models[r] = linear_model.MultiTaskLassoCV()
elif r == 'OrthogonalMatchingPursuit':
regression_models[r] = linear_model.OrthogonalMatchingPursuit()
elif r == 'OrthogonalMatchingPursuitCV':
regression_models[r] = linear_model.OrthogonalMatchingPursuitCV()
elif r == 'PassiveAggressiveClassifier':
regression_models[r] = linear_model.PassiveAggressiveClassifier()
elif r == 'PassiveAggressiveRegressor':
regression_models[r] = linear_model.PassiveAggressiveRegressor()
elif r == 'Perceptron':
regression_models[r] = linear_model.Perceptron()
elif r == 'RANSACRegressor':
regression_models[r] = linear_model.RANSACRegressor()
elif r == 'Ridge':
regression_models[r] = linear_model.Ridge()
elif r == 'RidgeClassifier':
regression_models[r] = linear_model.RidgeClassifier()
elif r == 'RidgeClassifierCV':
regression_models[r] = linear_model.RidgeClassifierCV()
elif r == 'RidgeCV':
regression_models[r] = linear_model.RidgeCV()
elif r == 'SGDClassifier':
regression_models[r] = linear_model.SGDClassifier()
elif r == 'SGDRegressor':
regression_models[r] = linear_model.SGDRegressor()
elif r == 'TheilSenRegressor':
regression_models[r] = linear_model.TheilSenRegressor()
else:
print(
r +
" is an unsupported regression type. Check if you have misspelled the name."
)
def models(self) -> Dict[str, LinearModel]:
return {
"LinearRegression":
linear_model.LinearRegression(
), # LinearRegression([…]) Ordinary least squares Linear Regression.
"ARDRegression":
linear_model.ARDRegression(
), # ARDRegression([n_iter, tol, …]) Bayesian ARD regression.
"BayesianRidge":
linear_model.BayesianRidge(
), # BayesianRidge([n_iter, tol, …]) Bayesian ridge regression.
"HuberRegressor":
linear_model.HuberRegressor(
), # HuberRegressor([epsilon, …]) Linear regression model that is robust to outliers.
"OrthogonalMatchingPursuitCV":
linear_model.OrthogonalMatchingPursuitCV(
cv=5
), # OrthogonalMatchingPursuitCV([…]) Cross-validated Orthogonal Matching Pursuit model (OMP).
"Perceptron":
linear_model.Perceptron(
max_iter=1000, tol=1e-3
), # Perceptron([penalty, alpha, …]) Read more in the User Guide.
"RANSACRegressor":
linear_model.RANSACRegressor(
), # RANSACRegressor([…]) RANSAC (RANdom SAmple Consensus) algorithm.
"SGDRegressor":
linear_model.SGDRegressor(
max_iter=1000, tol=1e-3
), # SGDRegressor([loss, penalty, …]) Linear model fitted by minimizing a regularized empirical loss with SGD
"TheilSenRegressor":
linear_model.TheilSenRegressor(
), # TheilSenRegressor([…]) Theil-Sen Estimator: robust multivariate regression model.
"PassiveAggressiveRegressor":
linear_model.PassiveAggressiveRegressor(
max_iter=1000, tol=1e-3
), # PassiveAggressiveRegressor([C, …]) Passive Aggressive Regressor
"Lars":
linear_model.Lars(
eps=0.01
), # Lars([fit_intercept, verbose, …]) Least Angle Regression model a.k.a.
"LarsCV":
linear_model.LarsCV(
cv=5, eps=0.01
), # LarsCV([fit_intercept, …]) Cross-validated Least Angle Regression model.
"Lasso":
linear_model.Lasso(
alpha=1, max_iter=1000
), # Lasso([alpha, fit_intercept, …]) Linear Model trained with L1 prior as regularizer (aka the Lasso)
"LassoCV":
linear_model.LassoCV(
cv=5
), # LassoCV([eps, n_alphas, …]) Lasso linear model with iterative fitting along a regularization path.
"LassoLars":
linear_model.LassoLars(
eps=0.01
), # LassoLars([alpha, …]) Lasso model fit with Least Angle Regression a.k.a.
"LassoLarsCV":
linear_model.LassoLarsCV(
cv=5, eps=0.01, max_iter=100
), # LassoLarsCV([fit_intercept, …]) Cross-validated Lasso, using the LARS algorithm.
"LassoLarsIC":
linear_model.LassoLarsIC(
eps=0.01
), # LassoLarsIC([criterion, …]) Lasso model fit with Lars using BIC or AIC for model selection
"Ridge":
linear_model.Ridge(
), # Ridge([alpha, fit_intercept, …]) Linear least squares with l2 regularization.
"RidgeClassifier":
linear_model.RidgeClassifier(
), # RidgeClassifier([alpha, …]) Classifier using Ridge regression.
"RidgeClassifierCV":
linear_model.RidgeClassifierCV(
cv=5
), # RidgeClassifierCV([alphas, …]) Ridge classifier with built-in cross-validation.
"RidgeCV":
linear_model.RidgeCV(
cv=5
), # RidgeCV([alphas, …]) Ridge regression with built-in cross-validation.
"SGDClassifier":
linear_model.SGDClassifier(
max_iter=1000, tol=1e-3
), # SGDClassifier([loss, penalty, …]) Linear classifiers (SVM, logistic regression, a.o.) with SGD training.
"ElasticNet":
linear_model.ElasticNet(
), # linear_model.ElasticNet([alpha, l1_ratio, …]) Linear regression with combined L1 and L2 priors as regularizer.
"ElasticNetCV":
linear_model.ElasticNetCV(
cv=5
), # linear_model.ElasticNetCV([l1_ratio, eps, …]) Elastic Net model with iterative fitting along a regularization path.
### Ignore These
# "LogisticRegression": linear_model.LogisticRegression(), # LogisticRegression([penalty, …]) Logistic Regression (aka logit, MaxEnt) classifier.
# "LogisticRegressionCV": linear_model.LogisticRegressionCV(cv=5), # LogisticRegressionCV([Cs, …]) Logistic Regression CV (aka logit, MaxEnt) classifier.
# "MultiTaskLasso": linear_model.MultiTaskLasso(), # MultiTaskLasso([alpha, …]) Multi-task Lasso model trained with L1/L2 mixed-norm as regularizer.
# "MultiTaskElasticNet": linear_model.MultiTaskElasticNet(), # MultiTaskElasticNet([alpha, …]) Multi-task ElasticNet model trained with L1/L2 mixed-norm as regularizer
# "MultiTaskLassoCV": linear_model.MultiTaskLassoCV(cv=5), # MultiTaskLassoCV([eps, …]) Multi-task Lasso model trained with L1/L2 mixed-norm as regularizer.
# "MultiTaskElasticNetCV": linear_model.MultiTaskElasticNetCV(cv=5), # MultiTaskElasticNetCV([…]) Multi-task L1/L2 ElasticNet with built-in cross-validation.
# "OrthogonalMatchingPursuit": linear_model.OrthogonalMatchingPursuit(), # OrthogonalMatchingPursuit([…]) Orthogonal Matching Pursuit model (OMP)
# "PassiveAggressiveClassifier": linear_model.PassiveAggressiveClassifier(), # PassiveAggressiveClassifier([…]) Passive Aggressive Classifier
### Normalization seems to make the score worse!
# "LinearRegressionNormalize": linear_model.LinearRegression(normalize=True), # LinearRegression([…]) Ordinary least squares Linear Regression.
# "RidgeCVNormalize": linear_model.RidgeCV(cv=5, normalize=True), # RidgeCV([alphas, …]) Ridge regression with built-in cross-validation.
# "LassoLarsNormalize": linear_model.LassoLars(eps=0.01, normalize=True), # LassoLars([alpha, …]) Lasso model fit with Least Angle Regression a.k.a.
# "LassoLarsICNormalize": linear_model.LassoLarsIC(eps=0.01, normalize=True), # LassoLarsIC([criterion, …]) Lasso model fit with Lars using BIC or AIC for model selection
# "ARDRegressionNormalize": linear_model.ARDRegression(normalize=True), # ARDRegression([n_iter, tol, …]) Bayesian ARD regression.
# "BayesianRidgeNormalize": linear_model.BayesianRidge(normalize=True), # BayesianRidge([n_iter, tol, …]) Bayesian ridge regression.
}
def __init__(self, method, yrange, params, i=0, ransacparams={}):
self.method = method
self.outliers = None
self.inliers = None
self.ransac = False
self.yrange = yrange[i]
if self.method[i] == 'PLS':
self.model = PLSRegression(**params[i])
if self.method[i] == 'OLS':
self.model = linear.LinearRegression(**params[i])
if self.method[i] == 'OMP':
#check whether to do CV or not
self.do_cv = params[i]['CV']
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# Remove CV parameter
params_temp.pop('CV')
if self.do_cv is False:
self.model = linear.OrthogonalMatchingPursuit(**params_temp)
else:
params_temp.pop('n_nonzero_coefs')
self.model = linear.OrthogonalMatchingPursuitCV(**params_temp)
if self.method[i] == 'Lasso':
# check whether to do CV or not
self.do_cv = params[i]['CV']
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# Remove CV parameter
params_temp.pop('CV')
if self.do_cv is False:
self.model = linear.Lasso(**params_temp)
else:
params_temp.pop('alpha')
self.model = linear.LassoCV(**params_temp)
if self.method[i] == 'Elastic Net':
# check whether to do CV or not
self.do_cv = params[i]['CV']
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# Remove CV parameter
params_temp.pop('CV')
if self.do_cv is False:
self.model = linear.ElasticNet(**params_temp)
else:
params_temp.pop('alpha')
self.model = linear.ElasticNetCV(**params_temp)
if self.method[i] == 'Ridge':
# check whether to do CV or not
self.do_cv = params[i]['CV']
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# Remove CV parameter
params_temp.pop('CV')
if self.do_cv is False:
self.model = linear.Ridge(**params_temp)
else:
#Ridge requires a specific set of alphas to be provided... this needs more work to be implemented correctly
self.model = linear.RidgeCV(**params_temp)
if self.method[i] == 'Bayesian Ridge':
self.model = linear.BayesianRidge(**params[i])
if self.method[i] == 'ARD':
self.model = linear.ARDRegression(**params[i])
if self.method[i] == 'LARS':
# check whether to do CV or not
self.do_cv = params[i]['CV']
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# Remove CV parameter
params_temp.pop('CV')
if self.do_cv is False:
self.model = linear.Lars(**params_temp)
else:
self.model = linear.LarsCV(**params_temp)
if self.method[i] == 'Lasso LARS':
# check whether to do CV or not
self.do_cv = params[i]['CV']
# check whether to do IC or not
self.do_ic = params[i]['IC']
# create a temporary set of parameters
params_temp = copy.copy(params[i])
# Remove CV and IC parameter
params_temp.pop('CV')
params_temp.pop('IC')
if self.do_cv is False and self.do_ic is False:
self.model = linear.LassoLars(**params[i])
if self.do_cv is True and self.do_ic is False:
self.model = linear.LassoLarsCV(**params[i])
if self.do_cv is False and self.do_ic is True:
self.model = linear.LassoLarsIC(**params[i])
if self.do_cv is True and self.do_ic is True:
print(
"Can't use both cross validation AND information criterion to optimize!"
)
if self.method[i] == 'SVR':
self.model = svm.SVR(**params[i])
if self.method[i] == 'KRR':
self.model = kernel_ridge.KernelRidge(**params[i])
if self.method[i] == 'GP':
#get the method for dimensionality reduction and the number of components
self.reduce_dim = params[i]['reduce_dim']
self.n_components = params[i]['n_components']
#create a temporary set of parameters
params_temp = copy.copy(params[i])
#Remove parameters not accepted by Gaussian Process
params_temp.pop('reduce_dim')
params_temp.pop('n_components')
self.model = GaussianProcess(**params_temp)
modeldict = {
'ardregression': lm.ARDRegression(),
'bayesianridge': lm.BayesianRidge(),
'elasticnet': lm.ElasticNet(),
'elasticnetcv': lm.ElasticNetCV(),
'huberregression': lm.HuberRegressor(),
'lars': lm.Lars(),
'larscv': lm.LarsCV(),
'lasso': lm.Lasso(),
'lassocv': lm.LassoCV(),
'lassolars': lm.LassoLars(),
'lassolarscv': lm.LassoLarsCV(),
'lassolarsic': lm.LassoLarsIC(),
'linearregression': lm.LinearRegression(),
'orthogonalmatchingpursuit': lm.OrthogonalMatchingPursuit(),
'orthogonalmatchingpursuitcv': lm.OrthogonalMatchingPursuitCV(),
'passiveagressiveregressor': lm.PassiveAggressiveRegressor(),
'ridge': lm.Ridge(),
'ridgecv': lm.RidgeCV(),
'sgdregressor': lm.SGDRegressor(),
'theilsenregressor': lm.TheilSenRegressor(),
'decisiontreeregressor': DecisionTreeRegressor(),
'randomforestregressor': RandomForestRegressor(),
'adaboostregressor': AdaBoostRegressor(),
'baggingregressor': BaggingRegressor(),
'extratreeregressor': ExtraTreeRegressor(),
'linearsvr': LinearSVR(),
'nusvr': NuSVR(),
'svr': SVR(),
}
def run_simple_model(train_x, train_y, dev_x, dev_y, test_x, test_y, model_type, out_dir=None, class_weight=None):
from sklearn import datasets, neighbors, linear_model, svm
totalTime = 0
startTrainTime = time()
logger.info("Start training...")
if model_type == 'ARDRegression':
model = linear_model.ARDRegression().fit(train_x, train_y)
elif model_type == 'BayesianRidge':
model = linear_model.BayesianRidge().fit(train_x, train_y)
elif model_type == 'ElasticNet':
model = linear_model.ElasticNet().fit(train_x, train_y)
elif model_type == 'ElasticNetCV':
model = linear_model.ElasticNetCV().fit(train_x, train_y)
elif model_type == 'HuberRegressor':
model = linear_model.HuberRegressor().fit(train_x, train_y)
elif model_type == 'Lars':
model = linear_model.Lars().fit(train_x, train_y)
elif model_type == 'LarsCV':
model = linear_model.LarsCV().fit(train_x, train_y)
elif model_type == 'Lasso':
model = linear_model.Lasso().fit(train_x, train_y)
elif model_type == 'LassoCV':
model = linear_model.LassoCV().fit(train_x, train_y)
elif model_type == 'LassoLars':
model = linear_model.LassoLars().fit(train_x, train_y)
elif model_type == 'LassoLarsCV':
model = linear_model.LassoLarsCV().fit(train_x, train_y)
elif model_type == 'LassoLarsIC':
model = linear_model.LassoLarsIC().fit(train_x, train_y)
elif model_type == 'LinearRegression':
model = linear_model.LinearRegression().fit(train_x, train_y)
elif model_type == 'LogisticRegression':
model = linear_model.LogisticRegression(class_weight=class_weight).fit(train_x, train_y)
elif model_type == 'LogisticRegressionCV':
model = linear_model.LogisticRegressionCV(class_weight=class_weight).fit(train_x, train_y)
elif model_type == 'MultiTaskLasso':
model = linear_model.MultiTaskLasso().fit(train_x, train_y)
elif model_type == 'MultiTaskElasticNet':
model = linear_model.MultiTaskElasticNet().fit(train_x, train_y)
elif model_type == 'MultiTaskLassoCV':
model = linear_model.MultiTaskLassoCV().fit(train_x, train_y)
elif model_type == 'MultiTaskElasticNetCV':
model = linear_model.MultiTaskElasticNetCV().fit(train_x, train_y)
elif model_type == 'OrthogonalMatchingPursuit':
model = linear_model.OrthogonalMatchingPursuit().fit(train_x, train_y)
elif model_type == 'OrthogonalMatchingPursuitCV':
model = linear_model.OrthogonalMatchingPursuitCV().fit(train_x, train_y)
elif model_type == 'PassiveAggressiveClassifier':
model = linear_model.PassiveAggressiveClassifier(class_weight=class_weight).fit(train_x, train_y)
elif model_type == 'PassiveAggressiveRegressor':
model = linear_model.PassiveAggressiveRegressor().fit(train_x, train_y)
elif model_type == 'Perceptron':
model = linear_model.Perceptron(class_weight=class_weight).fit(train_x, train_y)
elif model_type == 'RandomizedLasso':
model = linear_model.RandomizedLasso().fit(train_x, train_y)
elif model_type == 'RandomizedLogisticRegression':
model = linear_model.RandomizedLogisticRegression().fit(train_x, train_y)
elif model_type == 'RANSACRegressor':
model = linear_model.RANSACRegressor().fit(train_x, train_y)
elif model_type == 'Ridge':
model = linear_model.Ridge().fit(train_x, train_y)
elif model_type == 'RidgeClassifier':
model = linear_model.RidgeClassifier(class_weight=class_weight).fit(train_x, train_y)
elif model_type == 'RidgeClassifierCV':
model = linear_model.RidgeClassifierCV(class_weight=class_weight).fit(train_x, train_y)
elif model_type == 'RidgeCV':
model = linear_model.RidgeCV().fit(train_x, train_y)
elif model_type == 'SGDClassifier':
model = linear_model.SGDClassifier(class_weight=class_weight).fit(train_x, train_y)
elif model_type == 'SGDRegressor':
model = linear_model.SGDRegressor().fit(train_x, train_y)
elif model_type == 'TheilSenRegressor':
model = linear_model.TheilSenRegressor().fit(train_x, train_y)
elif model_type == 'lars_path':
model = linear_model.lars_path().fit(train_x, train_y)
elif model_type == 'lasso_path':
model = linear_model.lasso_path().fit(train_x, train_y)
elif model_type == 'lasso_stability_path':
model = linear_model.lasso_stability_path().fit(train_x, train_y)
elif model_type == 'logistic_regression_path':
model = linear_model.logistic_regression_path(class_weight=class_weight).fit(train_x, train_y)
elif model_type == 'orthogonal_mp':
model = linear_model.orthogonal_mp().fit(train_x, train_y)
elif model_type == 'orthogonal_mp_gram':
model = linear_model.orthogonal_mp_gram().fit(train_x, train_y)
elif model_type == 'LinearSVC':
model = svm.LinearSVC(class_weight=class_weight).fit(train_x, train_y)
elif model_type == 'SVC':
model = svm.SVC(class_weight=class_weight, degree=3).fit(train_x, train_y)
else:
raise NotImplementedError('Model not implemented')
logger.info("Finished training.")
endTrainTime = time()
trainTime = endTrainTime - startTrainTime
logger.info("Training time : %d seconds" % trainTime)
logger.info("Start predicting train set...")
train_pred_y = model.predict(train_x)
logger.info("Finished predicting train set.")
logger.info("Start predicting test set...")
test_pred_y = model.predict(test_x)
logger.info("Finished predicting test set.")
endTestTime = time()
testTime = endTestTime - endTrainTime
logger.info("Testing time : %d seconds" % testTime)
totalTime += trainTime + testTime
train_pred_y = np.round(train_pred_y)
test_pred_y = np.round(test_pred_y)
np.savetxt(out_dir + '/preds/best_test_pred' + '.txt', test_pred_y, fmt='%i')
logger.info('[TRAIN] Acc: %.3f' % (accuracy_score(train_y, train_pred_y)))
logger.info('[TEST] Acc: %.3f' % (accuracy_score(test_y, test_pred_y)))
return accuracy_score(test_y, test_pred_y)
