def randomforst_model_tpe():
estim = HyperoptEstimator(classifier=random_forest('my_clf'),
preprocessing=[pca('my_pca')],
algo=tpe.suggest,
max_evals=150,
trial_timeout=60,
verbose=0)
estim.fit(x_train, y_train)
print("f1score", f1_score(estim.predict(x_test), y_test))
print("accuracy score", accuracy_score(estim.predict(x_test), y_test))
print(estim.best_model())
def bench_classifiers(name):
classifiers = [
ada_boost(name + '.ada_boost'), # boo
gaussian_nb(name + '.gaussian_nb'), # eey
knn(name + '.knn', sparse_data=True), # eey
linear_discriminant_analysis(name + '.linear_discriminant_analysis', n_components=1), # eey
random_forest(name + '.random_forest'), # boo
sgd(name + '.sgd') # eey
]
if xgboost:
classifiers.append(xgboost_classification(name + '.xgboost')) # boo
return hp.choice('%s' % name, classifiers)
def tpe_classifier(name='clf'):
linear_svc_space = hp.choice('liblinear_combination',
[{'penalty': "l1", 'loss': "squared_hinge", 'dual': False},
{'penalty': "l2", 'loss': "hinge", 'dual': True},
{'penalty': "l2", 'loss': "squared_hinge", 'dual': True},
{'penalty': "l2", 'loss': "squared_hinge", 'dual': False}])
return hp.choice(name,
[gaussian_nb('hpsklearn_gaussian_nb'),
liblinear_svc('hpsklearn_liblinear_svc',
C=hp.choice('hpsklearn_liblinear_svc_c',
[1e-4, 1e-3, 1e-2, 1e-1, 0.5, 1., 5., 10., 15., 20., 25.]),
loss=linear_svc_space['loss'],
penalty=linear_svc_space['penalty'],
dual=linear_svc_space['dual'],
tol=hp.choice('hpsklearn_liblinear_svc_tol', [1e-5, 1e-4, 1e-3, 1e-2, 1e-1])
),
decision_tree('decision_tree',
criterion=hp.choice('decision_tree_criterion', ["gini", "entropy"]),
max_depth=hp.randint('decision_tree_max_depth', 10) + 1,
min_samples_split=hp.randint('decision_tree_min_samples_split', 19) + 2,
min_samples_leaf=hp.randint('decision_tree_min_samples_leaf', 20) + 1),
knn('knn',
n_neighbors=hp.randint('knn_n', 100) + 1,
weights=hp.choice('knn_weights', ['uniform', 'distance']),
p=hp.choice('knn_p', [1, 2])),
extra_trees('et',
n_estimators=100,
criterion=hp.choice('et_criterion', ["gini", "entropy"]),
max_features=hp.randint('et_max_features', 20) * 0.05 + 0.05,
min_samples_split=hp.randint('et_min_samples_split', 19) + 2,
min_samples_leaf=hp.randint('et_min_samples_leaf', 20) + 1,
bootstrap=hp.choice('et_bootstrap', [True, False])),
random_forest('rf',
n_estimators=100,
criterion=hp.choice('rf_criterion', ["gini", "entropy"]),
max_features=hp.randint('rf_max_features', 20) * 0.05 + 0.05,
min_samples_split=hp.randint('rf_min_samples_split', 19) + 2,
min_samples_leaf=hp.randint('rf_min_samples_leaf', 20) + 1,
bootstrap=hp.choice('rf_bootstrap', [True, False])),
gradient_boosting('gb',
n_estimators=100,
learning_rate=hp.choice('gb_lr', [1e-3, 1e-2, 1e-1, 0.5, 1.]),
max_depth=hp.randint('gb_max_depth', 10) + 1,
min_samples_split=hp.randint('gb_min_samples_split', 19) + 2,
min_samples_leaf=hp.randint('gb_min_samples_leaf', 20) + 1,
subsample=hp.randint('gb_subsample', 20) * 0.05 + 0.05,
max_features=hp.randint('gb_max_features', 20) * 0.05 + 0.05,
)
])
def main():
df_train = pd.read_csv('../train_dataset.csv')
df_test = pd.read_csv('../test_dataset.csv')
X_train, y_train = df_train.iloc[:, 2:].values, df_train.iloc[:, 0].values
X_test, y_test = df_test.iloc[:, 2:].values, df_test.iloc[:, 0].values
estim = HyperoptEstimator(classifier=random_forest('myDT'),
algo=tpe.suggest,
max_evals=150,
trial_timeout=120,
verbose=True)
estim.fit(X_train, y_train)
print("\n\n{}\n\n".format(estim.score(X_test, y_test)))
print("\n\n{}\n\n".format(estim.best_model()))
print("\ndata is loaded - next step > model testing\n")
n_job = 6
select_classes = [0, 1, 2, 3, 4, 5]
val_dist = X_val_mini.shape[0] / X_train_mini.shape[0]
name = 'my_est_oVa'
tic_mod_all = time.time()
select_alg = [
ada_boost(name + '.ada_boost'),
gaussian_nb(name + '.gaussian_nb'),
knn(name + '.knn', sparse_data=True),
linear_discriminant_analysis(name +
'.linear_discriminant_analysis',
n_components=1),
random_forest(name + '.random_forest'),
sgd(name + '.sgd'),
xgboost_classification(name + '.xgboost')
]
# fitting models
estim_one_vs_rest = dict()
# scoring models
algo_scoring = dict()
save_score_path = r'C:/Users/anden/PycharmProjects/NovelEEG/results'
for alg in [select_alg[args.index]]:
tic_mod = time.time()
print("~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
"running on %s" % (alg.name + '.one_V_all'),
"\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~")
clf_method = one_vs_rest(str(alg.name + '.one_V_all'),
def main():
# Download the data and split into training and test sets
iris = load_iris()
X = iris.data
y = iris.target
test_size = int(0.2 * len(y))
np.random.seed(13)
indices = np.random.permutation(len(X))
X_train = X[indices[:-test_size]]
y_train = y[indices[:-test_size]]
X_test = X[indices[-test_size:]]
y_test = y[indices[-test_size:]]
# for other datas, there will more complex data clearning
# list all machine learning algorithms for hyper params tuning
MLA = {
'rfc': [
RandomForestClassifier(),
#RandomForestClassifier (n_estimators=100, criterion="entropy", max_depth=5, max_features=0.5, random_state=1),
{
'n_estimators': [50,100,200], #default=1.0
'criterion': ['entropy'], #edfault: auto
'max_depth': [4,5,6], #default:ovr
#'min_samples_split': [5,10,.03,.05,.10],
'max_features': [.5],
'random_state': [1],
},
random_forest('my_rfc'),
],
'etc': [
ExtraTreesClassifier(),
#ExtraTreesClassifier (n_estimators=100, criterion="entropy", max_depth=5, max_features=0.5, random_state=1),
{
'n_estimators': [50,100,200], #default=1.0
'criterion': ['entropy'], #edfault: auto
'max_depth': [4,5,6], #default:ovr
'max_features': [.5],
'random_state': [1],
},
extra_trees('my_etc'),
],
'gbc': [
GradientBoostingClassifier(),
#GradientBoostingClassifier(n_estimators=100, learning_rate=0.1, max_depth=5, max_features=0.5, random_state=1),
{
#'loss': ['deviance', 'exponential'],
'learning_rate': [.1,.25,.5],
'n_estimators': [50,100,200],
#'criterion': ['friedman_mse', 'mse', 'mae'],
'max_depth': [4,5,6],
'max_features': [.5],
#'min_samples_split': [5,10,.03,.05,.10],
#'min_samples_leaf': [5,10,.03,.05,.10],
'random_state': [1],
},
gradient_boosting('my_rgc'),
],
'lr': [
LogisticRegression(),
#LogisticRegression(random_state=1)
{
#'fit_intercept': grid_bool,
#'penalty': ['l1','l2'],
#'solver': ['newton-cg', 'lbfgs', 'liblinear', 'sag', 'saga'],
'random_state': [1],
},
],
'svc': [
svm.SVC(),
{
#SVC - http://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html#sklearn.svm.SVC
#http://blog.hackerearth.com/simple-tutorial-svm-parameter-tuning-python-r
#'kernel': ['linear', 'poly', 'rbf', 'sigmoid'],
'C': [1,2,3,4,5], #default=1.0
'gamma': [.1, .25, .5, .75, 1.0], #edfault: auto
'decision_function_shape': ['ovo', 'ovr'], #default:ovr
'probability': [True],
'random_state': [0]
},
],
'xgb': [
XGBClassifier(),
{
#XGBClassifier - http://xgboost.readthedocs.io/en/latest/parameter.html
'learning_rate': [.01, .03, .05, .1, .25], #default: .3
'max_depth': [1,2,4,6,8,10], #default 2
'n_estimators': [10, 50, 100, 300],
'seed': [0]
},
]
}
# list some algorithms for HyperoptEstimator, but error !!!
#MLA2 = {
#'rfc': [
#random_forest('my_rfc'),
#],
#'etc': [
#extra_trees('my_etc'),
#],
#'gbc': [
#gradient_boosting('my_rgc'),
#],
#}
# list some algorithms for HyperoptEstimator, but error !!!
def opt(clf):
est = MLA[clf][0]
# ---------want to use Hyperopt, but has some errors !!!
#estim = HyperoptEstimator(classifier=MLA2[clf][0],
#preprocessing=[],
#algo=tpe.suggest,
#max_evals=3,
#trial_timeout=120)
#estim.fit( X_train, y_train )
#est = estim
# ---------want to use Hyperopt, but has some errors !!!
# use GridSearchCV, it's too slow
est = model_selection.GridSearchCV(estimator=est, param_grid=MLA[clf][1], cv=5) # --, scoring='roc_auc'
return est
# for StackNetClassifier
#models=[
######### First level ########
#[RandomForestClassifier(n_estimators=100, criterion="entropy", max_depth=5, max_features=0.5, random_state=1),
#ExtraTreesClassifier(n_estimators=100, criterion="entropy", max_depth=5, max_features=0.5, random_state=1),
#GradientBoostingClassifier(n_estimators=100, learning_rate=0.1, max_depth=5, max_features=0.5, random_state=1),
#LogisticRegression(random_state=1)
#],
######### Second level ########
#[RandomForestClassifier(n_estimators=200, criterion="entropy", max_depth=5, max_features=0.5, random_state=1)]
#]
models=[
######## First level ########
[
opt('rfc'),
opt('etc'),
#opt('gbc'),
#opt('lr'),
],
######## Second level ########
[
opt('rfc'),
],
]
# use StackNet to stacking the models
StackNetmodel=StackNetClassifier(models, folds=4, # --metric="auc",
restacking=False, use_retraining=True, use_proba=True,
random_state=12345, n_jobs=1, verbose=1)
StackNetmodel.fit(X_train, y_train)
from hyperopt import tpe
X = df[features].values
y = df["outcome"]
test_size = int(0.1 * len(y))
np.random.seed(10)
indices = np.random.permutation(len(X))
X_train = np.float64(X[indices[:-test_size]])
y_train = np.float64(y[indices[:-test_size]])
X_test = np.float64(X[indices[-test_size:]])
y_test = np.float64(y[indices[-test_size:]])
estim = HyperoptEstimator(algo=tpe.suggest,
trial_timeout=300,
classifier=random_forest('my_random_forest'))
estim.fit(X_train, y_train)
print(estim.score(X_test, y_test))
# <<show score here>>
print(estim.best_model())
# In[Another look at error: Out of bag error, plot written by Kian Ho]:
import matplotlib.pyplot as plt
from collections import OrderedDict
from sklearn.datasets import make_classification
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier
from sklearn.model_selection import RepeatedStratifiedKFold
from sklearn.metrics import *
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.decomposition import PCA
from sklearn.manifold import TSNE
import matplotlib.pyplot as plt
from hpsklearn import HyperoptEstimator, svc, random_forest, knn
from hyperopt import tpe
from sklearn.metrics import f1_score
def scorer(yt, yp):
return 1 - f1_score(yt, yp, average='macro')
if __name__ == '__main__':
np.random.seed(42)
train_X = np.load('data/train_X.npy')
test_X = np.load('data/test_X.npy')
train_Y = np.load('data/train_Y.npy')
test_Y = np.load('data/test_Y.npy')
estim = HyperoptEstimator(classifier=random_forest('rf'),
algo=tpe.suggest,
loss_fn=scorer,
max_evals=200,
trial_timeout=1200)
estim.fit(train_X, train_Y)
yp = estim.predict(test_X)
print(f1_score(test_Y, yp, average='macro'))