class EXTRATREE():
"""docstring for ClassName"""
def __init__(self, ExtraTreesRegressor, N):
self.cores_number = int(np.ceil(multiprocessing.cpu_count() / N))
self.model = ExtraTreesRegressor(bootstrap=False,
criterion='mse',
max_depth=None,
max_features='auto',
max_leaf_nodes=None,
min_impurity_decrease=0.0,
min_impurity_split=None,
min_samples_leaf=1,
min_samples_split=2,
min_weight_fraction_leaf=0.0,
n_estimators=200,
n_jobs=self.cores_number,
oob_score=False,
random_state=None,
verbose=True,
warm_start=False)
print("ExtraTreesRegressor Cores: ", self.cores_number)
def fit(self, X_train, y_train, X_test, y_test, error_type="MAE"):
error_dict = {"MSE": "mse", "MAE": "mae"}
error_metric = error_dict[error_type]
self.model.set_params(criterion=error_metric)
self.model.fit(X_train, y_train)
def predict(self, X_test):
prediction = self.model.predict(X_test)
return (prediction)
def __init__(self, nb_classes, bags=1, params={}):
# params
self.params = params
#common
self.nb_classes = nb_classes
self.bags = bags
self.bags_models = tuple()
self.train_y = None
for bag in range(self.bags):
model = ExtraTreesRegressor()
model.set_params(**self.params)
model.set_params(random_state = (self.params['random_state'] + bag))
self.bags_models = self.bags_models + (model, )
def Extra_trees_regression(X_train, y_train, X_test, params):
# Случайный поиск по сетке
if hyperparameters == 'RandomGridSearch':
# Осуществляем поиск по сетке с кросс-валидацией (число фолдов равно 3)
max_depth = [5, 10, 15, 20, 25]
min_samples_split = [2, 5, 10]
max_leaf_nodes = [10, 50, 100]
param_grid = {'max_depth': max_depth, 'min_samples_split': min_samples_split, 'max_leaf_nodes': max_leaf_nodes}
# Задаем модель, которую будем обучать
estimator = ExtraTreesRegressor(n_estimators = 200, n_jobs = 8)
# Производим обучение модели с заданными вариантами параметров (осуществляем поиск по сетке)
optimizer = RandomizedSearchCV(estimator, param_grid, n_iter = 5, cv = 3, iid = 'deprecated', scoring = 'neg_mean_absolute_error')
optimizer.fit(X_train, y_train)
regression = optimizer.best_estimator_
predicted = regression.predict(X_test)
validation_score = optimizer.best_score_
# Полный поиск по сетке
elif hyperparameters == 'GridSearch':
max_depth = [5, 10, 15, 20, 25]
min_samples_split = [2, 5, 10]
max_leaf_nodes = [10, 50, 100]
param_grid = {'max_depth': max_depth, 'min_samples_split': min_samples_split,'max_leaf_nodes': max_leaf_nodes}
# Задаем модель, которую будем обучать
estimator = ExtraTreesRegressor(n_estimators = 200, n_jobs = 8)
# Производим обучение модели с заданными вариантами параметров (осуществляем поиск по сетке)
optimizer = GridSearchCV(estimator, param_grid, cv = 3, iid = 'deprecated', scoring = 'neg_mean_absolute_error')
optimizer.fit(X_train, np.ravel(y_train))
regression = optimizer.best_estimator_
predicted = regression.predict(X_test)
validation_score = optimizer.best_score_
elif hyperparameters == 'Custom':
estimator = ExtraTreesRegressor()
# Задаем нужные параметры
estimator.set_params(**params)
# Проверка по кросс-валидации
fold = KFold(n_splits = 3, shuffle = True)
validation_score = cross_val_score(estimator = estimator, X = X_train, y = y_train, cv = fold, scoring = 'neg_mean_absolute_error')
# Обучаем модель уже на всех данных
estimator.fit(X_train, np.ravel(y_train))
predicted = estimator.predict(X_test)
return(predicted, validation_score)
def extra_trees_regression(X_train,
y_train,
X_test,
params,
use_cv: bool = True):
# If there are not enough points for cross validation
if use_cv is False:
if params is None:
model = ExtraTreesRegressor()
else:
model = ExtraTreesRegressor(**params)
model.fit(X_train, y_train)
predicted = model.predict(X_test)
# Calculate score on train
train_predicted = model.predict(X_train)
validation_score = mean_absolute_error(
np.ravel(y_train), np.ravel(train_predicted))
return predicted, validation_score
# Random grid search
if hyperparameters == 'RandomGridSearch':
# Carry out a random grid search with cross-validation (the number of folds is 3)
max_depth = [5, 10, 15, 20, 25]
min_samples_split = [2, 5, 10]
max_leaf_nodes = [10, 50, 100]
param_grid = {
'max_depth': max_depth,
'min_samples_split': min_samples_split,
'max_leaf_nodes': max_leaf_nodes
}
# Set the model to be trained
estimator = ExtraTreesRegressor(n_estimators=50, n_jobs=-1)
# Train the model with the given options of parameters
optimizer = RandomizedSearchCV(
estimator,
param_grid,
n_iter=5,
cv=3,
iid='deprecated',
scoring='neg_mean_absolute_error')
optimizer.fit(X_train, y_train)
regression = optimizer.best_estimator_
predicted = regression.predict(X_test)
validation_score = optimizer.best_score_
# Full grid search
elif hyperparameters == 'GridSearch':
max_depth = [5, 10, 15, 20, 25]
min_samples_split = [2, 5, 10]
max_leaf_nodes = [10, 50, 100]
param_grid = {
'max_depth': max_depth,
'min_samples_split': min_samples_split,
'max_leaf_nodes': max_leaf_nodes
}
# Set the model to be trained
estimator = ExtraTreesRegressor(n_estimators=50, n_jobs=-1)
# Train the model with the given options of parameters
optimizer = GridSearchCV(estimator,
param_grid,
cv=3,
iid='deprecated',
scoring='neg_mean_absolute_error')
optimizer.fit(X_train, np.ravel(y_train))
regression = optimizer.best_estimator_
predicted = regression.predict(X_test)
validation_score = optimizer.best_score_
elif hyperparameters == 'Custom':
estimator = ExtraTreesRegressor()
# Set the params
estimator.set_params(**params)
# Cross-validation
fold = KFold(n_splits=3, shuffle=True)
validation_score = cross_val_score(
estimator=estimator,
X=X_train,
y=y_train,
cv=fold,
scoring='neg_mean_absolute_error')
estimator.fit(X_train, np.ravel(y_train))
predicted = estimator.predict(X_test)
return predicted, validation_score
from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_error
from sklearn.model_selection import train_test_split
import pickle
x, y = datahelper.get_xy('data/', num_hours=3, error_minutes=15)
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2)
extra_trees = ExtraTreesRegressor(
n_jobs=-1) # n_jobs=-1 is used for parallel calculations without limit
estimators = np.arange(10, 1000, 10)
scores = dict()
current_index = 0
for n in estimators:
extra_trees.set_params(n_estimators=n)
extra_trees.fit(x_train, y_train)
scores[current_index] = extra_trees.score(x_test, y_test)
current_index += 1
sorted_by_scores = [(k, scores[k])
for k in sorted(scores, key=scores.get, reverse=True)]
index, score = sorted_by_scores[0]
extra_trees.set_params(n_estimators=estimators[index])
extra_trees.fit(x_train, y_train)
filename = '../models/extra_trees_model.sav'
print('Saving model with ', estimators[index], ' estimators to file ',
filename)
with open(filename, 'wb') as h:
import ch9util
from tempfile import mkdtemp
import os
import joblib
X_train, X_test, y_train, y_test = ch9util.temp_split()
params = {
'min_samples_split': [1, 3],
'bootstrap': [True, False],
'min_samples_leaf': [3, 4]
}
gscv = GridSearchCV(ExtraTreesRegressor(random_state=41),
param_grid=params,
cv=5)
gscv.fit(X_train, y_train)
preds = gscv.predict(X_test)
ch9util.npy_save('etr.npy', preds)
dir = mkdtemp()
pkl = os.path.join(dir, 'params.pkl')
joblib.dump(gscv.best_params_, pkl)
params = joblib.load(pkl)
print('Best params', gscv.best_params_)
print('From pkl', params)
est = ExtraTreesRegressor(random_state=41)
est.set_params(**params)
est.fit(X_train, y_train)
preds2 = est.predict(X_test)
print('Max diff', (preds - preds2).max())
from sklearn.grid_search import GridSearchCV
from sklearn.ensemble import ExtraTreesRegressor
import ch9util
from tempfile import mkdtemp
import os
import joblib
X_train, X_test, y_train, y_test = ch9util.temp_split()
params = {'min_samples_split': [1, 3],
'bootstrap': [True, False],
'min_samples_leaf': [3, 4]}
gscv = GridSearchCV(ExtraTreesRegressor(random_state=41),
param_grid=params, cv=5)
gscv.fit(X_train, y_train)
preds = gscv.predict(X_test)
ch9util.npy_save('etr.npy', preds)
dir = mkdtemp()
pkl = os.path.join(dir, 'params.pkl')
joblib.dump(gscv.best_params_, pkl)
params = joblib.load(pkl)
print('Best params', gscv.best_params_)
print('From pkl', params)
est = ExtraTreesRegressor(random_state=41)
est.set_params(**params)
est.fit(X_train, y_train)
preds2 = est.predict(X_test)
print('Max diff', (preds - preds2).max())
