import numpy as np
import xgboost as xgb
from hyperopt import hp
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.pipeline import Pipeline
from config import random_seed
from utils.python_utils import quniform_int
steps = [
('lda', LinearDiscriminantAnalysis(n_components=55)),
# ('xgb', xgb.XGBClassifier(n_estimators=5900, max_depth=11, min_child_weight=4, subsample=0.932626370862, gamma=0.7, colsample_bytree=0.85, learning_rate=0.125, silent=True, nthread=3, seed=random_seed))
('xgb',
xgb.XGBClassifier(n_estimators=5900,
silent=True,
nthread=3,
seed=random_seed))
]
model = Pipeline(steps=steps)
params_space = {
'lda__n_components': quniform_int('n_components', 10, 500, 5),
# 'xgb__max_depth': quniform_int('max_depth', 10, 30, 1),
# 'xgb__min_child_weight': hp.quniform('min_child_weight', 1, 20, 1),
# 'xgb__subsample': hp.uniform('subsample', 0.8, 1),
'xgb__n_estimators': quniform_int('n_estimators', 1000, 10000, 50),
# 'xgb__learning_rate': hp.loguniform('learning_rate', np.log(0.0001), np.log(0.5)) - 0.0001,
# 'xgb__gamma': hp.loguniform('gamma', np.log(0.0001), np.log(5)) - 0.0001,
# 'xgb__colsample_bytree': hp.quniform('colsample_bytree', 0.5, 1, 0.05)
}
xgb.XGBClassifier(n_estimators=2900,
max_depth=23,
min_child_weight=8,
subsample=0.823469937115,
gamma=0.000220375249699,
colsample_bytree=0.7,
learning_rate=0.387889737181,
silent=True,
nthread=16,
seed=random_seed))]
model = Pipeline(steps=steps)
params_space = {
'xgb__max_depth':
quniform_int('max_depth', 5, 30, 1),
'xgb__min_child_weight':
hp.quniform('min_child_weight', 1, 20, 1),
'xgb__subsample':
hp.uniform('subsample', 0.8, 1),
'xgb__n_estimators':
quniform_int('n_estimators', 1000, 10000, 50),
'xgb__learning_rate':
hp.loguniform('learning_rate', np.log(0.0001), np.log(0.5)) - 0.0001,
'xgb__gamma':
hp.loguniform('gamma', np.log(0.0001), np.log(5)) - 0.0001,
'xgb__colsample_bytree':
hp.quniform('colsample_bytree', 0.5, 1, 0.05),
'xgb__seed':
random_seed
}
from hyperopt import hp
from sklearn.ensemble import RandomForestClassifier
from sklearn.pipeline import Pipeline
from config import random_seed
from utils.python_utils import quniform_int
steps = [('rf',
RandomForestClassifier(n_estimators=1000,
n_jobs=2,
random_state=random_seed))]
model = Pipeline(steps=steps)
params_space = {
'rf__max_depth': quniform_int('max_depth', 2, 30, 1),
'rf__criterion': hp.choice('criterion', ["gini", "entropy"]),
'rf__n_estimators': quniform_int('n_estimators', 1000, 10000, 50),
'rf__min_samples_split': quniform_int('min_samples_split', 2, 100, 1),
}
import numpy as np
from hyperopt import hp
from sklearn.neighbors import KNeighborsClassifier
from config import random_seed
from utils.python_utils import quniform_int
from imblearn.pipeline import Pipeline
from imblearn.over_sampling import EditedNearestNeighbours
steps = [
('oversampler', EditedNearestNeighbours(random_state=random_seed)),
('knn', KNeighborsClassifier(n_neighbors=5, n_jobs=-1)),
]
model = Pipeline(steps=steps)
params_space = {
'knn__n_neighbors': quniform_int('n_neighbors', 1, 50, 2),
'knn__weights': hp.choice('weights', ['uniform', 'distance']),
'knn__p': hp.quniform('p', 2.5, 5.5, 1),
}
xgb.XGBClassifier(n_estimators=6700,
max_depth=11,
min_child_weight=9,
subsample=0.900152352061,
gamma=0.188234394605,
colsample_bytree=0.8,
learning_rate=0.00540318190441,
silent=True,
nthread=1,
seed=random_seed))]
model = Pipeline(steps=steps)
params_space = {
'pca__n_components':
quniform_int('n_components', 10, 75, 1),
'xgb__max_depth':
quniform_int('max_depth', 10, 30, 1),
'xgb__min_child_weight':
hp.quniform('min_child_weight', 1, 20, 1),
'xgb__subsample':
hp.uniform('subsample', 0.8, 1),
'xgb__n_estimators':
quniform_int('n_estimators', 1000, 10000, 50),
'xgb__learning_rate':
hp.loguniform('learning_rate', np.log(0.0001), np.log(0.5)) - 0.0001,
'xgb__gamma':
hp.loguniform('gamma', np.log(0.0001), np.log(5)) - 0.0001,
'xgb__colsample_bytree':
hp.quniform('colsample_bytree', 0.5, 1, 0.05)
}
import numpy as np
import xgboost as xgb
from hyperopt import hp
from sklearn.decomposition import FastICA
from sklearn.pipeline import Pipeline
from config import random_seed
from utils.python_utils import quniform_int
steps = [
('ica', FastICA(n_components=51, random_state=random_seed)),
('xgb', xgb.XGBClassifier(n_estimators=5900, max_depth=11, min_child_weight=4, subsample=0.932626370862, gamma=0.7, colsample_bytree=0.85, learning_rate=0.125, silent=True, nthread=1, seed=random_seed))
]
model = Pipeline(steps=steps)
params_space = {
'pca__n_components': quniform_int('n_components', 10, 75, 1),
'xgb__max_depth': quniform_int('max_depth', 10, 30, 1),
'xgb__min_child_weight': hp.quniform('min_child_weight', 1, 20, 1),
'xgb__subsample': hp.uniform('subsample', 0.8, 1),
'xgb__n_estimators': quniform_int('n_estimators', 1000, 10000, 50),
'xgb__learning_rate': hp.loguniform('learning_rate', np.log(0.0001), np.log(0.5)) - 0.0001,
'xgb__gamma': hp.loguniform('gamma', np.log(0.0001), np.log(5)) - 0.0001,
'xgb__colsample_bytree': hp.quniform('colsample_bytree', 0.5, 1, 0.05)
}
import numpy as np
import xgboost as xgb
from hyperopt import hp
from imblearn.pipeline import Pipeline
from imblearn.under_sampling import OneSidedSelection
from config import random_seed
from utils.python_utils import quniform_int
steps = [
('undersampler', OneSidedSelection(random_state = random_seed)),
('xgb', xgb.XGBClassifier(n_estimators=1000, silent=True, nthread=3, seed=random_seed))
]
model = Pipeline(steps=steps)
params_space = {
'xgb__max_depth': quniform_int('max_depth', 10, 30, 1),
'xgb__min_child_weight': hp.quniform('min_child_weight', 1, 20, 1),
'xgb__subsample': hp.uniform('subsample', 0.8, 1),
'xgb__n_estimators': quniform_int('n_estimators', 1000, 10000, 50),
'xgb__learning_rate': hp.loguniform('learning_rate', np.log(0.0001), np.log(0.5)) - 0.0001,
'xgb__gamma': hp.loguniform('gamma', np.log(0.0001), np.log(5)) - 0.0001,
'xgb__colsample_bytree': hp.quniform('colsample_bytree', 0.5, 1, 0.05)
}