def fn(params):
global counter
counter +=1
params['C'] = params['C'] / 10
params['max_iter'] = int(1.3 ** params['max_iter'])
model_id = qm.add_by_params(
LogisticRegression(
n_jobs=-1,
max_iter=params['max_iter'],
solver=params['solver'],
C=params['C']
),
'hyperopt log_regr',
predict_fn='predict_proba'
)
res = cv.cross_val(model_id, params['data_id'], seed=1000, early_stop_cv=lambda x: x>CV_SCORE_TO_STOP)
res = np.float64(res)
res_arr = [res]
# if res < CV_SCORE_TO_STOP:
# for i in range(7):
# res = cv.cross_val(model_id, data_id, seed=1001 + i, force=True)
# res = np.float64(res)
# res_arr.append(res)
print(params['data_id'], model_id, "{}/{}".format(counter, rounds), res_arr, datetime.datetime.now(), params)
return np.mean(res_arr)
def fn(params):
global counter
counter += 1
params['max_features'] = params['max_features'] / 10
params['n_estimators'] = int(1.3**params['n_estimators'])
model_id = qm.add_by_params(ExtraTreesClassifier(
max_depth=int(params['max_depth']),
n_estimators=int(params['n_estimators']),
max_features=float(params['max_features']),
n_jobs=-1),
'hyperopt rand_forest',
predict_fn='predict_proba')
res = cv.cross_val(model_id,
params['data_id'],
seed=1000,
early_stop_cv=lambda x: x > CV_SCORE_TO_STOP)
res = np.float64(res)
res_arr = [res]
# if res < CV_SCORE_TO_STOP:
# for i in range(7):
# res = cv.cross_val(model_id, data_id, seed=1001 + i, force=True)
# res = np.float64(res)
# res_arr.append(res)
print(params['data_id'], model_id, "{}/{}".format(counter, rounds),
res_arr, datetime.datetime.now(), params)
return np.mean(res_arr)
def fn(params):
global counter
counter += 1
params['epochs'] = int(1.3**params['epochs'])
model_id = qm.add_by_params(
QNN2(middle_dim=int(params['middle_dim']),
epochs=int(params['epochs'])), 'hyperopt nn1')
res = cv.cross_val(model_id,
params['data_id'],
seed=1000,
early_stop_cv=lambda x: x > CV_SCORE_TO_STOP)
res = np.float64(res)
res_arr = [res]
# if res < CV_SCORE_TO_STOP:
# for i in range(7):
# res = cv.cross_val(model_id, data_id, seed=1001 + i, force=True)
# res = np.float64(res)
# res_arr.append(res)
print(params['data_id'], model_id, "{}/{}".format(counter, rounds),
res_arr, datetime.datetime.now(), params)
return np.mean(res_arr)
def fn(params):
global counter
counter += 1
data_id = params['data_id']
del params['data_id']
params['num_boost_rounds'] = int(1.3**params['num_boost_rounds'])
params['eta'] = round(1 / (1.3**params['eta']), 4)
params['lr_decay'] = round(1 / (2**params['lr_decay']), 4)
params['subsample'] = params['subsample'] / 10
params['colsample_bytree'] = params['colsample_bytree'] / 10
params['colsample_bylevel'] = params['colsample_bylevel'] / 10
params['gamma'] = round(5**params['gamma'], 3)
params['alpha'] = round(5**params['alpha'], 3)
model_id = qm.add_by_params(
QXgb2(
booster='gbtree',
objective='binary:logistic',
eval_metric='logloss',
subsample=params['subsample'],
colsample_bytree=params['colsample_bytree'],
colsample_bylevel=params['colsample_bylevel'],
eta=params['eta'],
gamma=params['gamma'],
alpha=params['alpha'],
max_depth=params['maxdepth'],
num_boost_round=params['num_boost_rounds'],
lr_decay=params['lr_decay'],
), 'hyperopt xgb')
res = cv.cross_val(model_id,
data_id,
seed=1000,
early_stop_cv=lambda x: x > CV_SCORE_TO_STOP)
res = np.float64(res)
res_arr = [res]
if res < CV_SCORE_TO_STOP:
for i in range(7):
res = cv.cross_val(model_id,
data_id,
seed=1001 + i,
force=True)
res = np.float64(res)
res_arr.append(res)
print(data_id, model_id, "{}/{}".format(counter, rounds), res_arr,
datetime.datetime.now(), params)
return np.mean(res_arr)
for r in res:
for m in r['models'].split(','):
results.append([int(m), r['data_id']])
for i in range(ROUNDS):
random.shuffle(results)
models = list(results[:random.randint(2, 10)])
models = sorted(models, key=lambda x: (x[0], x[1]))
print('{}/{}'.format(i, ROUNDS), models)
try:
model_id = qm.add_by_params(
QAvg(models)
)
print(cv.cross_val(model_id, -1, early_stop_cv=lambda x: x>CV_SCORE_TO_STOP))
conn.execute("update qml_models set level=2 where model_id={}".format(model_id))
# model_id = qm.add_by_params(
# QAvg(models, is_geom=True)
# )
# print(cv.cross_val(model_id, -1, early_stop_cv=lambda x: x>CV_SCORE_TO_STOP))
# conn.execute("update qml_models set level=2 where model_id={}".format(model_id))
model_id = qm.add_by_params(
QRankedAvg(models)
)
print(cv.cross_val(model_id, -1, early_stop_cv=lambda x: x>CV_SCORE_TO_STOP))
conn.execute("update qml_models set level=2 where model_id={}".format(model_id))
results = []
best_models = []
for r in res:
for m in r['models'].split(','):
results.append([int(m), r['data_id'], 1000])
for i in range(ROUNDS):
random.shuffle(results)
models = list(results[:random.randint(4, 25)])
models = sorted(models, key=lambda x: (x[0], x[1]))
print('{}/{}'.format(i, ROUNDS), models)
try:
model_id2 = qm.add_by_params(Ridge(alpha=0.05))
if len(models) >= 4:
model_id = qm.add_by_params(
QStackModel(models,
second_layer_model=model_id2,
nsplits=2))
conn.execute(
"update qml_models set level=2 where model_id={}".format(
model_id))
print(
model_id,
cv.cross_val(model_id,
-1,
early_stop_cv=lambda x: x > CV_SCORE_TO_STOP))
def fn(params):
global counter
counter += 1
params['C'] = params['C'] / 10
params['max_iter'] = int(1.3**params['max_iter'])
model_id = qm.add_by_params(LogisticRegression(
n_jobs=-1,
max_iter=params['max_iter'],
solver=params['solver'],
C=params['C']),
'hyperopt log_regr',
predict_fn='predict_proba')
model_id_main = qm.add_by_params(
QStackModel(
[[1747, 69, 1000], [101655, 266, 1000], [1831, 266, 1000],
[101457, 266, 1000]
# [1747, 69, 1000],
# [1747, 66, 1000],
# [1747, 47, 1000],
#[1747, 69, 1001],
# [101340, 69, 1000],
# [101340, 66, 1000],
# [101340, 47, 1000],
# #[101340, 69, 1001],
# [101331, 69, 1000],
# [101331, 66, 1000],
# [101331, 47, 1000],
# #[101331, 69, 1001],
# [101261, 69, 1000],
# [101261, 66, 1000],
# [101261, 47, 1000],
#
# [101655, 266, 1000],
# [101655, 269, 1000],
#
# [1831, 266, 1000],
# [1831, 269, 1000],
#
# [101457, 266, 1000],
# [101457, 269, 1000],
#
# [101657, 269, 1000],
# [101657, 266, 1000],
#
# [1841, 269, 1000],
# [1841, 266, 1000],
#
# [101411, 269, 1000],
# [101411, 266, 1000],
],
second_layer_model=model_id,
nsplits=5),
level=-2)
res = cv.cross_val(model_id_main,
params['data_id'],
seed=1000,
early_stop_cv=lambda x: x > CV_SCORE_TO_STOP)
res = np.float64(res)
res_arr = [res]
# if res < CV_SCORE_TO_STOP:
# for i in range(7):
# res = cv.cross_val(model_id, data_id, seed=1001 + i, force=True)
# res = np.float64(res)
# res_arr.append(res)
print(params['data_id'], model_id, "{}/{}".format(counter, rounds),
res_arr, datetime.datetime.now(), params)
return np.mean(res_arr)
import datetime
import random
from hyperopt import hp, fmin, tpe
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
import workdir.classes.config # loads local config
from qml.cv import QCV
from qml.helpers import get_engine
from qml.models import QXgb, QAvg, QRankedAvg, QStackModel, QPostProcessingModel, QRankedByLineAvg, QAvgOneModelData
from workdir.classes.models import qm
cv = QCV(qm)
# print(cv.cross_val(465, 15))
# print(cv.cross_val(465, 16))
# print(cv.cross_val(466, 15))
# print(cv.cross_val(466, 16))
new_model_id = qm.add_by_params(QAvgOneModelData(636, 8), level=-2)
print(new_model_id)
qm.qpredict(new_model_id, 25)
# # print(new_model_id)
#
# for model_id in [416]: #450
# for data_id in [25]:#13,15,16,17
#
# for i in range(8):
# res = cv.cross_val(model_id, data_id, seed=1000 + i, force=True)
# print('##', model_id, data_id, i, res)
import workdir.classes.config
from qml.cv import QCV
from qml.models import QXgb, QAvg, QAvgOneModelData
from workdir.classes.models import qm
cv = QCV(qm)
# model_id = qm.add_by_params(
# QXgb(
# ** {"alpha": 1.0, "booster": "gbtree", "colsample_bylevel": 0.7, "colsample_bytree": 0.8, "eta": 0.004, "eval_metric": "logloss",
# "gamma": 0.2, "max_depth": 4, "num_boost_round": 2015, "objective": "binary:logistic", "subsample": 0.8, "tree_method": "hist"}
# ),
# 'hyperopt xgb', level=-1
# )
model_id = qm.add_by_params(QAvgOneModelData(416, 2), level=-2)
cv.features_sel_del(
model_id,
23,
early_stop_cv=lambda x: x < 0.557, # minmax
log_file='workdir/logs/data23_sub_cols3.txt',
exclude=[
'data__daily__data_vol_mb__median__max',
'data__daily__cell_count__min',
'voice__hourly__voice_dur_min__sum__max',
'voice__daily__voice_dur_min__sum__median',
'data__daily__data_vol_mb__sum__min',
'data__daily__data_vol_mb__avg__avg',
'voice__hourly__voice_dur_min__median__max',
'voice__hourly__voice_dur_min__sum__min',
import datetime
import numpy as np
from hyperopt import hp, fmin, tpe
import os
import sys
sys.path.insert(0, os.getcwd())
import workdir.classes.config
from qml.cv import QCV
from qml.models import QXgb, QAvg, QAvgOneModelData
from workdir.classes.models import qm
cv = QCV(qm)
model_id = qm.add_by_params(
QXgb(
** {"alpha": 1.0, "booster": "gbtree", "colsample_bylevel": 0.7, "colsample_bytree": 0.8, "eta": 0.004, "eval_metric": "logloss",
"gamma": 0.2, "max_depth": 4, "num_boost_round": 2015, "objective": "binary:logistic", "subsample": 0.8, "tree_method": "hist"}
),
'hyperopt xgb', level=-1
)
model_id =qm.add_by_params(QAvgOneModelData(model_id, 3), level=-2)
cv.features_sel_del(model_id, 66, early_stop_cv=lambda x: x>0.5414, log_file='workdir/logs/feat19.txt', exclude=[])
def fn(params):
global counter
counter +=1
data_id = params['data_id']
del params['data_id']
params['num_boost_rounds'] = int(1.3**params['num_boost_rounds'])
params['eta'] = round(1 / (1.3**params['eta']), 4)
params['subsample'] = 1#params['subsample']/10
params['colsample_bytree'] = 1#params['colsample_bytree']/10
params['colsample_bylevel'] = 1#params['colsample_bylevel']/10
params['gamma'] = round(5 ** params['gamma'], 3)
params['alpha'] = round(5 ** params['alpha'], 3)
model_id = qm.add_by_params(
QXgb(
booster='gbtree',
objective='binary:logistic',
eval_metric='logloss',
subsample=params['subsample'],
colsample_bytree=params['colsample_bytree'],
colsample_bylevel=params['colsample_bylevel'],
eta=params['eta'],
gamma=params['gamma'],
alpha=params['alpha'],
max_depth=params['maxdepth'],
num_boost_round=params['num_boost_rounds']#, tree_method='hist'
),
'hyperopt xgb'
)
model_id_main = qm.add_by_params(
QStackModel(
[
[1747, 69, 1000],
[101655, 266, 1000],
[1831, 266, 1000],
[101457, 266, 1000]
# [1747, 69, 1000],
# [1747, 66, 1000],
# [1747, 47, 1000],
#[1747, 69, 1001],
# [101340, 69, 1000],
# [101340, 66, 1000],
# [101340, 47, 1000],
# #[101340, 69, 1001],
# [101331, 69, 1000],
# [101331, 66, 1000],
# [101331, 47, 1000],
# #[101331, 69, 1001],
# [101261, 69, 1000],
# [101261, 66, 1000],
# [101261, 47, 1000],
#
# [101655, 266, 1000],
# [101655, 269, 1000],
#
# [1831, 266, 1000],
# [1831, 269, 1000],
#
# [101457, 266, 1000],
# [101457, 269, 1000],
#
# [101657, 269, 1000],
# [101657, 266, 1000],
#
# [1841, 269, 1000],
# [1841, 266, 1000],
#
# [101411, 269, 1000],
# [101411, 266, 1000],
],
second_layer_model=model_id,
nsplits=5
), level=-2
)
res = cv.cross_val(model_id_main, data_id, seed=1000, early_stop_cv=lambda x: x>CV_SCORE_TO_STOP)
res = np.float64(res)
res_arr = [res]
# if res < CV_SCORE_TO_STOP:
# for i in range(7):
# res = cv.cross_val(model_id, data_id, seed=1001 + i, force=True)
# res = np.float64(res)
# res_arr.append(res)
print(data_id, model_id, "{}/{}".format(counter, rounds), res_arr, datetime.datetime.now(), params)
return np.mean(res_arr)
group by data_id, cls, descr
""".format(CV_SCORE_TO_SELECT)).fetchall()
results = []
for r in res:
for m in r['models'].split(','):
results.append([int(m), r['data_id'], 1000])
for i in range(5000):
random.shuffle(results)
models = list(results[:random.randint(2, 20)])
models = sorted(models, key=lambda x: (x[0], x[1]))
print('{}/{}'.format(i, ROUNDS), models)
model_id = qm.add_by_params(QAvg(models))
print(
cv.cross_val(model_id,
-1,
early_stop_cv=lambda x: x > CV_SCORE_TO_STOP))
conn.execute(
"update qml_models set level=3 where model_id={}".format(model_id))
# model_id = qm.add_by_params(
# QAvg(models, is_geom=True)
# )
# print(cv.cross_val(model_id, -1, early_stop_cv=lambda x: x>CV_SCORE_TO_STOP))
# conn.execute("update qml_models set level=3 where model_id={}".format(model_id))
#
# model_id = qm.add_by_params(
# QRankedAvg(models)
import workdir.classes.config
from qml.cv import QCV
from qml.models import QXgb, QAvg, QAvgOneModelData
from workdir.classes.models import qm
cv = QCV(qm)
model_id = qm.add_by_params(
QXgb(
**{
"alpha": 0.008,
"booster": "gbtree",
"colsample_bylevel": 0.9,
"colsample_bytree": 0.9,
"eta": 0.0024,
"eval_metric": "logloss",
"gamma": 0.04,
"max_depth": 4,
"num_boost_round": 2619,
"objective": "binary:logistic",
"subsample": 0.7,
"tree_method": "hist"
}),
'hyperopt xgb',
)
#model_id =qm.add_by_params(QAvgOneModelData(model_id, 8), level=-2)
cv.features_sel_add(
model_id,
60, [
'age', 'height', 'weight', 'ap_hi', 'ap_lo', 'smoke', 'alco', 'active',
