hyperparameter_hunter
v3.0.0 (Artemis)
自動保存並從實驗結果中學習，從而導致長期的持續優化，以紀念您的所有測試。
HyperParameterHunter為機器學習算法提供了一個包裝器，可保存所有重要數據。通過讓HyperParameterHunter進行錄製，組織和從測試中學習的辛勤工作來簡化實驗和超參數調整過程，同時使用了您已經做過的相同庫。不要讓任何實驗浪費，然後開始按原定的方式進行超參數優化。
pip install hyperparameter-hunter不要將超級參數獵人視為另一個優化庫，只有在進行超參數優化的時間時才出現。當然，它確實進行了優化，但是最好將HyperParameterHunter視為您自己的個人機器學習工具箱/助手。
這個想法是立即開始使用HyperGaremeterHunter。通過它運行所有基準/一次性實驗。
您使用HyperParameterHunter的越多，結果就越好。當然，如果您只將其用於優化，它將完成您想要的工作，但這缺少了HyperParameterHunter的點。
如果您一直在整個項目的整個過程中都使用它進行實驗和優化，那麼當您決定進行超參數優化時，HyperparameterHunter已經意識到您已經完成的所有工作，而這是HyperParameterHunter做一些出色的事情。它不會像其他庫那樣從頭開始優化。它從您已經通過它運行的所有實驗和以前的優化回合開始。
建立一個環境來組織實驗和優化結果。
我們執行的任何實驗或優化回合都將使用我們的主動環境。
from hyperparameter_hunter import Environment , CVExperiment
import pandas as pd
from sklearn . datasets import load_breast_cancer
from sklearn . model_selection import StratifiedKFold
data = load_breast_cancer ()
df = pd . DataFrame ( data = data . data , columns = data . feature_names )
df [ 'target' ] = data . target
env = Environment (
train_dataset = df , # Add holdout/test dataframes, too
results_path = 'path/to/results/directory' , # Where your result files will go
metrics = [ 'roc_auc_score' ], # Callables, or strings referring to `sklearn.metrics`
cv_type = StratifiedKFold , # Class, or string in `sklearn.model_selection`
cv_params = dict ( n_splits = 5 , shuffle = True , random_state = 32 )
)僅通過提供模型初始化器和超級參數來對您喜歡的庫進行實驗
# Same format used by `keras.wrappers.scikit_learn`. Nothing new to learn
def build_fn ( input_shape ): # `input_shape` calculated for you
model = Sequential ([
Dense ( 100 , kernel_initializer = 'uniform' , input_shape = input_shape , activation = 'relu' ),
Dropout ( 0.5 ),
Dense ( 1 , kernel_initializer = 'uniform' , activation = 'sigmoid' )
]) # All layer arguments saved (whether explicit or Keras default) for future use
model . compile ( optimizer = 'adam' , loss = 'binary_crossentropy' , metrics = [ 'accuracy' ])
return model
experiment = CVExperiment (
model_initializer = KerasClassifier ,
model_init_params = build_fn , # We interpret your build_fn to save hyperparameters in a useful, readable format
model_extra_params = dict (
callbacks = [ ReduceLROnPlateau ( patience = 5 )], # Use Keras callbacks
batch_size = 32 , epochs = 10 , verbose = 0 # Fit/predict arguments
)
) experiment = CVExperiment (
model_initializer = LinearSVC , # (Or any of the dozens of other SK-Learn algorithms)
model_init_params = dict ( penalty = 'l1' , C = 0.9 ) # Default values used and recorded for kwargs not given
) experiment = CVExperiment (
model_initializer = XGBClassifier ,
model_init_params = dict ( objective = 'reg:linear' , max_depth = 3 , n_estimators = 100 , subsample = 0.5 )
) experiment = CVExperiment (
model_initializer = LGBMClassifier ,
model_init_params = dict ( boosting_type = 'gbdt' , num_leaves = 31 , max_depth = - 1 , min_child_samples = 5 , subsample = 0.5 )
) experiment = CVExperiment (
model_initializer = CatboostClassifier ,
model_init_params = dict ( iterations = 500 , learning_rate = 0.01 , depth = 7 , allow_writing_files = False ),
model_extra_params = dict ( fit = dict ( verbose = True )) # Send kwargs to `fit` and other extra methods
) experiment = CVExperiment (
model_initializer = RGFClassifier ,
model_init_params = dict ( max_leaf = 1000 , algorithm = 'RGF' , min_samples_leaf = 10 )
)就像實驗一樣，但是如果您想優化超參數，請使用以下導入的類
from hyperparameter_hunter import Real , Integer , Categorical
from hyperparameter_hunter import optimization as opt def build_fn ( input_shape ):
model = Sequential ([
Dense ( Integer ( 50 , 150 ), input_shape = input_shape , activation = 'relu' ),
Dropout ( Real ( 0.2 , 0.7 )),
Dense ( 1 , activation = Categorical ([ 'sigmoid' , 'softmax' ]))
])
model . compile (
optimizer = Categorical ([ 'adam' , 'rmsprop' , 'sgd' , 'adadelta' ]),
loss = 'binary_crossentropy' , metrics = [ 'accuracy' ]
)
return model
optimizer = opt . RandomForestOptPro ( iterations = 7 )
optimizer . forge_experiment (
model_initializer = KerasClassifier ,
model_init_params = build_fn ,
model_extra_params = dict (
callbacks = [ ReduceLROnPlateau ( patience = Integer ( 5 , 10 ))],
batch_size = Categorical ([ 32 , 64 ]),
epochs = 10 , verbose = 0
)
)
optimizer . go () optimizer = opt . DummyOptPro ( iterations = 42 )
optimizer . forge_experiment (
model_initializer = AdaBoostClassifier , # (Or any of the dozens of other SKLearn algorithms)
model_init_params = dict (
n_estimators = Integer ( 75 , 150 ),
learning_rate = Real ( 0.8 , 1.3 ),
algorithm = 'SAMME.R'
)
)
optimizer . go () optimizer = opt . BayesianOptPro ( iterations = 10 )
optimizer . forge_experiment (
model_initializer = XGBClassifier ,
model_init_params = dict (
max_depth = Integer ( low = 2 , high = 20 ),
learning_rate = Real ( 0.0001 , 0.5 ),
n_estimators = 200 ,
subsample = 0.5 ,
booster = Categorical ([ 'gbtree' , 'gblinear' , 'dart' ]),
)
)
optimizer . go () optimizer = opt . BayesianOptPro ( iterations = 100 )
optimizer . forge_experiment (
model_initializer = LGBMClassifier ,
model_init_params = dict (
boosting_type = Categorical ([ 'gbdt' , 'dart' ]),
num_leaves = Integer ( 5 , 20 ),
max_depth = - 1 ,
min_child_samples = 5 ,
subsample = 0.5
)
)
optimizer . go () optimizer = opt . GradientBoostedRegressionTreeOptPro ( iterations = 32 )
optimizer . forge_experiment (
model_initializer = CatBoostClassifier ,
model_init_params = dict (
iterations = 100 ,
eval_metric = Categorical ([ 'Logloss' , 'Accuracy' , 'AUC' ]),
learning_rate = Real ( low = 0.0001 , high = 0.5 ),
depth = Integer ( 4 , 7 ),
allow_writing_files = False
)
)
optimizer . go () optimizer = opt . ExtraTreesOptPro ( iterations = 10 )
optimizer . forge_experiment (
model_initializer = RGFClassifier ,
model_init_params = dict (
max_leaf = 1000 ,
algorithm = Categorical ([ 'RGF' , 'RGF_Opt' , 'RGF_Sib' ]),
l2 = Real ( 0.01 , 0.3 ),
normalize = Categorical ([ True , False ]),
learning_rate = Real ( 0.3 , 0.7 ),
loss = Categorical ([ 'LS' , 'Expo' , 'Log' , 'Abs' ])
)
)
optimizer . go ()這是您可以期望Experiment生成的文件結構的簡單說明。有關目錄結構和各種文件內容的深入說明，請參見文檔中的文件結構概述部分。但是，必需品如下：
Experiment將文件添加到每個高參數hunterassets/實驗子目錄中，由experiment_id命名Experiment還為HyperParameterHunterAssets/排行榜/GlobAlleaderboard.csv添加了一個條目Environment的file_blacklist和do_full_save kwargs創建的（此處記錄） HyperparameterHunterAssets
| Heartbeat.log
|
└───Experiments
| |
| └───Descriptions
| | | <Files describing Experiment results, conditions, etc.>.json
| |
| └───Predictions<OOF/Holdout/Test>
| | | <Files containing Experiment predictions for the indicated dataset>.csv
| |
| └───Heartbeats
| | | <Files containing the log produced by the Experiment>.log
| |
| └───ScriptBackups
| | <Files containing a copy of the script that created the Experiment>.py
|
└───Leaderboards
| | GlobalLeaderboard.csv
| | <Other leaderboards>.csv
|
└───TestedKeys
| | <Files named by Environment key, containing hyperparameter keys>.json
|
└───KeyAttributeLookup
| <Files linking complex objects used in Experiments to their hashes>
pip install hyperparameter-hunter
如果您喜歡登頂，並且想要所有最新的發展，請運行：
pip install git+https://github.com/HunterMcGushion/hyperparameter_hunter.git
如果您想為HyperparameterHunter做出貢獻，請在此處開始。
沒關係。不要感到難過。纏繞您的頭有些奇怪。這是一個示例，說明了一切如何相關：
from hyperparameter_hunter import Environment , CVExperiment , BayesianOptPro , Integer
from hyperparameter_hunter . utils . learning_utils import get_breast_cancer_data
from xgboost import XGBClassifier
# Start by creating an `Environment` - This is where you define how Experiments (and optimization) will be conducted
env = Environment (
train_dataset = get_breast_cancer_data ( target = 'target' ),
results_path = 'HyperparameterHunterAssets' ,
metrics = [ 'roc_auc_score' ],
cv_type = 'StratifiedKFold' ,
cv_params = dict ( n_splits = 10 , shuffle = True , random_state = 32 ),
)
# Now, conduct an `Experiment`
# This tells HyperparameterHunter to use the settings in the active `Environment` to train a model with these hyperparameters
experiment = CVExperiment (
model_initializer = XGBClassifier ,
model_init_params = dict (
objective = 'reg:linear' ,
max_depth = 3
)
)
# That's it. No annoying boilerplate code to fit models and record results
# Now, the `Environment`'s `results_path` directory will contain new files describing the Experiment just conducted
# Time for the fun part. We'll set up some hyperparameter optimization by first defining the `OptPro` (Optimization Protocol) we want
optimizer = BayesianOptPro ( verbose = 1 )
# Now we're going to say which hyperparameters we want to optimize.
# Notice how this looks just like our `experiment` above
optimizer . forge_experiment (
model_initializer = XGBClassifier ,
model_init_params = dict (
objective = 'reg:linear' , # We're setting this as a constant guideline - Not one to optimize
max_depth = Integer ( 2 , 10 ) # Instead of using an int like the `experiment` above, we provide a space to search
)
)
# Notice that our range for `max_depth` includes the `max_depth=3` value we used in our `experiment` earlier
optimizer . go () # Now, we go
assert experiment . experiment_id in [ _ [ 2 ] for _ in optimizer . similar_experiments ]
# Here we're verifying that the `experiment` we conducted first was found by `optimizer` and used as learning material
# You can also see via the console that we found `experiment`'s saved files, and used it to start optimization
last_experiment_id = optimizer . current_experiment . experiment_id
# Let's save the id of the experiment that was just conducted by `optimizer`
optimizer . go () # Now, we'll start up `optimizer` again...
# And we can see that this second optimization round learned from both our first `experiment` and our first optimization round
assert experiment . experiment_id in [ _ [ 2 ] for _ in optimizer . similar_experiments ]
assert last_experiment_id in [ _ [ 2 ] for _ in optimizer . similar_experiments ]
# It even did all this without us having to tell it what experiments to learn from
# Now think about how much better your hyperparameter optimization will be when it learns from:
# - All your past experiments, and
# - All your past optimization rounds
# And the best part: HyperparameterHunter figures out which experiments are compatible all on its own
# You don't have to worry about telling it that KFold=5 is different from KFold=10,
# Or that max_depth=12 is outside of max_depth=Integer(2, 10) 這些可能會“ getcha”
OptPro提供初始搜索點？OptPro優化回合CVExperiment特定的搜索點（尚未記錄）開始Experiment適合您的OptPro定義的搜索空間，則優化器將在Experiment結果中找到和讀取Experiment ，因為結果已保存。離開它只會一遍又一遍地執行相同的ExperimentActivation層之間的切換而引起的，並提供一個Dense層的activation kwargDense(10, activation='sigmoid')Dense(10); Activation('sigmoid')Activation層，要么在其他層提供activation kwargs，然後堅持使用！model.compile參數： optimizer和optimizer_params同時？optimizers期望不同的論點optimizer=Categorical(['adam', 'rmsprop'])時， optimizer_params有兩種不同的命令optimizer ，而optimizer_params則可以分別優化optimizer_params值。這樣，每個optimizer將使用其默認參數optimizer是最佳的，並設置optimizer=<best optimizer> ，然後繼續調整optimizer_params ，並使用特定於您選擇的optimizer參數__init__方法在其他地方定義了kwargs None默認值None
