About CV-Assistant GRIDSEARCHCV

The first tool to be introduced is the Sklearn model selection API (GRIDSEARCHCV)

Website Link: http://scikit-learn.org/stable/modules/generated/sklearn.grid_search.GridSearchCV.html section I: Usage of GRIDSEARCHCV function

Sklearn.grid_search. GRIDSEARCHCV (
	estimator, # is the model you want to train booster
	Param_grid, # The params of the dictionary type needs to select the parameter
	scoring=none, # The standard for judging performance such as auc:scoring= ' Roc_auc '
	fit_params=none, 
	N_jobs=1, # Number of jobs running in parallel
	iid=true, Refit=true, Cv=none, 
	# Ratio of training set to validation set, equivalent to nfold=5
	verbose=0, 
	pre_dispatch= ' 2*n_jobs ', 
	error_score= ' raise '
)

A simple example is as follows:

#-*-coding:utf-8-*-
Import pandas as PD from
sklearn import SVM, datasets from
sklearn.model_selection impo RT GRIDSEARCHCV
from sklearn.metrics import classification_report

iris = Datasets.load_iris ()
# Super parameter to be adjusted
parameters = {
	' kernel ':(' linear ', ' RBF '), 
	' C ': [1, 2, 4], 
	' gamma ': [0.125, 0.25, 0.5, 1, 2, 4]
}< C11/>svr = SVM. SVC () # model
CLF = GRIDSEARCHCV (SVR, parameters, n_jobs=4)
clf.fit (Iris.data, Iris.target) #你和模型
# clf.cv_ Results_ is the log information for the Select parameter
cv_result = PD. Dataframe.from_dict (CLF.CV_RESULTS_)
with open ('./data/cv_result.csv ', ' WB ') as F:cv_result.to_csv (f)
print ' The parameters of the best model was: '
print  clf.best_params_  # prints out the most appropriate model parameters
Y_pred_array = cl F.predict (iris.data) # prediction Results
Print classification_report (Y_true=iris.target, Y_pred=y_pred_array)

Where print Clf.best_params_ prints the following information, which is the optimal parameter

{' Kernel ': ' linear ', ' C ': 2, ' gamma ': 0.125}

Print Classification_report (y_true=iris.target, Y_pred=y_pred_array) prints the following results

             Precision    Recall  f1-score   support

          0       1.00      1.00      1.00
          1       1.00      0.94      0.97
          2       0.94      1.00      0.97      , avg/total 0.98 0.98      0.98       150

section II: LIGHTGBM using GRIDSEARCHCV AssistantThe parameters that lgbmregressor can invoke are configured as follows

Lightgbm.sklearn.LGBMRegressor ( 
    boosting_type= ' GBDT ', 
    num_leaves=31, 
    max_depth=-1, 
    learning_ rate=0.1, 
    n_estimators=10, 
    max_bin=255, 
    subsample_for_bin=50000, 
    objective= ' regression ', 
    Min_split_gain=0, 
    min_child_weight=5, 
    min_child_samples=10, 
    subsample=1, 
    subsample_freq=1, 
    colsample_bytree=1, 
    reg_alpha=0, 
    reg_lambda=0, 
    seed=0, 
    nthread=-1, 
    silent=true, 
    huber_delta=1.0, 
    gaussian_eta=1.0, 
    fair_c=1.0, 
    poisson_max_delta_step=0.7, 
    drop_rate =0.1, 
    skip_drop=0.5, 
    max_drop=50, 
    uniform_drop=false, 
    xgboost_dart_mode=false
)