gridsearchcv

, train_y): from sklearn.grid_search import GridSearchCV from sklearn.svm import SVC model = SVC(kernel='rbf', probability=True) param_grid = {'C': [1e-3, 1e-2, 1e-1, 1, 10, 100, 1000], 'gamma': [0.001, 0.0001]} grid_search = GridSearchCV(model, param_grid, n_jobs = 1, verbose=1) grid_search.fit(train_x, train_y) best_parameters = grid_search.best_estimator_.get_params()

=train_test_split (x, y) #用信息增益启发式算法建立决策树pipeline =pipeline ([' CLF ', Decisiontreeclassifier (criterion= ' entropy ')]) parameters = {' clf__max_depth ': [155], Clf__min_samples_ Split ': (1, 2, 3), ' Clf__min_samples_leaf ': (1, 2, 3)} #f1查全率和查准率的调和平均grid_search =GRIDSEARCHCV (pipeline,parameters,n_ Jobs=-1, verbose=1,scoring= ' F1 ') grid_search.fit (x_train,y_train) print ' best results:%0.3f '%grid_search.best_score_ print

This blog content is in the last blog scikit feature selection, Xgboost regression prediction, model optimization on the basis of the actual combat optimization, so before reading this blog, please go to see the previous article. The work I did earlier was basically about feature selection, and I wanted to write about some of the little experiences with xgboost parameter adjustments. I have also seen a lot of relevant content on the site before, basically translation from an English blog, but al

of a well-trained model,This allows you to know which variables need to be preserved and which can be discarded. The following two classes need to be introduced: From Xgboost import plot_importance from matplotlib import Pyplot Compared to the previous code, it is the importance of adding two lines after fit to draw a feature Model.fit (X, y) plot_importance (model) pyplot.show () 4. Parameter adjustment How to adjust the parameters, the following is the three parameters of the general prac

from matplotlib.colors import Normalize to SKLEARN.SVM import SVC from Sklearn.preprocessin G Import Standardscaler from sklearn.datasets import load_iris from sklearn.model_selection Import stratifiedshufflesplit# layered shuffle split cross validation from sklearn.model_selection import GRIDSEARCHCV # Utility function to move the Midpoi NT of a colormap to be around # the values of interest. Class Midpointnormalize (Normalize): Def __init__ (self,

overall model is not suitable. In the following case analysis, the overall model performance we will talk about refers to the average accuracy. Please be careful.2.3.1 Random Forest parameter adjustment case: Digit Recognizer Here, we select Digit Recognizer in the 101 teaching competition on Kaggle as the case to demonstrate the process of adjusting parameters for RandomForestClassifier. Of course, we should not set different parameters manually and then train the model. Using the

. Decisiontreeclassifier () Model.fit (train_x, train_y) return model# GBDT (Gradient boosting decision Tree) Classifierd EF Gradient_boosting_classifier (train_x, train_y): From sklearn.ensemble import gradientboostingclassifier model = G Radientboostingclassifier (n_estimators=200) model.fit (train_x, train_y) return model# SVM classifierdef Svm_classifi ER (train_x, train_y): From SKLEARN.SVM Import svc model = svc (kernel= ' RBF ', probability=true) Model.fit (train_x, train_y) return model#

=5): 5 params = None 6 top_scores = Sorted (Grid_scores, Key=itemgetter (1), reverse=true) [: N_top] 7 for-I, score in Enumerate (top_scores): 8 pri NT ("Parameters with rank: {0}". Format (i + 1)) 9 print ("Mean validation score: {0:.4f} (std: {1:.4f})". Format (10 Score.mean_validation_score, NP.STD (score.cv_validation_scores)) One print ("Parameters: {0}". Format ( score.parameters)) ("") [params = = none:15 Params = score.parameters Params # simple grid Test Gr

delimited hyper-plane, H1, H2 plt.scatter (x[:,0],x[:,1],c=y,cmap=plt.cm.paired) Plt.scatter ( Clf.support_vectors_[:,0],clf.support_vectors_[:,1],color= ' K ') # Draw support Vector point plt.show () # non-linear can be divided into: from sklearn import datasets # load Data iris = Datasets.load_iris () X = iris.data y = iris.target print Iris.target_names [' Setosa ' versicolor ' virginica '] From sklearn.model_selection import Train_test_split X_train, X_test, y_train, y_test = Train

to reduce features.General preference Use the following method: Enhanced regularization (this is said to reduce the value of C in Linearsvc)Regularization is the most effective way to reduce overfitting Plot_learning_curve (Linearsvc (c=0.1), ' Linearsvc (c=0.1) ', x,y,ylim= (0.8,1), Train_sizes=np.linspace (. 05,0.2,5)) Adjust the regularization coefficient, found that there is a certain degree of relief, but still what problem, our coefficients are self-finalized, there is no way to automati