Python ExtraTreesClassifier.get_params方法代码示例

# 需要导入模块: from sklearn.ensemble import ExtraTreesClassifier [as 别名]
# 或者: from sklearn.ensemble.ExtraTreesClassifier import get_params [as 别名]
def train_UsingExtraTreesClassifier(df,header,x_train, y_train,x_test,y_test) :

    # training
    clf = ExtraTreesClassifier(n_estimators=200,random_state=0,criterion='gini',bootstrap=True,oob_score=1,compute_importances=True)
    # Also tried entropy for the information gain but 'gini' seemed to give marginally better fit, bith in sample & out of sample
    clf.fit(x_train, y_train)
    #estimation of goodness of fit
    print "Estimation of goodness of fit using the ExtraTreesClassifier is : %f  \n" % clf.score(x_test,y_test)
    print "Estimation of out of bag score  using the ExtraTreesClassifier is : %f \n \n  " % clf.oob_score_
    # getting paramters back, if needed
    clf.get_params()
    # get the vector of predicted prob back
    y_test_predicted= clf.predict(x_test)
    X = df[df.columns - [header[-1]]]

    feature_importance = clf.feature_importances_
    # On a scale of 10 - make importances relative to max importance and plot them
    feature_importance = 10.0 * (feature_importance / feature_importance.max())
    sorted_idx = np.argsort(feature_importance) #Returns the indices that would sort an array.
    pos = np.arange(sorted_idx.shape[0]) + .5
    plt.figure(figsize=(12, 6))
    plt.subplot(1, 1, 1)
    plt.barh(pos, feature_importance[sorted_idx], align='center')
    plt.yticks(pos, X.columns[sorted_idx])
    plt.xlabel('Relative Importance')
    plt.title('Variable Importance')
    plt.show()
    return y_test_predicted

# 需要导入模块: from sklearn.ensemble import ExtraTreesClassifier [as 别名]
# 或者: from sklearn.ensemble.ExtraTreesClassifier import get_params [as 别名]
    clf_etree.fit(X_train, y_train)
    print "Validation set score: ERF " , clf_etree.score(X_val, y_val)

    clf_boost = AdaBoostClassifier(DecisionTreeClassifier(max_depth=1),algorithm="SAMME", n_estimators=500, random_state=74494, learning_rate=0.8) 
    clf_boost.fit(X_train, y_train)
    print "Validation set score: ABOOST " , clf_boost.score(X_val, y_val)


    #clf_gboost = GradientBoostingClassifier(n_estimators=int(reg), random_state=74494, learning_rate=0.2) 
    #clf_gboost.fit(X_train, y_train)
    #print "Validation set score:LR " , clf_gboost.score(X_val, y_val)


    print "Classifier:"
    print clf, clf.get_params()
    print clf_etree, clf_etree.get_params()
    print clf_boost, clf_boost.get_params()
    

    if(fe==1): #L1 norm based feature elimination
        clf_fe = LogisticRegression(C=1000,penalty='l1',random_state=0)
        clf_fe.fit(X_train, y_train)
        X_train = X_train[:,clf_fe.coef_.ravel()!=0]
        print "Xtrain.shape: ", X_train.shape
        X_val = X_val[:,clf_fe.coef_.ravel()!=0]

        clf2_l = svm.SVC(kernel='linear', C=reg)
        clf2_l.fit(X_train, y_train)
        print "Lasso Validation set score filtered coeff linear: " , clf2_l.score(X_val, y_val)
        clf2 = svm.SVC(kernel='rbf', C=reg, gamma=g)
        clf2.fit(X_train, y_train)

# 需要导入模块: from sklearn.ensemble import ExtraTreesClassifier [as 别名]
# 或者: from sklearn.ensemble.ExtraTreesClassifier import get_params [as 别名]

# In[14]:

from sklearn import grid_search
from sklearn.metrics import f1_score, make_scorer
from sklearn.ensemble import ExtraTreesClassifier

parameters = {'n_estimators': [1, 32]}
model = ExtraTreesClassifier()
f1_scorer = make_scorer(f1_score, pos_label='yes')
clf = grid_search.GridSearchCV(model, param_grid=parameters, scoring=f1_scorer)
model.fit(X_train, Y_train)
Y_pred = model.predict(X_test)

print model.get_params()
print "F1 score for test set: {}".format(metrics.f1_score(Y_test, Y_pred))


# In[12]:

import numpy as np
import matplotlib.pyplot as plt

from sklearn.ensemble import ExtraTreesClassifier

# Build a forest and compute the feature importances
forest = ExtraTreesClassifier(n_estimators=250, random_state=0)

forest.fit(X, Y)
importances = forest.feature_importances_