Nestimators

$$Nestimators$$

from xgboost import XGBClassifier
import xgboost as xgb

import pandas as pd 
import numpy as np

from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import StratifiedKFold

from sklearn.metrics import log_loss

from matplotlib import pyplot
import seaborn as sns
%matplotlib inline

# path to where the data lies
#dpath = '/Users/qing/desktop/XGBoost/data/'
dpath = './data/'
train = pd.read_csv(dpath +"Otto_train.csv")
#train.head()

sns.countplot(train.target);
pyplot.xlabel('target');
pyplot.ylabel('Number of occurrences');

# drop ids and get labels
y_train = train['target']
y_train = y_train.map(lambda s: s[6:])
y_train = y_train.map(lambda s: int(s)-1)

train = train.drop(["id", "target"], axis=1)
X_train = np.array(train)

# prepare cross validation
kfold = StratifiedKFold(n_splits=5, shuffle=True, random_state=3)

再次调整弱分类器数目

def modelfit(alg, X_train, y_train, useTrainCV=True, cv_folds=None, early_stopping_rounds=100):
    
    if useTrainCV:
        xgb_param = alg.get_xgb_params()
        xgb_param['num_class'] = 9
        
        xgtrain = xgb.DMatrix(X_train, label = y_train)
        
        cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=alg.get_params()['n_estimators'], folds =cv_folds,
                         metrics='mlogloss', early_stopping_rounds=early_stopping_rounds)
        
        n_estimators = cvresult.shape[0]
        alg.set_params(n_estimators = n_estimators)
        
        print cvresult
        #result = pd.DataFrame(cvresult)   #cv缺省返回结果为DataFrame
        #result.to_csv('my_preds.csv', index_label = 'n_estimators')
        cvresult.to_csv('my_preds4_2_3_699.csv', index_label = 'n_estimators')
        
        # plot
        test_means = cvresult['test-mlogloss-mean']
        test_stds = cvresult['test-mlogloss-std'] 
        
        train_means = cvresult['train-mlogloss-mean']
        train_stds = cvresult['train-mlogloss-std'] 

        x_axis = range(0, n_estimators)
        pyplot.errorbar(x_axis, test_means, yerr=test_stds ,label='Test')
        pyplot.errorbar(x_axis, train_means, yerr=train_stds ,label='Train')
        pyplot.title("XGBoost n_estimators vs Log Loss")
        pyplot.xlabel( 'n_estimators' )
        pyplot.ylabel( 'Log Loss' )
        pyplot.savefig( 'n_estimators4_2_3_699.png' )
    
    #Fit the algorithm on the data
    alg.fit(X_train, y_train, eval_metric='mlogloss')
        
    #Predict training set:
    train_predprob = alg.predict_proba(X_train)
    logloss = log_loss(y_train, train_predprob)

        
    #Print model report:
    print ("logloss of train :" )
    print logloss

#调整max_depth和min_child_weight之后再次调整n_estimators(6,4)
xgb2_3 = XGBClassifier(
        learning_rate =0.1,
        n_estimators=699,  #数值大没关系，cv会自动返回合适的n_estimators
        max_depth=6,
        min_child_weight=4,
        gamma=0,
        subsample=0.3,
        colsample_bytree=0.8,
        colsample_bylevel=0.7,
        objective= 'multi:softprob',
        seed=3)

modelfit(xgb2_3, X_train, y_train, cv_folds = kfold)
#from sklearn.model_selection import cross_val_score
#results = cross_val_score(xgb2_3, X_train, y_train, metrics='mlogloss', cv=kfold)
#print results
#print("CV logloss: %.2f%% (%.2f%%)" % (results.mean()*100, results.std()*100))

cvresult = pd.DataFrame.from_csv('my_preds4_2_3_699.csv')

cvresult = cvresult.iloc[100:]
# plot
test_means = cvresult['test-mlogloss-mean']
test_stds = cvresult['test-mlogloss-std'] 
        
train_means = cvresult['train-mlogloss-mean']
train_stds = cvresult['train-mlogloss-std'] 

x_axis = range(100,cvresult.shape[0]+100)
        
fig = pyplot.figure(figsize=(10, 10), dpi=100)
pyplot.errorbar(x_axis, test_means, yerr=test_stds ,label='Test')
pyplot.errorbar(x_axis, train_means, yerr=train_stds ,label='Train')
pyplot.title("XGBoost n_estimators vs Log Loss")
pyplot.xlabel( 'n_estimators' )
pyplot.ylabel( 'Log Loss' )
pyplot.savefig( 'n_estimators_detail4_2_3_699.png' )

pyplot.show()