Python ExtraTreesRegressor.score方法代码示例

# 需要导入模块: from sklearn.ensemble import ExtraTreesRegressor [as 别名]
# 或者: from sklearn.ensemble.ExtraTreesRegressor import score [as 别名]
def dummie_columns_extra_trees(train, test):
    from sklearn.ensemble import ExtraTreesRegressor
    print "-- {} --".format("Extremely Randomized Trees Regression using all but remarks")
    predicting_columns = list(train._get_numeric_data().columns.values)
    predicting_columns.remove("LISTPRICE")
    predicting_columns.remove("SOLDPRICE")
    rf = ExtraTreesRegressor(
        n_estimators=300, n_jobs=-1)
    rf.fit(train[predicting_columns], train["SOLDPRICE"])
    score = rf.score(test[predicting_columns], test["SOLDPRICE"])
    predictions = rf.predict(test[predicting_columns])
    sample_predictions(test, predictions)
    print "Accuracy: {}\n".format(score)
    return score, predictions

# 需要导入模块: from sklearn.ensemble import ExtraTreesRegressor [as 别名]
# 或者: from sklearn.ensemble.ExtraTreesRegressor import score [as 别名]
def simple_extremely_random_trees(data_train_x, data_test_x, data_train_y, data_test_y):
    from sklearn.ensemble import ExtraTreesRegressor
    print "-- {} --".format("Extremely Randomized Trees Regression using all but remarks")
    rf = ExtraTreesRegressor(
        n_estimators=300,
        n_jobs=-1
    )
    rf.fit(data_train_x, data_train_y)
    sample_predictions(rf.predict(data_test_x), data_test_y)
    score = rf.score(data_test_x, data_test_y)
    cross_validated_scores = cross_val_score(
        rf, data_test_x, data_test_y, cv=5)
    print "MSE Accuracy: {}".format(score)
    print "MSE Across 5 Folds: {}".format(cross_validated_scores)
    print "95%% Confidence Interval: %0.3f (+/- %0.3f)\n" % (cross_validated_scores.mean(), cross_validated_scores.std() * 1.96)

# 需要导入模块: from sklearn.ensemble import ExtraTreesRegressor [as 别名]
# 或者: from sklearn.ensemble.ExtraTreesRegressor import score [as 别名]
def trainRegressorsAndSave(computeScore=False):
    for db in dbs:
        if (not os.path.exists("clfs/" + db)):
            clf = ExtraTreesRegressor(n_estimators=500, random_state=1, n_jobs=-1)
            saveTrainedClassifier(db, clf)
        elif (computeScore):
            clf = joblib.load("clfs/" + db)

        if (computeScore):
            print("Loading test data...")
            loaded = loadDB(db + ".csv")
            X_test = loaded[:, 0:-1]
            y_test = loaded[:, -1]

            print("Normalized score is {}".format(clf.score(X_test, y_test)))
            X_test = y_test = 0

# 需要导入模块: from sklearn.ensemble import ExtraTreesRegressor [as 别名]
# 或者: from sklearn.ensemble.ExtraTreesRegressor import score [as 别名]
etr_y_predict = etr.predict(X_test)

# 使用GradientBoostingRegressor训练模型，并对测试数据做出预测，结果存储在变量gbr_y_predict中。
gbr = GradientBoostingRegressor()
gbr.fit(X_train, y_train)
gbr_y_predict = gbr.predict(X_test)

from sklearn.metrics import mean_absolute_error,mean_squared_error
# 使用R-squared、MSE以及MAE指标对默认配置的随机回归森林在测试集上进行性能评估。
print('R-squared value of RandomForestRegressor:', rfr.score(X_test, y_test))
print( 'The mean squared error of RandomForestRegressor:', mean_squared_error(y_test, rfr_y_predict))
print( 'The mean absoluate error of RandomForestRegressor:', mean_absolute_error(y_test, rfr_y_predict))


# 使用R-squared、MSE以及MAE指标对默认配置的极端回归森林在测试集上进行性能评估。
print('R-squared value of ExtraTreesRegessor:', etr.score(X_test, y_test))
print('The mean squared error of  ExtraTreesRegessor:', mean_squared_error(y_test,etr_y_predict))
print('The mean absoluate error of ExtraTreesRegessor:', mean_absolute_error(y_test, etr_y_predict))

# 利用训练好的极端回归森林模型，输出每种特征对预测目标的贡献度。
print(zip(etr.feature_importances_, boston.feature_names))
featrue_importance = zip(etr.feature_importances_, boston.feature_names)
print(np.sort(list(featrue_importance), axis= 0))
# 使用R-squared、MSE以及MAE指标对默认配置的梯度提升回归树在测试集上进行性能评估。
print('R-squared value of GradientBoostingRegressor:', gbr.score(X_test, y_test))
print('The mean squared error of GradientBoostingRegressor:', mean_squared_error(y_test, gbr_y_predict))
print('The mean absoluate error of GradientBoostingRegressor:', mean_absolute_error(y_test, gbr_y_predict))


# 许多业界从事商业分析系统开发和搭建的工作者更加青睐于集成模型，
#并经常以这些模型的性能表现为基准，与新设计的其他模型性能进行比对。

# 需要导入模块: from sklearn.ensemble import ExtraTreesRegressor [as 别名]
# 或者: from sklearn.ensemble.ExtraTreesRegressor import score [as 别名]
with open('model.txt','wt') as f:
  print >> f, xfr
with open('estimators_.txt','wt') as f:
  #f.write(xfr.estimators_)
  print >> f, xfr.estimators_
with open('feature_importances_.txt','wt') as f:
  print >> f, xfr.feature_importances_
#with open('oob_score_.txt','wt') as f:
  #print >> f, xfr.oob_score_
#with open('oob_prediction_.txt','wt') as f:
  #print >> f, xfr.oob_prediction_

predict_loc_regres = xfr.predict(data_test)
if 'target_test' in locals():
  score = xfr.score(data_test,target_test)
  gn = normalized_weighted_gini(target_test,predict_loc_regres,data_test.var11)
end = time.clock()

#outdf = pd.DataFrame([data_test.ix[:,'id']])
if 'target_test' in locals():
  target_test.columns = ['true_target']
  outdf = pd.concat([data_test.ix[:,'id'].astype(int),pd.DataFrame(predict_loc_regres,columns=['target']),target_test],axis=1)
else:
  outdf = pd.concat([data_test.ix[:,'id'].astype(int),pd.DataFrame(predict_loc_regres,columns=['target'])],axis=1)

out_filename = (os.path.splitext(os.path.basename(sys.argv[1]))[0]+"_predict.csv")
outdf.to_csv(out_filename,index=0)
if 'target_test' in locals():
  print out_filename, score , gn
else:

# 需要导入模块: from sklearn.ensemble import ExtraTreesRegressor [as 别名]
# 或者: from sklearn.ensemble.ExtraTreesRegressor import score [as 别名]
    score = gbr.score(X_test, Y_test)
    print('Problem 2 part 4 Test score : {}'.format(score))
    
    
    
    etr = ExtraTreesRegressor(n_estimators=100, max_depth=8,min_samples_leaf=2 )
    
    etr.fit(X_train, Y_train)
    
    Y_etr = etr.predict(X_test)    
    score = r2_score(Y_test.values, Y_etr)
    print('Problem 2 part 5a Test score : {}'.format(score))
    

    score = etr.score(X_test, Y_test)
    print('Problem 2 part 5b Test score : {}'.format(score))
    



if(runProblem3):
    from keras.models import Sequential
    from keras.layers.core import Activation, Dense, Dropout
    from keras.callbacks import EarlyStopping


    #X = dataset[['Feature_5', 'Feature_7','Ret_MinusTwo', 'Ret_MinusOne']+['Ret_{}'.format(i) for i in range(2,121)]]
    #Y = dataset['Ret_MinusZero']

    #X['Feature_5'] = (X['Feature_5'] - np.mean(X['Feature_5']))/np.std(X['Feature_5'])

# 需要导入模块: from sklearn.ensemble import ExtraTreesRegressor [as 别名]
# 或者: from sklearn.ensemble.ExtraTreesRegressor import score [as 别名]
class mixmodels:
    def __init__(self,nest=10):
        self.nest = nest
    def fit(self,data_train,target):
        self.target_train = target
        self.catcol = data_train.filter(like='var').columns.tolist()
        #start_gbr_tr = time.clock()
        self.gbr = GradientBoostingRegressor(n_estimators =self.nest,max_depth=7)
        self.gbr.fit(data_train,self.target_train)
        self.transformed_train_gbr = self.gbr.transform(data_train,threshold="0.35*mean")
        self.gbr_tr_fit = GradientBoostingRegressor(n_estimators =self.nest,max_depth=7)
        self.gbr_tr_fit.fit(self.transformed_train_gbr,self.target_train)
        #end_gbr_tr = time.clock()
        #print >> log, "time_gbr_tr = ", end_gbr_tr-start_gbr_tr

        #start_xfr_tr = time.clock()
        self.xfr= ExtraTreesRegressor(n_estimators =self.nest,max_depth=7)
        self.xfr.fit(data_train,self.target_train)
        self.transformed_train_xfr = self.xfr.transform(data_train,threshold="0.35*mean")
        self.xfr_tr_fit = ExtraTreesRegressor(n_estimators =self.nest,max_depth=7)
        self.xfr_tr_fit.fit(self.transformed_train_xfr,self.target_train)
        #end_xfr_tr = time.clock()
        #print >> log, "time_xfr_tr = ", end_xfr_tr-start_xfr_tr

        #start_gbr_cat = time.clock()
        self.gbr_cat_fit = GradientBoostingRegressor(n_estimators =self.nest,max_depth=7)
        self.gbr_cat_fit.fit(data_train[self.catcol],self.target_train)
        #end_gbr_cat = time.clock()
        #print >> log, "time_gbr_cat = ", end_gbr_cat-start_gbr_cat

        #start_xfr_cat = time.clock()
        self.xfr_cat_fit = ExtraTreesRegressor(n_estimators =self.nest,max_depth=7)
        self.xfr_cat_fit.fit(data_train[self.catcol],self.target_train)
        #end_xfr_cat = time.clock()
        #print >> log, "time_xfr_cat = ", end_xfr_cat-start_xfr_cat
        return self

    def predict(self,data_test):
        mix_test_list = []

        transformed_test_gbr = self.gbr.transform(data_test,threshold="0.35*mean")
        mix_test_list += [pd.Series(self.gbr_tr_fit.predict(transformed_test_gbr))]

        transformed_test_xfr = self.xfr.transform(data_test,threshold="0.35*mean")
        mix_test_list += [pd.Series(self.xfr_tr_fit.predict(transformed_test_xfr))]

        mix_test_list += [pd.Series(self.gbr_cat_fit.predict(data_test[self.catcol]))]

        mix_test_list += [pd.Series(self.xfr_cat_fit.predict(data_test[self.catcol]))]

        mix_test = pd.concat(mix_test_list,1)

        mix_ave = mix_test.mean(1)
        mix_ave.name='target'

        return mix_ave
    def score(self,data_test,target_test):
        total_score = []
        transformed_test_gbr = self.gbr.transform(data_test,threshold="0.35*mean")
        total_score += [ self.gbr_tr_fit.score(transformed_test_gbr,target_test) ]
        transformed_test_xfr = self.xfr.transform(data_test,threshold="0.35*mean")
        total_score += [ self.xfr_tr_fit.score(transformed_test_xfr,target_test) ]
        total_score += [ self.gbr_cat_fit.score(data_test[self.catcol],target_test) ]
        total_score += [ self.xfr_cat_fit.score(data_test[self.catcol],target_test) ]
        return sum(total_score)/float(len(total_score))

    def gini(self,data_test,target_test):
        weight = data_test.var11
        gns = []
        transformed_test_gbr = self.gbr.transform(data_test,threshold="0.35*mean")
        gns += [normalized_weighted_gini(target_test.tolist(),self.gbr_tr_fit.predict(transformed_test_gbr).tolist(),weight.tolist()) ]
        transformed_test_xfr = self.xfr.transform(data_test,threshold="0.35*mean")
        gns += [normalized_weighted_gini(target_test.tolist(),self.xfr_tr_fit.predict(transformed_test_xfr).tolist(),weight.tolist()) ]
        gns += [normalized_weighted_gini(target_test.tolist(),self.gbr_cat_fit.predict(data_test[self.catcol]).tolist(),weight.tolist()) ]
        gns += [normalized_weighted_gini(target_test.tolist(),self.xfr_cat_fit.predict(data_test[self.catcol]).tolist(),weight.tolist()) ]
        return sum(gns)/float(len(gns))

# 需要导入模块: from sklearn.ensemble import ExtraTreesRegressor [as 别名]
# 或者: from sklearn.ensemble.ExtraTreesRegressor import score [as 别名]
X = scaler.transform(X)

timeit("Standardizing the data")
'''

from sklearn.ensemble import ExtraTreesRegressor
#from sklearn.neighbors import KNeighborsRegressor

clf = ExtraTreesRegressor(n_estimators=10)
#clf = KNeighborsRegressor()

clf.fit(X_train, Y_train)

timeit("Training")

print "Validation score: " + str(clf.score(X_test, Y_test))

timeit("Validation")

#score = 0.
#wrong = []
#for i, item in enumerate(X_test):
#	if unconvert(clf.predict(item)[0]) == unconvert(Y_test[i]):
#		score += 1
#	else:
#		wrong.append((unconvert(clf.predict(item)[0]),unconvert(Y_test[i])))
#score /= len(X_test)
#print "Manual validation score: " + str(score)

#timeit("Manual validation")