Python scikit learn ExtraTreesClassifier预测使用Pandas DataFarme、datatale Frame和Numpy阵列提供不同的执行时间
我正在使用scikit学习树外分类器Python scikit learn ExtraTreesClassifier预测使用Pandas DataFarme、datatale Frame和Numpy阵列提供不同的执行时间,python,pandas,numpy,optimization,scikit-learn,Python,Pandas,Numpy,Optimization,Scikit Learn,我正在使用scikit学习树外分类器 import pandas as pd import datatable as dt import numpy as np from sklearn.ensemble import ExtraTreesClassifier def __init__(self): self.ExTrCl = ExtraTreesClassifier() 熊猫数据场与datatale帧与Numpy阵列的预测给出了不同的执行时间 首先,我基于测试数据集生成一个nump
import pandas as pd
import datatable as dt
import numpy as np
from sklearn.ensemble import ExtraTreesClassifier
def __init__(self):
self.ExTrCl = ExtraTreesClassifier()
熊猫数据场与datatale帧与Numpy阵列的预测给出了不同的执行时间强>
首先,我基于测试数据集生成一个numpy 2d数组,generateTestPart(testDataSet,列出列中使用的主题)
我使用三种方法进行预测,使用1)熊猫数据场:
def test_groupe_score_pd(self, test_matrix)
start_time_0 = time.time()
dftest = pd.DataFrame(test_matrix,columns=self.list_motifs)
end_time = time.time()
print(" time creating DataFrame = ", end_time-start_time_0)
start_time = time.time()
result = self.ExTrCl.predict(dftest)
end_time = time.time()
print(" Time pred only = ",end_time-start_time," s")
print(" Time create + pred = ",end_time-start_time_0," s")
def test_groupe_score_dt(self, test_matrix):
start_0_time = time.time()
dt_dftest = dt.Frame(np.array(test_matrix),names=self.list_motifs)
end_time = time.time()
print(" time create Fram dt = ",end_time-start_0_time)
start_time = time.time()
result = self.ExTrCl.predict(dt_dftest)
end_time = time.time()
print(" Time pred only = ",end_time-start_time," s")
print(" Time pred + create = ",end_time-start_0_time," s")
def test_groupe_score_numpy(self, test_matrix):
start_0_time = time.time()
start_time = time.time()
result = self.ExTrCl.predict(test_matrix)
end_time = time.time()
print(" Time pred only = ",end_time-start_time," s")