def rfcScores(self,Xn,y,cv=5,param_name='max_depth',estimatorsRange=(10,11,1),paramRange=(1,10,1),trainW=1,testW=2,title='Randorm Forest classifier',clfArg={},plot=False):
"""
Perform the validation_curve function using Random Forest classifier (RFC)
and get the best param value based on the highest test_score.
cv indicates the cross validation k-fold. Default param to optimize is max_depth.
paramRange=(a,b,c) is the range to evaluate the param_name. a start degree, b end degree, c step.
estimatorsRange=(a,b,c) is the range to evaluate the number of estimators (n_estimators).
After the function gets the best param value, associated test_score and train_score
are used to calculated a weighted_score.
trainW and testW are the weights used to calculated a
weighted_score=test_score*testW+train_score*trainW)/(testW+trainW).
clfArg is a dictionary to add any additional parameters to the RFC.
To see how the best score is collected set plot=True.
The function calculates the scores for the RFC criterions gini and entropy.
"""
clf=RFC(**clfArg)
model_scores=list()
param_range=np.arange(paramRange[0],paramRange[1],paramRange[2])
e_range=np.arange(estimatorsRange[0],estimatorsRange[1],estimatorsRange[2])
criterions=['gini','entropy']
for criterion in criterions:
clf.criterion=criterion
for e in e_range:
clf.n_estimators=e
dtitle=title+". Criterion: "+criterion+". Estimators: "+str(e)
train_sc, test_sc = validation_curve(clf,Xn,y,param_name=param_name,param_range=param_range,cv=cv)
param_score=self.plotTrainTest(train_sc,test_sc,param_range,t=dtitle,xlabel=param_name,plot=plot)
scoreDic={'model':dtitle,'param_name':param_name}
scoreDic.update(param_score)
model_scores.append(scoreDic.copy())
return self.scoreModelListDf(model_scores,trainW=trainW,testW=testW)
import pandas as pd #1
from sklearn.model_selection import train_test_split #2
from sklearn.ensemble import RandomForestClassifier #3
from sklearn.metrics import confusion_matrix #4
# import libs
datas = pd.read_csv("datas.csv") # read datas
#1
x = datas.iloc[:, 3:-3].values
y = datas.iloc[:, -2].values
# split values
x_train, x_test, y_train, y_test = train_test_split(
x, y, test_size=0.10, random_state=0) # 90% for train, %10 for test
#2
rfc = RandomForestClassifier()
#3
rfc.max_depth = 100
rfc.criterion = "entropy" #select criterion,other criterion is 'gini'
rfc.n_estimators = 1
rfc.fit(x_train, y_train)
y_pred = rfc.predict(x_test)
cm = confusion_matrix(y_test, y_pred)
#4
print("RFC")
print(cm)