#!/usr/bin/env python
# coding: utf-8
# In[1]:
from sklearn import tree
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_wine
import graphviz
import warnings
# In[2]:
x = load_wine().data
y = load_wine().target
# In[3]:
x,y
# In[4]:
xtrain,xtest,ytrain,ytest = train_test_split(x,y,test_size=0.3,random_state=123)
# In[5]:
clf = tree.DecisionTreeClassifier(criterion='gini',splitter='best',random_state=12)
score = clf.fit(xtrain,ytrain).score(xtest,ytest)
score
# In[6]:
from sklearn.model_selection import GridSearchCV
# In[7]:
params = {'criterion':['entropy','gini']
,'max_depth':range(2,10)
,'min_samples_leaf':range(2,10)
,'min_samples_split':range(2,30,2)}
# In[8]:
gv = GridSearchCV(tree.DecisionTreeClassifier(splitter='best',random_state=12),params,cv=10)
gv.fit(xtrain,ytrain)
# In[9]:
gv.best_params_
# In[10]:
clf_0 = tree.DecisionTreeClassifier(criterion='gini',splitter='best'
,max_depth=3,min_samples_leaf=2,min_samples_split=2
,random_state=12)
score_0 = clf_0.fit(xtrain,ytrain).score(xtest,ytest)
score_0
# In[ ]: