机器学习-决策树案例[判断蘑菇是否有毒]

欢迎访问我的主页

本案例为通过csv文件中数据集，使用决策树方法对蘑菇是否有毒进行预测。
数据集网盘链接：https://pan.baidu.com/s/1AZR4EKFYjqsJ3hoTo34rTQ
提取码：v1oo

最终实现的树模型：

#导入相关库
import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score

#数据
from sklearn import tree
from sklearn.datasets import load_wine
from sklearn.model_selection import train_test_split    #切分数据集，训练集和测试集

#导入CSV数据（关于蘑菇的各项特征数据表）
import csv
import pandas as pd

dpath = 'data/'
data = pd.read_csv("mushrooms.csv")
data.head(6)

wine=load_wine()
print(type(wine))   #--------------<class 'sklearn.utils.Bunch'>
wine

data.isnull().sum()#缺失值

data['class'].unique()      #p有毒    e无毒   
#unique的作用是从输入序列中“删除”所有相邻的重复元素

data.dtypes

from sklearn.preprocessing import LabelEncoder
labelencoder=LabelEncoder()
for col in data.columns:
    data[col] = labelencoder.fit_transform(data[col])
data.head()#-----------<class 'pandas.core.frame.DataFrame'>

X = data.iloc[:,1:23]  # 所有行、所有功能和无标签
y = data.iloc[:,0]  # 所有行，仅标签
X.head()
y.head()

#将数据剪切成训练和测试数据集
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.2,random_state=4)
X_train.shape
# X_test.shape

clf=tree.DecisionTreeClassifier(criterion='entropy')
clf=clf.fit(X_train,y_train)
score=clf.score(X_test,y_test)
score

clf.feature_importances_   #

data.dtypes
print(type(data.dtypes))

# data.dtypes
feature_name=['cap-shape','cap-surface','cap-color','bruises','odor','gill-attachment','gill-spacing','gill-size','gill-color','stalk-shape'
              ,'stalk-root','stalk-surface-above-ring','stalk-surface-below-ring','stalk-color-above-ring','stalk-color-below-ring','veil-type'
              ,'veil-color','ring-number','ring-type','spore-print-color','population','habitat']

print(len(feature_name))
# feature_name=[]
# for i in range(len(data.dtypes)):
#     feature_name.append()

[*zip(feature_name,clf.feature_importances_)]

clf=tree.DecisionTreeClassifier(criterion='entropy',random_state=30)
clf=clf.fit(X_train,y_train)
score=clf.score(X_test,y_test)

score

clf=tree.DecisionTreeClassifier(criterion='entropy'      #优化!
                                ,random_state=30
                                ,splitter='random')
clf=clf.fit(X_train,y_train)
score=clf.score(X_test,y_test)
score

import graphviz
dot_data=tree.export_graphviz(clf
                             ,feature_names=feature_name
                             ,class_names=['有毒','无毒']
                             ,filled=True
                             ,rounded=True)
graph=graphviz.Source(dot_data)
graph

clf.apply(X_test)

clf.predict(X_test)
print(clf.predict(X_test))
print(len(clf.predict(X_test)))
# for i in range(len(clf.predict(X_test))):
#     print(clf.predict(X_test)[i])    #p 1 有毒    e 0 无毒

score=clf.score(X_test,y_test)
score

print(X_test)

欢迎访问我的主页，一起学习机器学习n_n