pyhton_機器學習筆記對sklearn的集成分類器進行學習

使用泰坦尼克生還數據集，利用sklearn決集成分類器對對其進行預測分類，

#-*-coding:utf-8-*-
import pandas as pd
from sklearn.model_selection import  train_test_split
from sklearn.feature_extraction import DictVectorizer
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier
titanic = pd.read_csv("titanic.txt")

#人工選取特徵
X=titanic[['pclass','age','sex']]
y=titanic['survivd']

X['age'].fillna(X['age'].mean(),inplace=True)
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.25,random_state=33)

#將特徵轉化爲向量
vec = DictVectorizer(sparse=False)
X_train = vec.fit_transform(X_train.to_dict(orient='record'))
X_test = vec.transform(X_test.to_dict(orient='record'))

#使用單一決策樹進行模型訓練及預測分析
dtc=DecisionTreeClassifier()
dtc.fit(X_train,y_train)
dtc_y_pred=dtc.predict(X_test)

#使用隨機森林分類器進行模型訓練及預測分析
rfc=RandomForestClassifier()
rfc.fit(X_train,y_train)
rfc_y_pred = rfc.predict(X_test)

#使用梯度提升決策樹進行集成模型訓練預測分析
gbc=GradientBoostingClassifier()
gbc.fit(X_train,y_train)
gbc_y_pred = gbc.predict(X_test)

作者：WangB