机器学习实战-集成学习-23

集成学习-泰坦尼克号船员获救预测

import pandas 

titanic = pandas.read_csv("titanic_train.csv")
titanic

# 空余的age填充整体age的中值
titanic["Age"] = titanic["Age"].fillna(titanic["Age"].median())
print(titanic.describe())

print(titanic["Sex"].unique())

# 把male变成0，把female变成1
titanic.loc[titanic["Sex"] == "male", "Sex"] = 0
titanic.loc[titanic["Sex"] == "female", "Sex"] = 1

print(titanic["Embarked"].unique())
# 数据填充
titanic["Embarked"] = titanic["Embarked"].fillna('S')
# 把类别变成数字
titanic.loc[titanic["Embarked"] == "S", "Embarked"] = 0
titanic.loc[titanic["Embarked"] == "C", "Embarked"] = 1
titanic.loc[titanic["Embarked"] == "Q", "Embarked"] = 2

from sklearn.preprocessing import StandardScaler

# 选定特征
predictors = ["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked"]
x_data = titanic[predictors]
y_data = titanic["Survived"]

# 数据标准化
scaler = StandardScaler()
x_data = scaler.fit_transform(x_data)

逻辑回归

from sklearn import model_selection  
from sklearn.linear_model import LogisticRegression

# 逻辑回归模型
LR = LogisticRegression()
# 计算交叉验证的误差
scores = model_selection.cross_val_score(LR, x_data, y_data, cv=3)
# 求平均
print(scores.mean())

神经网络

from sklearn.neural_network import MLPClassifier

# 建模
mlp = MLPClassifier(hidden_layer_sizes=(20,10),max_iter=1000)
# 计算交叉验证的误差
scores = model_selection.cross_val_score(mlp, x_data, y_data, cv=3)
# 求平均
print(scores.mean())

KNN

from sklearn import neighbors

knn = neighbors.KNeighborsClassifier(21)
# 计算交叉验证的误差
scores = model_selection.cross_val_score(knn, x_data, y_data, cv=3)
# 求平均
print(scores.mean())

决策树

from sklearn import tree

# 决策树模型
dtree = tree.DecisionTreeClassifier(max_depth=5, min_samples_split=4)
# 计算交叉验证的误差
scores = model_selection.cross_val_score(dtree, x_data, y_data, cv=3)
# 求平均
print(scores.mean())

随机森林

# 随机森林
from sklearn.ensemble import RandomForestClassifier

RF1 = RandomForestClassifier(random_state=1, n_estimators=10, min_samples_split=2)
# 计算交叉验证的误差
scores = model_selection.cross_val_score(RF1, x_data, y_data, cv=3)
# 求平均
print(scores.mean())

RF2 = RandomForestClassifier(n_estimators=100, min_samples_split=4)
# 计算交叉验证的误差
scores = model_selection.cross_val_score(RF2, x_data, y_data, cv=3)
# 求平均
print(scores.mean())

Bagging

from sklearn.ensemble import BaggingClassifier

bagging_clf = BaggingClassifier(RF2, n_estimators=20)
# 计算交叉验证的误差
scores = model_selection.cross_val_score(bagging_clf, x_data, y_data, cv=3)
# 求平均
print(scores.mean())

Adaboost

from sklearn.ensemble import AdaBoostClassifier

# AdaBoost模型
adaboost = AdaBoostClassifier(bagging_clf,n_estimators=10)
# 计算交叉验证的误差
scores = model_selection.cross_val_score(adaboost, x_data, y_data, cv=3)
# 求平均
print(scores.mean())

Stacking

from sklearn.ensemble import VotingClassifier
from mlxtend.classifier import StackingClassifier 

sclf = StackingClassifier(classifiers=[bagging_clf, mlp, LR],   
                          meta_classifier=LogisticRegression())

sclf2 = VotingClassifier([('adaboost',adaboost), ('mlp',mlp), ('LR',LR),('knn',knn),('dtree',dtree)])  

# 计算交叉验证的误差
scores = model_selection.cross_val_score(sclf2, x_data, y_data, cv=3)
# 求平均
print(scores.mean())

集成学习-乳腺癌预测

import numpy as np
import pandas as pd

import seaborn as sns
import matplotlib.pyplot as plt
import warnings
warnings.filterwarnings("ignore")

df = pd.read_csv("data.csv")
df.head()

df = df.drop('id', axis=1)

df.diagnosis.unique()

df['diagnosis'] = df['diagnosis'].map({'M':1,'B':0})
df.head()

df.describe()

# 画热力图，数值为两个变量之间的相关系数
plt.figure(figsize=(20,20))  
p=sns.heatmap(df.corr(), annot=True ,square=True) 
plt.show()

# 查看标签分布
print(df.diagnosis.value_counts())
# 使用柱状图的方式画出标签个数统计
p=df.diagnosis.value_counts().plot(kind="bar")
plt.show()

# 获取训练数据和标签
x_data  = df.drop(['diagnosis'], axis=1)
y_data = df['diagnosis']

from sklearn.model_selection import train_test_split
# 切分数据集，stratify=y表示切分后训练集和测试集中的数据类型的比例跟切分前y中的比例一致
# 比如切分前y中0和1的比例为1:2，切分后y_train和y_test中0和1的比例也都是1:2
x_train,x_test,y_train,y_test = train_test_split(x_data, y_data, test_size=0.3, stratify=y_data)

from sklearn.metrics import accuracy_score
from sklearn.neural_network import MLPClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, BaggingClassifier


classifiers = [
    KNeighborsClassifier(3),
    LogisticRegression(),
    MLPClassifier(hidden_layer_sizes=(20,50),max_iter=10000),
    DecisionTreeClassifier(),
    RandomForestClassifier(max_depth=9,min_samples_split=3),
    AdaBoostClassifier(),
    BaggingClassifier(),
    ]

log = []
for clf in classifiers:
    clf.fit(x_train, y_train)
    name = clf.__class__.__name__
    
    print("="*30)
    print(name)
    
    print('****Results****')
    test_predictions = clf.predict(x_test)
    acc = accuracy_score(y_test, test_predictions)
    print("Accuracy: {:.4%}".format(acc))
    
    log.append([name, acc*100])
    
print("="*30)

log = pd.DataFrame(log)
log

log.rename(columns={0: 'Classifier', 1:'Accuracy'}, inplace=True)

sns.barplot(x='Accuracy', y='Classifier', data=log, color="b")

plt.xlabel('Accuracy %')
plt.title('Classifier Accuracy')
plt.show()