目录
一、转换器与估计器
二、分类算法
K-近邻算法
案例代码:
模型选择与调优
案例代码:
朴素贝叶斯算法:
朴素贝叶斯算法总结
案例代码:
决策树总结:
案例代码:
使用随机森林来实现:
随机森林总结
总结
本次案例的代码集:
KNN算法总结:
优点:
简单、易于理解、易于实现、无需训练
缺点:
1)必须指定K值,K值选定不当则分类精度不能保证。
2)懒惰算法,对测试样本分类时的计算量大,内存开销大
使用场景:
小数据场景,几千~几万条样本,具体使用看业务场景。
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier
def knn_iris():
"""
用KNN算法对iris数据进行分类
:return:
"""
# 1)获取数据
iris = load_iris()
# 2)划分数据集
x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=6
)
# 3) 特征工程:标准化
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 4) KNN算法预估器
estimator = KNeighborsClassifier(n_neighbors=3)
estimator.fit(x_train, y_train)
# 5) 模型评估
# 方法1:直接比对真实值和预测值
y_predict = estimator.predict(x_test)
print("y_predict:\n", y_predict)
print("直接比对真实值和预测值:\n", y_test == y_predict)
# 方法2: 计算准确率
score = estimator.score(x_test, y_test)
print("准确率为:\n", score)
return None
if __name__ == '__main__':
# 代码1:用KNN算法对iris数据进行分类
knn_iris()
案例代码
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import GridSearchCV
def knn_iris_gscv():
"""
用KNN算法对iris数据进行分类,添加网格搜索和交叉验证
:return:
"""
# 1)获取数据
iris = load_iris()
# 2)划分数据集
x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=6
)
# 3) 特征工程:标准化
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 4) KNN算法预估器
estimator = KNeighborsClassifier()
# 加入网格搜索和交叉验证
# 参数准备
param_dict = {"n_neighbors": [1, 3, 5, 7, 9, 11]}
estimator = GridSearchCV(estimator, param_grid=param_dict, cv=10)
estimator.fit(x_train, y_train)
# 5) 模型评估
# 方法1:直接比对真实值和预测值
y_predict = estimator.predict(x_test)
print("y_predict:\n", y_predict)
print("直接比对真实值和预测值:\n", y_test == y_predict)
# 方法2: 计算准确率
score = estimator.score(x_test, y_test)
print("准确率为:\n", score)
# 最佳参数结果:best_param_
print("最佳参数:\n", estimator.best_params_)
# 最佳结果:best_score_
print("最佳结果:\n", estimator.best_score_)
# 最佳估计器:best_estimator_
print("最佳估计器:\n", estimator.best_estimator_)
# 交叉验证结果: cv_results_
print("交叉验证结果:\n", estimator.cv_results_)
return None
if __name__ == '__main__':
# 代码2: 用KNN算法对iris数据进行分类,添加网格搜索和交叉验证
knn_iris_gscv()
facebook数据挖掘案例:
import pandas as pd
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.neighbors import KNeighborsClassifier
from sklearn.preprocessing import StandardScaler
def predict_data():
"""
数据预处理
:return:
"""
# 1)读取数据
data = pd.read_csv("./train.csv")
# 2)基本数据处理
# 缩小范围
data = data.query("x<2.5 & x>2 & y<1.5 & y>1.0")
# 处理时间特征
time_value = pd.to_datatime(data["time"], unit="s")
date = pd.DatetimeIndex(time_value)
data.loc[:, "day"] = date.day
data.loc[:, "weekday"] = date.weekday
data["hour"] = data.hour
# 3)过滤签到次数少的地点
data.groupby("place_id").count()
place_count = data.groupby("place_id").count()["row_id"]
data_final = data[data['place_id'].isin(place_count[place_count > 3].index.vlaues)]
# 筛选特征值和目标值
x = data_final[["x", "y", "accuracy", "day", "weekday", "hour"]]
y = data_final["place_id"]
# 数据集划分
# 机器学习
x_train, x_test, y_train, y_test = train_test_split(x, y)
# 3) 特征工程:标准化
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 4) KNN算法预估器
estimator = KNeighborsClassifier()
# 加入网格搜索和交叉验证
# 参数准备
param_dict = {"n_neighbors": [1, 3, 5, 7, 9, 11]}
estimator = GridSearchCV(estimator, param_grid=param_dict, cv=3)
estimator.fit(x_train, y_train)
# 5) 模型评估
# 方法1:直接比对真实值和预测值
y_predict = estimator.predict(x_test)
print("y_predict:\n", y_predict)
print("直接比对真实值和预测值:\n", y_test == y_predict)
# 方法2: 计算准确率
score = estimator.score(x_test, y_test)
print("准确率为:\n", score)
# 最佳参数结果:best_param_
print("最佳参数:\n", estimator.best_params_)
# 最佳结果:best_score_
print("最佳结果:\n", estimator.best_score_)
# 最佳估计器:best_estimator_
print("最佳估计器:\n", estimator.best_estimator_)
# 交叉验证结果: cv_results_
print("交叉验证结果:\n", estimator.cv_results_)
return None
if __name__ == '__main__':
predict_data()
案例代码
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
def nb_news():
"""
用朴素贝叶斯算法对新闻进行分类
:return:
"""
# 1)获取数据
news = fetch_20newsgroups(subset="all")
# 2)划分数据集
x_train, x_test, y_train, y_test = train_test_split(news.data, news.target)
# 3)特征工程文本特征抽取-tfidf
transfer = TfidfVectorizer()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 4)朴素贝叶斯算法预估器流程
estimator = MultinomialNB()
estimator.fit(x_train, y_train)
# 5)模型评估
# 方法1:直接比对真实值和预测值
y_predict = estimator.predict(x_test)
print("y_predict:\n", y_predict)
print("直接比对真实值和预测值:\n", y_test == y_predict)
# 方法2:计算准确率
score = estimator.score(x_test, y_test)
print("准确率为:\n", score)
return None
if __name__ == '__main__':
# 代码3:用朴素贝叶斯算法对新闻进行分类
nb_news()
优点:
对缺失数据不太敏感,算法比较简单,常用于文本分类。
分类准确度高,速度快。
缺点:
由于使用样本独立的假设,所以如果特征之间关联,预测效果不明显。
决策树
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.tree import DecisionTreeClassifier, export_graphviz
def decision_iris():
"""
用决策树对iris数据进行分类
:return:
"""
# 1)获取数据集
iris = load_iris()
# 2)划分数据集
x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=22)
# 3)决策树预估器
estimator = DecisionTreeClassifier(criterion="entropy")
estimator.fit(x_train, y_train)
# 4)模型评估
# 方法1:直接比对真实值和预测值
y_predict = estimator.predict(x_test)
print("y_predict:\n", y_predict)
print("直接比对真实值和预测值:\n", y_test == y_predict)
# 方法2: 计算准确率
score = estimator.score(x_test, y_test)
print("准确率为:\n", score)
# 可视化决策树
export_graphviz(estimator, out_file="iris_tree.dot", feature_names=iris.feature_names)
return None
if __name__ == '__main__':
# 代码4:用决策树对iris数据进行分类
decision_iris()
决策树支持可视化:
.dot文件转换为可视化图像的网页:Graphviz Online
优点:
可视化——解释性强
缺点:
容易产生过拟合,这时候使用随机森林效果会好些
决策树的实验项目——titanic数据的案例
import pandas as pd
from sklearn.feature_extraction import DictVectorizer
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier, export_graphviz
def decision_titanic():
# 1、获取数据
titanic = pd.read_csv("./titanic.csv")
print(titanic)
# 筛选特征值和目标值
x = titanic[["pclass", "age", "sex"]]
y = titanic["survived"]
# 2、数据处理
# 1)缺失值处理
x['age'].fillna(x["age"].mean(), inplace=True)
# 2)转换成字典
x = x.to_dict(orient="records")
# 3、数据集划分
x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=22)
transfer = DictVectorizer()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 3)决策树预估器
estimator = DecisionTreeClassifier(criterion="entropy", max_depth=8)
estimator.fit(x_train, y_train)
# 4)模型评估
# 方法1:直接比对真实值和预测值
y_predict = estimator.predict(x_test)
print("y_predict:\n", y_predict)
print("直接比对真实值和预测值:\n", y_test == y_predict)
# 方法2:计算准确率
score = estimator.score(x_test, y_test)
print("准确率为:\n", score)
# 可视化决策树
export_graphviz(estimator, out_file="titanic_tree.dot", feature_names=transfer.get_feature_names())
if __name__ == '__main__':
decision_titanic()
import pandas as pd
from sklearn.feature_extraction import DictVectorizer
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier, export_graphviz
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import GridSearchCV
def decision_titanic():
# 1、获取数据
titanic = pd.read_csv("./titanic.csv")
print(titanic)
# 筛选特征值和目标值
x = titanic[["pclass", "age", "sex"]]
y = titanic["survived"]
# 2、数据处理
# 1)缺失值处理
x['age'].fillna(x["age"].mean(), inplace=True)
# 2)转换成字典
x = x.to_dict(orient="records")
# 3、数据集划分
x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=22)
transfer = DictVectorizer()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 3)随机森林预估器
estimator = RandomForestClassifier()
# 加入网格搜索与交叉验证
# 参数准备
param_dict = {"n_estimators": [120, 200, 300, 500, 800, 1200],
"max_depth": [5, 8, 15, 25, 30]}
estimator = GridSearchCV(estimator, param_grid=param_dict, cv=3)
estimator.fit(x_train, y_train)
# 4)模型评估
# 方法1:直接比对真实值和预测值
y_predict = estimator.predict(x_test)
print("y_predict:\n", y_predict)
print("直接比对真实值和预测值:\n", y_test == y_predict)
# 方法2:计算准确率
score = estimator.score(x_test, y_test)
print("准确率为:\n", score)
# 可视化决策树
export_graphviz(estimator, out_file="titanic_tree.dot", feature_names=transfer.get_feature_names())
if __name__ == '__main__':
decision_titanic()
优点:
能够有效的运行在大数据集上
处理具有高维特征的输入样本,而且不需要降维。
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.tree import DecisionTreeClassifier, export_graphviz
def knn_iris():
"""
用KNN算法对iris数据进行分类
:return:
"""
# 1)获取数据
iris = load_iris()
# 2)划分数据集
x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=6
)
# 3) 特征工程:标准化
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 4) KNN算法预估器
estimator = KNeighborsClassifier(n_neighbors=3)
estimator.fit(x_train, y_train)
# 5) 模型评估
# 方法1:直接比对真实值和预测值
y_predict = estimator.predict(x_test)
print("y_predict:\n", y_predict)
print("直接比对真实值和预测值:\n", y_test == y_predict)
# 方法2: 计算准确率
score = estimator.score(x_test, y_test)
print("准确率为:\n", score)
return None
def knn_iris_gscv():
"""
用KNN算法对iris数据进行分类,添加网格搜索和交叉验证
:return:
"""
# 1)获取数据
iris = load_iris()
# 2)划分数据集
x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=6
)
# 3) 特征工程:标准化
transfer = StandardScaler()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 4) KNN算法预估器
estimator = KNeighborsClassifier()
# 加入网格搜索和交叉验证
# 参数准备
param_dict = {"n_neighbors": [1, 3, 5, 7, 9, 11]}
estimator = GridSearchCV(estimator, param_grid=param_dict, cv=10)
estimator.fit(x_train, y_train)
# 5) 模型评估
# 方法1:直接比对真实值和预测值
y_predict = estimator.predict(x_test)
print("y_predict:\n", y_predict)
print("直接比对真实值和预测值:\n", y_test == y_predict)
# 方法2: 计算准确率
score = estimator.score(x_test, y_test)
print("准确率为:\n", score)
# 最佳参数结果:best_param_
print("最佳参数:\n", estimator.best_params_)
# 最佳结果:best_score_
print("最佳结果:\n", estimator.best_score_)
# 最佳估计器:best_estimator_
print("最佳估计器:\n", estimator.best_estimator_)
# 交叉验证结果: cv_results_
print("交叉验证结果:\n", estimator.cv_results_)
return None
def nb_news():
"""
用朴素贝叶斯算法对新闻进行分类
:return:
"""
# 1)获取数据
news = fetch_20newsgroups(subset="all")
# 2)划分数据集
x_train, x_test, y_train, y_test = train_test_split(news.data, news.target)
# 3)特征工程文本特征抽取-tfidf
transfer = TfidfVectorizer()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)
# 4)朴素贝叶斯算法预估器流程
estimator = MultinomialNB()
estimator.fit(x_train, y_train)
# 5)模型评估
# 方法1:直接比对真实值和预测值
y_predict = estimator.predict(x_test)
print("y_predict:\n", y_predict)
print("直接比对真实值和预测值:\n", y_test == y_predict)
# 方法2:计算准确率
score = estimator.score(x_test, y_test)
print("准确率为:\n", score)
return None
def decision_iris():
"""
用决策树对iris数据进行分类
:return:
"""
# 1)获取数据集
iris = load_iris()
# 2)划分数据集
x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=22)
# 3)决策树预估器
estimator = DecisionTreeClassifier(criterion="entropy")
estimator.fit(x_train, y_train)
# 4)模型评估
# 方法1:直接比对真实值和预测值
y_predict = estimator.predict(x_test)
print("y_predict:\n", y_predict)
print("直接比对真实值和预测值:\n", y_test == y_predict)
# 方法2: 计算准确率
score = estimator.score(x_test, y_test)
print("准确率为:\n", score)
# 可视化决策树
export_graphviz(estimator, out_file="iris_tree.dot", feature_names=iris.feature_names)
return None
if __name__ == '__main__':
# 代码1:用KNN算法对iris数据进行分类
# knn_iris()
# 代码2: 用KNN算法对iris数据进行分类,添加网格搜索和交叉验证
# knn_iris_gscv()
# 代码3:用朴素贝叶斯算法对新闻进行分类
# nb_news()
# 代码4:用决策树对iris数据进行分类
decision_iris()