「超级干货大放送」机器学习十二种经典模型实例
目录
实例一：线性回归波士顿房价
实例二：KNN实现电影分类
实例三：基于线性回归预测波士顿房价
实例四：sklearn完成逻辑回归鸢尾花分类
实例五：支持向量机完成逻辑回归鸢尾花分类
实例六：使用决策树实现鸢尾花分类
实例七：使用随机森林实现鸢尾花分类
实例八：使用朴素贝叶斯进行鸢尾花分类
实例九：使用Kmeans来进行鸢尾花分类
实例十：K最近邻的使用方式
实例十一：kmeans的其他展示方式
实例十二：Kmeans实现鸢尾花聚类
实例一：线性回归波士顿房价
'''
实例一：线性回归波士顿房价【回归问题】
'''
from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt
X, y = load_boston(return_X_y=True)
X1 = X[:,5:6]
train_x, test_x, train_y, test_y = train_test_split(X1, y, test_size=0.3, random_state=2)
lr = LinearRegression()
lr.fit(train_x, train_y)
result = lr.predict(test_x)
plt.scatter(train_x, train_y, color='blue')
plt.plot(test_x, result, color='red')
plt.show()
实例二：KNN实现电影分类
'''
实例二：KNN实现电影分类【分类问题】
'''
import numpy as np
import pandas as pd
train_data = {'宝贝当家':[45,2,9,'喜剧片'],
'美人鱼':[21,17,5,'喜剧片'],
'澳门风云3':[54,9,11,'喜剧片'],
'功夫熊猫3':[39,0,31,'喜剧片'],
'谍影重重':[5,2,57,'动作片'],
'叶问3':[3,2,65,'动作片'],
'我的特工爷爷':[6,4,21,'动作片'],
'奔爱':[7,46,4,'爱情片'],
'夜孔雀':[9,39,8,'爱情片'],
'代理情人':[9,38,2,'爱情片'],
'新步步惊心':[8,34,17,'爱情片'],
'伦敦陷落':[2,3,55,'动作片']
}
train_df = pd.DataFrame(train_data).T
train_df.columns = ['搞笑镜头','拥抱镜头','打斗镜头','电影类型']
test_data = {'唐人街探案':[23,3,17]}
def euclidean_distance(vec1,vec2):
return np.sqrt(np.sum(np.square(vec1 - vec2)))
K = 3
movie = '唐人街探案'
d = []
for train_x in train_df.values[:,:-1]:
test_x = np.array(test_data[movie])
d.append(euclidean_distance(train_x,test_x))
dd = pd.DataFrame(train_df.values, index=d)
dd1 = pd.DataFrame(dd.sort_index())
print(dd1.values[:K,-1:].max())
'
实例三：基于线性回归预测波士顿房价
'''
实例三：基于线性回归预测波士顿房价
'''
import pandas as pd
from sklearn.datasets import load_boston
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
boston = load_boston()
X = boston.data
y = boston.target
X = MinMaxScaler().fit_transform(X)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=2020)
import numpy as np
import matplotlib.pyplot as plt
class LinearRegression:
'''线性回归算法实现'''
def __init__(self, alpha=0.1, epoch=5000, fit_bias=True):
'''
alpha: 学习率，控制参数更新的幅度
epoch: 在整个训练集上训练迭代（参数更新）的次数
fit_bias: 是否训练偏置项参数
'''
self.alpha = alpha
self.epoch = epoch
self.cost_record = []
self.fit_bias = fit_bias
def predict(self, X_test):
'''
X_test: m x n 的 numpy 二维数组
'''
if self.fit_bias:
x_0 = np.ones(X_test.shape[0])
X_test = np.column_stack((x_0, X_test))
return np.dot(X_test, self.w)
def fit(self, X_train, y_train):
'''
X_train: m x n 的 numpy 二维数组
y_train：有 m 个元素的 numpy 一维数组
'''
if self.fit_bias:
x_0 = np.ones(X_train.shape[0])
X_train = np.column_stack((x_0, X_train))
m = X_train.shape[0]
n = X_train.shape[1]
self.w = np.ones(n)
for i in range(self.epoch):
y_pred = np.dot(X_train, self.w)
cost = np.dot(y_pred - y_train, y_pred - y_train) / (2 * m)
self.cost_record.append(cost)
self.w -= self.alpha / m * np.dot(y_pred - y_train, X_train)
self.save_model()
def polt_cost(self):
plt.plot(np.arange(self.epoch), self.cost_record)
plt.xlabel("epoch")
plt.ylabel("cost")
plt.show()
def save_model(self):
np.savetxt("model.txt", self.w)
def load_model(self):
self.w = np.loadtxt("model.txt")
model = LinearRegression()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
print('偏置参数：', 'ToDo')
print('特征权重：', 'ToDo')
print('预测结果：', y_pred[:5])
实例四：sklearn完成逻辑回归鸢尾花分类
'''
实例四：sklearn完成逻辑回归鸢尾花分类
'''
from sklearn import datasets
import numpy as np
import matplotlib.pyplot as plt
from mlxtend.plotting import plot_decision_regions
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.3, random_state=0)
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
from sklearn.linear_model import LogisticRegression
lr = LogisticRegression(C=1000.0, random_state=0)
lr.fit(X_train_std, y_train)
X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X_combined_std, y_combined, clf=lr, filler_feature_ranges=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.show()
实例五：支持向量机完成逻辑回归鸢尾花分类
'''
实例五：支持向量机完成逻辑回归鸢尾花分类
'''
from sklearn import datasets
import numpy as np
from sklearn.svm import SVC
import matplotlib.pyplot as plt
from mlxtend.plotting import plot_decision_regions
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.3, random_state=0)
from sklearn.preprocessing import StandardScaler
ss = StandardScaler().fit(X_train)
x_train_std = ss.transform(X_train)
x_test_std = ss.transform(X_test)
svc = SVC(kernel='rbf', random_state=0, gamma=0.2, C=1.0)
svc.fit(x_train_std,y_train)
X_combined_std = np.vstack((x_train_std, x_test_std))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X_combined_std, y_combined, clf=svc, filler_feature_ranges=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.show()
实例六：使用决策树实现鸢尾花分类
'''
实例六：使用决策树实现鸢尾花分类
'''
from sklearn import datasets
import numpy as np
from sklearn.svm import SVC
import matplotlib.pyplot as plt
from sklearn.tree import DecisionTreeClassifier
from mlxtend.plotting import plot_decision_regions
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.3, random_state=0)
from sklearn.preprocessing import StandardScaler
ss = StandardScaler().fit(X_train)
x_train_std = ss.transform(X_train)
x_test_std = ss.transform(X_test)
dtc = DecisionTreeClassifier(criterion='entropy',random_state=0,max_depth=3)
dtc.fit(X_train,y_train)
X_combined_std = np.vstack((x_train_std, x_test_std))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X_combined_std, y_combined, clf=dtc, filler_feature_ranges=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.show()
实例七：使用随机森林实现鸢尾花分类
'''
实例七：使用随机森林实现鸢尾花分类
'''
from sklearn import datasets
import numpy as np
from sklearn.svm import SVC
import matplotlib.pyplot as plt
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from mlxtend.plotting import plot_decision_regions
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.3, random_state=0)
from sklearn.preprocessing import StandardScaler
ss = StandardScaler().fit(X_train)
x_train_std = ss.transform(X_train)
x_test_std = ss.transform(X_test)
rfc = RandomForestClassifier(criterion='entropy',n_estimators=10, random_state=1,n_jobs=2)
rfc.fit(X_train,y_train)
X_combined_std = np.vstack((x_train_std, x_test_std))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X_combined_std, y_combined, clf=rfc, filler_feature_ranges=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.show()
实例八：使用朴素贝叶斯进行鸢尾花分类
'''
实例八：使用朴素贝叶斯进行鸢尾花分类
'''
from sklearn import datasets
import numpy as np
from sklearn.svm import SVC
import matplotlib.pyplot as plt
from sklearn.naive_bayes import GaussianNB
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from mlxtend.plotting import plot_decision_regions
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.3, random_state=0)
from sklearn.preprocessing import StandardScaler
ss = StandardScaler().fit(X_train)
x_train_std = ss.transform(X_train)
x_test_std = ss.transform(X_test)
gnb = GaussianNB()
gnb.fit(X_train,y_train)
X_combined_std = np.vstack((x_train_std, x_test_std))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X_combined_std, y_combined, clf=gnb, filler_feature_ranges=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.show()
实例九：使用Kmeans来进行鸢尾花分类
'''
实例九：使用Kmeans来进行鸢尾花分类
'''
from sklearn import datasets
import numpy as np
from sklearn.svm import SVC
import matplotlib.pyplot as plt
from sklearn.naive_bayes import GaussianNB
from sklearn.cluster import KMeans
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from mlxtend.plotting import plot_decision_regions
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.3, random_state=0)
from sklearn.preprocessing import StandardScaler
ss = StandardScaler().fit(X_train)
x_train_std = ss.transform(X_train)
x_test_std = ss.transform(X_test)
km = KMeans(n_clusters=3)
km.fit(X_train,y_train)
X_combined_std = np.vstack((x_train_std, x_test_std))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X_combined_std, y_combined, clf=km, filler_feature_ranges=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.show()
实例十：K最近邻的使用方式
'''
实例十：K最近邻的使用方式
'''
from sklearn import datasets
import numpy as np
from sklearn.svm import SVC
import matplotlib.pyplot as plt
from sklearn.naive_bayes import GaussianNB
from sklearn.cluster import KMeans
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from mlxtend.plotting import plot_decision_regions
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.3, random_state=0)
from sklearn.preprocessing import StandardScaler
ss = StandardScaler().fit(X_train)
x_train_std = ss.transform(X_train)
x_test_std = ss.transform(X_test)
knn = KNeighborsClassifier(n_neighbors=5, p=2, metric='minkowski')
knn.fit(x_train_std, y_train)
X_combined_std = np.vstack((x_train_std, x_test_std))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X_combined_std, y_combined, clf=knn, filler_feature_ranges=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
plt.show()
实例十一：kmeans的其他展示方式
''''
实例十一：•kmeans的其他展示方式
'''
import pandas as pd
from sklearn import datasets
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
iris = datasets.load_iris()
X = iris.data[:, [2, 3]]
y = iris.target
df = pd.DataFrame(X)
df.columns=['x','y']
df['kind'] = y
df['kind'] = y
data = iris
data1 = df
km = KMeans(n_clusters=3)
km.fit(data1)
predict = km.predict(data1)
colored = ['orange', 'green', 'pink']
col = [colored[i] for i in predict]
plt.scatter(data1['x'], data1['y'], color=col)
plt.xlabel('x')
plt.ylabel('y')
plt.show()
print(predict)
class_mapping = {'Iris-setosa': 0, 'Iris-versicolor': 1, 'Iris-virginica': 2}
data1['kind'] = data1['kind'].map(class_mapping)
c = [colored[i] for i in y]
plt.scatter(data1['x'], data1['y'], color=c)
plt.xlabel('x')
plt.ylabel('y')
plt.show()
实例十二：Kmeans实现鸢尾花聚类
import pandas as pd
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt
data = pd.read_csv(r"C:Users单纯小男子Downloadsiris.csv")
data1 = data.drop(['kind'], axis=1)
km = KMeans(n_clusters=3)
km.fit(data1)
predict = km.predict(data1)
colored = ['orange', 'green', 'pink']
col = [colored[i] for i in predict]
plt.scatter(data1['x'], data1['y'], color=col)
plt.xlabel('x')
plt.ylabel('y')
plt.show()
print(predict)
class_mapping = {'Iris-setosa': 0, 'Iris-versicolor': 1, 'Iris-virginica': 2}
data['kind'] = data['kind'].map(class_mapping)
c = [colored[i] for i in data['kind']]
plt.scatter(data['x'], data['y'], color=c)
plt.xlabel('x')
plt.ylabel('y')
plt.show()
相关知识
干货来袭，谷歌最新机器学习术语表（下）
【机器学习】Sklearn 集成学习
【机器学习】鸢尾花分类：机器学习领域经典入门项目实战
干货来袭，谷歌最新机器学习术语表
机器学习之路：经典的鸢尾花数据集
《机器学习》（西瓜书）学习笔记
机器学习术语表
机器学习=编程？NO！
机器学习与因果推断
机器学习鸢尾花数据集
网址: 「超级干货大放送」机器学习十二种经典模型实例 https://m.huajiangbk.com/newsview1385939.html
| 上一篇: leetcode5. 最长回文子 |
下一篇: 2024广州木棉花观赏点有哪些（ |
