本节介绍分类算法一:感知机模型
perceptron_class.py:
# -*- coding: utf-8 -*-
# @Time : 2018/7/16 17:30
# @Author : Alan
# @Email : xiezhengwen2013@163.com
# @File : perceptron_class.py
# @Software: PyCharm
import numpy as np
class Perceptron(object):
'''Perceptron classifier.
Parameters
------------
eta : float
Learning rate (between 0.0 and 1.0)
n_iter : int
Passes over the training dataset.
Attributes
-----------
w_ : 1d-array
Weights after fitting.
errors_ : list
Number of misclassifications in every epoch.
'''
def __init__(self, eta=0.01, n_iter=10):
self.eta = eta
self.n_iter = n_iter
def fit(self, X, y):
'''
Fit training data.
Parameters
----------
X : {array-like}, shape = [n_samples, n_features]
Training vectors, where n_samples
is the number of samples and
n_features is the number of features.
y : array-like, shape = [n_samples]
Target values.
Returns
-------
self : object
'''
self.w_ = np.zeros(1 + X.shape[1])
self.errors_ = []
for _ in range(self.n_iter):
errors = 0
for xi, target in zip(X, y):
update = self.eta * (target - self.predict(xi))
self.w_[1:] += update * xi
self.w_[0] += update
errors += int(update != 0.0)
self.errors_.append(errors)
return self
def net_input(self, X):
'''Calculate net input'''
return np.dot(X, self.w_[1:]) + self.w_[0]
def predict(self, X):
'''Return class label after unit step'''
return np.where(self.net_input(X) >= 0.0, 1, -1)
perceptron_test1.py:
'''
所用数据集为Lris数据集
plt.legend:显示图例
np.meshgrid:[X,Y] = meshgrid(x,y) 将向量x和y定义的区域转换成矩阵X和Y,其中矩阵X的行向量是向量x的简单复制,而矩阵Y的列向量是向量y的简单
假设x是长度为m的向量,y是长度为n的向量,则最终生成的矩阵X和Y的维度都是 n*m (注意不是m*n)。
https://www.aliyun.com/jiaocheng/516456.html
x.ravel():将二维数组降为一维,
x = np.array([[1, 2], [3, 4]])
x.ravel()
array([1, 2, 3, 4])
plt.contourf:绘制等高线,contourf会对等高线间的区域进行填充
plt.xlim():设置x轴刻度的取值范围
np.nrange():arange(start, end, step),例:np.arange(1,10,2)
array([1, 3, 5, 7, 9])
'''
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import perceptron_class
from matplotlib.colors import ListedColormap
df = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data', header=None)
df.tail()
y = df.iloc[0:100,4].values
y = np.where(y == 'Iris-setosa',-1,1)
X = df.iloc[0:100,[0,2]].values
plt.scatter(X[:50,0],X[:50,1],color = 'red',marker='o',label = 'setosa')
plt.scatter(X[50:100, 0], X[50:100, 1],color='blue', marker='x', label='versicolor')
plt.xlabel('petal length')
plt.ylabel('sepal length')
plt.legend(loc='upper left')
ppn = perceptron_class.Perceptron(eta=0.1,n_iter=10)
ppn.fit(X,y)
plt.plot(range(1,len(ppn.errors_)+1),ppn.errors_,marker='o')
#相当于plt.plot(x,y) x为从1到10,y为每次迭代出现的错误分类的个数
plt.xlabel('Epochs')
plt.ylabel('Number of misclassifications')
#plt.show()
def plot_decision_regions(X, y, classifier, resolution=0.02):
# setup marker generator and color map
markers = ('s', 'x', 'o', '^', 'v')
colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
cmap = ListedColormap(colors[:len(np.unique(y))])
# plot the decision surface
x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1
x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),
np.arange(x2_min, x2_max, resolution))
Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
Z = Z.reshape(xx1.shape)
plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)
plt.xlim(xx1.min(), xx1.max())
plt.ylim(xx2.min(), xx2.max())
# plot class samples
for idx, cl in enumerate(np.unique(y)):
plt.scatter(x=X[y == cl, 0], y=X[y == cl, 1],
alpha=0.8, c=cmap(idx),
marker=markers[idx], label=cl)
plot_decision_regions(X, y, classifier=ppn)
plt.xlabel('sepal length [cm]')
plt.ylabel('petal length [cm]')
plt.legend(loc='upper left')
plt.show()
结果图:
reference:
《python machine learning》