統計學習(第二章)李航 感知機

1. 

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
import pandas as pd

#數據集加載
iris = load_iris()
df = pd.DataFrame(iris.data, columns=iris.feature_names)
df['label'] = iris.target
df.columns = [
    'sepal length', 'sepal width', 'petal length', 'petal width', 'label'
]
print(df.label.value_counts())

plt.scatter(df[:50]['sepal length'], df[:50]['sepal width'], label='0')
plt.scatter(df[50:100]['sepal length'], df[50:100]['sepal width'], label='1')
plt.xlabel('sepal length')
plt.ylabel('sepal width')
plt.legend()
plt.show()

data = np.array(df.iloc[:100, [0, 1, -1]])
x, y = data[:,:-1], data[:,-1]
y = np.array([1 if i==1 else -1 for i in y])

'感知機'
#數據線性可分，二分類
class Model:
    def __init__(self):
        self.w = np.ones(len(data[0])-1, dtype=np.float32)
        self.b = 0
        self.l_rate = 0.1

    def sign(self, x, w, b):
        return np.dot(w, x) + b

    def fit(self, x_train, y_train):#隨機梯度下降
        is_wrong = False
        while not is_wrong:
            wrong_count = 0
            for i in range(len(x_train)):
                x = x_train[i]
                y = y_train[i]
                if y * self.sign(x, self.w, self.b) <= 0:#感知機損失函數L(w,b) = -∑y*(wx+b)
                    #w,b參數更新
                    self.w = self.w + self.l_rate * np.dot(y, x)
                    self.b = self.b + self.l_rate * y
                    wrong_count += 1
            if wrong_count == 0:
                is_wrong = True
        return 'Perceptron Model'

    def score(self):
        pass

perceptron = Model()
print(perceptron.fit(x, y))

x_points = np.linspace(4, 7, 10)
y_ = -(perceptron.w[0] * x_points + perceptron.b) / perceptron.w[1]#各分類點到超平面的距離
plt.plot(x_points, y_)

plt.plot(data[:50, 0], data[:50, 1], 'bo', color='blue', label='0')
plt.plot(data[50:100, 0], data[50:100, 1], 'bo', color='orange', label='1')
plt.xlabel('sepal length')
plt.ylabel('sepal width')
plt.legend()
plt.show()