IndexError Traceback (most recent call last)
<ipython-input-45-a65b21b8df17> in <module>
----> 1 plot_decision_regions(X,y,ppn,resolution=0.02)
2 plt.xlabel('花径长度')
3 plt.ylabel('花瓣长度')
4 plt.legend(loc='upper left')
5 plt.show()
<ipython-input-44-85f310d48d44> in plot_decision_regions(X, y, classifier, resolution)
30
31 for idx,cl in enumerate(np.unique(y)):
---> 32 plt.scatter(x=X[y==cl,0],y=X[y==cl,1],alpha=0.8,c=cmap(idx),marker=marker[idx],label=cl)
IndexError: boolean index did not match indexed array along dimension 0; dimension is 100 but corresponding boolean dimension is 101
望采纳~~
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
from matplotlib.colors import ListedColormap
class Perceptron(object):
def __init__(self, eta = 0.01, n_iter = 10):
self.eta = eta
self.n_iter = n_iter
def fit(self, X, y):
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)
def net_input(self, X):
return np.dot(X, self.w_[1:]) + self.w_[0]
def predict(self, X):
return np.where(self.net_input(X) >= 0.0, 1, -1)
file = "C:/Users/YYDL/Desktop/data.csv"
df = pd.read_csv(file, header = None)
y = df.loc[0:100, 4].values
y = np.where(y == 'Iris-setosa', -1, 1)
X = df.iloc[0:100, [0, 2]].values
ppn = Perceptron(eta=0.1, n_iter=10)
ppn.fit(X, y)
def plot_decision_region(X, y, classifier, resolution=0.02):
marker = ('s', 'x', 'o', 'v')
colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
cmap = ListedColormap(colors[:len(np.unique(y))])
x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max()
x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max()
print(x1_min, x1_max)
print(x2_min, x2_max)
xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution), np.arange(x2_min, x2_max, resolution))
print(np.arange(x1_min, x1_max, resolution).shape)
print(np.arange(x1_min, x1_max, resolution))
print(xx1.shape)
print(xx1)
print(np.arange(x2_min, x2_max, resolution).shape)
print(np.arange(x2_min, x2_max, resolution))
print(xx2.shape)
print(xx2)
plot_decision_region(X, y, ppn, resolution=0.02)将y = df.loc[0:100, 4].values改为y = df.iloc[0:100, 4].values
看出区别了吗？loc前面多个i。不然y的维度为101。
当然你也可以直接改成y = df.loc[0:99, 4].values