【发布时间】：2021-11-18 10:22:00
【问题描述】：
我运行了这段代码
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_blobs
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.covariance import OAS
n_train = 20 # samples for training
n_test = 200 # samples for testing
n_averages = 50 # how often to repeat classification
n_features_max = 75 # maximum number of features
step = 4 # step size for the calculation
def generate_data(n_samples, n_features):
"""Generate random blob-ish data with noisy features.
This returns an array of input data with shape `(n_samples, n_features)`
and an array of `n_samples` target labels.
Only one feature contains discriminative information, the other features
contain only noise.
"""
X, y = make_blobs(n_samples=n_samples, n_features=1, centers=[[-2], [2]])
# add non-discriminative features
if n_features > 1:
X = np.hstack([X, np.random.randn(n_samples, n_features - 1)])
return X, y
acc_clf1, acc_clf2, acc_clf3 = [], [], []
n_features_range = range(1, n_features_max + 1, step)
for n_features in n_features_range:
score_clf1, score_clf2, score_clf3 = 0, 0, 0
for _ in range(n_averages):
X, y = generate_data(n_train, n_features)
clf1 = LinearDiscriminantAnalysis(solver='lsqr',
shrinkage='auto').fit(X, y)
clf2 = LinearDiscriminantAnalysis(solver='lsqr',
shrinkage=None).fit(X, y)
oa = OAS(store_precision=False, assume_centered=False)
clf3 = LinearDiscriminantAnalysis(solver='lsqr',
covariance_estimator=oa).fit(X, y)
X, y = generate_data(n_test, n_features)
score_clf1 += clf1.score(X, y)
score_clf2 += clf2.score(X, y)
score_clf3 += clf3.score(X, y)
acc_clf1.append(score_clf1 / n_averages)
acc_clf2.append(score_clf2 / n_averages)
acc_clf3.append(score_clf3 / n_averages)
features_samples_ratio = np.array(n_features_range) / n_train
plt.plot(features_samples_ratio, acc_clf1, linewidth=2,
label="Linear Discriminant Analysis with Ledoit Wolf", color='navy')
plt.plot(features_samples_ratio, acc_clf2, linewidth=2,
label="Linear Discriminant Analysis", color='gold')
plt.plot(features_samples_ratio, acc_clf3, linewidth=2,
label="Linear Discriminant Analysis with OAS", color='red')
plt.xlabel('n_features / n_samples')
plt.ylabel('Classification accuracy')
plt.legend(loc=3, prop={'size': 12})
plt.suptitle('Linear Discriminant Analysis vs. ' + '\n'
+ 'Shrinkage Linear Discriminant Analysis vs. ' + '\n'
+ 'OAS Linear Discriminant Analysis (1 discriminative feature)')
plt.show()
这是一个来自 sklearn here的例子
我遇到了这个错误：
TypeError: __init__() got an unexpected keyword argument 'covariance_estimator'
从这一行
clf3 = LinearDiscriminantAnalysis(solver='lsqr',
covariance_estimator=oa).fit(X, y)
对我来说，它在语法上似乎是正确的。所以，我不确定出了什么问题，或者这个参数可能存在版本依赖关系（？）。
任何想法都将不胜感激。
【问题讨论】：
标签： python-3.x scikit-learn linear-discriminant