Python mlxtend库数据科学和机器学习补充工具功能探索

pip install mlxtend  

import pandas as pd
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from mlxtend.feature_selection import SequentialFeatureSelector as SFS

iris = load_iris()
X = iris.data
y = iris.target

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1)

scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

sfs = SFS(LogisticRegression(),
          k_features='best',
          forward=True,
          floating=False,
          scoring='accuracy',
          cv=5)
sfs = sfs.fit(X_train_scaled, y_train)

import matplotlib.pyplot as plt
from mlxtend.plotting import plot_sequential_feature_selection as plot_sfs

# 打印选择的特征
print(sfs.subsets_[3]['feature_names'])
# 输出准确率
print(sfs.subsets_[3]['avg_score'])
#('0', '2', '3')
#0.9523809523809523
# 绘制模型准确率
plot_sfs(sfs.get_metric_dict( )) 
plt.show()