Question

import pandas as pd
import numpy as np
from sklearn import model_selection
from sklearn.model_selection import KFold
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.svm import SVC
import matplotlib.pyplot as plt
from sklearn.model_selection import learning_curve
 
data = pd.read_csv("training5.csv")
X= np.array(data[['x1','x2']])
y=np.array(data['y'])
np.random.seed(55)
 
estimator = LogisticRegression()
 
 
 
def randomize(X, Y):
    permutation = np.random.permutation(Y.shape[0])
    X2 = X[permutation,:]
    Y2 = Y[permutation]
    return X2, Y2
 
X2, y2 = randomize(X, y)
 
def draw_learning_curves(X, y, estimator, num_trainings):
    train_sizes, train_scores, test_scores = learning_curve(
        estimator, X2, y2, cv=None, n_jobs=1, train_sizes=np.linspace(.1, 1.0, num_trainings))
 
    train_scores_mean = np.mean(train_scores, axis=1)
    train_scores_std = np.std(train_scores, axis=1)
    test_scores_mean = np.mean(test_scores, axis=1)
    test_scores_std = np.std(test_scores, axis=1)
 
    plt.grid()
 
    plt.title("Learning Curves")
    plt.xlabel("Training examples")
    plt.ylabel("Score")
 
    plt.plot(train_scores_mean, 'o-', color="g",
             label="Training score")
    plt.plot(test_scores_mean, 'o-', color="y",
             label="Cross-validation score")
 
 
    plt.legend(loc="best")
 
    plt.show()

数据http://www.mediafire.com/file/mik8ufsxp91auy4/training5.csv/file 我对ML和python还是陌生的，所以有人可以从def randomize（X，Y）到代码末尾解释每个细节的工作原理 TIA <3

Answer 1

这是一个很大的问题，但是不幸的是，在Stackoverflow答案中，让狗穿过代码的每一行都是不可行的。我建议您查看DataCamp以获得涵盖您在此处显示的所有内容的优秀课程。

一个简单的立即解决方案是让您在定义函数后调用它。在当前代码块的末尾，只需添加：

draw_learning_curves(X2, y2, estimator, 5)

这将执行您使用X2，y2和estimator变量作为参数定义的函数。将最后一个参数更改为您想可视化的任意数量的训练。

plt.show（）无法与此代码一起使用

1 个答案: