这个比例是什么意思？

Question

我试图通过使用我找到的代码来查看数据集中最有贡献的特征。代码如下

def f_importances(coef, names):
    imp = coef
    imp,names = zip(*sorted(zip(imp,names)))
    plt.barh(range(len(names)), imp, align='center')
    plt.yticks(range(len(names)), names)
    plt.show()

features_names = ['text', 'jumlah kata', 'jam']

n_classes = 3
n_features = len(features_names)

clf_coef_ = np.random.randint(1, 30, size=(int(0.5*n_classes*(n_classes-1)), n_features))

f_importances(clf_coef_.sum(axis=0), features_names)

从该代码中，我得到了以下结果

我的问题是

1. X 平面上的数字是什么意思？有 10、20、30 等等。我无法询问上传者。
2. 这似乎是随机的。如何让它不随机？例如我想使用所有的数据

Answer 1

第一个问题：

features_names = ['text', 'jumlah kata', 'jam']

n_classes = 3
n_features = len(features_names)

clf_coef_ = np.random.randint(1, 30, size=(int(0.5*n_classes*(n_classes-1)), n_features))

# clf_coef_ is a 3*3 random matrix
# each of its value is in range(1,30)
# for example
# [[22  4 22]
#  [15 18  8]
#  [23 22 13]]

f_importances(clf_coef_.sum(axis=0), features_names)
# clf_coef_.sum(axis=0)
# summary on columns
#
# [22+15+23,  4+18+22,   22+8+13]
# then it will become [60, 44, 43]

# f_importances finally will take arguments:
# [60,44,43] & ['text', 'jumlah kata', 'jam']
# sequence is corresponded
# sorted by values (this may differ with your codes, due to random values)
# jam  --> 43
# jumlah kata  --> 44
# text --> 60
# then plot will be got

要回答您的第二个问题，您可以将clf_coef_ 不定义为随机数组。