决策树（决策树的分支深度及重要特征检测）

Posted 2020-07-02 挣脱生命的束缚...

import matplotlib.pyplot as plt
from sklearn import datasets
import numpy as np
from sklearn.tree import DecisionTreeClassifier

n_features = 200
X, y = datasets.make_classification(750, 200,n_informative=5)

#后面的P，是正负的比例
training = np.random.choice([True, False], p=[.75, .25],size=len(y))

c = 0
for x in training:
    if(x == True):
        c = c+1
print(c,c/750)


accuracies = []
for x in np.arange(1, n_features+1):
    dt = DecisionTreeClassifier(max_depth=x)
    dt.fit(X[training], y[training])
    preds = dt.predict(X[~training])
    accuracies.append((preds == y[~training]).mean())

f, ax = plt.subplots(figsize=(7, 5))
ax.plot(range(1, n_features+1), accuracies, color=\'k\')
ax.set_title("Decision Tree Accuracy")
ax.set_ylabel("% Correct")
ax.set_xlabel("Max Depth")
f.show()


N = 15
f, ax = plt.subplots(figsize=(7, 5))
ax.plot(range(1, n_features+1)[:N], accuracies[:N], color=\'k\')
ax.set_title("Decision Tree Accuracy")
ax.set_ylabel("% Correct")
ax.set_xlabel("Max Depth")
f.show()

\'\'\'
老的版本无这个参数,这个参数很好，可以检查重要的特征
dt_ci = DecisionTreeClassifier(compute_importances=True)
dt.fit(X, y)
ne0 = dt.feature_importances_ != 0
y_comp = dt.feature_importances_[ne0]
x_comp = np.arange(len(dt.feature_importances_))[ne0]
f, ax = plt.subplots(figsize=(7, 5))
ax.bar(x_comp, y_comp)
f.show()
\'\'\'