code-data-science/xgboost_visual_explanation.py at master · yang-zhang/code-data-science · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68

# coding: utf-8

# # Setup

# In[24]:

get_ipython().magic('matplotlib inline')
import numpy as np
import pandas as pd

import xgboost

import sklearn.datasets
import sklearn.model_selection
import sklearn.metrics


# # [Example 1](http://machinelearningmastery.com/develop-first-xgboost-model-python-scikit-learn/)

# In[25]:

data = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/pima-indians-diabetes/pima-indians-diabetes.data',
           header=None)
data = np.array(data)

X_train = data[:, :-1]

y_train = data[:, -1]

mdl = xgboost.XGBClassifier()

mdl.fit(X_train, y_train)


# In[26]:

xgboost.plot_importance(mdl)


# In[27]:

xgboost.plot_tree(mdl)


# # Example 2: Iris

# In[28]:

data = sklearn.datasets.load_iris()

X_train = data.data

y_train = data.target

mdl = xgboost.XGBClassifier()

mdl.fit(X_train, y_train)


# In[29]:

xgboost.plot_tree(mdl)


# In[30]:

xgboost.plot_importance(mdl)