决策树的构造和展示

本是古典何须时尚 2023-06-21 13:24 20阅读 0赞

%matplotlib inline
    import matplotlib.pyplot as plt
    import pandas as pd

from sklearn.datasets.california_housing import fetch_california_housing
    housing = fetch_california_housing()
    print(housing.DESCR)

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70]

housing.data.shape

![在这里插入图片描述][2019121222420683.png]

housing.data[0]

![在这里插入图片描述][20191212224229954.png]

from sklearn import tree
    dtr = tree.DecisionTreeRegressor(max_depth = 2)
    # housing.target最终的结果值
    dtr.fit(housing.data[:, [6, 7]], housing.target)

![在这里插入图片描述][20191212224336922.png]

#要可视化显示 首先需要安装 graphviz http://www.graphviz.org/Download..php
    dot_data = \
        tree.export_graphviz(
            dtr,
            out_file = None,
            feature_names = housing.feature_names[6:8],
            filled = True,
            impurity = False,
            rounded = True
        )

#pip install pydotplus
    import pydotplus
    graph = pydotplus.graph_from_dot_data(dot_data)
    graph.get_nodes()[7].set_fillcolor("#FFF2DD")
    from IPython.display import Image
    Image(graph.create_png())

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 1]

graph.write_png("dtr_white_background.png")

True

### 参数选择 ###

from sklearn.model_selection import train_test_split
    data_train, data_test, target_train, target_test = \
        train_test_split(housing.data, housing.target, test_size = 0.1, random_state = 42)
    dtr = tree.DecisionTreeRegressor(random_state = 42)
    dtr.fit(data_train, target_train)
    
    dtr.score(data_test, target_test)

from sklearn.ensemble import RandomForestRegressor
    rfr = RandomForestRegressor( random_state = 42)
    rfr.fit(data_train, target_train)
    rfr.score(data_test, target_test)

from sklearn.grid_search import GridSearchCV
    tree_param_grid = {  'min_samples_split': list((3,6,9)),'n_estimators':list((10,50,100))}
    grid = GridSearchCV(RandomForestRegressor(),param_grid=tree_param_grid, cv=5)
    grid.fit(data_train, target_train)
    grid.grid_scores_, grid.best_params_, grid.best_score_

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 2]

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 3]

#### 使用找出来的最好的参数 ####

rfr = RandomForestRegressor( min_samples_split=3,n_estimators = 100,random_state = 42)
    rfr.fit(data_train, target_train)
    rfr.score(data_test, target_test)

![在这里插入图片描述][20191213105441875.png]

pd.Series(rfr.feature_importances_, index = housing.feature_names).sort_values(ascending = False)

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 4]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20191212222107338.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg==,size_16,color_FFFFFF,t_70
[2019121222420683.png]: https://img-blog.csdnimg.cn/2019121222420683.png
[20191212224229954.png]: https://img-blog.csdnimg.cn/20191212224229954.png
[20191212224336922.png]: https://img-blog.csdnimg.cn/20191212224336922.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 1]: https://img-blog.csdnimg.cn/20191213095018241.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 2]: https://img-blog.csdnimg.cn/20191213101718679.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 3]: https://img-blog.csdnimg.cn/20191213105223412.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg==,size_16,color_FFFFFF,t_70
[20191213105441875.png]: https://img-blog.csdnimg.cn/20191213105441875.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 4]: https://img-blog.csdnimg.cn/20191213105520171.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg==,size_16,color_FFFFFF,t_70