U
    ½mœdUB  ã                   @   sT  d Z ddlmZmZ ddlmZ ddlmZ ddlZddl	m
Z
 ddlmZmZ ddlmZ dd	lmZmZmZ dd
lmZ ddlmZ ddgddgddgddgddgddggZddddddgZddgddgddgddgddgddggZddddddgZddddddgZdd„ Zdd„ Zdd„ Zdd„ Zdd„ Z dd„ Z!dd„ Z"d d!„ Z#d"d#„ Z$dS )$zG
Testing for export functions of decision trees (sklearn.tree.export).
é    )ÚfinditerÚsearch)Údedent)ÚRandomStateN)Úis_classifier)ÚDecisionTreeClassifierÚDecisionTreeRegressor)ÚGradientBoostingClassifier)Úexport_graphvizÚ	plot_treeÚexport_text)ÚStringIO)ÚNotFittedErroréþÿÿÿéÿÿÿÿé   é   é   g      à?c               
   C   s˜  t ddddd�} |  tt¡ t| d d�}d}||ks8t‚t| ddgd d	�}d
}||ksZt‚t| ddgd d�}d}||ks|t‚t| dddddd dd�}d}||ks¤t‚t| ddd d�}d}||ksÄt‚t| ddd dd�}d}||ksæt‚t ddddd�} | jtttd�} t| ddd d�}d}||k�s(t‚tddddd�} |  tt¡ t| ddd dddd�}d}||k�slt‚t dd�} |  tt	¡ t| dd d �}d!}d S )"Nr   r   Úgini©Ú	max_depthÚmin_samples_splitÚ	criterionÚrandom_state©Úout_filea„  digraph Tree {
node [shape=box, fontname="helvetica"] ;
edge [fontname="helvetica"] ;
0 [label="x[0] <= 0.0\ngini = 0.5\nsamples = 6\nvalue = [3, 3]"] ;
1 [label="gini = 0.0\nsamples = 3\nvalue = [3, 0]"] ;
0 -> 1 [labeldistance=2.5, labelangle=45, headlabel="True"] ;
2 [label="gini = 0.0\nsamples = 3\nvalue = [0, 3]"] ;
0 -> 2 [labeldistance=2.5, labelangle=-45, headlabel="False"] ;
}Zfeature0Zfeature1)Úfeature_namesr   aˆ  digraph Tree {
node [shape=box, fontname="helvetica"] ;
edge [fontname="helvetica"] ;
0 [label="feature0 <= 0.0\ngini = 0.5\nsamples = 6\nvalue = [3, 3]"] ;
1 [label="gini = 0.0\nsamples = 3\nvalue = [3, 0]"] ;
0 -> 1 [labeldistance=2.5, labelangle=45, headlabel="True"] ;
2 [label="gini = 0.0\nsamples = 3\nvalue = [0, 3]"] ;
0 -> 2 [labeldistance=2.5, labelangle=-45, headlabel="False"] ;
}ÚyesÚno)Úclass_namesr   aª  digraph Tree {
node [shape=box, fontname="helvetica"] ;
edge [fontname="helvetica"] ;
0 [label="x[0] <= 0.0\ngini = 0.5\nsamples = 6\nvalue = [3, 3]\nclass = yes"] ;
1 [label="gini = 0.0\nsamples = 3\nvalue = [3, 0]\nclass = yes"] ;
0 -> 1 [labeldistance=2.5, labelangle=45, headlabel="True"] ;
2 [label="gini = 0.0\nsamples = 3\nvalue = [0, 3]\nclass = no"] ;
0 -> 2 [labeldistance=2.5, labelangle=-45, headlabel="False"] ;
}TFÚsans)ÚfilledÚimpurityÚ
proportionZspecial_charactersÚroundedr   Úfontnameaí  digraph Tree {
node [shape=box, style="filled, rounded", color="black", fontname="sans"] ;
edge [fontname="sans"] ;
0 [label=<x<SUB>0</SUB> &le; 0.0<br/>samples = 100.0%<br/>value = [0.5, 0.5]>, fillcolor="#ffffff"] ;
1 [label=<samples = 50.0%<br/>value = [1.0, 0.0]>, fillcolor="#e58139"] ;
0 -> 1 [labeldistance=2.5, labelangle=45, headlabel="True"] ;
2 [label=<samples = 50.0%<br/>value = [0.0, 1.0]>, fillcolor="#399de5"] ;
0 -> 2 [labeldistance=2.5, labelangle=-45, headlabel="False"] ;
}r   )r   r   r   zâdigraph Tree {
node [shape=box, fontname="helvetica"] ;
edge [fontname="helvetica"] ;
0 [label="x[0] <= 0.0\ngini = 0.5\nsamples = 6\nvalue = [3, 3]\nclass = y[0]"] ;
1 [label="(...)"] ;
0 -> 1 ;
2 [label="(...)"] ;
0 -> 2 ;
})r   r!   r   Znode_idsa;  digraph Tree {
node [shape=box, style="filled", color="black", fontname="helvetica"] ;
edge [fontname="helvetica"] ;
0 [label="node #0\nx[0] <= 0.0\ngini = 0.5\nsamples = 6\nvalue = [3, 3]", fillcolor="#ffffff"] ;
1 [label="(...)", fillcolor="#C0C0C0"] ;
0 -> 1 ;
2 [label="(...)", fillcolor="#C0C0C0"] ;
0 -> 2 ;
})Zsample_weight)r!   r"   r   aÏ  digraph Tree {
node [shape=box, style="filled", color="black", fontname="helvetica"] ;
edge [fontname="helvetica"] ;
0 [label="x[0] <= 0.0\nsamples = 6\nvalue = [[3.0, 1.5, 0.0]\n[3.0, 1.0, 0.5]]", fillcolor="#ffffff"] ;
1 [label="samples = 3\nvalue = [[3, 0, 0]\n[3, 0, 0]]", fillcolor="#e58139"] ;
0 -> 1 [labeldistance=2.5, labelangle=45, headlabel="True"] ;
2 [label="x[0] <= 1.5\nsamples = 3\nvalue = [[0.0, 1.5, 0.0]\n[0.0, 1.0, 0.5]]", fillcolor="#f1bd97"] ;
0 -> 2 [labeldistance=2.5, labelangle=-45, headlabel="False"] ;
3 [label="samples = 2\nvalue = [[0, 1, 0]\n[0, 1, 0]]", fillcolor="#e58139"] ;
2 -> 3 ;
4 [label="samples = 1\nvalue = [[0.0, 0.5, 0.0]\n[0.0, 0.0, 0.5]]", fillcolor="#e58139"] ;
2 -> 4 ;
}Zsquared_error)r!   Zleaves_parallelr   Úrotater$   r%   aT  digraph Tree {
node [shape=box, style="filled, rounded", color="black", fontname="sans"] ;
graph [ranksep=equally, splines=polyline] ;
edge [fontname="sans"] ;
rankdir=LR ;
0 [label="x[0] <= 0.0\nsquared_error = 1.0\nsamples = 6\nvalue = 0.0", fillcolor="#f2c09c"] ;
1 [label="squared_error = 0.0\nsamples = 3\nvalue = -1.0", fillcolor="#ffffff"] ;
0 -> 1 [labeldistance=2.5, labelangle=-45, headlabel="True"] ;
2 [label="squared_error = 0.0\nsamples = 3\nvalue = 1.0", fillcolor="#e58139"] ;
0 -> 2 [labeldistance=2.5, labelangle=45, headlabel="False"] ;
{rank=same ; 0} ;
{rank=same ; 1; 2} ;
}©r   )r!   r   z¾digraph Tree {
node [shape=box, style="filled", color="black", fontname="helvetica"] ;
edge [fontname="helvetica"] ;
0 [label="gini = 0.0\nsamples = 6\nvalue = 6.0", fillcolor="#ffffff"] ;
})
r   ÚfitÚXÚyr
   ÚAssertionErrorÚy2Úwr   Ú
y_degraded)ÚclfZ	contents1Z	contents2© r0   úW/home/sam/Atlas/atlas_env/lib/python3.8/site-packages/sklearn/tree/tests/test_export.pyÚtest_graphviz_toy   sª       ÿÿ  ÿÿÿøÿÿ    ÿÿ   ÿÿ   ÿù
ÿ
ÿr2   c               	   C   sR  t ddd�} tƒ }t t¡� t| |ƒ W 5 Q R X |  tt¡ d}tjt	|d�� t| d dgd� W 5 Q R X d}tjt	|d�� t| d dd	d
gd� W 5 Q R X d}tjt
|d�� t|  tt¡jƒ W 5 Q R X tƒ }t t¡� t| |g d� W 5 Q R X tƒ }tjt	dd�� t| |dd� W 5 Q R X tjt	dd�� t| |dd� W 5 Q R X d S )Nr   r   )r   r   z?Length of feature_names, 1 does not match number of features, 2©ÚmatchÚa©r   z?Length of feature_names, 3 does not match number of features, 2ÚbÚczis not an estimator instance)r   zshould be greater or equalr   )Ú	precisionzshould be an integerÚ1)r   r   ÚpytestÚraisesr   r
   r(   r)   r*   Ú
ValueErrorÚ	TypeErrorZtree_Ú
IndexError)r/   ÚoutÚmessager0   r0   r1   Útest_graphviz_errorsü   s,    rB   c                  C   s†   t ddd�} |  tt¡ tƒ }t| |d� tddd�} |  tt¡ | jD ]}t|d |d� qHtd| 	¡ ƒD ]}d| 
¡ kslt‚qld S )NÚfriedman_mser   )r   r   r   r   )Zn_estimatorsr   z\[.*?samples.*?\])r   r(   r)   r*   r   r
   r	   Zestimators_r   ÚgetvalueÚgroupr+   )r/   Údot_dataZ	estimatorÚfindingr0   r0   r1   Útest_friedman_mse_in_graphviz#  s    
rH   c            	      C   s8  t dƒ} t dƒ}t|  d¡| d¡f|  d¡|jddd�ftdd	d
d�td
d	d�fƒD ]Ü\}}}| ||¡ dD ]À}t|d |dd�}td|ƒD ]&}t	t
d| ¡ ƒ ¡ ƒ|d
 ksŽt‚qŽt|ƒrÄd}nd}t||ƒD ]&}t	t
d| ¡ ƒ ¡ ƒ|d
 ksÒt‚qÒtd|ƒD ]*}t	t
d| ¡ ƒ ¡ ƒ|d
 k�st‚�qqpqVd S )Nr   é   )é   r   )éè  é   )rJ   )rK   )ÚsizerC   r   r   )r   r   r   ©r   r   )rL   r   T)r   r9   r#   zvalue = \d+\.\d+z\.\d+zgini = \d+\.\d+zfriedman_mse = \d+\.\d+z<= \d+\.\d+)r   ÚzipZrandom_sampleÚrandintr   r   r(   r
   r   Úlenr   rE   r+   r   )	Zrng_regZrng_clfr)   r*   r/   r9   rF   rG   Úpatternr0   r0   r1   Útest_precision2  s<      ÿ
üý   ÿ$$rS   c               	   C   sÆ   t ddd�} |  tt¡ d}tjt|d�� t| dd� W 5 Q R X d}tjt|d�� t| d	gd
� W 5 Q R X d}tjt|d�� t| dd� W 5 Q R X d}tjt|d�� t| dd� W 5 Q R X d S )Nr   r   rN   z max_depth bust be >= 0, given -1r3   r   r'   z,feature_names must contain 2 elements, got 1r5   r6   zdecimals must be >= 0, given -1©Údecimalszspacing must be > 0, given 0©Úspacing)r   r(   r)   r*   r;   r<   r=   r   )r/   Úerr_msgr0   r0   r1   Útest_export_text_errors^  s    rY   c                  C   sV  t ddd�} |  tt¡ tdƒ ¡ }t| ƒ|ks4t‚t| dd�|ksHt‚t| dd�|ks\t‚tdƒ ¡ }t| dd	gd
�|ks€t‚tdƒ ¡ }t| dd�|ks t‚tdƒ ¡ }t| dd�|ksÀt‚ddgddgddgddgddgddgddgg}dddddddg}t ddd�} |  ||¡ tdƒ ¡ }t| dd�|k�s:t‚ddgddgddgddgddgddgg}ddgddgddgddgddgddgg}tddd�}| ||¡ tdƒ ¡ }t|dd�|k�sÄt‚t|ddd�|k�sÜt‚dgdgdgdgdgdgg}tddd�}| ||¡ tdƒ ¡ }t|ddgd�|k�s6t‚t|dddgd�|k�sRt‚d S )Nr   r   rN   zh
    |--- feature_1 <= 0.00
    |   |--- class: -1
    |--- feature_1 >  0.00
    |   |--- class: 1
    r'   é
   zX
    |--- b <= 0.00
    |   |--- class: -1
    |--- b >  0.00
    |   |--- class: 1
    r5   r7   r6   z”
    |--- feature_1 <= 0.00
    |   |--- weights: [3.00, 0.00] class: -1
    |--- feature_1 >  0.00
    |   |--- weights: [0.00, 3.00] class: 1
    T)Úshow_weightsz\
    |- feature_1 <= 0.00
    | |- class: -1
    |- feature_1 >  0.00
    | |- class: 1
    r   rV   r   r   rL   z{
    |--- feature_1 <= 0.00
    |   |--- class: -1
    |--- feature_1 >  0.00
    |   |--- truncated branch of depth 2
    zy
    |--- feature_1 <= 0.0
    |   |--- value: [-1.0, -1.0]
    |--- feature_1 >  0.0
    |   |--- value: [1.0, 1.0]
    rT   )rU   r[   zq
    |--- first <= 0.0
    |   |--- value: [-1.0, -1.0]
    |--- first >  0.0
    |   |--- value: [1.0, 1.0]
    Úfirst)rU   r   )rU   r[   r   )	r   r(   r)   r*   r   Úlstripr   r+   r   )r/   Zexpected_reportZX_lZy_lZX_moZy_moÚregZX_singler0   r0   r1   Útest_export_textp  s`    ÿ	ÿÿÿ.ÿ((ÿÿÿÿr_   c                 C   s€   t ddddd�}| tt¡ ddg}t||d�}t|ƒdks@t‚|d  ¡ d	ksTt‚|d
  ¡ dksht‚|d  ¡ dks|t‚d S )Nr   r   Zentropyr   ú
first featÚsepal_widthr6   r   z:first feat <= 0.0
entropy = 1.0
samples = 6
value = [3, 3]r   z(entropy = 0.0
samples = 3
value = [3, 0]z(entropy = 0.0
samples = 3
value = [0, 3]©r   r(   r)   r*   r   rQ   r+   Zget_text©Úpyplotr/   r   Znodesr0   r0   r1   Útest_plot_tree_entropyÓ  s        ÿ
ÿÿre   c                 C   s€   t ddddd�}| tt¡ ddg}t||d�}t|ƒdks@t‚|d  ¡ d	ksTt‚|d
  ¡ dksht‚|d  ¡ dks|t‚d S )Nr   r   r   r   r`   ra   r6   r   z7first feat <= 0.0
gini = 0.5
samples = 6
value = [3, 3]r   z%gini = 0.0
samples = 3
value = [3, 0]z%gini = 0.0
samples = 3
value = [0, 3]rb   rc   r0   r0   r1   Útest_plot_tree_giniç  s        ÿ
ÿÿrf   c              	   C   s(   t ƒ }t t¡� t|ƒ W 5 Q R X d S )N)r   r;   r<   r   r   )rd   r/   r0   r0   r1   Útest_not_fitted_treeû  s    rg   )%Ú__doc__Úrer   r   Útextwrapr   Znumpy.randomr   r;   Zsklearn.baser   Zsklearn.treer   r   Zsklearn.ensembler	   r
   r   r   Úior   Zsklearn.exceptionsr   r)   r*   r,   r-   r.   r2   rB   rH   rS   rY   r_   re   rf   rg   r0   r0   r0   r1   Ú<module>   s2   (( d',c