U
    mdUB                     @   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).
    )finditersearch)dedent)RandomStateN)is_classifier)DecisionTreeClassifierDecisionTreeRegressor)GradientBoostingClassifier)export_graphviz	plot_treeexport_text)StringIO)NotFittedError         g      ?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stt| ddd d}d}||kstt| ddd dd}d}||kst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   gini	max_depthmin_samples_split	criterionrandom_state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)feature_namesr   a  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"] ;
}yesno)class_namesr   a  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"] ;
}TFsans)filledimpurity
proportionZspecial_charactersroundedr   fontnamea  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   zdigraph 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   a  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   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   zdigraph 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   fitXyr
   AssertionErrory2wr   
y_degraded)clfZ	contents1Z	contents2 r0   W/home/sam/Atlas/atlas_env/lib/python3.8/site-packages/sklearn/tree/tests/test_export.pytest_graphviz_toy   s                   

r2   c               	   C   sR  t ddd} t }tt t| | 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 W 5 Q R X t }tt t| |g d W 5 Q R X t }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matchar   z?Length of feature_names, 3 does not match number of features, 2bczis not an estimator instance)r   zshould be greater or equalr   )	precisionzshould be an integer1)r   r   pytestraisesr   r
   r(   r)   r*   
ValueError	TypeErrorZtree_
IndexError)r/   outmessager0   r0   r1   test_graphviz_errors   s,    rB   c                  C   s   t ddd} | tt t }t| |d tddd} | tt | jD ]}t|d |d qHtd|	 D ]}d|
 ksltqld S )Nfriedman_mser   )r   r   r   r   )Zn_estimatorsr   z\[.*?samples.*?\])r   r(   r)   r*   r   r
   r	   Zestimators_r   getvaluegroupr+   )r/   dot_dataZ	estimatorfindingr0   r0   r1   test_friedman_mse_in_graphviz#  s    
rH   c            	      C   s8  t d} t d}t| d|df| d|jdddftdd	d
dtd
d	dfD ]\}}}||| dD ]}t|d |dd}td|D ]&}t	t
d|  |d
 kstqt|rd}nd}t||D ]&}t	t
d|  |d
 kstqtd|D ]*}t	t
d|  |d
 kstqqpqVd S )Nr      )   r   )     )rJ   )rK   )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   zipZrandom_samplerandintr   r   r(   r
   r   lenr   rE   r+   r   )	Zrng_regZrng_clfr)   r*   r/   r9   rF   rG   patternr0   r0   r1   test_precision2  s<      
   $$rS   c               	   C   s   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decimalszspacing must be > 0, given 0spacing)r   r(   r)   r*   r;   r<   r=   r   )r/   err_msgr0   r0   r1   test_export_text_errors^  s    rY   c                  C   sV  t ddd} | tt td }t| |ks4tt| dd|ksHtt| dd|ks\ttd }t| dd	gd
|ksttd }t| dd|ksttd }t| dd|kst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 }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 }t|dd|kstt|ddd|kstdgdgdgdgdgdgg}tddd}||| td }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'   
   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)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]
    first)rU   r   )rU   r[   r   )	r   r(   r)   r*   r   lstripr   r+   r   )r/   Zexpected_reportZX_lZy_lZX_moZy_moregZX_singler0   r0   r1   test_export_textp  s`    	.((r_   c                 C   s   t ddddd}|tt ddg}t||d}t|dks@t|d  d	ksTt|d
  dksht|d  dks|td S )Nr   r   Zentropyr   
first feat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pyplotr/   r   Znodesr0   r0   r1   test_plot_tree_entropy  s        
re   c                 C   s   t ddddd}|tt ddg}t||d}t|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   test_plot_tree_gini  s        
rf   c              	   C   s(   t  }tt t| W 5 Q R X d S )N)r   r;   r<   r   r   )rd   r/   r0   r0   r1   test_not_fitted_tree  s    rg   )%__doc__rer   r   textwrapr   Znumpy.randomr   r;   Zsklearn.baser   Zsklearn.treer   r   Zsklearn.ensembler	   r
   r   r   ior   Zsklearn.exceptionsr   r)   r*   r,   r-   r.   r2   rB   rH   rS   rY   r_   re   rf   rg   r0   r0   r0   r1   <module>   s2   (( d',c