notebook.community

Edit and run



In [15]:

    
from sklearn.datasets import load_iris
from sklearn import tree
import pydotplus 
import pandas as pd
iris = load_iris()
clf = tree.DecisionTreeClassifier()
clf = clf.fit(iris.data, iris.target)



In [6]:

    
from IPython.display import Image  
dot_data = tree.export_graphviz(clf, out_file=None, 
                         feature_names=iris.feature_names,  
                         class_names=iris.target_names,  
                         filled=True, rounded=True,  
                         special_characters=True)  
graph = pydotplus.graph_from_dot_data(dot_data)  
Image(graph.create_png())









    Out[6]:



In [7]:

    
type(iris.data)









    Out[7]:





numpy.ndarray



In [9]:

    
iris.data









    Out[9]:





array([[ 5.1,  3.5,  1.4,  0.2],
       [ 4.9,  3. ,  1.4,  0.2],
       [ 4.7,  3.2,  1.3,  0.2],
       [ 4.6,  3.1,  1.5,  0.2],
       [ 5. ,  3.6,  1.4,  0.2],
       [ 5.4,  3.9,  1.7,  0.4],
       [ 4.6,  3.4,  1.4,  0.3],
       [ 5. ,  3.4,  1.5,  0.2],
       [ 4.4,  2.9,  1.4,  0.2],
       [ 4.9,  3.1,  1.5,  0.1],
       [ 5.4,  3.7,  1.5,  0.2],
       [ 4.8,  3.4,  1.6,  0.2],
       [ 4.8,  3. ,  1.4,  0.1],
       [ 4.3,  3. ,  1.1,  0.1],
       [ 5.8,  4. ,  1.2,  0.2],
       [ 5.7,  4.4,  1.5,  0.4],
       [ 5.4,  3.9,  1.3,  0.4],
       [ 5.1,  3.5,  1.4,  0.3],
       [ 5.7,  3.8,  1.7,  0.3],
       [ 5.1,  3.8,  1.5,  0.3],
       [ 5.4,  3.4,  1.7,  0.2],
       [ 5.1,  3.7,  1.5,  0.4],
       [ 4.6,  3.6,  1. ,  0.2],
       [ 5.1,  3.3,  1.7,  0.5],
       [ 4.8,  3.4,  1.9,  0.2],
       [ 5. ,  3. ,  1.6,  0.2],
       [ 5. ,  3.4,  1.6,  0.4],
       [ 5.2,  3.5,  1.5,  0.2],
       [ 5.2,  3.4,  1.4,  0.2],
       [ 4.7,  3.2,  1.6,  0.2],
       [ 4.8,  3.1,  1.6,  0.2],
       [ 5.4,  3.4,  1.5,  0.4],
       [ 5.2,  4.1,  1.5,  0.1],
       [ 5.5,  4.2,  1.4,  0.2],
       [ 4.9,  3.1,  1.5,  0.1],
       [ 5. ,  3.2,  1.2,  0.2],
       [ 5.5,  3.5,  1.3,  0.2],
       [ 4.9,  3.1,  1.5,  0.1],
       [ 4.4,  3. ,  1.3,  0.2],
       [ 5.1,  3.4,  1.5,  0.2],
       [ 5. ,  3.5,  1.3,  0.3],
       [ 4.5,  2.3,  1.3,  0.3],
       [ 4.4,  3.2,  1.3,  0.2],
       [ 5. ,  3.5,  1.6,  0.6],
       [ 5.1,  3.8,  1.9,  0.4],
       [ 4.8,  3. ,  1.4,  0.3],
       [ 5.1,  3.8,  1.6,  0.2],
       [ 4.6,  3.2,  1.4,  0.2],
       [ 5.3,  3.7,  1.5,  0.2],
       [ 5. ,  3.3,  1.4,  0.2],
       [ 7. ,  3.2,  4.7,  1.4],
       [ 6.4,  3.2,  4.5,  1.5],
       [ 6.9,  3.1,  4.9,  1.5],
       [ 5.5,  2.3,  4. ,  1.3],
       [ 6.5,  2.8,  4.6,  1.5],
       [ 5.7,  2.8,  4.5,  1.3],
       [ 6.3,  3.3,  4.7,  1.6],
       [ 4.9,  2.4,  3.3,  1. ],
       [ 6.6,  2.9,  4.6,  1.3],
       [ 5.2,  2.7,  3.9,  1.4],
       [ 5. ,  2. ,  3.5,  1. ],
       [ 5.9,  3. ,  4.2,  1.5],
       [ 6. ,  2.2,  4. ,  1. ],
       [ 6.1,  2.9,  4.7,  1.4],
       [ 5.6,  2.9,  3.6,  1.3],
       [ 6.7,  3.1,  4.4,  1.4],
       [ 5.6,  3. ,  4.5,  1.5],
       [ 5.8,  2.7,  4.1,  1. ],
       [ 6.2,  2.2,  4.5,  1.5],
       [ 5.6,  2.5,  3.9,  1.1],
       [ 5.9,  3.2,  4.8,  1.8],
       [ 6.1,  2.8,  4. ,  1.3],
       [ 6.3,  2.5,  4.9,  1.5],
       [ 6.1,  2.8,  4.7,  1.2],
       [ 6.4,  2.9,  4.3,  1.3],
       [ 6.6,  3. ,  4.4,  1.4],
       [ 6.8,  2.8,  4.8,  1.4],
       [ 6.7,  3. ,  5. ,  1.7],
       [ 6. ,  2.9,  4.5,  1.5],
       [ 5.7,  2.6,  3.5,  1. ],
       [ 5.5,  2.4,  3.8,  1.1],
       [ 5.5,  2.4,  3.7,  1. ],
       [ 5.8,  2.7,  3.9,  1.2],
       [ 6. ,  2.7,  5.1,  1.6],
       [ 5.4,  3. ,  4.5,  1.5],
       [ 6. ,  3.4,  4.5,  1.6],
       [ 6.7,  3.1,  4.7,  1.5],
       [ 6.3,  2.3,  4.4,  1.3],
       [ 5.6,  3. ,  4.1,  1.3],
       [ 5.5,  2.5,  4. ,  1.3],
       [ 5.5,  2.6,  4.4,  1.2],
       [ 6.1,  3. ,  4.6,  1.4],
       [ 5.8,  2.6,  4. ,  1.2],
       [ 5. ,  2.3,  3.3,  1. ],
       [ 5.6,  2.7,  4.2,  1.3],
       [ 5.7,  3. ,  4.2,  1.2],
       [ 5.7,  2.9,  4.2,  1.3],
       [ 6.2,  2.9,  4.3,  1.3],
       [ 5.1,  2.5,  3. ,  1.1],
       [ 5.7,  2.8,  4.1,  1.3],
       [ 6.3,  3.3,  6. ,  2.5],
       [ 5.8,  2.7,  5.1,  1.9],
       [ 7.1,  3. ,  5.9,  2.1],
       [ 6.3,  2.9,  5.6,  1.8],
       [ 6.5,  3. ,  5.8,  2.2],
       [ 7.6,  3. ,  6.6,  2.1],
       [ 4.9,  2.5,  4.5,  1.7],
       [ 7.3,  2.9,  6.3,  1.8],
       [ 6.7,  2.5,  5.8,  1.8],
       [ 7.2,  3.6,  6.1,  2.5],
       [ 6.5,  3.2,  5.1,  2. ],
       [ 6.4,  2.7,  5.3,  1.9],
       [ 6.8,  3. ,  5.5,  2.1],
       [ 5.7,  2.5,  5. ,  2. ],
       [ 5.8,  2.8,  5.1,  2.4],
       [ 6.4,  3.2,  5.3,  2.3],
       [ 6.5,  3. ,  5.5,  1.8],
       [ 7.7,  3.8,  6.7,  2.2],
       [ 7.7,  2.6,  6.9,  2.3],
       [ 6. ,  2.2,  5. ,  1.5],
       [ 6.9,  3.2,  5.7,  2.3],
       [ 5.6,  2.8,  4.9,  2. ],
       [ 7.7,  2.8,  6.7,  2. ],
       [ 6.3,  2.7,  4.9,  1.8],
       [ 6.7,  3.3,  5.7,  2.1],
       [ 7.2,  3.2,  6. ,  1.8],
       [ 6.2,  2.8,  4.8,  1.8],
       [ 6.1,  3. ,  4.9,  1.8],
       [ 6.4,  2.8,  5.6,  2.1],
       [ 7.2,  3. ,  5.8,  1.6],
       [ 7.4,  2.8,  6.1,  1.9],
       [ 7.9,  3.8,  6.4,  2. ],
       [ 6.4,  2.8,  5.6,  2.2],
       [ 6.3,  2.8,  5.1,  1.5],
       [ 6.1,  2.6,  5.6,  1.4],
       [ 7.7,  3. ,  6.1,  2.3],
       [ 6.3,  3.4,  5.6,  2.4],
       [ 6.4,  3.1,  5.5,  1.8],
       [ 6. ,  3. ,  4.8,  1.8],
       [ 6.9,  3.1,  5.4,  2.1],
       [ 6.7,  3.1,  5.6,  2.4],
       [ 6.9,  3.1,  5.1,  2.3],
       [ 5.8,  2.7,  5.1,  1.9],
       [ 6.8,  3.2,  5.9,  2.3],
       [ 6.7,  3.3,  5.7,  2.5],
       [ 6.7,  3. ,  5.2,  2.3],
       [ 6.3,  2.5,  5. ,  1.9],
       [ 6.5,  3. ,  5.2,  2. ],
       [ 6.2,  3.4,  5.4,  2.3],
       [ 5.9,  3. ,  5.1,  1.8]])



In [10]:

    
clf.predict([[ 5.1,  3.5,  1.4,  0.2]])









    Out[10]:





array([0])



In [11]:

    
iris.target









    Out[11]:





array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])



In [12]:

    
clf.predict([[5.9,  3. ,  5.1,  1.8]])









    Out[12]:





array([2])



In [16]:

    
book = pd.read_csv("/Users/page/data/book/newbook.csv")



In [17]:

    
book.head()









    Out[17]:






  
    
      
      Unnamed: 0
      CBS_Class
      CBS_MY_Order
      CBS_MY_Rate
      CBS_XS_MY
      CBS_DXPZ
      CBS_XSCS
      CBS_CRTAX
      Book_Class
      CBS_BK_Average_price
      ...
      FXS_Class
      User_Area
      User_Get_Price
      FXS_Discount
      FXS_BK_MY_Order
      FXS_BK_MY_Rate
      FXS_BK_MY
      FXS_BK_DXPZ
      FXS_BK_XSCS
      FXS_BK_Average_Price
    
  
  
    
      0
      0
      1
      11
      1.0934
      90678033.8
      2921
      2357742
      0.07
      1
      34.83
      ...
      3
      2
      9.0
      0.585
      2
      3.4196
      15289978.1
      1579
      426206
      35.87
    
    
      1
      1
      1
      11
      1.0934
      90678033.8
      2921
      2357742
      0.07
      6
      17.75
      ...
      3
      2
      9.0
      0.585
      484
      0.0000
      36.0
      1
      2
      18.00
    
    
      2
      2
      1
      11
      1.0934
      90678033.8
      2921
      2357742
      0.08
      5
      32.51
      ...
      3
      2
      9.0
      0.585
      235
      0.0099
      15346.0
      7
      478
      32.10
    
    
      3
      3
      1
      11
      1.0934
      90678033.8
      2921
      2357742
      0.07
      3
      47.25
      ...
      3
      2
      9.0
      0.585
      3
      3.1915
      10890168.2
      405
      232732
      46.79
    
    
      4
      4
      1
      11
      1.0934
      90678033.8
      2921
      2357742
      0.08
      7
      60.70
      ...
      3
      2
      9.0
      0.585
      181
      0.0240
      59391.0
      21
      1022
      58.11
    
  

5 rows × 25 columns



In [18]:

    
book.columns









    Out[18]:





Index(['Unnamed: 0', 'CBS_Class', 'CBS_MY_Order', 'CBS_MY_Rate', 'CBS_XS_MY',
       'CBS_DXPZ', 'CBS_XSCS', 'CBS_CRTAX', 'Book_Class',
       'CBS_BK_Average_price', 'CBS_BK_MY_Order', 'CBS_BK_MY_Rate',
       'CBS_BK_XS_MY', 'CBS_BK_DXPZ', 'CBS_BK_XSCS', 'FXS_Class', 'User_Area',
       'User_Get_Price', 'FXS_Discount', 'FXS_BK_MY_Order', 'FXS_BK_MY_Rate',
       'FXS_BK_MY', 'FXS_BK_DXPZ', 'FXS_BK_XSCS', 'FXS_BK_Average_Price'],
      dtype='object')



In [19]:

    
x = book[['CBS_Class', 'CBS_MY_Order', 'CBS_MY_Rate',
       'CBS_XS_MY', 'CBS_DXPZ', 'CBS_XSCS', 'CBS_CRTAX', 'Book_Class',
       'CBS_BK_Average_price', 'CBS_BK_MY_Order', 'CBS_BK_MY_Rate',
       'CBS_BK_XS_MY', 'CBS_BK_DXPZ', 'FXS_Class', 'User_Area',
       'User_Get_Price', 'FXS_Discount', 'FXS_BK_MY_Order', 'FXS_BK_MY_Rate',
       'FXS_BK_MY', 'FXS_BK_DXPZ', 'FXS_BK_XSCS', 'FXS_BK_Average_Price']]



In [20]:

    
y = book[['CBS_BK_XSCS']]



In [21]:

    
clf = tree.DecisionTreeClassifier()
clf = clf.fit(x, y)



In [22]:

    
from IPython.display import Image



In [23]:

    
dot_data = tree.export_graphviz(clf, out_file=None, 
                         feature_names=x,
                         class_names=y,  
                         filled=True, rounded=True,
                         special_characters=True)









    



---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
/usr/local/lib/python3.5/site-packages/pandas/indexes/base.py in get_loc(self, key, method, tolerance)
   2133             try:
-> 2134                 return self._engine.get_loc(key)
   2135             except KeyError:

pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:4433)()

pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:4279)()

pandas/src/hashtable_class_helper.pxi in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:13742)()

pandas/src/hashtable_class_helper.pxi in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:13696)()

KeyError: 11

During handling of the above exception, another exception occurred:

KeyError                                  Traceback (most recent call last)
<ipython-input-23-8de1aa33087e> in <module>()
      3                          class_names=y,
      4                          filled=True, rounded=True,
----> 5                          special_characters=True)

/usr/local/lib/python3.5/site-packages/sklearn/tree/export.py in export_graphviz(decision_tree, out_file, max_depth, feature_names, class_names, label, filled, leaves_parallel, impurity, node_ids, proportion, rotate, rounded, special_characters)
    431             recurse(decision_tree, 0, criterion="impurity")
    432         else:
--> 433             recurse(decision_tree.tree_, 0, criterion=decision_tree.criterion)
    434 
    435         # If required, draw leaf nodes at same depth as each other

/usr/local/lib/python3.5/site-packages/sklearn/tree/export.py in recurse(tree, node_id, criterion, parent, depth)
    319             out_file.write('%d [label=%s'
    320                            % (node_id,
--> 321                               node_to_str(tree, node_id, criterion)))
    322 
    323             if filled:

/usr/local/lib/python3.5/site-packages/sklearn/tree/export.py in node_to_str(tree, node_id, criterion)
    217             # Always write node decision criteria, except for leaves
    218             if feature_names is not None:
--> 219                 feature = feature_names[tree.feature[node_id]]
    220             else:
    221                 feature = "X%s%s%s" % (characters[1],

/usr/local/lib/python3.5/site-packages/pandas/core/frame.py in __getitem__(self, key)
   2057             return self._getitem_multilevel(key)
   2058         else:
-> 2059             return self._getitem_column(key)
   2060 
   2061     def _getitem_column(self, key):

/usr/local/lib/python3.5/site-packages/pandas/core/frame.py in _getitem_column(self, key)
   2064         # get column
   2065         if self.columns.is_unique:
-> 2066             return self._get_item_cache(key)
   2067 
   2068         # duplicate columns & possible reduce dimensionality

/usr/local/lib/python3.5/site-packages/pandas/core/generic.py in _get_item_cache(self, item)
   1384         res = cache.get(item)
   1385         if res is None:
-> 1386             values = self._data.get(item)
   1387             res = self._box_item_values(item, values)
   1388             cache[item] = res

/usr/local/lib/python3.5/site-packages/pandas/core/internals.py in get(self, item, fastpath)
   3541 
   3542             if not isnull(item):
-> 3543                 loc = self.items.get_loc(item)
   3544             else:
   3545                 indexer = np.arange(len(self.items))[isnull(self.items)]

/usr/local/lib/python3.5/site-packages/pandas/indexes/base.py in get_loc(self, key, method, tolerance)
   2134                 return self._engine.get_loc(key)
   2135             except KeyError:
-> 2136                 return self._engine.get_loc(self._maybe_cast_indexer(key))
   2137 
   2138         indexer = self.get_indexer([key], method=method, tolerance=tolerance)

pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:4433)()

pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:4279)()

pandas/src/hashtable_class_helper.pxi in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:13742)()

pandas/src/hashtable_class_helper.pxi in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:13696)()

KeyError: 11



In [24]:

    
print(book.dtypes)









    



Unnamed: 0                int64
CBS_Class                 int64
CBS_MY_Order              int64
CBS_MY_Rate             float64
CBS_XS_MY               float64
CBS_DXPZ                  int64
CBS_XSCS                  int64
CBS_CRTAX               float64
Book_Class                int64
CBS_BK_Average_price    float64
CBS_BK_MY_Order           int64
CBS_BK_MY_Rate          float64
CBS_BK_XS_MY            float64
CBS_BK_DXPZ               int64
CBS_BK_XSCS               int64
FXS_Class                 int64
User_Area                 int64
User_Get_Price          float64
FXS_Discount            float64
FXS_BK_MY_Order           int64
FXS_BK_MY_Rate          float64
FXS_BK_MY               float64
FXS_BK_DXPZ               int64
FXS_BK_XSCS               int64
FXS_BK_Average_Price    float64
dtype: object



In [25]:

    
print(x.dtypes)









    



CBS_Class                 int64
CBS_MY_Order              int64
CBS_MY_Rate             float64
CBS_XS_MY               float64
CBS_DXPZ                  int64
CBS_XSCS                  int64
CBS_CRTAX               float64
Book_Class                int64
CBS_BK_Average_price    float64
CBS_BK_MY_Order           int64
CBS_BK_MY_Rate          float64
CBS_BK_XS_MY            float64
CBS_BK_DXPZ               int64
FXS_Class                 int64
User_Area                 int64
User_Get_Price          float64
FXS_Discount            float64
FXS_BK_MY_Order           int64
FXS_BK_MY_Rate          float64
FXS_BK_MY               float64
FXS_BK_DXPZ               int64
FXS_BK_XSCS               int64
FXS_BK_Average_Price    float64
dtype: object



In [26]:

    
type(book)









    Out[26]:





pandas.core.frame.DataFrame



In [27]:

    
type(x)









    Out[27]:





pandas.core.frame.DataFrame



In [35]:

    
type(iris.feature_names)









    Out[35]:





list



In [36]:

    
type(iris.target_names)









    Out[36]:





numpy.ndarray



In [32]:

    
iris.data.shape









    Out[32]:





(150, 4)



In [33]:

    
iris.target.shape









    Out[33]:





(150,)



In [34]:

    
iris.feature_names.shape









    



---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-34-98f658ef357a> in <module>()
----> 1 iris.feature_names.shape

AttributeError: 'list' object has no attribute 'shape'



In [38]:

    
iris.target_names.shape









    Out[38]:





(3,)



In [1]:

    
import numpy as np
import pylab as pl
x = [1, 2, 3, 4, 5]# Make an array of x values
y = [1, 4, 9, 16, 25]# Make an array of y values for each x value
pl.plot(x, y)# use pylab to plot x and y
pl.show()# show the plot on the screen



In [ ]:

	Unnamed: 0	CBS_Class	CBS_MY_Order	CBS_MY_Rate	CBS_XS_MY	CBS_DXPZ	CBS_XSCS	CBS_CRTAX	Book_Class	CBS_BK_Average_price	...	FXS_Class	User_Area	User_Get_Price	FXS_Discount	FXS_BK_MY_Order	FXS_BK_MY_Rate	FXS_BK_MY	FXS_BK_DXPZ	FXS_BK_XSCS	FXS_BK_Average_Price
0	0	1	11	1.0934	90678033.8	2921	2357742	0.07	1	34.83	...	3	2	9.0	0.585	2	3.4196	15289978.1	1579	426206	35.87
1	1	1	11	1.0934	90678033.8	2921	2357742	0.07	6	17.75	...	3	2	9.0	0.585	484	0.0000	36.0	1	2	18.00
2	2	1	11	1.0934	90678033.8	2921	2357742	0.08	5	32.51	...	3	2	9.0	0.585	235	0.0099	15346.0	7	478	32.10
3	3	1	11	1.0934	90678033.8	2921	2357742	0.07	3	47.25	...	3	2	9.0	0.585	3	3.1915	10890168.2	405	232732	46.79
4	4	1	11	1.0934	90678033.8	2921	2357742	0.08	7	60.70	...	3	2	9.0	0.585	181	0.0240	59391.0	21	1022	58.11