基于sklearn的决策树分类器理论基础代码实现

import pandas as pd

titan = pd.read_csv("http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt")
print(titan.head())

   row.names pclass  survived  \
0          1    1st         1   
1          2    1st         0   
2          3    1st         0   
3          4    1st         0   
4          5    1st         1   

                                              name      age     embarked  \
0                     Allen, Miss Elisabeth Walton  29.0000  Southampton   
1                      Allison, Miss Helen Loraine   2.0000  Southampton   
2              Allison, Mr Hudson Joshua Creighton  30.0000  Southampton   
3  Allison, Mrs Hudson J.C. (Bessie Waldo Daniels)  25.0000  Southampton   
4                    Allison, Master Hudson Trevor   0.9167  Southampton   

                         home.dest room      ticket   boat     sex  
0                     St Louis, MO  B-5  24160 L221      2  female  
1  Montreal, PQ / Chesterville, ON  C26         NaN    NaN  female  
2  Montreal, PQ / Chesterville, ON  C26         NaN  (135)    male  
3  Montreal, PQ / Chesterville, ON  C26         NaN    NaN  female  
4  Montreal, PQ / Chesterville, ON  C22         NaN     11    male  

print(titan.info())

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1313 entries, 0 to 1312
Data columns (total 11 columns):
row.names    1313 non-null int64
pclass       1313 non-null object
survived     1313 non-null int64
name         1313 non-null object
age          633 non-null float64
embarked     821 non-null object
home.dest    754 non-null object
room         77 non-null object
ticket       69 non-null object
boat         347 non-null object
sex          1313 non-null object
dtypes: float64(1), int64(2), object(8)
memory usage: 112.9+ KB
None

x = titan[["pclass","age","sex"]]
y = titan["survived"]
print(x.info())

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1313 entries, 0 to 1312
Data columns (total 3 columns):
pclass    1313 non-null object
age       633 non-null float64
sex       1313 non-null object
dtypes: float64(1), object(2)
memory usage: 30.9+ KB
None

x['age'].fillna(x['age'].mean(),inplace=True)
print(x.info())

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1313 entries, 0 to 1312
Data columns (total 3 columns):
pclass    1313 non-null object
age       1313 non-null float64
sex       1313 non-null object
dtypes: float64(1), object(2)
memory usage: 30.9+ KB
None


c:\users\qiank\appdata\local\programs\python\python35\lib\site-packages\pandas\core\generic.py:3660: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  self._update_inplace(new_data)

from sklearn.cross_validation import train_test_split
x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.25,random_state=1)
print(x_train.shape)
print(x_test.shape)

(984, 3)
(329, 3)

from sklearn.feature_extraction import DictVectorizer
vec = DictVectorizer(sparse=False)
x_train = vec.fit_transform(x_train.to_dict(orient='record'))
x_test = vec.transform(x_test.to_dict(orient='record'))
print(vec.feature_names_,"\n",x_train[:5])

['age', 'pclass=1st', 'pclass=2nd', 'pclass=3rd', 'sex=female', 'sex=male'] 
 [[ 31.19418104   0.           0.           1.           0.           1.        ]
 [ 31.19418104   0.           0.           1.           0.           1.        ]
 [ 35.           0.           1.           0.           1.           0.        ]
 [ 31.           0.           1.           0.           0.           1.        ]
 [ 26.           0.           0.           1.           0.           1.        ]]

from sklearn.tree import DecisionTreeClassifier
dtc = DecisionTreeClassifier()
dtc.fit(x_train,y_train)

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')

dtc.score(x_test,y_test)

0.81155015197568392

from sklearn.metrics import classification_report
y_pre = dtc.predict(x_test)
print(classification_report(y_pre,y_test,target_names=["died","survived"]))

             precision    recall  f1-score   support

       died       0.91      0.80      0.85       226
   survived       0.66      0.83      0.74       103

avg / total       0.83      0.81      0.82       329