Python_sklearn机器学习库学习笔记(四)decision_tree(决策树)
# 决策树
import pandas as pd from sklearn.tree import DecisionTreeClassifier from sklearn.cross_validation import train_test_split from sklearn.metrics import classification_report from sklearn.pipeline import Pipeline from sklearn.grid_search import GridSearchCV
import zipfile #压缩节省空间 z=zipfile.ZipFile('ad-dataset.zip') # df=pd.read_csv(z.open(z.namelist()[0]),header=None,low_memory=False) # df = pd.read_csv(z.open(z.namelist()[0]), header=None, low_memory=False)
df=pd.read_csv('.\\tree_data\\ad.data',header=None) explanatory_variable_columns=set(df.columns.values) response_variable_column=df[len(df.columns.values)-1] #最后一列是代表的标签类型 explanatory_variable_columns.remove(len(df.columns)-1)
y=[1 if e =='ad.' else 0 for e in response_variable_column] X=df.loc[:,list(explanatory_variable_columns)]
#匹配?字符,并把值转化为-1 X.replace(to_replace=' *\?', value=-1, regex=True, inplace=True)
X_train,X_test,y_train,y_test=train_test_split(X,y) #用信息增益启发式算法建立决策树 pipeline=Pipeline([('clf',DecisionTreeClassifier(criterion='entropy'))]) parameters = { 'clf__max_depth': (150, 155, 160), 'clf__min_samples_split': (1, 2, 3), 'clf__min_samples_leaf': (1, 2, 3) } #f1查全率和查准率的调和平均 grid_search=GridSearchCV(pipeline,parameters,n_jobs=-1, verbose=1,scoring='f1') grid_search.fit(X_train,y_train) print '最佳效果:%0.3f'%grid_search.best_score_ print '最优参数' best_parameters=grid_search.best_estimator_.get_params() best_parameters
输出结果:
Fitting 3 folds for each of 27 candidates, totalling 81 fits
Out[123]:
for param_name in sorted(parameters.keys()): print ('\t%s:%r'%(param_name,best_parameters[param_name])) predictions=grid_search.predict(X_test) print classification_report(y_test,predictions)
输出结果:
clf__max_depth:150
clf__min_samples_leaf:1
clf__min_samples_split:1
precision recall f1-score support
0 0.97 0.99 0.98 703
1 0.91 0.84 0.87 117
avg / total 0.96 0.96 0.96 820
df.head()
输出结果;
0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | ... | 1549 | 1550 | 1551 | 1552 | 1553 | 1554 | 1555 | 1556 | 1557 | 1558 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 125 | 125 | 1.0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ad. |
1 | 57 | 468 | 8.2105 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ad. |
2 | 33 | 230 | 6.9696 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ad. |
3 | 60 | 468 | 7.8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ad. |
4 | 60 | 468 | 7.8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ad. |
# 决策树集成
#coding:utf-8 import pandas as pd from sklearn.ensemble import RandomForestClassifier from sklearn.cross_validation import train_test_split from sklearn.metrics import classification_report from sklearn.pipeline import Pipeline from sklearn.grid_search import GridSearchCV df=pd.read_csv('.\\tree_data\\ad.data',header=None,low_memory=False) explanatory_variable_columns=set(df.columns.values) response_variable_column=df[len(df.columns.values)-1]
df.head()
0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | ... | 1549 | 1550 | 1551 | 1552 | 1553 | 1554 | 1555 | 1556 | 1557 | 1558 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 125 | 125 | 1.0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ad. |
1 | 57 | 468 | 8.2105 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ad. |
2 | 33 | 230 | 6.9696 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ad. |
3 | 60 | 468 | 7.8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ad. |
4 | 60 | 468 | 7.8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | ... | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | ad. |
#The last column describes the targets(去掉最后一列) explanatory_variable_columns.remove(len(df.columns.values)-1) y=[1 if e=='ad.' else 0 for e in response_variable_column] X=df.loc[:,list(explanatory_variable_columns)] #置换有?的为-1 X.replace(to_replace=' *\?', value=-1, regex=True, inplace=True) X_train,X_test,y_train,y_test=train_test_split(X,y) pipeline=Pipeline([('clf',RandomForestClassifier(criterion='entropy'))]) parameters = { 'clf__n_estimators': (5, 10, 20, 50), 'clf__max_depth': (50, 150, 250), 'clf__min_samples_split': (1, 2, 3), 'clf__min_samples_leaf': (1, 2, 3) } grid_search = GridSearchCV(pipeline,parameters,n_jobs=-1,verbose=1,scoring='f1') grid_search.fit(X_train,y_train)
print(u'最佳效果:%0.3f'%grid_search.best_score_) print u'最优的参数:' best_parameters=grid_search.best_estimator_.get_params() for param_name in sorted(parameters.keys()): print('\t%s:%r'%(param_name,best_parameters[param_name]))
输出结果:
predictions=grid_search.predict(X_test) print classification_report(y_test,predictions)
输出结果:
precision recall f1-score support
0 0.98 1.00 0.99 705
1 0.97 0.90 0.93 115
avg / total 0.98 0.98 0.98 820