使用sklearn的DecisionTreeClassifier解决分类问题实例。
数据集描述
数据集存放在一个csv文件中，其中11列特征变量，1列目标变量。特征变量的类型有数字类型和字符串类型。
加载数据
from sklearn import tree
from sklearn.model_selection import train_test_split
import pandas as pandas
in_file = 'titanic_data.csv'
full_data = pd.read_csv(in_file)
处理数据
1、剔除Nan的数据
full_data = full_data.dropna(axis=0)
2、拆分特征变量和目标变量
out = full_data['Survived']
features = full_data.drop('Survived', axis = 1)
3、将特征变量中的字符串类型转成数字类型
features = pandas.get_dummies(features)
拆分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(features, out, test_size = 0.2, random_state = 0)
# 显示切分的结果
print "Training set has {} samples.".format(X_train.shape[0])
print "Testing set has {} samples.".format(X_test.shape[0])
定义评价指标
def accuracy_score(truth, pred):
""" Returns accuracy score for input truth and predictions. """
# Ensure that the number of predictions matches number of outcomes
# 确保预测的数量与结果的数量一致
if len(truth) == len(pred):
# Calculate and return the accuracy as a percent
# 计算预测准确率（百分比）
# 用bool的平均数算百分比
return(truth == pred).mean()*100
else:
return 0
建模
用两种方式，一种是用网格搜索和交叉验证找决策树的最优参数，创建有最优参数的决策树，一种是默认决策树
创建决策树,用网格搜索和交叉验证找最优参数并拟合数据
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import KFold
from sklearn.metrics import make_scorer
from sklearn.tree import DecisionTreeClassifier
def fit_model_k_fold(X, y):
""" Performs grid search over the 'max_depth' parameter for a
decision tree regressor trained on the input data [X, y]. """
# Create cross-validation sets from the training data
# cv_sets = ShuffleSplit(n_splits = 10, test_size = 0.20, random_state = 0)
k_fold = KFold(n_splits=10)
# Create a decision tree clf object
clf = DecisionTreeClassifier(random_state=80)
params = {'max_depth':range(1,21),'criterion':np.array(['entropy','gini'])}
# Transform 'accuracy_score' into a scoring function using 'make_scorer'
scoring_fnc = make_scorer(accuracy_score)
# Create the grid search object
grid = GridSearchCV(clf, param_grid=params,scoring=scoring_fnc,cv=k_fold)
# Fit the grid search object to the data to compute the optimal model
grid = grid.fit(X, y)
# Return the optimal model after fitting the data
return grid.best_estimator_
查看最优参数
print "k_fold Parameter 'max_depth' is {} for the optimal model.".format(clf.get_params()['max_depth'])
print "k_fold Parameter 'criterion' is {} for the optimal model.".format(clf.get_params()['criterion'])
创建默认参数的决策树
def predict_4(X, Y):
clf = tree.DecisionTreeClassifier()
clf = clf.fit(X, Y)
return clf
预测
clf = fit_model_k_fold(X_train, y_train)
绘制决策树
from IPython.display import Image
import pydotplus
dot_data = tree.export_graphviz(clf, out_file=None,
class_names=['0','1'],
filled=True, rounded=True,
special_characters=True)
graph = pydotplus.graph_from_dot_data(dot_data)
Image(graph.create_png())
决策树
以上内容来自822实验室2017年5月7日17:30第二次知识分享活动：Titanic幸存者预测。
我们的822，我们的青春
欢迎所有热爱知识热爱生活的朋友和822实验室一起成长，吃喝玩乐，享受知识。
