泰坦尼克号生存预测

import pandas as pd

titanic = pd.read_csv('http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt')

titanic.head()

titanic.info()

X = titanic[['pclass', 'age', 'sex']]

y = titanic['survived']

X['age'].fillna(X['age'].mean, inplace = True)

from sklearn.cross_validation import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, train_size = 0.25, random_state = 33)

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'))

from sklearn.tree import DecisionTreeClassifier

dtc = DecisionTreeClassifier()

dtc.fit(X_train, y_train)

y_predict = dtc.predict(X_test)

from sklearn.metrics import classification_report

print('Accuracy of DecisionTree is :',dtc.score(X_test, y_test))

print(classification_report(y_predict, y_test, target_names=['died', 'suevived']))

结果：