sklearn 决策树

import pandas as pd
import numpy as np
import pylab as pl
#from sklearn.cross_validation import train_test_split
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score
from sklearn.feature_extraction import DictVectorizer
from sklearn.tree import DecisionTreeClassifier
from sklearn import feature_selection
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report

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

#X=titanic[['pclass', 'age', 'sex']]
X=titanic.drop(['row.names', 'name', 'survived'], axis = 1)
y=titanic['survived']

# print(X.info())

X['age'].fillna(X['age'].mean(), inplace=True)
X.fillna('UNKNOWN', inplace=True)
# print(X.info())

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

vec = DictVectorizer(sparse=True)

X_train=vec.fit_transform(X_train.to_dict(orient='record'))
print(len(vec.feature_names_))

X_test=vec.transform(X_test.to_dict(orient='record'))

#决策树
dtc = DecisionTreeClassifier()
dtc.fit(X_train, y_train)
y_predict = dtc.predict(X_test)
print('Decision Tree: ', dtc.score(X_test, y_test))
print(classification_report(y_predict, y_test, target_names=['died', 'survived']))

dt=DecisionTreeClassifier(criterion='entropy')
dtc.fit(X_train, y_train)
y_predict = dtc.predict(X_test)
print('Decision Tree entropy: ', dtc.score(X_test, y_test))
print(classification_report(y_predict, y_test, target_names=['died', 'survived']))



percentiles = range(1,100,2)
results=[]
for i in percentiles:
    fs = feature_selection.SelectPercentile(feature_selection.chi2, percentile=i)
    X_train_fs = fs.fit_transform(X_train, y_train)
    scores=cross_val_score(dt,X_train_fs,y_train,cv=5)
    results=np.append(results, scores.mean())
print(results)

opt = np.where(results == results.max())[0]
print('Optimal number of features %d'  %np.array(percentiles)[opt])

pl.plot(percentiles, results)
pl.xlabel('percentiles of features')
pl.ylabel('accuracy')
pl.show()

fs = feature_selection.SelectPercentile(feature_selection.chi2, percentile=20)
X_train_fs = fs.fit_transform(X_train, y_train)
dt.fit(X_train_fs, y_train)
X_test_fs = fs.transform(X_test)
y_predict = dt.predict(X_test_fs)
print('Decision Tree SelectPercentile 20: ', dt.score(X_test_fs, y_test))
print(classification_report(y_predict, y_test, target_names=['died', 'survived']))

fs=feature_selection.SelectPercentile(feature_selection.chi2, percentile=7)
X_train_fs = fs.fit_transform(X_train, y_train)
dt.fit(X_train_fs, y_train)
X_test_fs = fs.transform(X_test)
y_predict = dt.predict(X_test_fs)
print('Decision Tree SelectPercentile 7: ', dt.score(X_test_fs, y_test))
print(classification_report(y_predict, y_test, target_names=['died', 'survived']))

#梯度提升决策树
gbc=GradientBoostingClassifier()
gbc.fit(X_train, y_train)
y_predict = gbc.predict(X_test)
print('Gradient Boosting: ', gbc.score(X_test, y_test))
print(classification_report(y_predict, y_test, target_names=['died', 'survived']))

#随机森林
rfc=RandomForestClassifier()
rfc.fit(X_train,y_train)
y_predict = rfc.predict(X_test)
print('Random Forest: ', rfc.score(X_test, y_test))
print(classification_report(y_predict, y_test, target_names=['died', 'survived']))