如下代码是参考博客：https://blog.csdn.net/han_xiaoyang/article/details/49797143#commentsedit中的例子实现的，具体包括
1、数据查看
'''
该部分用于分析各类属性获救情况
'''
import pandas as pd #数据分析
import numpy as np #科学计算
from pandas import Series,DataFrame
import matplotlib.pyplot as plt
from pylab import mpl
mpl.rcParams['font.sans-serif'] = ['SimHei'] #指定默认字体
'''
加载并查看训练集数据信息
'''
data_train = pd.read_csv("H:/Titanic_data/train.csv")
# data_train.info()
fig = plt.figure()
fig.set(alpha=0.2) # 设定图表颜色alpha参数
# '''
# 数据初步分析---利用图标查看乘客各属性分布
# '''
# plt.subplot2grid((2,3),(0,0)) # 在一张大图里分列几个小图
# data_train.Survived.value_counts().plot(kind='bar')# 获救情况统计--柱状图，value_count()统计各类次数
# plt.title(u"获救情况 (1为获救)") # 标题
# plt.ylabel(u"人数")
#
# plt.subplot2grid((2,3),(0,1))
# data_train.Pclass.value_counts().plot(kind="bar")
# plt.ylabel(u"人数")
# plt.title(u"乘客等级分布")
#
# plt.subplot2grid((2,3),(0,2))
# plt.scatter(data_train.Survived, data_train.Age) #scatter为散点图
# plt.ylabel(u"年龄") # 设定纵坐标名称
# plt.grid(b=True, which='major', axis='y') #网格线,aixs表示网格线的方向
# plt.title(u"按年龄看获救分布 (1为获救)")
#
#
# plt.subplot2grid((2,3),(1,0), colspan=2) #clospan表示图像尺寸，此处2表示占据第二排从0开始连续两个位置
# data_train.Age[data_train.Pclass == 1].plot(kind='kde') #kde为
# data_train.Age[data_train.Pclass == 2].plot(kind='kde')
# data_train.Age[data_train.Pclass == 3].plot(kind='kde')
# plt.xlabel(u"年龄")# plots an axis lable
# plt.ylabel(u"密度")
# plt.title(u"各等级的乘客年龄分布")
# plt.legend((u'头等舱', u'2等舱',u'3等舱'),loc='best') # sets our legend for our graph.
#
#
# plt.subplot2grid((2,3),(1,2))
# data_train.Embarked.value_counts().plot(kind='bar')
# plt.title(u"各登船口岸上船人数")
# plt.ylabel(u"人数")
# plt.show()
'''
属性与获救结果的关联统计
'''
# #各等级获救与未获救人数查看。重要特征！！！
# Survived_0 = data_train.Pclass[data_train.Survived == 0].value_counts()
# Survived_1 = data_train.Pclass[data_train.Survived == 1].value_counts()
# df=pd.DataFrame({u'获救':Survived_1,u'未获救':Survived_0})
# df.plot(kind ='bar',stacked=True) #stack把同一组数据描述在一个直方条上
# plt.title(u'各乘客等级获救情况')
# plt.xlabel(u'乘客等级')
# plt.ylabel(u'人数')
# plt.show()
#获救与未获救人中男女分布情况。重要特征！！！
# Survived_m = data_train.Survived[data_train.Sex == 'male'].value_counts()
# Survived_f = data_train.Survived[data_train.Sex == 'female'].value_counts()
# df=pd.DataFrame({u'男性':Survived_m, u'女性':Survived_f})
# df.plot(kind='bar', stacked=True)
# plt.title(u"按性别看获救情况")
# plt.xlabel(u"性别")
# plt.ylabel(u"人数")
# plt.show()
#各种舱级别情况下各性别的获救情况
# plt.title(u'根据舱等级和性别的获救情况')
# ax1=fig.add_subplot(141)
# data_train.Survived[data_train.Sex == 'female'][data_train.Pclass != 3].value_counts().plot(kind='bar', label="female,highclass", color='#FA2479')
# ax1.set_xticklabels([u"未获救", u"获救"], rotation=0)
# ax1.legend([u"女性/高级舱"], loc='best')
#
# ax2=fig.add_subplot(142,sharey=ax1)
# data_train.Survived[data_train.Sex == 'female'][data_train.Pclass == 3].value_counts().plot(kind='bar', label="female,lowclass", color='pink')
# ax2.set_xticklabels([u"未获救", u"获救"], rotation=0)
# ax2.legend([u"女性/低级舱"], loc='best')
#
# ax3=fig.add_subplot(143,sharey=ax1)
# data_train.Survived[data_train.Sex == 'male'][data_train.Pclass != 3].value_counts().plot(kind='bar', label="male,highclass", color='lightblue')
# ax3.set_xticklabels([u"未获救", u"获救"], rotation=0)
# ax3.legend([u"男性/高级舱"], loc='best')
#
# ax4=fig.add_subplot(144,sharey=ax1)
# data_train.Survived[data_train.Sex == 'male'][data_train.Pclass == 3].value_counts().plot(kind='bar', label="male,lowclass", color='steelblue')
# ax4.set_xticklabels([u"未获救", u"获救"], rotation=0)
# ax4.legend([u"男性/低级舱"], loc='best')
# plt.show()
#获取各登船港口的获救情况
# Survived_0 = data_train.Embarked[data_train.Survived == 0].value_counts()
# Survived_1 = data_train.Embarked[data_train.Survived == 1].value_counts()
# df=pd.DataFrame({u'获救':Survived_1,u'未获救':Survived_0})
# df.plot(kind ='bar',stacked=True) #stack把同一组数据描述在一个直方条上
# plt.title(u'各港口获救情况')
# plt.xlabel(u'登陆港口')
# plt.ylabel(u'人数')
'''
#堂兄/妹，孩子/父母有几人，对获救的影响
PassengerId
SibSp Survived
0 0 398
1 210
1 0 97
1 112
2 0 15
1 13
3 0 12
1 4
4 0 15
1 3
5 0 5
8 0 7
'''
# g = data_train.groupby(['SibSp','Survived']) #groupby()用法
# df = pd.DataFrame(g.count()['PassengerId'])
# print(df)
'''
Cabin属性：
应该算作类目型的，本来缺失值就多，还如此不集中，注定是个棘手货…第一感觉，这玩意儿如
果直接按照类目特征处理的话，太散了，估计每个因子化后的特征都拿不到什么权重。加上有那
么多缺失值，要不我们先把Cabin缺失与否作为条件(虽然这部分信息缺失可能并非未登记，maybe
只是丢失了而已，所以这样做未必妥当)，先在有无Cabin信息这个粗粒度上看看Survived的情况
好了。
有cabin获救率看着比未获救概率大了些
'''
# Survived_cabin = data_train.Survived[pd.notnull(data_train.Cabin)].value_counts()
# Survived_nocabin = data_train.Survived[pd.isnull(data_train.Cabin)].value_counts()
# df=pd.DataFrame({u'有':Survived_cabin,u'未获救':Survived_nocabin})
# df.plot(kind ='bar',stacked=True) #stack把同一组数据描述在一个直方条上
# plt.title(u'有无cabin分类获救情况')
# plt.xlabel(u'carbin有无')
# plt.ylabel(u'人数')
# plt.show()
根据上述函数查看各特征与结果之间的关系
2、数据处理：（1）对缺失值，参考完整的数据，根据其他特征进行补充-----拟合补全。
（2）对于变化比较大的特征进行sacle处理
import pandas as pd
from sklearn.ensemble import RandomForestRegressor
import sklearn.preprocessing as preprocessing
import numpy as np #科学计算
from pylab import mpl
data_train = pd.read_csv("G:/KNNtest/Titanic/train.csv")
data_test = pd.read_csv("G:/KNNtest/Titanic/test.csv")
'''
一、数据处理
我这里说的数据预处理，其实就包括了很多Kaggler津津乐道的feature engineering过程，
灰常灰常有必要！
特征工程(feature engineering)太重要了！此处需要对
1、cabin（有无）
2、Age属性进行处理（缺失）
通常遇到缺值的情况，我们会有几种常见的处理方式
1、如果缺值的样本占总数比例极高，我们可能就直接舍弃了，作为特征加入的话，可能反倒带入noise，影响最后的结果了
2、如果缺值的样本适中，而该属性非连续值特征属性(比如说类目属性)，那就把NaN作为一个新类别，加到类别特征中
3、如果缺值的样本适中，而该属性为连续值特征属性，有时候我们会考虑给定一个step(比如这里的age，我们可以考虑每
隔2/3岁为一个步长)，然后把它离散化，之后把NaN作为一个type加到属性类目中。
4、有些情况下，缺失的值个数并不是特别多，那我们也可以试着根据已有的值，拟合一下数据，补充上。
本例中，后两种处理方式应该都是可行的，我们先试试拟合补全(虽然说没有特别多的背景可供我们拟合，这不一定是一个多
么好的选择)
我们这里用scikit-learn中的RandomForest来拟合一下缺失的年龄数据(注：RandomForest是一个用在原始数据中做不同采
样，建立多颗DecisionTree，再进行average等等来降低过拟合现象，提高结果的机器学习算法。
注：填补缺失值代码运行后并未在原数据表中看到更改，但是打印可以看出‘Age’项空缺值已被填补
'''
# 使用RandomForestRegressor填补年龄的缺失值
def set_missing_ages(df):
# 把已有的数据特征取出来丢进RandomForestRegressor
age_df = df[['Age', 'Fare', 'Parch', 'SibSp', 'Pclass']]
# 乘客分为已知年龄和未知年龄两部分
known_age = age_df[age_df.Age.notnull()].as_matrix()
unknown_age = age_df[age_df.Age.isnull()].as_matrix()
# y即目标年龄
y = known_age[:, 0]
# x即特诊属性值
x = known_age[:, 1:]
# fit到RandomForestRegressor中
rfr = RandomForestRegressor(random_state=0, n_estimators=2000, n_jobs=-1) # n_estimators为决策树个数,n_jobs=-1表示CPU有
# 多少core，就启动多少job
rfr.fit(x, y)
# 用得到的模型进行未知年龄的预测
predicatedAges = rfr.predict(unknown_age[:, 1::])
# 用得到的预测结果填补原缺失数据
df.loc[(df.Age.isnull()), 'Age'] = predicatedAges
scaler = preprocessing.StandardScaler() # 利用scaler对Age,Fare进行处理
df['Age'] = scaler.fit_transform(df[['Age']])
df['Fare'] = scaler.fit_transform(df[['Fare']])
return df, rfr
'''
Age和Fare两个属性，乘客的数值幅度变化很大！如果大家了解逻辑回归与梯度下降的话，会知道各属性值之
间scale差距太大，将对收敛速度造成几万点伤害值！甚至不收敛！所以我们先用scikit-learn里面的preprocessing
模块对这俩属性做一个scaling，将一些变化幅度较大的特征化到[-1,1]之内。
'''
def set_cabin_type(df):
df.loc[(df.Cabin.notnull()), 'Cabin'] = "Yes"
df.loc[(df.Cabin.isnull()), 'Cabin'] = "No"
dummies_Cabin = pd.get_dummies(df.Cabin, prefix='Cabin')
dummies_Embarked = pd.get_dummies(df.Embarked, prefix='Embarked')
dummies_Sex = pd.get_dummies(df.Sex, prefix='Sex')
dummies_Pclass = pd.get_dummies(df.Pclass, prefix='Pclass')
df = pd.concat([df, dummies_Cabin, dummies_Embarked, dummies_Sex, dummies_Pclass], axis=1)
df.drop(['Pclass', 'Name', 'Sex', 'Ticket', 'Cabin', 'Embarked'], axis=1, inplace=True)
return df
3、特征提取部分主要是通过1部分观察特征与结果之间的关系现得到大概特征项，再调整
4、建立模型
from sklearn import linear_model
from sklearn.ensemble import BaggingRegressor
def LogisticRegre(df):
train_df = df.filter(regex='Survived|Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
train_np = train_df.as_matrix()
#y为survival结果
y = train_np[:,0]
#x为特征属性值
X= train_np[:,1:]
clf = linear_model.LogisticRegression(C=1.0,penalty='l1',tol=1e-6)
bagging_clf = BaggingRegressor(clf, n_estimators=20, max_samples=0.8, max_features=1.0, bootstrap=True,
bootstrap_features=False, n_jobs=-1)
return bagging_clf.fit(X, y)
pd.DataFrame({"columns": list(te_d.columns)[2:14], "coef": list(train_clf.coef_.T)})#把model系数和feature关联起来
5交叉验证
#!!!!数据分割，训练数据：CV数据 = 7：3，该部分写在主程序中
split_train,split_cv = model_selection.train_test_split(te_d,test_size=0.3,random_state=0)
train_df = split_train.filter(regex='Survived|Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
# 生成模型
clf = linear_model.LogisticRegression(C=1.0, penalty='l1', tol=1e-6)
clf.fit(train_df.as_matrix()[:, 1:], train_df.as_matrix()[:, 0])
# train_df.to_csv("G:/KNNtest/Titanic/train_df.csv")
# !!!对cross validation数据进行预测
cv_df = split_cv.filter(regex='Survived|Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
predictions = clf.predict(cv_df.as_matrix()[:, 1:])
clf = linear_model.LogisticRegression(C=1.0, penalty='l1', tol=1e-6)
all_data = tr_d.filter(regex='Survived|Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
X = all_data.as_matrix()[:, 1:]
y = all_data.as_matrix()[:, 0]
# print(model_selection.cross_val_score(clf, X, y, cv=5)) #交叉验证结果
6、learning curve
import numpy as np
import matplotlib.pyplot as plt
from sklearn.learning_curve import learning_curve
# 用sklearn的learning_curve得到training_score和cv_score，使用matplotlib画出learning curve
def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None, n_jobs=1,
train_sizes=np.linspace(.05, 1., 20), verbose=0, plot=True):
"""
画出data在某模型上的learning curve.
参数解释
----------
estimator : 你用的分类器。
title : 表格的标题。
X : 输入的feature，numpy类型
y : 输入的target vector
ylim : tuple格式的(ymin, ymax), 设定图像中纵坐标的最低点和最高点
cv : 做cross-validation的时候，数据分成的份数，其中一份作为cv集，其余n-1份作为training(默认为3份)
n_jobs : 并行的的任务数(默认1)
"""
train_sizes, train_scores, test_scores = learning_curve(
estimator, X, y, cv=cv, n_jobs=n_jobs, train_sizes=train_sizes, verbose=verbose)
train_scores_mean = np.mean(train_scores, axis=1)
train_scores_std = np.std(train_scores, axis=1)
test_scores_mean = np.mean(test_scores, axis=1)
test_scores_std = np.std(test_scores, axis=1)
if plot:
plt.figure()
plt.title(title)
if ylim is not None:
plt.ylim(*ylim)
plt.xlabel(u"训练样本数")
plt.ylabel(u"得分")
plt.gca().invert_yaxis()
plt.grid()
plt.fill_between(train_sizes, train_scores_mean - train_scores_std, train_scores_mean + train_scores_std,
alpha=0.1, color="b")
plt.fill_between(train_sizes, test_scores_mean - test_scores_std, test_scores_mean + test_scores_std,
alpha=0.1, color="r")
plt.plot(train_sizes, train_scores_mean, 'o-', color="b", label=u"训练集上得分")
plt.plot(train_sizes, test_scores_mean, 'o-', color="r", label=u"交叉验证集上得分")
plt.legend(loc="best")
plt.draw()
plt.show()
plt.gca().invert_yaxis()
midpoint = ((train_scores_mean[-1] + train_scores_std[-1]) + (test_scores_mean[-1] - test_scores_std[-1])) / 2
diff = (train_scores_mean[-1] + train_scores_std[-1]) - (test_scores_mean[-1] - test_scores_std[-1])
return midpoint, diff
7、模型融合
from sklearn import linear_model
from sklearn.ensemble import BaggingRegressor
def LogisticRegre(df):
train_df = df.filter(regex='Survived|Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
train_np = train_df.as_matrix()
#y为survival结果
y = train_np[:,0]
#x为特征属性值
X= train_np[:,1:]
clf = linear_model.LogisticRegression(C=1.0,penalty='l1',tol=1e-6)
bagging_clf = BaggingRegressor(clf, n_estimators=20, max_samples=0.8, max_features=1.0, bootstrap=True,
bootstrap_features=False, n_jobs=-1)
return clf.fit(X, y)
main()函数：
import pandas as pd
import numpy as np
import DataTreating
import LogisticRegression
from sklearn.ensemble import RandomForestRegressor
import sklearn.preprocessing as preprocessing
from sklearn import linear_model
from sklearn import model_selection
import learning_curve
from pylab import mpl
mpl.rcParams['font.sans-serif'] = ['SimHei'] #指定默认字体
if __name__ == '__main__':
data_train = pd.read_csv("G:/KNNtest/Titanic/train.csv")
data_test = pd.read_csv("G:/KNNtest/Titanic/test1.csv")
tr_data,rfr1= DataTreating.set_missing_ages(data_train)
tr_d = DataTreating.set_cabin_type(tr_data)
te_data,rfr2= DataTreating.set_missing_ages(data_test)
te_d = DataTreating.set_cabin_type(te_data)
# test =te_d .filter(regex='Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
# clf = LogisticRegression.LogisticRegre(test)
# predictions = clf.predict(test)
# result = pd.DataFrame(
# {'PassengerId': te_d['PassengerId'].as_matrix(), 'Survived': predictions.astype(np.int32)})
# result.to_csv("G:/KNNtest/Titanic/logistic_regression_predictions.csv", index=False)
#!!!!数据分割，训练数据：CV数据 = 7：3
split_train,split_cv = model_selection.train_test_split(te_d,test_size=0.3,random_state=0)
train_df = split_train.filter(regex='Survived|Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
# 生成模型
clf = linear_model.LogisticRegression(C=1.0, penalty='l1', tol=1e-6)
clf.fit(train_df.as_matrix()[:, 1:], train_df.as_matrix()[:, 0])
# train_df.to_csv("G:/KNNtest/Titanic/train_df.csv")
# !!!对cross validation数据进行预测
cv_df = split_cv.filter(regex='Survived|Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
predictions = clf.predict(cv_df.as_matrix()[:, 1:])
# cv_df.to_csv("G:/KNNtest/Titanic/cv_df.csv")
# #bad_case查看
# origin_data_train = pd.read_csv("G:/KNNtest/Titanic/train.csv")
# bad_cases = origin_data_train.loc[
# origin_data_train['PassengerId'].isin(split_cv[predictions != cv_df.as_matrix()[:, 0]]['PassengerId'].values)]
# bad_cases.to_csv("G:/KNNtest/Titanic/bad_cases.csv")
#!!!!! 构造逻辑回归模型
train_clf = LogisticRegression.LogisticRegre(tr_d)
pd.DataFrame({"columns": list(te_d.columns)[2:14], "coef": list(train_clf.coef_.T)})#把model系数和feature关联起来
clf = linear_model.LogisticRegression(C=1.0, penalty='l1', tol=1e-6)
all_data = tr_d.filter(regex='Survived|Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
X = all_data.as_matrix()[:, 1:]
y = all_data.as_matrix()[:, 0]
# print(model_selection.cross_val_score(clf, X, y, cv=5)) #交叉验证结果
#!!!!!learning curve曲线
learning_curve.plot_learning_curve(clf,X = all_data.as_matrix()[:, 1:],y = all_data.as_matrix()[:, 0],title='Learning_Curve')
print(clf.score(X,y))