实战Kaggle比赛(一)——泰坦尼克号

泰坦迪克号，预测其他人的存活状况

 

比赛网址  https://www.kaggle.com/c/titanic

 

数据下载

 

train.csv

 

code

# -*- coding: utf-8 -*-

import pandas as pd #数据分析
import numpy as np #科学计算
from pandas import Series,DataFrame
from sklearn.ensemble import RandomForestRegressor
import sklearn.preprocessing as preprocessing
from sklearn import linear_model


### 使用 RandomForestClassifier 填补缺失的年龄属性
def set_missing_ages(df):

    # 把已有的数值型特征取出来丢进Random Forest Regressor中
    age_df = df[['Age','Fare', 'Parch', 'SibSp', 'Pclass']]

    # 乘客分成已知年龄和未知年龄两部分
    #known_age = age_df[age_df.Age.notnull()].as_matrix()
    known_age = age_df[age_df.Age.notnull()].values
    #unknown_age = age_df[age_df.Age.isnull()].as_matrix()
    unknown_age = age_df[age_df.Age.isnull()].values

    # y即目标年龄
    y = known_age[:, 0]

    # X即特征属性值
    X = known_age[:, 1:]

    # fit到RandomForestRegressor之中
    rfr = RandomForestRegressor(random_state=0, n_estimators=2000, n_jobs=-1)
    rfr.fit(X, y)

    # 用得到的模型进行未知年龄结果预测
    predictedAges = 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' ] = predictedAges

    return df, rfr

def set_Cabin_type(df):
    df.loc[ (df.Cabin.notnull()), 'Cabin' ] = "Yes"
    df.loc[ (df.Cabin.isnull()), 'Cabin' ] = "No"
    return df




data_train = pd.read_csv("kaggle/titanic/train.csv")
print(data_train)


data_train, rfr = set_missing_ages(data_train)  #填补缺失的年龄属性
data_train = set_Cabin_type(data_train)


dummies_Cabin = pd.get_dummies(data_train['Cabin'], prefix= 'Cabin')

dummies_Embarked = pd.get_dummies(data_train['Embarked'], prefix= 'Embarked')

dummies_Sex = pd.get_dummies(data_train['Sex'], prefix= 'Sex')

dummies_Pclass = pd.get_dummies(data_train['Pclass'], prefix= 'Pclass')

df = pd.concat([data_train, dummies_Cabin, dummies_Embarked, dummies_Sex, dummies_Pclass], axis=1)
df.drop(['Pclass', 'Name', 'Sex', 'Ticket', 'Cabin', 'Embarked'], axis=1, inplace=True)



scaler = preprocessing.StandardScaler()



# 用正则取出我们要的属性值
train_df = df.filter(regex='Survived|Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
train_np = train_df.values

# y即Survival结果
y = train_np[:, 0]

# X即特征属性值
X = train_np[:, 1:]

# fit到RandomForestRegressor之中
clf = linear_model.LogisticRegression(C=1.0, penalty='l1', tol=1e-6,solver='liblinear')
clf.fit(X, y)




data_test = pd.read_csv("kaggle/titanic/test.csv")
data_test.loc[ (data_test.Fare.isnull()), 'Fare' ] = 0
# 接着我们对test_data做和train_data中一致的特征变换
# 首先用同样的RandomForestRegressor模型填上丢失的年龄
tmp_df = data_test[['Age','Fare', 'Parch', 'SibSp', 'Pclass']]
null_age = tmp_df[data_test.Age.isnull()].values
# 根据特征属性X预测年龄并补上
X = null_age[:, 1:]
predictedAges = rfr.predict(X)
data_test.loc[ (data_test.Age.isnull()), 'Age' ] = predictedAges

data_test = set_Cabin_type(data_test)
dummies_Cabin = pd.get_dummies(data_test['Cabin'], prefix= 'Cabin')
dummies_Embarked = pd.get_dummies(data_test['Embarked'], prefix= 'Embarked')
dummies_Sex = pd.get_dummies(data_test['Sex'], prefix= 'Sex')
dummies_Pclass = pd.get_dummies(data_test['Pclass'], prefix= 'Pclass')


df_test = pd.concat([data_test, dummies_Cabin, dummies_Embarked, dummies_Sex, dummies_Pclass], axis=1)
df_test.drop(['Pclass', 'Name', 'Sex', 'Ticket', 'Cabin', 'Embarked'], axis=1, inplace=True)


test = df_test.filter(regex='Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass_.*')
predictions = clf.predict(test)
result = pd.DataFrame({'PassengerId':data_test['PassengerId'].values, 'Survived':predictions.astype(np.int32)})
result.to_csv("kaggle/titanic/logistic_regression_predictions.csv", index=False)

运行后会生成logistic_regression_predictions.csv

 

 

提交

将这个文件提交上去，得到自己的成绩名次

提交文件的内容格式在这里看