题记：第一个手写的机器学习的项目实战选择了经典的kaggle竞赛题目：泰坦尼克号沉船预测。典型的回归问题，希望在此过程中熟练掌握机器学习的基本流程，数据预处理与特征选择的思路。同类型经典赛题：阿里云天池大赛的工业蒸汽量预测问题。
Pycharm和jupyter的选择问题：kaggle在线训练平台提供的是类似于jupyter的接口，方便直观的看到数据的流动，但是结构性和逻辑性不足。而Pycharm通过函数的封装能很好体现逻辑性。个人更倾向于Jupyter做前期的数据分析工作，后面的算法由Pycharm实现。
Score：0.77751
# -*- coding: utf-8 -*-"""@Time ： /4/4 10:39@Auth ： zyt@File ：01regression.py@IDE ：PyCharm@Motto：ABC(Always Be Coding)"""'''问题描述：泰坦尼克号沉船预测事件'''import pandas as pdimport sklearn.preprocessing as preprocessingfrom sklearn import svmdef pre(data_train):# 由于姓名、船票编号属于唯一标识符对于预测来说无意义故直接删除data_train.drop('Name',axis=1,inplace=True)data_train.drop('Ticket', axis=1, inplace=True)return data_train#缺失值def set_missing_train(data_train):null_all = data_train.isnull().sum()print(null_all)#1.Age平均值填充age_median = data_train.Age.median()data_train.Age.fillna(age_median,inplace=True)#2.Cabin列删除data_train.drop('Cabin',axis=1,inplace=True)#3.Embarked行删除data_train.dropna(axis=0,how='any',thresh=None,subset=None,inplace=True)return data_traindef set_missing_test(data_test):null_all = data_test.isnull().sum()print(null_all)#1.Age平均值填充age_median = data_test.Age.median()data_test.Age.fillna(age_median,inplace=True)#2.Cabin列删除data_test.drop('Cabin',axis=1,inplace=True)#3.Fare平均值填充Fare_median = data_test.Fare.median()data_test.Fare.fillna(Fare_median, inplace=True)return data_test#标准化def set_norm(data_train):#特征因子化dummies_Sex = pd.get_dummies(data_train['Sex'],prefix='Sex')data_train.drop('Sex',axis=1,inplace = True)data_train = pd.concat([data_train,dummies_Sex],axis=1)dummies_Embarked = pd.get_dummies(data_train['Embarked'], prefix='Embarked')data_train.drop('Embarked',axis=1,inplace=True)data_train = pd.concat([data_train, dummies_Embarked], axis=1)dummies_Pclass = pd.get_dummies(data_train['Pclass'], prefix='Pclass')data_train.drop('Pclass',axis=1,inplace=True)data_train = pd.concat([data_train, dummies_Pclass], axis=1)#特征标准化scaler = preprocessing.StandardScaler()age_scaler_param = scaler.fit(data_train['Age'].values.reshape(-1,1))data_train['Age'] = scaler.fit_transform(data_train['Age'].values.reshape(-1,1),age_scaler_param)Fare_scaler_param = scaler.fit(data_train['Fare'].values.reshape(-1, 1))data_train['Fare'] = scaler.fit_transform(data_train['Fare'].values.reshape(-1, 1), Fare_scaler_param)return data_traindef predict(data_train,data_test):y = data_train['Survived']features = ['Age','SibSp','Parch','Fare','Sex_female','Sex_male','Pclass_1','Pclass_2','Pclass_3','Embarked_C','Embarked_Q','Embarked_S']x = pd.DataFrame(data_train[features],columns=features)x_test = pd.DataFrame(data_test[features],columns=features)model =svm.SVC(C=3,kernel='rbf',gamma=0.1)model.fit(x,y)predictions = model.predict(x_test)output = pd.DataFrame({'PassengerId': data_test.PassengerId, 'Survived': predictions})output.to_csv('./data/submission.csv', index=False)print("Your submission was successfully saved!")if __name__ == '__main__':# 数据导入data_train = pd.read_csv('./data/train.csv')data_train = pre(data_train)data_train = set_missing_train(data_train)data_train = set_norm(data_train)data_test = pd.read_csv('./data/test.csv')data_test = pre(data_test)data_test = set_missing_test(data_test)data_test = set_norm(data_test)predict(data_train,data_test)
