一、简介

1.数据

（1）训练集（train.csv）

（2）测试集（test.csv）

（3）提交文件示例（gender_submission.csv）

对于训练集，我们为每位乘客提供结果。模型将基于乘客的性别和阶级等“特征”也可以使用特征工程来创建新特征。我们要做的就是对于测试集中的每个乘客，使用训练的模型来预测他们是否在泰坦尼克号沉没中幸存下来。

2.属性说明

3.网站指引

1.网站注册是“register”，注册的时候需要连接“特殊工具”，不然没法进行人机验证。具体解决办法可以跳转到：/liuxiaomin/p/11785645.html【解决】

2.数据下载、结果提交

二、数据预处理

1.导入第三方库和数据文件

#导入第三方库import pandas as pdimport numpy as np#读取数据train = pd.read_csv('train.csv')test = pd.read_csv('test.csv')submit = pd.read_csv('gender_submission.csv')

2.查看缺失值

代码：

print(train.info())

结果：

3.观察变量信息

代码：

print(train.describe())

结果：

4.总结

从上面的缺失值和变量关系可以看出，训练集的数据中"Age"，"Embarked"有缺失值的情况，因为891条数据里，只有"Age"的count只有714，"Embarked"的count只有。所以需要对"Age"的缺失值进行处理。

三、数据处理

1.缺失值处理

代码：

# 用中值填补缺失值train['Age'] = train['Age'].fillna(train['Age'].median())#缺失值print(train.info())

结果：

2.数据转化

把数据类型是"object"转化

代码：

print(train['Sex'].unique())# titanic.loc[0]表示第0行的样本# titanic.loc[0, 'PassengerId']表示行为0，列为PassengerId的值train.loc[train['Sex'] == 'male', 'Sex'] = 0train.loc[train['Sex'] == 'female', 'Sex'] = 1

完整：

"""导入库"""# 数据分析与整理import pandas as pdimport numpy as npimport random as rnd# 可视化import seaborn as snsimport matplotlib.pyplot as plt%matplotlib inline# 机器学习from sklearn.linear_model import LogisticRegressionfrom sklearn.svm import SVC, LinearSVCfrom sklearn.ensemble import RandomForestClassifierfrom sklearn.neighbors import KNeighborsClassifierfrom sklearn.naive_bayes import GaussianNBfrom sklearn.linear_model import Perceptronfrom sklearn.linear_model import SGDClassifierfrom sklearn.tree import DecisionTreeClassifier"""获取数据"""train_df = pd.read_csv('train.csv')test_df = pd.read_csv('test.csv')combine = [train_df, test_df]train_df = train_df.drop(['Ticket', 'Cabin'], axis=1)test_df = test_df.drop(['Ticket', 'Cabin'], axis=1)combine = [train_df, test_df]for dataset in combine:dataset['Title'] = dataset.Name.str.extract(' ([A-Za-z]+)\.', expand=False)# expand=False表示返回DataFrame# 用一个更常见的名字替换许多标题，分类稀有标题for dataset in combine:dataset['Title'] = dataset['Title'].replace(['Lady', 'Countess','Capt', 'Col',\'Don', 'Dr', 'Major', 'Rev', 'Sir', 'Jonkheer', 'Dona'], 'Rare')dataset['Title'] = dataset['Title'].replace('Mlle', 'Miss')dataset['Title'] = dataset['Title'].replace('Ms', 'Miss')dataset['Title'] = dataset['Title'].replace('Mme', 'Mrs')train_df = train_df.drop(['Name', 'PassengerId'], axis=1)test_df = test_df.drop(['Name'], axis=1)combine = [train_df, test_df]for dataset in combine:dataset['Sex'] = dataset['Sex'].map( {'female': 1, 'male': 0} ).astype(int)all_data = pd.concat([train_df, test_df], ignore_index = True)#用随机森林对Age缺失值进行填充from sklearn import model_selectionfrom sklearn.ensemble import RandomForestRegressortrain_df = all_data[all_data['Survived'].notnull()]test_df = all_data[all_data['Survived'].isnull()]# 分割数据，按照 训练数据:cv数据 = 1:1的比例train_split_1, train_split_2 = model_selection.train_test_split(train_df, test_size=0.5, random_state=0)def predict_age_use_cross_validationg(df1,df2,dfTest):age_df1 = df1[['Age', 'Pclass','Sex','Title']]age_df1 = pd.get_dummies(age_df1)age_df2 = df2[['Age', 'Pclass','Sex','Title']]age_df2 = pd.get_dummies(age_df2)known_age = age_df1[age_df1.Age.notnull()].iloc[:,:].valuesunknow_age_df1 = age_df1[age_df1.Age.isnull()].iloc[:,:].valuesunknown_age = age_df2[age_df2.Age.isnull()].iloc[:,:].valuesprint (unknown_age.shape)y = known_age[:, 0]X = known_age[:, 1:]rfr = RandomForestRegressor(random_state=0, n_estimators=100, n_jobs=-1)rfr.fit(X, y)predictedAges = rfr.predict(unknown_age[:, 1::])df2.loc[ (df2.Age.isnull()), 'Age' ] = predictedAges predictedAges = rfr.predict(unknow_age_df1[:,1::])df1.loc[(df1.Age.isnull()),'Age'] = predictedAgesage_Test = dfTest[['Age', 'Pclass','Sex','Title']]age_Test = pd.get_dummies(age_Test)age_Tmp = df2[['Age', 'Pclass','Sex','Title']]age_Tmp = pd.get_dummies(age_Tmp)age_Tmp = pd.concat([age_Test[age_Test.Age.notnull()],age_Tmp])known_age1 = age_Tmp.iloc[:,:].valuesunknown_age1 = age_Test[age_Test.Age.isnull()].iloc[:,:].valuesy = known_age1[:,0]x = known_age1[:,1:]rfr.fit(x, y)predictedAges = rfr.predict(unknown_age1[:, 1:])dfTest.loc[ (dfTest.Age.isnull()), 'Age' ] = predictedAges return dfTestt1 = train_split_1.copy()t2 = train_split_2.copy()tmp1 = test_df.copy()t5 = predict_age_use_cross_validationg(t1,t2,tmp1)t1 = pd.concat([t1,t2])t3 = train_split_1.copy()t4 = train_split_2.copy()tmp2 = test_df.copy()t6 = predict_age_use_cross_validationg(t4,t3,tmp2)t3 = pd.concat([t3,t4])train_df['Age'] = (t1['Age'] + t3['Age'])/2test_df['Age'] = (t5['Age'] + t6['Age']) / 2all_data = pd.concat([train_df,test_df])print (train_df.describe())print (test_df.describe())guess_ages = np.zeros((2,3))# 迭代sex（0或1）和pclass（1，2，3）来计算六个组合的年龄估计值。for dataset in combine:for i in range(0, 2):for j in range(0, 3):guess_df = dataset[(dataset['Sex'] == i) & \(dataset['Pclass'] == j+1)]['Age'].dropna()age_guess = guess_df.median()guess_ages[i,j] = int( age_guess/0.5 + 0.5 ) * 0.5for i in range(0, 2):for j in range(0, 3):dataset.loc[ (dataset.Age.isnull()) & (dataset.Sex == i) & (dataset.Pclass == j+1),\'Age'] = guess_ages[i,j]dataset['Age'] = dataset['Age'].astype(int)train_df['AgeBand'] = pd.cut(train_df['Age'], 5)train_df[['AgeBand', 'Survived']].groupby(['AgeBand'], as_index=False).mean().sort_values(by='AgeBand', ascending=True)for dataset in combine: dataset.loc[ dataset['Age'] <= 16, 'Age'] = 0dataset.loc[(dataset['Age'] > 16) & (dataset['Age'] <= 32), 'Age'] = 1dataset.loc[(dataset['Age'] > 32) & (dataset['Age'] <= 48), 'Age'] = 2dataset.loc[(dataset['Age'] > 48) & (dataset['Age'] <= 64), 'Age'] = 3dataset.loc[ dataset['Age'] > 64, 'Age']train_df = train_df.drop(['AgeBand'], axis=1)combine = [train_df, test_df]for dataset in combine:dataset['FamilySize'] = dataset['SibSp'] + dataset['Parch'] + 1for dataset in combine:dataset['IsAlone'] = 0dataset.loc[dataset['FamilySize'] == 1, 'IsAlone'] = 1train_df = train_df.drop(['Parch', 'SibSp', 'FamilySize'], axis=1)test_df = test_df.drop(['Parch', 'SibSp', 'FamilySize'], axis=1)combine = [train_df, test_df]for dataset in combine:dataset['Age*Class'] = dataset.Age * dataset.Pclassfreq_port = train_df.Embarked.dropna().mode()[0]# 众数for dataset in combine:dataset['Embarked'] = dataset['Embarked'].fillna(freq_port)for dataset in combine:dataset['Embarked'] = dataset['Embarked'].map( {'S': 0, 'C': 1, 'Q': 2} ).astype(int)test_df['Fare'].fillna(test_df['Fare'].dropna().median(), inplace=True)train_df['FareBand'] = pd.qcut(train_df['Fare'], 4)train_df[['FareBand', 'Survived']].groupby(['FareBand'], as_index=False).mean().sort_values(by='FareBand', ascending=True)for dataset in combine:dataset.loc[ dataset['Fare'] <= 7.91, 'Fare'] = 0dataset.loc[(dataset['Fare'] > 7.91) & (dataset['Fare'] <= 14.454), 'Fare'] = 1dataset.loc[(dataset['Fare'] > 14.454) & (dataset['Fare'] <= 31), 'Fare'] = 2dataset.loc[ dataset['Fare'] > 31, 'Fare'] = 3dataset['Fare'] = dataset['Fare'].astype(int)train_df = train_df.drop(['FareBand'], axis=1)combine = [train_df, test_df]#将Title进行转化清洗train_df.loc[train_df['Title'] == 'Mr', 'Title'] = 0train_df.loc[train_df['Title'] == 'Miss', 'Title'] = 1train_df.loc[train_df['Title'] == 'Mrs', 'Title'] = 2train_df.loc[train_df['Title'] == 'Master', 'Title'] = 3train_df.loc[train_df['Title'] == 'Dr', 'Title'] = 4train_df.loc[train_df['Title'] == 'Rev', 'Title'] = 5train_df.loc[train_df['Title'] == 'Major', 'Title'] = 6train_df.loc[train_df['Title'] == 'Col', 'Title'] = 7train_df.loc[train_df['Title'] == 'Mlle', 'Title'] = 8train_df.loc[train_df['Title'] == 'Mme', 'Title'] = 9train_df.loc[train_df['Title'] == 'Don', 'Title'] = 10train_df.loc[train_df['Title'] == 'Lady', 'Title'] = 11train_df.loc[train_df['Title'] == 'Countess', 'Title'] = 12train_df.loc[train_df['Title'] == 'Jonkheer', 'Title'] = 13train_df.loc[train_df['Title'] == 'Sir', 'Title'] = 14train_df.loc[train_df['Title'] == 'Capt', 'Title'] = 15train_df.loc[train_df['Title'] == 'Ms', 'Title'] = 16train_df.loc[train_df['Title'] == 'Rare', 'Title'] = 17#将测试集Title进行转化清洗test_df.loc[test_df['Title'] == 'Mr', 'Title'] = 0test_df.loc[test_df['Title'] == 'Miss', 'Title'] = 1test_df.loc[test_df['Title'] == 'Mrs', 'Title'] = 2test_df.loc[test_df['Title'] == 'Master', 'Title'] = 3test_df.loc[test_df['Title'] == 'Dr', 'Title'] = 4test_df.loc[test_df['Title'] == 'Rev', 'Title'] = 5test_df.loc[test_df['Title'] == 'Major', 'Title'] = 6test_df.loc[test_df['Title'] == 'Col', 'Title'] = 7test_df.loc[test_df['Title'] == 'Mlle', 'Title'] = 8test_df.loc[test_df['Title'] == 'Mme', 'Title'] = 9test_df.loc[test_df['Title'] == 'Don', 'Title'] = 10test_df.loc[test_df['Title'] == 'Lady', 'Title'] = 11test_df.loc[test_df['Title'] == 'Countess', 'Title'] = 12test_df.loc[test_df['Title'] == 'Jonkheer', 'Title'] = 13test_df.loc[test_df['Title'] == 'Sir', 'Title'] = 14test_df.loc[test_df['Title'] == 'Capt', 'Title'] = 15test_df.loc[test_df['Title'] == 'Ms', 'Title'] = 16test_df.loc[test_df['Title'] == 'Rare', 'Title'] = 17#test_df = test_df.drop(['Survived'], axis=1)train_df = train_df.drop(['PassengerId'], axis=1)X_train = train_df.drop("Survived", axis=1)Y_train = train_df["Survived"]X_test = test_df.drop("PassengerId", axis=1).copy()

四、模型

1.决策树

# Decision Treedecision_tree = DecisionTreeClassifier()decision_tree.fit(X_train, Y_train)Y_pred = decision_tree.predict(X_test)acc_decision_tree = round(decision_tree.score(X_train, Y_train) * 100, 2)acc_decision_tree

2.SVC

# Support Vector Machinessvc = SVC()svc.fit(X_train, Y_train)Y_pred = svc.predict(X_test)acc_svc = round(svc.score(X_train, Y_train) * 100, 2)acc_svc

3.LogR

# Logistic Regressionlogreg = LogisticRegression()logreg.fit(X_train, Y_train)Y_pred = logreg.predict(X_test)acc_log = round(logreg.score(X_train, Y_train) * 100, 2)acc_log

4.KNN

knn = KNeighborsClassifier(n_neighbors = 3)knn.fit(X_train, Y_train)Y_pred = knn.predict(X_test)acc_knn = round(knn.score(X_train, Y_train) * 100, 2)acc_knn

5.Gaussian

# Gaussian Naive Bayesgaussian = GaussianNB()gaussian.fit(X_train, Y_train)Y_pred = gaussian.predict(X_test)acc_gaussian = round(gaussian.score(X_train, Y_train) * 100, 2)acc_gaussian

6.Perceptron

# Perceptronperceptron = Perceptron()perceptron.fit(X_train, Y_train)Y_pred = perceptron.predict(X_test)acc_perceptron = round(perceptron.score(X_train, Y_train) * 100, 2)acc_perceptron

7.Stochastic

# Stochastic Gradient Descentsgd = SGDClassifier()sgd.fit(X_train, Y_train)Y_pred = sgd.predict(X_test)acc_sgd = round(sgd.score(X_train, Y_train) * 100, 2)acc_sgd

Final

from sklearn.pipeline import Pipelinefrom sklearn.ensemble import RandomForestClassifierfrom sklearn.model_selection import GridSearchCVfrom sklearn.feature_selection import SelectKBestpipe=Pipeline([('select',SelectKBest(k='all')), ('classify', RandomForestClassifier(random_state = 10, max_features = 'sqrt'))])param_test = {'classify__n_estimators':list(range(20,50,2)), 'classify__max_depth':list(range(3,60,3))}gsearch = GridSearchCV(estimator = pipe, param_grid = param_test, scoring='roc_auc', cv=10)gsearch.fit(X_train,Y_train)print(gsearch.best_params_, gsearch.best_score_)

———————————————————

写的太烂了，重新去打基础学习了QAQ