# kaggle|泰坦尼克号生存预测

https://www.kaggle.com/c/titanic

# 1.数据分析

## 分类观察

train_df[['Pclass', 'Survived']].groupby(['Pclass'],
as_index=False).mean().sort_values(by='Survived', ascending=False)

   Pclass  Survived
0       1  0.629630
1       2  0.472826
2       3  0.242363


train_df[["Sex", "Survived"]].groupby(['Sex'],
as_index=False).mean().sort_values(by='Survived', ascending=False)

Sex	Survived
0	female	0.742038
1	male	0.188908


train_df[["SibSp", "Survived"]].groupby(['SibSp'],
as_index=False).mean().sort_values(by='Survived', ascending=False)

SibSp	Survived
1	1	0.535885
2	2	0.464286
0	0	0.345395
3	3	0.250000
4	4	0.166667
5	5	0.000000
6	8	0.000000

train_df[["Parch", "Survived"]].groupby(['Parch'],
as_index=False).mean().sort_values(by='Survived', ascending=False)

Parch	Survived
3	3	0.600000
1	1	0.550847
2	2	0.500000
0	0	0.343658
5	5	0.200000
4	4	0.000000
6	6	0.000000


## 可视化观察

g = sns.FacetGrid(train_df, col='Survived')
g.map(plt.hist, 'Age', bins=20)#bins是柱数量


grid = sns.FacetGrid(train_df, col='Survived', row='Pclass', size=2.2, aspect=1.6)
grid.map(plt.hist, 'Age', alpha=.5, bins=20)


grid = sns.FacetGrid(train_df, row='Embarked', size=2.2, aspect=1.6)
grid.map(sns.pointplot, 'Pclass', 'Survived', 'Sex', palette='deep')


grid = sns.FacetGrid(train_df, row='Embarked', col='Survived', size=2.2, aspect=1.6)
grid.map(sns.barplot, 'Sex', 'Fare', alpha=.5, ci=None)


# 2.数据处理

## 数据字符替换

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)
pd.crosstab(train_df['Title'], train_df['Sex'])

Sex       female  male
Title
Capt           0     1
Col            0     2
Countess       1     0
Don            0     1
Dr             1     6
Jonkheer       0     1
Major          0     2
Master         0    40
Miss         182     0
Mlle           2     0
Mme            1     0
Mr             0   517
Mrs          125     0
Ms             1     0
Rev            0     6
Sir            0     1


for dataset in combine:
'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[['Title', 'Survived']].groupby(['Title'], as_index=False).mean()

    Title  Survived
0  Master  0.575000
1    Miss  0.702703
2      Mr  0.156673
3     Mrs  0.793651
4    Rare  0.347826


title_mapping = {"Mr": 1, "Miss": 2, "Mrs": 3, "Master": 4, "Rare": 5}
for dataset in combine:
dataset['Title'] = dataset['Title'].map(title_mapping)
dataset['Title'] = dataset['Title'].fillna(0)


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)


port数值替换

for dataset in combine:
dataset['Embarked'] = dataset['Embarked'].map( {'S': 0, 'C': 1, 'Q': 2} ).astype(int)


## 缺失值填充

### 1.Age

(1).在平均值和标准差之间生成随机数

(2).使用其他相关特性

grid = sns.FacetGrid(train_df, row='Pclass', col='Sex', size=2.2, aspect=1.6)
grid.map(plt.hist, 'Age', alpha=.5, bins=20)


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_mean = guess_df.mean()
# age_std = guess_df.std()
# age_guess = rnd.uniform(age_mean - age_std, age_mean + age_std)

age_guess = guess_df.median()

# Convert random age float to nearest .5 age
guess_ages[i,j] = int( age_guess/0.5 + 0.5 ) * 0.5

for 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'] = 0
dataset.loc[(dataset['Age'] > 16) & (dataset['Age'] <= 32), 'Age'] = 1
dataset.loc[(dataset['Age'] > 32) & (dataset['Age'] <= 48), 'Age'] = 2
dataset.loc[(dataset['Age'] > 48) & (dataset['Age'] <= 64), 'Age'] = 3
dataset.loc[ dataset['Age'] > 64, 'Age']

train_df = train_df.drop(['AgeBand'], axis=1)
combine = [train_df, test_df]


### 2.port

freq_port = train_df.Embarked.dropna().mode()[0]
for dataset in combine:
dataset['Embarked'] = dataset['Embarked'].fillna(freq_port)


### 3.fare

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'] = 0
dataset.loc[(dataset['Fare'] > 7.91) & (dataset['Fare'] <= 14.454), 'Fare'] = 1
dataset.loc[(dataset['Fare'] > 14.454) & (dataset['Fare'] <= 31), 'Fare']   = 2
dataset.loc[ dataset['Fare'] > 31, 'Fare'] = 3
dataset['Fare'] = dataset['Fare'].astype(int)

train_df = train_df.drop(['FareBand'], axis=1)
combine = [train_df, test_df]


## 组合新特征

FamilySize

for dataset in combine:
dataset['FamilySize'] = dataset['SibSp'] + dataset['Parch'] + 1

train_df[['FamilySize', 'Survived']].groupby(['FamilySize'], as_index=False).mean().sort_values(by='Survived', ascending=False)


IsAlong

for dataset in combine:
dataset['IsAlone'] = 0
dataset.loc[dataset['FamilySize'] == 1, 'IsAlone'] = 1

train_df[['IsAlone', 'Survived']].groupby(['IsAlone'], as_index=False).mean()


train_df = train_df.drop(['Parch', 'SibSp', 'FamilySize'], axis=1)
test_df = test_df.drop(['Parch', 'SibSp', 'FamilySize'], axis=1)
combine = [train_df, test_df]



# 3.建立模型

## Naive Bayes

# Logistic Regression
logreg = LogisticRegression()
logreg.fit(X_train, Y_train)
Y_pred = logreg.predict(X_test)
acc_log = round(logreg.score(X_train, Y_train) * 100, 2)
#逻辑回归的同时，可以观察特征的相关度
coeff_df = pd.DataFrame(train_df.columns.delete(0))
coeff_df.columns = ['Feature']
coeff_df["Correlation"] = pd.Series(logreg.coef_[0])
a=coeff_df.sort_values(by='Correlation', ascending=False)

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

# 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)

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

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

# Linear SVC
linear_svc = LinearSVC()
linear_svc.fit(X_train, Y_train)
Y_pred = linear_svc.predict(X_test)
acc_linear_svc = round(linear_svc.score(X_train, Y_train) * 100, 2)

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

# Decision Tree
decision_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)

#Random Forest
random_forest = RandomForestClassifier(n_estimators=100)
random_forest.fit(X_train, Y_train)
Y_pred = random_forest.predict(X_test)
random_forest.score(X_train, Y_train)
acc_random_forest = round(random_forest.score(X_train, Y_train) * 100, 2)


                        Model  Score
3               Random Forest  86.76
8               Decision Tree  86.76
1                         KNN  84.74
0     Support Vector Machines  83.84
2         Logistic Regression  80.36
7                  Linear SVC  79.12
5                  Perceptron  78.00
4                 Naive Bayes  72.28


09-29 694

03-28 2182
08-18 121
04-04 7400
05-19
12-14 680
04-24 313
12-06 1218
09-12 2025
03-16 266
08-23 571
05-11 441