# 数据分析和处理
import numpy as np
import pandas as pd

# 数据可视化
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline

train_df = pd.read_csv('./train.csv')
test_df = pd.read_csv('./test.csv')
combine = [train_df, test_df]

print(train_df.columns)

Index(['PassengerId', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp',
       'Parch', 'Ticket', 'Fare', 'Cabin', 'Embarked'],
      dtype='object')

train_df.head()

train_df.info()
print('_'*40)
test_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
PassengerId    891 non-null int64
Survived       891 non-null int64
Pclass         891 non-null int64
Name           891 non-null object
Sex            891 non-null object
Age            714 non-null float64
SibSp          891 non-null int64
Parch          891 non-null int64
Ticket         891 non-null object
Fare           891 non-null float64
Cabin          204 non-null object
Embarked       889 non-null object
dtypes: float64(2), int64(5), object(5)
memory usage: 83.6+ KB
________________________________________
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 418 entries, 0 to 417
Data columns (total 11 columns):
PassengerId    418 non-null int64
Pclass         418 non-null int64
Name           418 non-null object
Sex            418 non-null object
Age            332 non-null float64
SibSp          418 non-null int64
Parch          418 non-null int64
Ticket         418 non-null object
Fare           417 non-null float64
Cabin          91 non-null object
Embarked       418 non-null object
dtypes: float64(2), int64(4), object(5)
memory usage: 36.0+ KB

train_df.describe()

train_df.describe(include='O')

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

train_df.groupby(['Sex'])['Sex','Survived'].mean()

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

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

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

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

<seaborn.axisgrid.FacetGrid at 0x1a12933d30>

grid = sns.FacetGrid(train_df, col='Survived', row='Pclass', size=2.2, aspect=1.6)
grid.map(plt.hist, 'Age', alpha=.5, bins=20)  #bins表示直方数量, alpha表示颜色的深浅程度
grid.add_legend() # legend:图例

<seaborn.axisgrid.FacetGrid at 0x10c589f60>

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

/Users/shenxin/anaconda3/lib/python3.6/site-packages/seaborn/axisgrid.py:703: UserWarning: Using the pointplot function without specifying `order` is likely to produce an incorrect plot.
  warnings.warn(warning)
/Users/shenxin/anaconda3/lib/python3.6/site-packages/seaborn/axisgrid.py:708: UserWarning: Using the pointplot function without specifying `hue_order` is likely to produce an incorrect plot.
  warnings.warn(warning)





<seaborn.axisgrid.FacetGrid at 0x1a1e2e9400>

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)
grid.add_legend()

/Users/shenxin/anaconda3/lib/python3.6/site-packages/seaborn/axisgrid.py:703: UserWarning: Using the barplot function without specifying `order` is likely to produce an incorrect plot.
  warnings.warn(warning)





<seaborn.axisgrid.FacetGrid at 0x1a1e75cc50>

print("Before", train_df.shape, test_df.shape, combine[0].shape, combine[1].shape)

Before (891, 12) (418, 11) (891, 12) (418, 11)

# 无关特征删除
train_df = train_df.drop(['Ticket', 'Cabin', 'Name'], axis=1)
test_df = test_df.drop(['Ticket', 'Cabin', 'Name'], axis=1)
combine = [train_df, test_df]
print("After", train_df.shape, test_df.shape, combine[0].shape, combine[1].shape)

After (891, 9) (418, 8) (891, 9) (418, 8)

# 分类特征转换为数值特征
for dataset in combine:
    dataset['Sex'] = dataset['Sex'].map({'female':1, 'male':0}).astype(int)
train_df.head()

# 数值特征缺失值处理
guess_ages = np.zeros((2,3))
guess_ages

array([[0., 0., 0.],
       [0., 0., 0.]])

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) * 0.5

    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]
train_df.head()       

# 连续数值转为分类特征
train_df['AgeBand'] = pd.cut(train_df['Age'], 5)   # 按数值值等分，区别 qcut()按数值个数等分
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.head()

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

# 分类特征缺失值处理（只有两个，所以按最常用的填补）
freq_port = train_df.Embarked.dropna().mode()[0]   # 最常见值
for dataset in combine:
    dataset['Embarked'] = dataset['Embarked'].fillna(freq_port)

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

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

# 缺失较少，取中值
test_df['Fare'].fillna(test_df['Fare'].dropna().median(), inplace=True)   

# 将票价离散化
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]
    
train_df.head(10)

# 尝试创建新特征
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)

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]

train_df.head()

# 数据准备
X_train = train_df.drop(["Survived","PassengerId"], axis=1)
Y_train = train_df["Survived"]
X_test  = test_df.drop(["PassengerId"], axis=1)
X_train.shape, Y_train.shape, X_test.shape

((891, 6), (891,), (418, 6))

# machine learning
# 采用以下模型进行建模

from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC, LinearSVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import Perceptron
from sklearn.linear_model import SGDClassifier
from sklearn.tree import DecisionTreeClassifier

# 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)
acc_log

78.56

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)
acc_svc

82.15

# 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

83.61

# 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)
acc_gaussian

75.31

# 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)
acc_perceptron

/Users/shenxin/anaconda3/lib/python3.6/site-packages/sklearn/linear_model/stochastic_gradient.py:128: FutureWarning: max_iter and tol parameters have been added in <class 'sklearn.linear_model.perceptron.Perceptron'> in 0.19. If both are left unset, they default to max_iter=5 and tol=None. If tol is not None, max_iter defaults to max_iter=1000. From 0.21, default max_iter will be 1000, and default tol will be 1e-3.
  "and default tol will be 1e-3." % type(self), FutureWarning)





77.1

# 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)
acc_linear_svc

78.56

# Stochastic Gradient Descent

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)
acc_sgd

/Users/shenxin/anaconda3/lib/python3.6/site-packages/sklearn/linear_model/stochastic_gradient.py:128: FutureWarning: max_iter and tol parameters have been added in <class 'sklearn.linear_model.stochastic_gradient.SGDClassifier'> in 0.19. If both are left unset, they default to max_iter=5 and tol=None. If tol is not None, max_iter defaults to max_iter=1000. From 0.21, default max_iter will be 1000, and default tol will be 1e-3.
  "and default tol will be 1e-3." % type(self), FutureWarning)





79.24

# 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)
acc_decision_tree

85.75

# 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)
acc_random_forest

85.75

# 把准确率排序

models = pd.DataFrame({
    'Model': ['Support Vector Machines', 'KNN', 'Logistic Regression', 
              'Random Forest', 'Naive Bayes', 'Perceptron', 
              'Stochastic Gradient Decent', 'Linear SVC', 
              'Decision Tree'],
    'Score': [acc_svc, acc_knn, acc_log, 
              acc_random_forest, acc_gaussian, acc_perceptron, 
              acc_sgd, acc_linear_svc, acc_decision_tree]})
models.sort_values(by='Score', ascending=False)