基于机器学习的泰坦尼克数据集数据分析

数据集以及ipynb文件放在了我的GitHub上面：欢迎自取
Titanic - Machine Learning from Disaster

如果本文对你有帮助，欢迎点赞、订阅以及star我的项目。
你的支持是我创作的最大动力！

泰坦尼克数据集

任务：预测泰坦尼克乘客生存概率

数据集：train.csv、test.csv

1. 训练集应用于构建您的机器学习模型。 对于训练集，我们为每位乘客提供结果（也称为“特征”）。 您的模型将基于乘客的性别和阶级等“特征”。 您还可以使用特征工程来创建新特征

2. 应该使用测试集来查看您的模型在看不见的数据上的表现如何。 对于测试集，我们不提供每位乘客的基本情况。 预测这些结果是您的工作。 对于测试集中的每位乘客，请使用您训练的模型来预测他们是否在泰坦尼克号沉没中幸存了下来

#   数据分析
import pandas as pd
import numpy as np
import random as rnd

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

#   机器学习
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

train_df = pd.read_csv('/content/train.csv')
test_df = pd.read_csv('/content/test.csv')

combine = [train_df, test_df]

print(train_df.columns.values)

train_df.head()
train_df.tail()
train_df.info()
test_df.info()
train_df.describe()

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

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

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

#  可视化数据
g = sns.FacetGrid(train_df, col='Survived')
g.map(plt.hist, 'Age', bins=20)

g = sns.FacetGrid(train_df, col='Survived')
g.map(plt.hist, 'Sex', bins=20)

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.add_legend()

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()

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

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

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

"After", train_df.shape, test_df.shape, combine[0].shape, combine[1].shape

for dataset in combine:
    dataset['Title'] = dataset.Name.str.extract(' ([A-Za-z]+)\.', expand=False)

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

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


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.head()


train_df = train_df.drop(['Name', 'PassengerId'], axis=1)
test_df = test_df.drop(['Name'], axis=1)
combine = [train_df, test_df]
train_df.shape, test_df.shape


for dataset in combine:
    dataset['Sex'] = dataset['Sex'].map({'female':1, 'male':0}).astype(int)

train_df.head()

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

guess_ages = np.zeros((2,3))
guess_ages


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.head()

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.head()

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

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()

for dataset in combine:
    dataset['Age*Class'] = dataset.Age * dataset.Pclass

train_df.loc[:, ['Age*Class', 'Age', 'Pclass']].head(10)

freq_port = train_df.Embarked.dropna().mode()[0]
freq_port

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()

test_df['Fare'].fillna(test_df['Fare'].dropna().median(), inplace=True)
test_df.head()

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)

"""
建模，预测，求解  
现在，我们准备训练模型并预测所需的解决方案。 有60多种预测建模算法可供选择。 我们必须了解问题的类型和解决方案的要求，以缩小到可以评估的少数几个模型。 我们的问题是分类和回归问题。 我们要确定输出（是否存活）与其他变量或特征（性别，年龄，港口...）之间的关系。 当我们使用给定的数据集训练模型时，我们也将机器学习称为“监督学习”。 通过这两个标准-监督学习加上分类和回归，我们可以将模型选择范围缩小到几个。 这些包括：  
- Logistic Regression
- KNN or k-Nearest Neighbors
- Support Vector Machines
- Naive Bayes classifier
- Decision Tree
- Random Forrest
- Perceptron
- Artificial neural network
- RVM or Relevance Vector Machine
"""

X_train = train_df.drop("Survived", axis=1)
Y_train = train_df["Survived"]
X_test = X_test  = test_df.drop("PassengerId", axis=1).copy()
X_train.shape, Y_train.shape, X_test.shape

# 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

coeff_df = pd.DataFrame(train_df.columns.delete(0))
coeff_df.columns = ['Feature']
coeff_df["Correlation"] = pd.Series(logreg.coef_[0])

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)
acc_svc

# 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

# 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

# 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

# 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

# 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

# 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

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)


submission = pd.DataFrame({
        "PassengerId": test_df["PassengerId"],
        "Survived": Y_pred
    })
# submission.to_csv('../output/submission.csv', index=False)
print(submission)