泰坦尼克号沉船数据分析与可视化、数据建模与分类预测【Python | 机器学习-Sklearn】_titanic.csv

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from pylab import *
import seaborn as sns
 
from sklearn import model_selection, preprocessing, naive_bayes, metrics, svm
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn import ensemble, tree
 
# 忽略警告提示
import warnings
warnings.filterwarnings('ignore')

data = pd.read_csv('titanic.csv')
print(data.shape)
data.sample(5)

data.isnull().sum()

data['age']=data['age'].fillna(data['age'].median())
del data['deck']
data['embarked']=data['embarked'].fillna('S')
data['embark_town']=data['embark_town'].fillna('Southampton')
 
data.isnull().sum()

survived = data['survived'].value_counts().to_frame().reset_index().rename(columns={'index': 'label', 'survived': 'counts'})
 
#计算存活率
survived_rate = round(342/891, 2)
survived['rate'] = [1-survived_rate, survived_rate]
survived

mpl.rcParams['axes.unicode_minus'] = False     #处理无法显示中文的问题
mpl.rcParams['font.sans-serif'] = ['SimHei']  
 
fig=plt.figure(1,figsize=(6,6))
ax1=fig.add_subplot(1,1,1)  
label=['遇难','存活']
color=['#C23531','#F5DEB3']
explode=0.05,0.05  #扇区间隔
 
patches,l_text,p_text = ax1.pie(survived.rate,labels=label,colors=color,startangle=90,autopct='%1.0f%%',explode=explode,shadow=True)
for t in l_text:
    t.set_size(20)
for t in p_text:
    t.set_size(20)
ax1.set_title('全体成员的生存情况', fontsize=20) 

fig = plt.figure(figsize=(15,10))
fig.set(alpha=0.3)  # 设定图表颜色alpha参数(透明度)
 
plt.subplot2grid((2,3),(0,0))
data.survived.value_counts().plot(kind='bar')
plt.title("获救情况 (1为获救)")
plt.ylabel("人数")
 
plt.subplot2grid((2,3),(0,1))
data.pclass.value_counts().plot(kind="bar")
plt.ylabel("人数")
plt.title("乘客等级分布")
 
plt.subplot2grid((2,3),(0,2))
plt.scatter(data.survived, data.age)
plt.ylabel("年龄")
plt.grid(b=True, which='major', axis='y')
plt.title("按年龄看获救分布 (1为获救)")
 
plt.subplot2grid((2,3),(1,0), colspan=2)
data.age[data.pclass == 1].plot(kind='kde')
data.age[data.pclass == 2].plot(kind='kde')
data.age[data.pclass == 3].plot(kind='kde')
plt.xlabel("年龄")
plt.ylabel("密度")
plt.title("各等级的乘客年龄分布")
plt.legend(('头等舱', '2等舱','3等舱'),loc='best')
 
plt.subplot2grid((2,3),(1,2))
data.embarked.value_counts().plot(kind='bar')
plt.title("各登船口岸上船人数")
plt.ylabel("人数")
plt.show()

sns.heatmap(data.corr(),annot=True,cmap='RdYlGn',linewidths=0.2)
fig=plt.gcf()
fig.set_size_inches(10,8)
plt.show()

fig = plt.figure(figsize=(15,4))
 
plt.subplot2grid((2,2),(0,0))
data.age[data.survived == 0].plot(kind='box', vert=False, patch_artist=True, notch = True, color='#C23531', fontsize=15)
plt.grid(linestyle="--", alpha=0.8)
plt.title("遇难", fontsize=15)
 
plt.subplot2grid((2,2),(0,1))
data.fare[data.survived == 0].plot(kind='box', vert=False, patch_artist=True, notch = True, color='#C23531', fontsize=15)
plt.grid(linestyle="--", alpha=0.8)
plt.title("遇难", fontsize=15)
 
plt.subplot2grid((2,2),(1,0))
data.age[data.survived == 1].plot(kind='box', vert=False, patch_artist=True, notch = True, color='#F5DEB3', fontsize=15)
plt.grid(linestyle="--", alpha=0.8)
plt.xlabel("存活", fontsize=15)
 
plt.subplot2grid((2,2),(1,1))
data.fare[data.survived == 1].plot(kind='box', vert=False, patch_artist=True, notch = True, color='#F5DEB3', fontsize=15)
plt.grid(linestyle="--", alpha=0.8)
plt.xlabel("存活", fontsize=15)

mpl.rcParams.update({'font.size': 14})
fig,axes=plt.subplots(2,2,figsize=(18, 12))
sns.violinplot("pclass","age", hue="survived", data=data, palette='autumn',ax=axes[0][0]).set_title('Pclass and Age vs Survived')
sns.swarmplot(x="pclass", y="age",hue="survived", data=data,palette='autumn',ax=axes[1][0]).legend(loc='upper right').set_title('survived')
sns.violinplot("sex","age", hue="survived", data=data, palette='winter', ax=axes[0][1]).set_title('Sex and Age vs Survived')
sns.swarmplot(x="sex", y="age",hue="survived", data=data,palette='winter',ax=axes[1][1]).legend(loc='upper right').set_title('survived')

fig,axes=plt.subplots(2,2,figsize=(18, 12))
sns.violinplot("pclass","fare", hue="survived", data=data, palette='autumn',ax=axes[0][0]).set_title('Pclass and Age vs Survived')
sns.stripplot("pclass", "fare",hue="survived", data=data,palette='autumn',ax=axes[1][0]).legend(loc='upper right').set_title('survived')
sns.violinplot("sex","fare", hue="survived", data=data, palette='winter', ax=axes[0][1]).set_title('Sex and Age vs Survived')
sns.stripplot("sex", "fare",hue="survived", data=data,palette='winter',ax=axes[1][1]).legend(loc='upper right').set_title('survived')

data.info()

le = preprocessing.LabelEncoder()
for col in data.columns:
    data[col] = le.fit_transform(data[col])
data.head()
data.to_csv('Preprocessing_Titanic.csv')

del data['who']

data_ = data.T.drop_duplicates().T
print('去重前：', len(data.columns))
print('去重后：', len(data_.columns))
 
for a in data.columns:
    if a not in data_.columns:
        for b in data_.columns:
            if list(data[b].values) == list(data[a].values):
                print(f'重复标签: {a} 和 {b}')
data = data_

data.head()

result_plot = data.hist(bins=50, figsize=(14, 12))

# 对数据进行标准化
# X = StandardScaler().fit_transform(X)

X = data.iloc[:, 1:]
y = data.iloc[:, 0]
 
x_train, x_test, y_train, y_test = train_test_split(X, y,test_size=0.1,shuffle=True,random_state=20)
 
print(x_train.shape)
print(x_test.shape)
print(y[:5])
X[:5]

model, train_score, test_score, roc_auc = [], [], [], []  # 存储相关模型信息，以便后续分析
 
def train_model(classifier, x_train, y_train, x_test):
    lr = classifier  # 初始化
    lr.fit(x_train, y_train)  # 训练
    y_pred_lr = lr.predict(x_test)  # 预测
 
    if '.' in str(classifier):
        model_name = str(classifier).split('(')[0].split('Classifier')[0].split('.')[1]
        print('\n{:=^60}'.format(model_name))
    else:
        model_name = str(classifier).split('(')[0].split('Classifier')[0]
        print('\n{:=^60}'.format(model_name))
    model.append(model_name)
        
    # 性能评估
    print('\n>>>在训练集上的表现：', lr.score(x_train, y_train))
    print('\n>>>在测试集上的表现：', metrics.accuracy_score(y_test, y_pred_lr))
    print('\n>>>预测的 Roc_auc：%.4f' % metrics.roc_auc_score(y_test, y_pred_lr))
    print('\n>>>混淆矩阵'),show_confusion_matrix(metrics.confusion_matrix(y_test,y_pred_lr))
    
    train_score.append(lr.score(x_train, y_train))
    test_score.append(metrics.accuracy_score(y_test, y_pred_lr))
    roc_auc.append(metrics.roc_auc_score(y_test, y_pred_lr))

def show_confusion_matrix(cnf_matrix):
    plt.matshow(cnf_matrix,cmap=plt.cm.YlGn,alpha=0.7)
    ax=plt.gca()
    ax.set_xlabel('Predicted Label',fontsize=16)
    ax.set_xticks(range(0,len(survived.label)))
    ax.set_xticklabels(survived.label,rotation=45)
    ax.set_ylabel('Actual Label',fontsize=16,rotation=90)
    ax.set_yticks(range(0,len(survived.label)))
    ax.set_yticklabels(survived.label)
    ax.xaxis.set_label_position('top')
    ax.xaxis.tick_top()
    for row in range(len(cnf_matrix)):
        for col in range(len(cnf_matrix[row])):
            ax.text(col,row,cnf_matrix[row][col],va='center',ha='center',fontsize=16)
    plt.show()

def show_roc_line(classifier, x_train, y_train):  
    y_train_prob=classifier.predict_proba(x_train)
    y_pred_prob=y_train_prob[:,1]                             #正例率 
    fpr,tpr,thresholds=metrics.roc_curve(y_train,y_pred_prob) #计算ROC曲线
    auc=metrics.auc(fpr,tpr)                                  #计算AUC 
    plt.plot(fpr,tpr,lw=2,label='ROC curve (area={:.2f})'.format(auc))
    plt.plot([0,1],[0,1],'r--')
    plt.xlim([-0.01, 1.02])
    plt.ylim([-0.01, 1.02])
    plt.xlabel('False Positive Rate')
    plt.ylabel('True Positive Rate')
    plt.title('Receiver Operating Characteristic')
    plt.legend(loc='lower right')
    plt.show() 

classifier = tree.DecisionTreeClassifier()
train_model(classifier, x_train, y_train, x_test)  #建模

labels = X.columns
importances = classifier.feature_importances_   # 获取特征权重值
indices = np.argsort(importances)[::-1]# 打印特征等级
 
features = [labels[i] for i in indices]
weights = [importances[i] for i in indices]
 
print("Feature ranking:")
for f in range(len(features)):
    print("%d. %s (%f)" % (f + 1, features[f], weights[f]))# 绘制随机森林的特征重要性
    
plt.figure()
plt.title("Feature importances")
plt.bar(features, np.array(weights), color='r')
plt.xticks(rotation=90)
plt.title('Feature Weights')
plt.show()

classifier = KNeighborsClassifier(n_neighbors=20)
train_model(classifier, x_train, y_train, x_test)  
show_roc_line(classifier, x_train, y_train)

classifier = svm.SVC()
train_model(classifier, x_train, y_train, x_test)

classifier = naive_bayes.GaussianNB()
train_model(classifier, x_train, y_train, x_test)  #建模

show_roc_line(classifier, x_train, y_train)  #绘制ROC曲线

df = pd.DataFrame()
df['model'] = model
df['Roc_auc'] = roc_auc
df['train_score'] = train_score
df['test_score'] = test_score
df

param = [{'criterion':['gini'],'max_depth': np.arange(20,50,10),'min_samples_leaf':np.arange(2,8,2),
          'min_impurity_decrease':np.linspace(0.1,0.9,10)},
         {'criterion':['gini','entropy']},
         {'min_impurity_decrease':np.linspace(0.1,0.9,10)}]
clf = GridSearchCV(tree.DecisionTreeClassifier(),param_grid=param,cv=10)
clf.fit(x_train,y_train)
print('最优参数:', clf.best_params_)
print('最好成绩:', clf.best_score_)

model = tree.DecisionTreeClassifier(criterion= 'gini', max_depth=20, min_impurity_decrease=0.1, min_samples_leaf= 2)
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
print('train score:', clf.score(x_train, y_train))
print('test score:', clf.score(x_test, y_test))
print("查准率：", metrics.precision_score(y_test,y_pred))
print('召回率:',metrics.recall_score(y_test,y_pred))
print('f1分数:', metrics.f1_score(y_test,y_pred)) #二分类评价标准