导入程序包

# """https://www.kaggle.com/ash316/eda-to-prediction-dietanic"""
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
plt.style.use('fivethirtyeight')
import warnings
warnings.filterwarnings("ignore")
%matplotlib inline

/work/anaconda3/lib/python3.6/importlib/_bootstrap.py:219: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88
  return f(*args, **kwds)

导入数据

data = pd.read_csv("/work/johnson_folder/biggamesData/titanic/train.csv")

data.head()

data.isnull().sum()

PassengerId      0
Survived         0
Pclass           0
Name             0
Sex              0
Age            177
SibSp            0
Parch            0
Ticket           0
Fare             0
Cabin          687
Embarked         2
dtype: int64

f,ax = plt.subplots(1,2,figsize=(18,8))
data['Survived'].value_counts().plot.pie(explode=[0,0.1],autopct='%1.1f%%',ax=ax[0],shadow=True)
ax[0].set_title('Survived')
ax[0].set_ylabel('')
sns.countplot('Survived',data=data,ax=ax[1])
ax[1].set_title('Survived')
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-wa2hDCaY-1581503014393)(output_6_0.png)]

data.groupby(['Sex','Survived'])['Survived'].count()

Sex     Survived
female  0            81
        1           233
male    0           468
        1           109
Name: Survived, dtype: int64

f,ax=plt.subplots(1,2,figsize=(18,8))
data[['Sex','Survived']].groupby(['Sex']).mean().plot.bar(ax=ax[0])
ax[0].set_title('Survived vs Sex')
sns.countplot('Sex',hue='Survived',data=data,ax=ax[1])
ax[1].set_title('Sex:Survived vs Dead')
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-Dh1YsmfZ-1581503014393)(output_8_0.png)]

pd.crosstab(data.Pclass,data.Survived,margins=True).style.background_gradient(cmap='summer_r')

f,ax=plt.subplots(1,2,figsize=(18,8))
data['Pclass'].value_counts().plot.bar(color=['#CD7F32','#FFDF00','#D3D3D3'],ax=ax[0])
ax[0].set_title('Number Of Passengers By Pclass')
ax[0].set_ylabel('Count')
sns.countplot('Pclass',hue='Survived',data=data,ax=ax[1])
ax[1].set_title('Pclass:Survived vs Dead')
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-Q7ZlCjag-1581503014394)(output_10_0.png)]

pd.crosstab([data.Sex,data.Survived],data.Pclass,margins=True).style.background_gradient(cmap='summer_r')

sns.factorplot('Pclass','Survived',hue='Sex',data=data)
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-aPAFMbTd-1581503014395)(output_12_0.png)]

f,ax=plt.subplots(1,2,figsize=(18,8))
sns.violinplot("Pclass","Age", hue="Survived", data=data,split=True,ax=ax[0])
ax[0].set_title('Pclass and Age vs Survived')
ax[0].set_yticks(range(0,110,10))
sns.violinplot("Sex","Age", hue="Survived", data=data,split=True,ax=ax[1])
ax[1].set_title('Sex and Age vs Survived')
ax[1].set_yticks(range(0,110,10))
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-6Jf8BacS-1581503014395)(output_13_0.png)]

#将名字中的字符串提取出来
data["Initial"] = 0
for i in data:
    data['Initial']=data.Name.str.extract('([A-Za-z]+).') #lets extract the Salutations

pd.crosstab(data.Initial,data.Sex).T.style.background_gradient(cmap='summer_r') #Checking the Initials with the Sex

#有些字符代表女士的提取出来
data['Initial'].replace(['Mlle','Mme','Ms','Dr','Major','Lady','Countess','Jonkheer','Col','Rev','Capt','Sir','Don'],['Miss','Miss','Miss','Mr','Mr','Mrs','Mrs','Other','Other','Other','Mr','Mr','Mr'],inplace=True)

data.groupby('Initial')['Age'].mean() #lets check the average age by Initials

Initial
Master     4.574167
Miss      21.860000
Mr        32.739609
Mrs       35.981818
Other     45.888889
Name: Age, dtype: float64

## Assigning the NaN Values with the Ceil values of the mean ages
data.loc[(data.Age.isnull())&(data.Initial=='Mr'),'Age']=33
data.loc[(data.Age.isnull())&(data.Initial=='Mrs'),'Age']=36
data.loc[(data.Age.isnull())&(data.Initial=='Master'),'Age']=5
data.loc[(data.Age.isnull())&(data.Initial=='Miss'),'Age']=22
data.loc[(data.Age.isnull())&(data.Initial=='Other'),'Age']=46

data.Age.isnull().sum()

0

f,ax = plt.subplots(1,2,figsize=(20,10))
data[data['Survived']==0].Age.plot.hist(ax=ax[0],bins=20,edgecolor="black",color="red")
ax[0].set_title('Survived= 0')
x1 = list(range(0,85,5))
ax[0].set_xticks(x1)
data[data['Survived']==1].Age.plot.hist(ax=ax[1],color='green',bins=20,edgecolor='black')
ax[1].set_title('Survived= 1')
x2=list(range(0,85,5))
ax[1].set_xticks(x2)
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-OS916mGB-1581503014395)(output_20_0.png)]

sns.factorplot('Pclass','Survived',col='Initial',data=data)
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-rUskFRwQ-1581503014396)(output_21_0.png)]

pd.crosstab([data.Embarked,data.Pclass],[data.Sex,data.Survived],margins=True).style.background_gradient(cmap='summer_r')

sns.factorplot('Embarked','Survived',data=data)
fig=plt.gcf()
fig.set_size_inches(5,3)
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-AL53G7EH-1581503014396)(output_23_0.png)]

f,ax=plt.subplots(2,2,figsize=(20,15))
sns.countplot('Embarked',data=data,ax=ax[0,0])
ax[0,0].set_title('No. Of Passengers Boarded')
sns.countplot('Embarked',hue='Sex',data=data,ax=ax[0,1])
ax[0,1].set_title('Male-Female Split for Embarked')
sns.countplot('Embarked',hue='Survived',data=data,ax=ax[1,0])
ax[1,0].set_title('Embarked vs Survived')
sns.countplot('Embarked',hue='Pclass',data=data,ax=ax[1,1])
ax[1,1].set_title('Embarked vs Pclass')
plt.subplots_adjust(wspace=0.2,hspace=0.5)
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-fUW0vtzZ-1581503014396)(output_24_0.png)]

sns.factorplot('Pclass','Survived',hue='Sex',col='Embarked',data=data)
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-Pee21T7y-1581503014397)(output_25_0.png)]

data["Embarked"].fillna("S",inplace=True)

pd.crosstab([data.SibSp],data.Survived).style.background_gradient(cmap='summer_r')

f,ax=plt.subplots(1,2,figsize=(20,8))
sns.barplot('SibSp','Survived',data=data,ax=ax[0])
ax[0].set_title('SibSp vs Survived')
sns.factorplot('SibSp','Survived',data=data,ax=ax[1])
ax[1].set_title('SibSp vs Survived')
plt.close(2)
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-alQbaTEo-1581503014397)(output_28_0.png)]

pd.crosstab(data.SibSp,data.Pclass).style.background_gradient(cmap='summer_r')

f,ax=plt.subplots(1,2,figsize=(20,8))
sns.barplot('Parch','Survived',data=data,ax=ax[0])
ax[0].set_title('Parch vs Survived')
sns.factorplot('Parch','Survived',data=data,ax=ax[1])
ax[1].set_title('Parch vs Survived')
plt.close(2)
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-ijG8TqaT-1581503014397)(output_30_0.png)]

print('Highest Fare was:',data['Fare'].max())
print('Lowest Fare was:',data['Fare'].min())
print('Average Fare was:',data['Fare'].mean())

Highest Fare was: 512.3292
Lowest Fare was: 0.0
Average Fare was: 32.2042079685746

f,ax=plt.subplots(1,3,figsize=(20,8))
sns.distplot(data[data['Pclass']==1].Fare,ax=ax[0])
ax[0].set_title('Fares in Pclass 1')
sns.distplot(data[data['Pclass']==2].Fare,ax=ax[1])
ax[1].set_title('Fares in Pclass 2')
sns.distplot(data[data['Pclass']==3].Fare,ax=ax[2])
ax[2].set_title('Fares in Pclass 3')
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-0kwn66pD-1581503014398)(output_32_0.png)]

sns.heatmap(data.corr(),annot=True,cmap="RdYlGn",linewidths=0.2) #相关系数矩阵
fig=plt.gcf()
fig.set_size_inches(10,8)
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-ZP66LeeS-1581503014398)(output_33_0.png)]

data['Age_band']=0
data.loc[data['Age']<=16,'Age_band']=0
data.loc[(data['Age']>16)&(data['Age']<=32),'Age_band']=1
data.loc[(data['Age']>32)&(data['Age']<=48),'Age_band']=2
data.loc[(data['Age']>48)&(data['Age']<=64),'Age_band']=3
data.loc[data['Age']>64,'Age_band']=4
data.head(2)

data['Age_band'].value_counts().to_frame().style.background_gradient(cmap='summer')#checking the number of passenegers in each band

sns.factorplot('Age_band','Survived',data=data,col='Pclass')
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-14IjuoTq-1581503014398)(output_36_0.png)]

data['Family_Size']=0
data['Family_Size']=data['Parch']+data['SibSp']#family size
data['Alone']=0
data.loc[data.Family_Size==0,'Alone']=1#Alone

f,ax=plt.subplots(1,2,figsize=(18,6))
sns.factorplot('Family_Size','Survived',data=data,ax=ax[0])
ax[0].set_title('Family_Size vs Survived')
sns.factorplot('Alone','Survived',data=data,ax=ax[1])
ax[1].set_title('Alone vs Survived')
plt.close(2)
plt.close(3)
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-OgSwZygT-1581503014399)(output_37_0.png)]

sns.factorplot('Alone','Survived',data=data,hue='Sex',col='Pclass')
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-8uAgWzzH-1581503014399)(output_38_0.png)]

data['Fare_Range'] = pd.qcut(data['Fare'],4)
data.groupby(['Fare_Range'])['Survived'].mean().to_frame().style.background_gradient(cmap='summer_r')

data['Fare_cat']=0
data.loc[data['Fare']<=7.91,'Fare_cat']=0
data.loc[(data['Fare']>7.91)&(data['Fare']<=14.454),'Fare_cat']=1
data.loc[(data['Fare']>14.454)&(data['Fare']<=31),'Fare_cat']=2
data.loc[(data['Fare']>31)&(data['Fare']<=513),'Fare_cat']=3

sns.factorplot('Fare_cat','Survived',data=data,hue='Sex')
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-MELN916b-1581503014399)(output_41_0.png)]

data['Sex'].replace(['male','female'],[0,1],inplace=True)
data['Embarked'].replace(['S','C','Q'],[0,1,2],inplace=True)
data['Initial'].replace(['Mr','Mrs','Miss','Master','Other'],[0,1,2,3,4],inplace=True)

data.drop(['Name','Age','Ticket','Fare','Cabin','Fare_Range','PassengerId'],axis=1,inplace=True)
sns.heatmap(data.corr(),annot=True,cmap='RdYlGn',linewidths=0.2,annot_kws={'size':20})
fig=plt.gcf()
fig.set_size_inches(18,15)
plt.xticks(fontsize=14)
plt.yticks(fontsize=14)
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-18HM73aF-1581503014400)(output_43_0.png)]

#importing all the required ML packages
from sklearn.linear_model import LogisticRegression #logistic regression
from sklearn import svm #support vector Machine
from sklearn.ensemble import RandomForestClassifier #Random Forest
from sklearn.neighbors import KNeighborsClassifier #KNN
from sklearn.naive_bayes import GaussianNB #Naive bayes
from sklearn.tree import DecisionTreeClassifier #Decision Tree
from sklearn.model_selection import train_test_split #training and testing data split
from sklearn import metrics #accuracy measure
from sklearn.metrics import confusion_matrix #for confusion matrix

train,test=train_test_split(data,test_size=0.3,random_state=0,stratify=data['Survived'])
train_X=train[train.columns[1:]]
train_Y=train[train.columns[:1]]
test_X=test[test.columns[1:]]
test_Y=test[test.columns[:1]]
X=data[data.columns[1:]]
Y=data['Survived']

model=svm.SVC(kernel='rbf',C=1,gamma=0.1)
model.fit(train_X,train_Y)
prediction1=model.predict(test_X)
print('Accuracy for rbf SVM is ',metrics.accuracy_score(prediction1,test_Y))

Accuracy for rbf SVM is  0.835820895522388

model=svm.SVC(kernel='linear',C=0.1,gamma=0.1)
model.fit(train_X,train_Y)
prediction2=model.predict(test_X)
print('Accuracy for linear SVM is',metrics.accuracy_score(prediction2,test_Y))

Accuracy for linear SVM is 0.8171641791044776

model = LogisticRegression()
model.fit(train_X,train_Y)
prediction3=model.predict(test_X)
print('The accuracy of the Logistic Regression is',metrics.accuracy_score(prediction3,test_Y))

The accuracy of the Logistic Regression is 0.8171641791044776

model=DecisionTreeClassifier()
model.fit(train_X,train_Y)
prediction4=model.predict(test_X)
print('The accuracy of the Decision Tree is',metrics.accuracy_score(prediction4,test_Y))

The accuracy of the Decision Tree is 0.8022388059701493

model=KNeighborsClassifier() 
model.fit(train_X,train_Y)
prediction5=model.predict(test_X)
print('The accuracy of the KNN is',metrics.accuracy_score(prediction5,test_Y))

The accuracy of the KNN is 0.832089552238806

a_index=list(range(1,11))
a=pd.Series()
x=[0,1,2,3,4,5,6,7,8,9,10]
for i in list(range(1,11)):
    model=KNeighborsClassifier(n_neighbors=i) 
    model.fit(train_X,train_Y)
    prediction=model.predict(test_X)
    a=a.append(pd.Series(metrics.accuracy_score(prediction,test_Y)))
plt.plot(a_index, a)
plt.xticks(x)
fig=plt.gcf()
fig.set_size_inches(12,6)
plt.show()
print('Accuracies for different values of n are:',a.values,'with the max value as ',a.values.max())

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-VgNUnDqp-1581503014400)(output_51_0.png)]

Accuracies for different values of n are: [0.75746269 0.79104478 0.80970149 0.80223881 0.83208955 0.81716418
 0.82835821 0.83208955 0.8358209  0.83208955] with the max value as  0.835820895522388

model=GaussianNB()
model.fit(train_X,train_Y)
prediction6=model.predict(test_X)
print('The accuracy of the NaiveBayes is',metrics.accuracy_score(prediction6,test_Y))

The accuracy of the NaiveBayes is 0.8134328358208955

model=RandomForestClassifier(n_estimators=100)
model.fit(train_X,train_Y)
prediction7=model.predict(test_X)
print('The accuracy of the Random Forests is',metrics.accuracy_score(prediction7,test_Y))

The accuracy of the Random Forests is 0.8171641791044776

from sklearn.model_selection import KFold #for K-fold cross validation
from sklearn.model_selection import cross_val_score #score evaluation
from sklearn.model_selection import cross_val_predict #prediction
kfold = KFold(n_splits=10,random_state=22) #K=10.split the data into 10 equals parts
xyz = []
accuracy = []
std = []

classifiers=['Linear Svm','Radial Svm','Logistic Regression','KNN','Decision Tree','Naive Bayes','Random Forest']
models=[svm.SVC(kernel='linear'),svm.SVC(kernel='rbf'),LogisticRegression(),KNeighborsClassifier(n_neighbors=9),DecisionTreeClassifier(),GaussianNB(),RandomForestClassifier(n_estimators=100)]

for i in models:
    model = i
    cv_result = cross_val_score(model,X,Y,cv=kfold,scoring="accuracy")
    xyz.append(cv_result.mean())
    std.append(cv_result.std())
    accuracy.append(cv_result)
    

new_models_dataframe2=pd.DataFrame({'CV Mean':xyz,'Std':std},index=classifiers)       
new_models_dataframe2

plt.subplots(figsize=(12,6))
box=pd.DataFrame(accuracy,index=[classifiers])
box.T.boxplot()

<matplotlib.axes._subplots.AxesSubplot at 0x7f9b24b58588>

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-bJXBP29j-1581503014400)(output_55_1.png)]

new_models_dataframe2['CV Mean'].plot.barh(width=0.8)
plt.title('Average CV Mean Accuracy')
fig=plt.gcf()
fig.set_size_inches(8,5)
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-frsnayd8-1581503014401)(output_56_0.png)]

f,ax=plt.subplots(3,3,figsize=(12,10))
y_pred = cross_val_predict(svm.SVC(kernel='rbf'),X,Y,cv=10)
sns.heatmap(confusion_matrix(Y,y_pred),ax=ax[0,0],annot=True,fmt='2.0f')
ax[0,0].set_title('Matrix for rbf-SVM')
y_pred = cross_val_predict(svm.SVC(kernel='linear'),X,Y,cv=10)
sns.heatmap(confusion_matrix(Y,y_pred),ax=ax[0,1],annot=True,fmt='2.0f')
ax[0,1].set_title('Matrix for Linear-SVM')
y_pred = cross_val_predict(KNeighborsClassifier(n_neighbors=9),X,Y,cv=10)
sns.heatmap(confusion_matrix(Y,y_pred),ax=ax[0,2],annot=True,fmt='2.0f')
ax[0,2].set_title('Matrix for KNN')
y_pred = cross_val_predict(RandomForestClassifier(n_estimators=100),X,Y,cv=10)
sns.heatmap(confusion_matrix(Y,y_pred),ax=ax[1,0],annot=True,fmt='2.0f')
ax[1,0].set_title('Matrix for Random-Forests')
y_pred = cross_val_predict(LogisticRegression(),X,Y,cv=10)
sns.heatmap(confusion_matrix(Y,y_pred),ax=ax[1,1],annot=True,fmt='2.0f')
ax[1,1].set_title('Matrix for Logistic Regression')
y_pred = cross_val_predict(DecisionTreeClassifier(),X,Y,cv=10)
sns.heatmap(confusion_matrix(Y,y_pred),ax=ax[1,2],annot=True,fmt='2.0f')
ax[1,2].set_title('Matrix for Decision Tree')
y_pred = cross_val_predict(GaussianNB(),X,Y,cv=10)
sns.heatmap(confusion_matrix(Y,y_pred),ax=ax[2,0],annot=True,fmt='2.0f')
ax[2,0].set_title('Matrix for Naive Bayes')
plt.subplots_adjust(hspace=0.2,wspace=0.2)
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-rP39shIv-1581503014401)(output_57_0.png)]

from sklearn.model_selection import GridSearchCV

C=[0.05,0.1,0.2,0.3,0.25,0.4,0.5,0.6,0.7,0.8,0.9,1]
gamma=[0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,1.0]
kernel=['rbf','linear']
hyper={'kernel':kernel,'C':C,'gamma':gamma}

gd = GridSearchCV(estimator=svm.SVC(),param_grid=hyper,verbose=True)
gd.fit(X,Y)
print(gd.best_params_)
print(gd.best_score_)

Fitting 3 folds for each of 240 candidates, totalling 720 fits


[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.


{'C': 0.5, 'gamma': 0.1, 'kernel': 'rbf'}
0.8282828282828283


[Parallel(n_jobs=1)]: Done 720 out of 720 | elapsed:   13.8s finished

n_estimators=range(100,1000,100)
hyper={'n_estimators':n_estimators}
gd=GridSearchCV(estimator=RandomForestClassifier(random_state=0),param_grid=hyper,verbose=True)
gd.fit(X,Y)
print(gd.best_score_)
print(gd.best_estimator_)

Fitting 3 folds for each of 9 candidates, totalling 27 fits


[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.
[Parallel(n_jobs=1)]: Done  27 out of  27 | elapsed:   15.1s finished


0.8170594837261503
RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
            max_depth=None, max_features='auto', max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, n_estimators=900, n_jobs=None,
            oob_score=False, random_state=0, verbose=0, warm_start=False)

from sklearn.ensemble import VotingClassifier
ensemble_lin_rbf=VotingClassifier(estimators=[('KNN',KNeighborsClassifier(n_neighbors=10)),
                                              ('RBF',svm.SVC(probability=True,kernel='rbf',C=0.5,gamma=0.1)),
                                              ('RFor',RandomForestClassifier(n_estimators=500,random_state=0)),
                                              ('LR',LogisticRegression(C=0.05)),
                                              ('DT',DecisionTreeClassifier(random_state=0)),
                                              ('NB',GaussianNB()),
                                              ('svm',svm.SVC(kernel='linear',probability=True))
                                             ], 
                       voting='soft').fit(train_X,train_Y)
print('The accuracy for ensembled model is:',ensemble_lin_rbf.score(test_X,test_Y))
cross=cross_val_score(ensemble_lin_rbf,X,Y, cv = 10,scoring = "accuracy")
print('The cross validated score is',cross.mean())

The accuracy for ensembled model is: 0.8246268656716418
The cross validated score is 0.8237660310974917

from sklearn.ensemble import BaggingClassifier
model=BaggingClassifier(base_estimator=KNeighborsClassifier(n_neighbors=3),random_state=0,n_estimators=700)
model.fit(train_X,train_Y)
prediction=model.predict(test_X)
print('The accuracy for bagged KNN is:',metrics.accuracy_score(prediction,test_Y))
result=cross_val_score(model,X,Y,cv=10,scoring='accuracy')
print('The cross validated score for bagged KNN is:',result.mean())

The accuracy for bagged KNN is: 0.835820895522388
The cross validated score for bagged KNN is: 0.8148893428668709

from sklearn.ensemble import GradientBoostingClassifier
grad=GradientBoostingClassifier(n_estimators=500,random_state=0,learning_rate=0.1)
result=cross_val_score(grad,X,Y,cv=10,scoring='accuracy')
print('The cross validated score for Gradient Boosting is:',result.mean())

The cross validated score for Gradient Boosting is: 0.8182862331176939

import xgboost as xg
xgboost=xg.XGBClassifier(n_estimators=900,learning_rate=0.1)
result=cross_val_score(xgboost,X,Y,cv=10,scoring='accuracy')
print('The cross validated score for XGBoost is:',result.mean())

The cross validated score for XGBoost is: 0.8104710021563954

from sklearn.ensemble import AdaBoostClassifier
n_estimators=list(range(100,1100,100))
learn_rate=[0.05,0.1,0.2,0.3,0.25,0.4,0.5,0.6,0.7,0.8,0.9,1]
hyper={'n_estimators':n_estimators,'learning_rate':learn_rate}
gd=GridSearchCV(estimator=AdaBoostClassifier(),param_grid=hyper,verbose=True)
gd.fit(X,Y)
print(gd.best_score_)
print(gd.best_estimator_)

Fitting 3 folds for each of 120 candidates, totalling 360 fits


[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.
[Parallel(n_jobs=1)]: Done 360 out of 360 | elapsed:  4.3min finished


0.8316498316498316
AdaBoostClassifier(algorithm='SAMME.R', base_estimator=None,
          learning_rate=0.05, n_estimators=200, random_state=None)

ada=AdaBoostClassifier(n_estimators=200,random_state=0,learning_rate=0.05)
result=cross_val_predict(ada,X,Y,cv=10)
sns.heatmap(confusion_matrix(Y,result),cmap='winter',annot=True,fmt='2.0f')
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-fLewcgrH-1581503014402)(output_65_0.png)]

f,ax=plt.subplots(2,2,figsize=(15,12))
model=RandomForestClassifier(n_estimators=500,random_state=0)
model.fit(X,Y)
pd.Series(model.feature_importances_,X.columns).sort_values(ascending=True).plot.barh(width=0.8,ax=ax[0,0])
ax[0,0].set_title('Feature Importance in Random Forests')
model=AdaBoostClassifier(n_estimators=200,learning_rate=0.05,random_state=0)
model.fit(X,Y)
pd.Series(model.feature_importances_,X.columns).sort_values(ascending=True).plot.barh(width=0.8,ax=ax[0,1],color='#ddff11')
ax[0,1].set_title('Feature Importance in AdaBoost')
model=GradientBoostingClassifier(n_estimators=500,learning_rate=0.1,random_state=0)
model.fit(X,Y)
pd.Series(model.feature_importances_,X.columns).sort_values(ascending=True).plot.barh(width=0.8,ax=ax[1,0],cmap='RdYlGn_r')
ax[1,0].set_title('Feature Importance in Gradient Boosting')
model=xg.XGBClassifier(n_estimators=900,learning_rate=0.1)
model.fit(X,Y)
pd.Series(model.feature_importances_,X.columns).sort_values(ascending=True).plot.barh(width=0.8,ax=ax[1,1],color='#FD0F00')
ax[1,1].set_title('Feature Importance in XgBoost')
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-yfS9Kjz3-1581503014403)(output_66_0.png)]

最后

以上就是称心乌冬面为你收集整理的机器学习实战-titanc_demo01导入程序包导入数据的全部内容，希望文章能够帮你解决机器学习实战-titanc_demo01导入程序包导入数据所遇到的程序开发问题。

如果觉得靠谱客网站的内容还不错，欢迎将靠谱客网站推荐给程序员好友。