今天找到了一份可以上0.83的代码，真是令人震惊，作者只是用了knn的单模型就做到了这个成绩。其中他构建了一个很新奇的特征：家庭中是否有人存活，我不知道是不是这个意思。最后也没有交叉验证，甚至划分出验证集，只是使用了网格搜索，当然，这并不意味着作者做了很少的工作，实际上在他的Kernels中它提到了自己尝试了很多模型，最后发现knn表现非常好，原文链接如下：https://www.kaggle.com/konstantinmasich/titanic-0-82-0-83
泰坦尼克号是一个经典的二分类问题，我查阅了很多人的解决方案，并记录了5份，这5份中有使用常用的树模型进行集成，有使用两层训练的方法，有使用投票的方法，还用使用深度学习的方法，以及单模型达到的良好结果。
在这些中我学到的是他们分析构建特征时的思路，如何去进行分析，良好的特征永远是最重要的，但是如何去寻找他们是一门学问。最后附一下大神的代码：
# -*- coding: utf-8 -*-
"""
Created on Tue Dec 4 20:19:56 2018
@author: www
"""
import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier #KNN
from sklearn.model_selection import GridSearchCV
from sklearn.preprocessing import LabelEncoder
train_df = pd.read_csv("./input/train.csv")
test_df = pd.read_csv("./input/test.csv")
data_df = train_df.append(test_df)
#特征工程
data_df['Title'] = data_df['Name']
for name_string in data_df['Name']:
data_df['Title'] = data_df['Name'].str.extract('([A-Za-z]+)\.', expand=True)
mapping = {'Mlle': 'Miss', 'Major': 'Mr', 'Col': 'Mr', 'Sir': 'Mr', 'Don': 'Mr', 'Mme': 'Miss',
'Jonkheer': 'Mr', 'Lady': 'Mrs', 'Capt': 'Mr', 'Countess': 'Mrs', 'Ms': 'Miss', 'Dona': 'Mrs'}
data_df.replace({'Title': mapping}, inplace=True)
titles = ['Dr', 'Master', 'Miss', 'Mr', 'Mrs', 'Rev']
for title in titles:
age_to_impute = data_df.groupby('Title')['Age'].median()[titles.index(title)]
data_df.loc[(data_df['Age'].isnull()) & (data_df['Title'] == title), 'Age'] = age_to_impute
train_df['Age'] = data_df['Age'][:891]
test_df['Age'] = data_df['Age'][891:]
data_df.drop('Title', axis = 1, inplace = True)
data_df['Family_Size'] = data_df['Parch'] + data_df['SibSp']
train_df['Family_Size'] = data_df['Family_Size'][:891]
test_df['Family_Size'] = data_df['Family_Size'][891:]
data_df['Last_Name'] = data_df['Name'].apply(lambda x: str.split(x, ",")[0])
data_df['Fare'].fillna(data_df['Fare'].mean(), inplace=True)
DEFAULT_SURVIVAL_VALUE = 0.5
data_df['Family_Survival'] = DEFAULT_SURVIVAL_VALUE
for grp, grp_df in data_df[['Survived','Name', 'Last_Name', 'Fare', 'Ticket', 'PassengerId',
'SibSp', 'Parch', 'Age', 'Cabin']].groupby(['Last_Name', 'Fare']):
if (len(grp_df) != 1):
# A Family group is found.
for ind, row in grp_df.iterrows():
smax = grp_df.drop(ind)['Survived'].max()
smin = grp_df.drop(ind)['Survived'].min()
passID = row['PassengerId']
if (smax == 1.0):
data_df.loc[data_df['PassengerId'] == passID, 'Family_Survival'] = 1
elif (smin==0.0):
data_df.loc[data_df['PassengerId'] == passID, 'Family_Survival'] = 0
print("Number of passengers with family survival information:",
data_df.loc[data_df['Family_Survival']!=0.5].shape[0])
for _, grp_df in data_df.groupby('Ticket'):
if (len(grp_df) != 1):
for ind, row in grp_df.iterrows():
if (row['Family_Survival'] == 0) | (row['Family_Survival']== 0.5):
smax = grp_df.drop(ind)['Survived'].max()
smin = grp_df.drop(ind)['Survived'].min()
passID = row['PassengerId']
if (smax == 1.0):
data_df.loc[data_df['PassengerId'] == passID, 'Family_Survival'] = 1
elif (smin==0.0):
data_df.loc[data_df['PassengerId'] == passID, 'Family_Survival'] = 0
print("Number of passenger with family/group survival information: "
+str(data_df[data_df['Family_Survival']!=0.5].shape[0]))
# # Family_Survival in TRAIN_DF and TEST_DF:
train_df['Family_Survival'] = data_df['Family_Survival'][:891]
test_df['Family_Survival'] = data_df['Family_Survival'][891:]
data_df['Fare'].fillna(data_df['Fare'].median(), inplace = True)
# Making Bins
data_df['FareBin'] = pd.qcut(data_df['Fare'], 5)
label = LabelEncoder()
data_df['FareBin_Code'] = label.fit_transform(data_df['FareBin'])
train_df['FareBin_Code'] = data_df['FareBin_Code'][:891]
test_df['FareBin_Code'] = data_df['FareBin_Code'][891:]
train_df.drop(['Fare'], 1, inplace=True)
test_df.drop(['Fare'], 1, inplace=True)
data_df['AgeBin'] = pd.qcut(data_df['Age'], 4)
label = LabelEncoder()
data_df['AgeBin_Code'] = label.fit_transform(data_df['AgeBin'])
train_df['AgeBin_Code'] = data_df['AgeBin_Code'][:891]
test_df['AgeBin_Code'] = data_df['AgeBin_Code'][891:]
train_df.drop(['Age'], 1, inplace=True)
test_df.drop(['Age'], 1, inplace=True)
train_df['Sex'].replace(['male','female'],[0,1],inplace=True)
test_df['Sex'].replace(['male','female'],[0,1],inplace=True)
train_df.drop(['Name', 'PassengerId', 'SibSp', 'Parch', 'Ticket', 'Cabin',
'Embarked'], axis = 1, inplace = True)
test_df.drop(['Name','PassengerId', 'SibSp', 'Parch', 'Ticket', 'Cabin',
'Embarked'], axis = 1, inplace = True)
X = train_df.drop('Survived', 1)
y = train_df['Survived']
X_test = test_df.copy()
std_scaler = StandardScaler()
X = std_scaler.fit_transform(X)
X_test = std_scaler.transform(X_test)
n_neighbors = [6,7,8,9,10,11,12,14,16,18,20,22]
algorithm = ['auto']
weights = ['uniform', 'distance']
leaf_size = list(range(1,50,5))
hyperparams = {'algorithm': algorithm, 'weights': weights, 'leaf_size': leaf_size,
'n_neighbors': n_neighbors}
gd=GridSearchCV(estimator = KNeighborsClassifier(), param_grid = hyperparams, verbose=True,
cv=10, scoring = "roc_auc")
gd.fit(X, y)
print(gd.best_score_) #0.879492358564
print(gd.best_estimator_)
#KNeighborsClassifier(algorithm='auto', leaf_size=26, metric='minkowski',
# metric_params=None, n_jobs=1, n_neighbors=18, p=2,
# weights='uniform')
gd.best_estimator_.fit(X, y)
y_pred = gd.best_estimator_.predict(X_test)
knn = KNeighborsClassifier(algorithm='auto', leaf_size=26, metric='minkowski',
metric_params=None, n_jobs=1, n_neighbors=6, p=2,
weights='uniform')
knn.fit(X, y)
y_pred = knn.predict(X_test)
temp = pd.DataFrame(pd.read_csv("./input/test.csv")['PassengerId'])
temp['Survived'] = y_pred
temp.to_csv("submission1.csv", index = False)
扫一扫
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
