版权声明:本文为博主原创文章,未经博主允许不得转载。 https://blog.csdn.net/qq_33765907/article/details/81779891
以下代码参考自:Titanic best working Classifier
提交上去score为0.79904
# 学习特征工程
# Learn Feather Engineering
%matplotlib inline
import numpy as np
import pandas as pd
import re as re
train = pd.read_csv('./input/train.csv', header = 0, dtype = {'Age': np.float64})
test = pd.read_csv('./input/test.csv', header = 0, dtype={'Age': np.float64})
full_data = [train, test]
print(train.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
None
print(train.head(10))
PassengerId Survived Pclass \
0 1 0 3
1 2 1 1
2 3 1 3
3 4 1 1
4 5 0 3
5 6 0 3
6 7 0 1
7 8 0 3
8 9 1 3
9 10 1 2
Name Sex Age SibSp \
0 Braund, Mr. Owen Harris male 22.0 1
1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1
2 Heikkinen, Miss. Laina female 26.0 0
3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1
4 Allen, Mr. William Henry male 35.0 0
5 Moran, Mr. James male NaN 0
6 McCarthy, Mr. Timothy J male 54.0 0
7 Palsson, Master. Gosta Leonard male 2.0 3
8 Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg) female 27.0 0
9 Nasser, Mrs. Nicholas (Adele Achem) female 14.0 1
Parch Ticket Fare Cabin Embarked
0 0 A/5 21171 7.2500 NaN S
1 0 PC 17599 71.2833 C85 C
2 0 STON/O2. 3101282 7.9250 NaN S
3 0 113803 53.1000 C123 S
4 0 373450 8.0500 NaN S
5 0 330877 8.4583 NaN Q
6 0 17463 51.8625 E46 S
7 1 349909 21.0750 NaN S
8 2 347742 11.1333 NaN S
9 0 237736 30.0708 NaN C
# 开始特征工程
# 填充缺省值的时候需要对所有数据,而分析数据的时候只能对于train
# 考虑Pclass
print(train[['Pclass', 'Survived']].groupby(['Pclass'], as_index = False).mean())
Pclass Survived
0 1 0.629630
1 2 0.472826
2 3 0.242363
# 考虑Sex
print(train[['Sex', 'Survived']].groupby(['Sex'], as_index = False).mean())
Sex Survived
0 female 0.742038
1 male 0.188908
# 考虑SibSp和Parch(兄弟姐妹人数,孩子父母人数)
# 根据这两个特征构造新的特征FamilySize
for dataset in full_data:
# 新的特征可以直接加入
dataset['FamilySize'] = dataset['SibSp'] + dataset['Parch'] + 1
# 考虑FamilySize
print(train[['FamilySize', 'Survived']].groupby(['FamilySize'], as_index = False).mean())
FamilySize Survived
0 1 0.303538
1 2 0.552795
2 3 0.578431
3 4 0.724138
4 5 0.200000
5 6 0.136364
6 7 0.333333
7 8 0.000000
8 11 0.000000
# 从上述数据可以看出似乎对最后的预测结果有好的影响
# 下面进一步考虑每位乘客在船上是否为独自一人
# 如果是独自一人,IsAlone设置为1
for dataset in full_data:
dataset['IsAlone'] = 0
dataset.loc[dataset['FamilySize'] == 1, 'IsAlone'] = 1
print(train[['IsAlone', 'Survived']].groupby(['IsAlone'], as_index = False).mean())
IsAlone Survived
0 0 0.505650
1 1 0.303538
# 考虑Embarked
# 首先填充缺省值,用最多出现的S去填充缺省值
for dataset in full_data:
dataset['Embarked'] = dataset['Embarked'].fillna('S')
print(train[['Embarked', 'Survived']].groupby(['Embarked'], as_index = False).mean())
Embarked Survived
0 C 0.553571
1 Q 0.389610
2 S 0.339009
# 考虑Fare
# 用Fare的平均值填充缺省值(使用训练数据Fare特征的平均值)
# 加入新特征CategoricalFare,将Fare分为4个区间
for dataset in full_data:
dataset['Fare'] = dataset['Fare'].fillna(train['Fare'].median())
train['CategoricalFare'] = pd.qcut(train['Fare'], 4)
print(train[['CategoricalFare', 'Survived']].groupby(['CategoricalFare'], as_index = False).mean())
CategoricalFare Survived
0 (-0.001, 7.91] 0.197309
1 (7.91, 14.454] 0.303571
2 (14.454, 31.0] 0.454955
3 (31.0, 512.329] 0.581081
# 考虑Age
# 有较多缺省值,在(mean - std)和(mean + std)随机生成数字,然后分成5个区间
for dataset in full_data:
age_avg = dataset['Age'].mean()
age_std = dataset['Age'].std()
age_null_count = dataset['Age'].isnull().sum()
age_null_random_list = np.random.randint(age_avg - age_std, age_avg + age_std, size = age_null_count)
dataset['Age'][np.isnan(dataset['Age'])] = age_null_random_list
dataset['Age'] = dataset['Age'].astype(int)
# 创建新特征
train['CategoricalAge'] = pd.cut(train['Age'], 5)
print(train[['CategoricalAge', 'Survived']].groupby(['CategoricalAge'], as_index = False).mean())
CategoricalAge Survived
0 (-0.08, 16.0] 0.508929
1 (16.0, 32.0] 0.359909
2 (32.0, 48.0] 0.369231
3 (48.0, 64.0] 0.434783
4 (64.0, 80.0] 0.090909
/Users/martin/anaconda3/lib/python3.6/site-packages/ipykernel_launcher.py:9: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame
See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
if __name__ == '__main__':
# 考虑Name,重点关注每个人的title
# 创建新特征Title
def get_title(name):
# 正则式第一个字符为空格不要忘
title_search = re.search(' ([A-Za-z]+)\.', name)
# 如果有title返回它
if title_search:
return title_search.group(1)
return ""
for dataset in full_data:
dataset['Title'] = dataset['Name'].apply(get_title)
print(pd.crosstab(train['Title'], train['Sex']))
Sex female male
Title
Capt 0 1
Col 0 2
Countess 1 0
Don 0 1
Dr 1 6
Jonkheer 0 1
Lady 1 0
Major 0 2
Master 0 40
Miss 182 0
Mlle 2 0
Mme 1 0
Mr 0 517
Mrs 125 0
Ms 1 0
Rev 0 6
Sir 0 1
# 对特征Title进行分类,并判断它对生存率的影响
for dataset in full_data:
# 出现次数很少的都归为Rare
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')
print(train[['Title', 'Survived']].groupby(['Title'], as_index = False).mean())
Title Survived
0 Master 0.575000
1 Miss 0.702703
2 Mr 0.156673
3 Mrs 0.793651
4 Rare 0.347826
# 再显示数据的基本信息
print(train.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 17 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 891 non-null int64
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 891 non-null object
FamilySize 891 non-null int64
IsAlone 891 non-null int64
CategoricalFare 891 non-null category
CategoricalAge 891 non-null category
Title 891 non-null object
dtypes: category(2), float64(1), int64(8), object(6)
memory usage: 106.4+ KB
None
# 开始数据清洗
# Data Cleaning
# 下面进行数据清洗并将特征值转化为数值
for dataset in full_data:
# Sex
dataset['Sex'] = dataset['Sex'].map({'female': 0, 'male': 1}).astype(int)
# Title
title_mapping = {'Mr': 1, 'Miss': 2, 'Mrs': 3, 'Master': 4, 'Rare': 5}
dataset['Title'] = dataset['Title'].map(title_mapping)
dataset['Title'] = dataset['Title'].fillna(0)
# Embarked
dataset['Embarked'] = dataset['Embarked'].map({'S': 0, 'C': 1, 'Q': 2}).astype(int)
# Fare
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)
# Age
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'] = 4
# 选取特征,将下列特征去除
drop_elements = ['PassengerId', 'Name', 'Ticket', 'Cabin', 'SibSp', 'Parch', 'FamilySize']
train = train.drop(drop_elements, axis = 1)
train = train.drop(['CategoricalAge', 'CategoricalFare'], axis = 1)
# 注意先把test的PassengerId保存下来,因为后面会删除,且最后输出到csv需要使用
test_passengerId = test['PassengerId']
# test也要去除特征
test = test.drop(drop_elements, axis = 1)
print(train.head(10))
train = train.values
test = test.values
Survived Pclass Sex Age Fare Embarked IsAlone Title
0 0 3 1 1 0 0 0 1
1 1 1 0 2 3 1 0 3
2 1 3 0 1 1 0 1 2
3 1 1 0 2 3 0 0 3
4 0 3 1 2 1 0 1 1
5 0 3 1 0 1 2 1 1
6 0 1 1 3 3 0 1 1
7 0 3 1 0 2 0 0 4
8 1 3 0 1 1 0 0 3
9 1 2 0 0 2 1 0 3
# 开始使用不同分类器进行预测
import matplotlib.pyplot as plt
import seaborn as sns
# 导入分类器的包
from sklearn.model_selection import StratifiedShuffleSplit
from sklearn.metrics import accuracy_score, log_loss
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis, QuadraticDiscriminantAnalysis
from sklearn.linear_model import LogisticRegression
classifiers = [
KNeighborsClassifier(3), # K = 3
SVC(probability=True),
DecisionTreeClassifier(),
RandomForestClassifier(),
AdaBoostClassifier(),
GradientBoostingClassifier(),
GaussianNB(),
LinearDiscriminantAnalysis(),
QuadraticDiscriminantAnalysis(),
LogisticRegression()]
# 将训练集分组,分为新的训练集和测试集,train/test组数为10,其中测试集比例为0.1(交叉验证)
sss = StratifiedShuffleSplit(n_splits = 10, test_size = 0.1, random_state = 0)
X = train[0::, 1::]
y = train[0::, 0] # Survived在第0列
acc_dict = {}
# 每一次迭代都将训练集划分为新的训练集和测试集,比例9:1
# train_index = [..., ..., ...], test_index = [..., ..., ...]
for train_index, test_index in sss.split(X, y):
# 新的训练集和测试集保存到新的变量中
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
for clf in classifiers:
name = clf.__class__.__name__
clf.fit(X_train, y_train)
train_predictions = clf.predict(X_test)
acc = accuracy_score(y_test, train_predictions)
if name in acc_dict:
acc_dict[name] += acc # 将正确率累加起来
else:
acc_dict[name] = acc
log_cols = ['Classifier', 'Accuracy']
log = pd.DataFrame(columns = log_cols)
for clf in acc_dict:
acc_dict[clf] = acc_dict[clf] / 10.0 # 除以组数
log_entry = pd.DataFrame([[clf, acc_dict[clf]]], columns = log_cols)
log = log.append(log_entry)
plt.xlabel('Accuracy')
plt.title('Classifier Accuracy')
sns.set_color_codes('muted')
sns.barplot(x = 'Accuracy', y = 'Classifier', data = log, color = 'b')
<matplotlib.axes._subplots.AxesSubplot at 0x1a239e2748>
# 从上图可以看出SVC效果最好,所以现在用SVC进行预测
candidate_classifier = SVC()
candidate_classifier.fit(train[0::, 1::], train[0::, 0])
result = candidate_classifier.predict(test)
print(result)
# 下面将结果输出到csv,第一列用之前保存的test_passengerId
submission = pd.DataFrame({
'PassengerId': test_passengerId,
'Survived': result
})
submission.to_csv('sina_version.csv', index = False)
[0 1 0 0 1 0 1 0 1 0 0 0 1 0 1 1 0 0 0 1 0 1 1 0 1 0 1 0 0 0 0 0 0 0 0 0 1
1 0 0 0 0 0 1 1 0 0 0 1 0 0 0 1 1 0 0 0 0 0 1 0 0 0 1 1 1 1 0 0 1 1 0 1 0
1 0 0 1 0 1 0 0 0 0 0 0 1 1 1 1 1 0 1 0 0 0 1 0 1 0 1 0 0 0 1 0 0 0 0 0 0
1 1 1 1 0 0 0 0 1 1 0 1 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 1 0 0 1 0 0 0 0 0 0
0 0 1 0 0 0 0 0 1 1 0 1 1 0 1 0 0 0 0 0 1 1 0 0 0 0 0 1 1 0 1 1 0 0 1 0 1
0 1 0 0 0 0 0 1 0 1 0 1 1 0 1 1 1 1 1 0 0 1 0 1 0 0 0 0 1 0 0 1 0 1 0 1 0
1 0 1 1 0 1 0 0 0 1 0 0 0 0 0 0 1 1 1 1 0 0 0 0 1 0 1 1 1 0 0 0 0 0 0 0 1
0 0 0 1 1 0 0 0 0 1 0 0 0 1 1 0 1 0 0 0 0 1 1 1 1 0 0 0 0 0 0 0 1 0 1 0 0
1 0 0 0 0 0 0 0 1 1 0 1 0 0 0 0 0 1 1 1 0 0 0 0 0 0 0 0 1 0 1 0 0 0 1 0 0
1 0 0 0 0 0 1 0 0 0 1 0 1 0 1 0 1 1 0 0 0 0 0 1 0 0 0 0 1 1 0 1 0 0 0 1 0
0 1 0 0 1 1 0 0 0 0 0 0 0 0 0 1 0 0 0 1 0 1 1 0 0 1 0 1 0 0 1 0 1 0 0 0 0
0 1 1 1 1 1 0 1 0 0 0]