1.数据集简介
此数据集一共有891条数据，数据内容如下，每列表示的意义如下：
| 乘客ID | 是否幸存 | 舱位等级 | 姓名 | 性别 | 年龄 | 一同上船的兄弟姐妹 | 父母和小孩数目 | 船号 | 船价 | 船仓号 | 登录地点 |
| PassengerId | Survived | Pclass | Name | Sex | Age | SibSp | Parch | Ticket | Fare | Cabin | Embarked |
| 1 | 0 | 3 | Braund, Mr. Owen Harris | male | 22 | 1 | 0 | A/5 21171 | 7.25 | S | |
| 2 | 1 | 1 | Cumings, Mrs. John Bradley (Florence Briggs Thayer) | female | 38 | 1 | 0 | PC 17599 | 71.2833 | C85 | C |
| 3 | 1 | 3 | Heikkinen, Miss. Laina | female | 26 | 0 | 0 | STON/O2. 3101282 | 7.925 | S | |
| 4 | 1 | 1 | Futrelle, Mrs. Jacques Heath (Lily May Peel) | female | 35 | 1 | 0 | 113803 | 53.1 | C123 | S |
| 5 | 0 | 3 | Allen, Mr. William Henry | male | 35 | 0 | 0 | 373450 | 8.05 | S |
2.缺失值处理：
查看数据后，发现在Age列，有部分值缺失，将缺失值用中位数进行填充
titanic = pandas.read_csv("titanic_train.csv")
print(titanic.head(5)) # 显示前5条信息
# pandas.set_option('display.max_columns', None) # 显示所有列
# pandas.set_option('display.max_rows', None) # 显示所有行
# 对Age列进行缺失值titanic["Age"].fillna 填充此列中位数titanic["Age"].median()
titanic["Age"] = titanic["Age"].fillna(titanic["Age"].median())
print(titanic.describe()) # 显示统计信息
填充完之后，初步显示模型的统计信息，主要包括数量、均值、标准差、最小值、4分位数、最大值。
PassengerId Survived Pclass Age SibSp \
count 891.000000 891.000000 891.000000 891.000000 891.000000
mean 446.000000 0.383838 2.308642 29.361582 0.523008
std 257.353842 0.486592 0.836071 13.019697 1.102743
min 1.000000 0.000000 1.000000 0.420000 0.000000
25% 223.500000 0.000000 2.000000 22.000000 0.000000
50% 446.000000 0.000000 3.000000 28.000000 0.000000
75% 668.500000 1.000000 3.000000 35.000000 1.000000
max 891.000000 1.000000 3.000000 80.000000 8.000000
Parch Fare
count 891.000000 891.000000
mean 0.381594 32.204208
std 0.806057 49.693429
min 0.000000 0.000000
25% 0.000000 7.910400
50% 0.000000 14.454200
75% 0.000000 31.000000
max 6.000000 512.329200
3.字符串数据转化为数值型变量，将男性用0表示，女性用1表示；登录地点S、C、Q分别用0,1,2表示。
print(titanic["Sex"].unique()) # Sex列的属性值有哪些值
titanic.loc[titanic["Sex"] == "male", "Sex"] = 0 # 将字符串映射为数字
titanic.loc[titanic["Sex"] == "female", "Sex"] = 1
# print(titanic["Embarked"].unique())
titanic["Embarked"] = titanic["Embarked"].fillna('S') # fillna()缺失值填充，用S
titanic.loc[titanic["Embarked"] == "S", "Embarked"] = 0 # 数值映射
titanic.loc[titanic["Embarked"] == "C", "Embarked"] = 1
titanic.loc[titanic["Embarked"] == "Q", "Embarked"] = 2
4. 构建模型进行分类
1.线性回归模型
划分数据，构建线性回归模型：
predictors = ["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked"] # 选用的特征
alg = LinearRegression() # 线性回归模型
kf = KFold(n_splits=3, shuffle=False, random_state=1) # K折交叉验证，把数据分成K份
predictions = []
for train, test in kf.split(titanic):
# print("%s %s" % (train.shape, test.shape))
# print("%s %s" % (train, test)) # 训练集、测试集的索引号
train_predictors = (titanic[predictors].iloc[train, :]) # 提取训练集中的特征数据
train_target = titanic["Survived"].iloc[train] # 对应的标签
alg.fit(train_predictors, train_target) # 训练
test_predictions = alg.predict(titanic[predictors].iloc[test, :]) # 预测
predictions.append(test_predictions) # 保存预测结果
计算准确率：
predictions = np.concatenate(predictions, axis=0) # 将3次结果拼接起来
predictions[predictions > .5] = 1 # 转为成2分类问题，概率大于0.5就认为是1
predictions[predictions <=.5] = 0
accuracy = sum(predictions == titanic["Survived"]) / len(predictions)
print(accuracy)
预测准确率为：0.7833894500561167
2. 逻辑回归算法
alg = LogisticRegression(solver="liblinear") # 创建预测模型
scores = cross_val_score(alg, titanic[predictors], titanic["Survived"], cv=3) # 3折交叉验证训练
print("逻辑回归准确率：", scores.mean())
逻辑回归准确率： 0.7878787878787877
3.随机森林预测
alg = RandomForestClassifier(random_state=1, n_estimators=100, min_samples_split=4, min_samples_leaf=2) # 100棵树
scores = cross_val_score(alg, titanic[predictors], titanic["Survived"], cv=3)
print("随机森林准确率：", scores.mean())
随机森林准确率： 0.8226711560044894
4.从原始数据中构建新特征
titanic["FamilySize"] = titanic["SibSp"] + titanic["Parch"] # 计算家庭成员数量 兄弟姐妹数量+携带孩子
titanic["NameLength"] = titanic["Name"].apply(lambda x: len(x)) # 计算名字长度
提取名字里面包含称呼，如小姐，女士，先生等等，构造新特征
# 得到名字中的称呼，返回匹配的值
def get_title(name):
title_search = re.search(' ([A-Za-z]+)\.', name) # 使用正则表达式搜索，大小写字母 + .
if title_search:
return title_search.group(1)
return ""
titles = titanic["Name"].apply(get_title)
print(pandas.value_counts(titles)) # 计算每个名称的数量
数据集每个名称的数量：
Mr 517
Miss 182
Mrs 125
Master 40
Dr 7
Rev 6
Major 2
Mlle 2
Col 2
Sir 1
Countess 1
Don 1
Jonkheer 1
Mme 1
Ms 1
Capt 1
Lady 1
Name: Name, dtype: int64
# 将每个标题映射到一个整数。有些标题非常罕见，并且被压缩到与其他标题相同的代码中
title_mapping = {"Mr": 1, "Miss": 2, "Mrs": 3, "Master": 4, "Dr": 5, "Rev": 6, "Major": 7, "Col": 7, "Mlle": 8,
"Mme": 8, "Don": 9, "Lady": 10, "Countess": 10, "Jonkheer": 10, "Sir": 9, "Capt": 7, "Ms": 2}
# 转为为对应的数字
for k, v in title_mapping.items():
titles[titles == k] = v
# print(pandas.value_counts(titles))
# 添加一个特征列
titanic["Title"] = titles
5.可视化特征比重：
# 构建新特征
predictors = ["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked", "FamilySize", "Title", "NameLength"]
selector = SelectKBest(f_classif, k=10) # 分类任务，选择前k个特征
selector.fit(titanic[predictors], titanic["Survived"])
scores = -np.log10(selector.pvalues_) # 转化特征得分的p_value值
plt.bar(range(len(predictors)), scores) # 条形图，x值，高度值
plt.xticks(range(len(predictors)), predictors, rotation='vertical') # x轴，x值，名称
plt.show()
6.使用集成算法预测
algorithms = [
[GradientBoostingClassifier(random_state=1, n_estimators=25, max_depth=3),
["Pclass", "Sex", "Age", "Fare", "Embarked", "FamilySize", "Title"]],
[LogisticRegression(solver="liblinear"), ["Pclass", "Sex", "Fare", "FamilySize", "Title", "Age", "Embarked"]]
] # 两种预测算法以及对应选择的特征
kf = KFold(3)
predictions = []
for train, test in kf.split(titanic):
train_target = titanic["Survived"].iloc[train]
full_test_predictions = []
# 对每个折叠中的每个算法进行预测
for alg, predictors in algorithms:
alg.fit(titanic[predictors].iloc[train, :], train_target)
test_predictions = alg.predict_proba(titanic[predictors].iloc[test, :].astype(float))[:, 1] # 获取预测为1的概率
full_test_predictions.append(test_predictions)
test_predictions = (full_test_predictions[0] * 1 + full_test_predictions[1] * 1) / 2 # 两种预测概率取平均
test_predictions[test_predictions <= .5] = 0
test_predictions[test_predictions > .5] = 1
predictions.append(test_predictions)
predictions = np.concatenate(predictions, axis=0)
accuracy = sum(predictions == titanic["Survived"]) / len(predictions)
print("两种方法平均准确率：", accuracy)
两种方法平均准确率： 0.8215488215488216
来源：CSDN
作者：王氏小明
链接：https://blog.csdn.net/weixin_43472830/article/details/103233740