Skip to content

Latest commit

 

History

History
256 lines (199 loc) · 7.59 KB

README.md

File metadata and controls

256 lines (199 loc) · 7.59 KB
Raw

泰坦尼克号逃生预测

sklearn 自带的决策树模型

分类器

clf = DecisionTreeClassifier(criterion='entropy')

参数列表

参数列表

分类器方法

  • 使用 fit 方法 数据拟合
  • 使用 predict 方法 数据预测
  • 使用 score 方法 得到准确率

表格：

分类器方法

# coding=utf-8
import pandas as pd

# 数据加载
train_data = pd.read_csv('./Titanic_Data/train.csv')
test_data = pd.read_csv('./Titanic_Data/test.csv')
# 数据探索
print(train_data.info())
print('-' * 30)
print(train_data.describe())
print('-' * 30)
print(train_data.describe(include=['O']))
print('-' * 30)
print(train_data.head())
print('-' * 30)
print(train_data.tail())
# coding=utf-8
import pandas as pd

# 数据加载
train_data = pd.read_csv('./Titanic_Data/train.csv')
test_data = pd.read_csv('./Titanic_Data/test.csv')
# 数据探索
print(train_data.info())
# 使用平均年龄来填充年龄中的 nan 值
train_data['Age'].fillna(train_data['Age'].mean(), inplace=True)
test_data['Age'].fillna(test_data['Age'].mean(),inplace=True)
# 使用票价的均值填充票价中的 nan 值
train_data['Fare'].fillna(train_data['Fare'].mean(), inplace=True)
test_data['Fare'].fillna(test_data['Fare'].mean(),inplace=True)

print(train_data['Embarked'].value_counts())


# 使用登录最多的港口来填充登录港口的 nan 值
train_data['Embarked'].fillna('S', inplace=True)
test_data['Embarked'].fillna('S',inplace=True)
# coding=utf-8
import pandas as pd
from sklearn.feature_extraction import DictVectorizer

# 数据加载
train_data = pd.read_csv('./Titanic_Data/train.csv')
test_data = pd.read_csv('./Titanic_Data/test.csv')
# 数据探索
print(train_data.info())
# 使用平均年龄来填充年龄中的 nan 值
train_data['Age'].fillna(train_data['Age'].mean(), inplace=True)
test_data['Age'].fillna(test_data['Age'].mean(), inplace=True)
# 使用票价的均值填充票价中的 nan 值
train_data['Fare'].fillna(train_data['Fare'].mean(), inplace=True)
test_data['Fare'].fillna(test_data['Fare'].mean(), inplace=True)

print(train_data['Embarked'].value_counts())


# 使用登录最多的港口来填充登录港口的 nan 值
train_data['Embarked'].fillna('S', inplace=True)
test_data['Embarked'].fillna('S', inplace=True)

# 特征选择
features = ['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked']
train_features = train_data[features]
train_labels = train_data['Survived']
test_features = test_data[features]

dvec = DictVectorizer(sparse=False)
train_features = dvec.fit_transform(train_features.to_dict(orient='record'))
print(dvec.feature_names_)
# coding=utf-8
import pandas as pd
from sklearn.feature_extraction import DictVectorizer
from sklearn.tree import DecisionTreeClassifier

# 数据加载
train_data = pd.read_csv('./Titanic_Data/train.csv')
test_data = pd.read_csv('./Titanic_Data/test.csv')
# 数据探索
print(train_data.info())
# 使用平均年龄来填充年龄中的 nan 值
train_data['Age'].fillna(train_data['Age'].mean(), inplace=True)
test_data['Age'].fillna(test_data['Age'].mean(), inplace=True)
# 使用票价的均值填充票价中的 nan 值
train_data['Fare'].fillna(train_data['Fare'].mean(), inplace=True)
test_data['Fare'].fillna(test_data['Fare'].mean(), inplace=True)

print(train_data['Embarked'].value_counts())


# 使用登录最多的港口来填充登录港口的 nan 值
train_data['Embarked'].fillna('S', inplace=True)
test_data['Embarked'].fillna('S', inplace=True)

# 特征选择
features = ['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked']
train_features = train_data[features]
train_labels = train_data['Survived']
test_features = test_data[features]

dvec = DictVectorizer(sparse=False)
train_features = dvec.fit_transform(train_features.to_dict(orient='record'))
print(dvec.feature_names_)



# 构造 ID3 决策树
clf = DecisionTreeClassifier(criterion='entropy')
# 决策树训练
clf.fit(train_features, train_labels)
# coding=utf-8
import pandas as pd
from sklearn.feature_extraction import DictVectorizer
from sklearn.tree import DecisionTreeClassifier

# 数据加载
train_data = pd.read_csv('./Titanic_Data/train.csv')
test_data = pd.read_csv('./Titanic_Data/test.csv')
# 数据探索
print(train_data.info())
# 使用平均年龄来填充年龄中的 nan 值
train_data['Age'].fillna(train_data['Age'].mean(), inplace=True)
test_data['Age'].fillna(test_data['Age'].mean(), inplace=True)
# 使用票价的均值填充票价中的 nan 值
train_data['Fare'].fillna(train_data['Fare'].mean(), inplace=True)
test_data['Fare'].fillna(test_data['Fare'].mean(), inplace=True)

print(train_data['Embarked'].value_counts())


# 使用登录最多的港口来填充登录港口的 nan 值
train_data['Embarked'].fillna('S', inplace=True)
test_data['Embarked'].fillna('S', inplace=True)

# 特征选择
features = ['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked']
train_features = train_data[features]
train_labels = train_data['Survived']
test_features = test_data[features]

dvec = DictVectorizer(sparse=False)
train_features = dvec.fit_transform(train_features.to_dict(orient='record'))
print(dvec.feature_names_)


# 构造 ID3 决策树
clf = DecisionTreeClassifier(criterion='entropy')
# 决策树训练
clf.fit(train_features, train_labels)
test_features = dvec.transform(test_features.to_dict(orient='record'))
# 决策树预测
pred_labels = clf.predict(test_features)

# 得到决策树准确率
acc_decision_tree = round(clf.score(train_features, train_labels), 6)
print(u'score 准确率为 %.4lf' % acc_decision_tree)
# coding=utf-8
import pandas as pd
from sklearn.feature_extraction import DictVectorizer
from sklearn.tree import DecisionTreeClassifier
import numpy as np
from sklearn.model_selection import cross_val_score

# 数据加载
train_data = pd.read_csv('./Titanic_Data/train.csv')
test_data = pd.read_csv('./Titanic_Data/test.csv')
# 数据探索
print(train_data.info())
# 使用平均年龄来填充年龄中的 nan 值
train_data['Age'].fillna(train_data['Age'].mean(), inplace=True)
test_data['Age'].fillna(test_data['Age'].mean(), inplace=True)
# 使用票价的均值填充票价中的 nan 值
train_data['Fare'].fillna(train_data['Fare'].mean(), inplace=True)
test_data['Fare'].fillna(test_data['Fare'].mean(), inplace=True)

print(train_data['Embarked'].value_counts())


# 使用登录最多的港口来填充登录港口的 nan 值
train_data['Embarked'].fillna('S', inplace=True)
test_data['Embarked'].fillna('S', inplace=True)

# 特征选择
features = ['Pclass', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked']
train_features = train_data[features]
train_labels = train_data['Survived']
test_features = test_data[features]

dvec = DictVectorizer(sparse=False)
train_features = dvec.fit_transform(train_features.to_dict(orient='record'))
print(dvec.feature_names_)


# 构造 ID3 决策树
clf = DecisionTreeClassifier(criterion='entropy')
# 决策树训练
clf.fit(train_features, train_labels)
test_features = dvec.transform(test_features.to_dict(orient='record'))
# 决策树预测
pred_labels = clf.predict(test_features)

# 得到决策树准确率
acc_decision_tree = round(clf.score(train_features, train_labels), 6)
print(u'score 准确率为 %.4lf' % acc_decision_tree)

# 使用 K 折交叉验证 统计决策树准确率
print(u'cross_val_score 准确率为 %.4lf' % np.mean(cross_val_score(clf, train_features, train_labels, cv=10)))