决策树_预测泰坦尼可号幸存者

%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

def read_dataset(fname):# 指定第一列作为行索引data = pd.read_csv(fname, index_col=0) # 丢弃无用的数据data.drop(['Name', 'Ticket', 'Cabin'], axis=1, inplace=True)# 处理性别数据data['Sex'] = (data['Sex'] == 'male').astype('int')# 处理登船港口数据labels = data['Embarked'].unique().tolist()data['Embarked'] = data['Embarked'].apply(lambda n: labels.index(n))# 处理缺失数据data = data.fillna(0)return datatrain = read_dataset('datasets/titanic/train.csv')

train.head()

	Survived	Pclass	Sex	Age	SibSp	Parch	Fare	Embarked
PassengerId
1	0	3	1	22.0	1	0	7.2500	0
2	1	1	0	38.0	1	0	71.2833	1
3	1	3	0	26.0	0	0	7.9250	0
4	1	1	0	35.0	1	0	53.1000	0
5	0	3	1	35.0	0	0	8.0500	0

from sklearn.model_selection import train_test_splity = train['Survived'].values
X = train.drop(['Survived'], axis=1).valuesX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)print('train dataset: {0}; test dataset: {1}'.format(X_train.shape, X_test.shape))

train dataset: (712, 7); test dataset: (179, 7)

from sklearn.tree import DecisionTreeClassifierclf = DecisionTreeClassifier()
clf.fit(X_train, y_train)
train_score = clf.score(X_train, y_train)
test_score = clf.score(X_test, y_test)
print('train score: {0}; test score: {1}'.format(train_score, test_score))

train score: 0.9901685393258427; test score: 0.7821229050279329

from sklearn.tree import export_graphvizwith open("titanic.dot", 'w') as f:f = export_graphviz(clf, out_file=f)

# 参数选择 max_depth
def cv_score(d):clf = DecisionTreeClassifier(max_depth=d)clf.fit(X_train, y_train)tr_score = clf.score(X_train, y_train)cv_score = clf.score(X_test, y_test)return (tr_score, cv_score)depths = range(2, 15)
scores = [cv_score(d) for d in depths]
tr_scores = [s[0] for s in scores]
cv_scores = [s[1] for s in scores]best_score_index = np.argmax(cv_scores)
best_score = cv_scores[best_score_index]
best_param = depths[best_score_index]
print('best param: {0}; best score: {1}'.format(best_param, best_score))plt.figure(figsize=(10, 6), dpi=144)
plt.grid()
plt.xlabel('max depth of decision tree')
plt.ylabel('score')
plt.plot(depths, cv_scores, '.g-', label='cross-validation score')
plt.plot(depths, tr_scores, '.r--', label='training score')
plt.legend()

best param: 4; best score: 0.8268156424581006<matplotlib.legend.Legend at 0x19bd6cbb4e0>

# 训练模型，并计算评分
def cv_score(val):clf = DecisionTreeClassifier(criterion='gini',min_impurity_split=val)clf.fit(X_train, y_train)tr_score = clf.score(X_train, y_train)cv_score = clf.score(X_test, y_test)return (tr_score, cv_score)# 指定参数范围，分别训练模型，并计算评分
values = np.linspace(0, 0.5, 50)
scores = [cv_score(v) for v in values]
tr_scores = [s[0] for s in scores]
cv_scores = [s[1] for s in scores]# 找出评分最高的模型参数
best_score_index = np.argmax(cv_scores)
best_score = cv_scores[best_score_index]
best_param = values[best_score_index]
print('best param: {0}; best score: {1}'.format(best_param, best_score))# 画出模型参数与模型评分的关系
plt.figure(figsize=(10, 6), dpi=144)
plt.grid()
plt.xlabel('threshold of entropy')
plt.ylabel('score')
plt.plot(values, cv_scores, '.g-', label='cross-validation score')
plt.plot(values, tr_scores, '.r--', label='training score')
plt.legend()

best param: 0.17346938775510204; best score: 0.8212290502793296<matplotlib.legend.Legend at 0x19be2859e80>

def plot_curve(train_sizes, cv_results, xlabel):train_scores_mean = cv_results['mean_train_score']train_scores_std = cv_results['std_train_score']test_scores_mean = cv_results['mean_test_score']test_scores_std = cv_results['std_test_score']plt.figure(figsize=(10, 6), dpi=144)plt.title('parameters turning')plt.grid()plt.xlabel(xlabel)plt.ylabel('score')plt.fill_between(train_sizes, train_scores_mean - train_scores_std,train_scores_mean + train_scores_std, alpha=0.1, color="r")plt.fill_between(train_sizes, test_scores_mean - test_scores_std,test_scores_mean + test_scores_std, alpha=0.1, color="g")plt.plot(train_sizes, train_scores_mean, '.--', color="r",label="Training score")plt.plot(train_sizes, test_scores_mean, '.-', color="g",label="Cross-validation score")plt.legend(loc="best")

from sklearn.model_selection import GridSearchCVthresholds = np.linspace(0, 0.5, 50)
# Set the parameters by cross-validation
param_grid = {'min_impurity_split': thresholds}clf = GridSearchCV(DecisionTreeClassifier(), param_grid, cv=5, return_train_score=True)
clf.fit(X, y)
print("best param: {0}\nbest score: {1}".format(clf.best_params_, clf.best_score_))plot_curve(thresholds, clf.cv_results_, xlabel='gini thresholds')

best param: {'min_impurity_split': 0.22448979591836732}
best score: 0.8181818181818182

from sklearn.model_selection import GridSearchCVentropy_thresholds = np.linspace(0, 1, 50)
gini_thresholds = np.linspace(0, 0.5, 50)# Set the parameters by cross-validation
param_grid = [{'criterion': ['entropy'], 'min_impurity_split': entropy_thresholds},{'criterion': ['gini'], 'min_impurity_split': gini_thresholds},{'max_depth': range(2, 10)},{'min_samples_split': range(2, 30, 2)}]clf = GridSearchCV(DecisionTreeClassifier(), param_grid, cv=5, return_train_score=True)
clf.fit(X, y)
print("best param: {0}\nbest score: {1}".format(clf.best_params_, clf.best_score_))

best param: {'criterion': 'entropy', 'min_impurity_split': 0.5306122448979591}
best score: 0.8271604938271605

print(clf.best_params_)

{'criterion': 'entropy', 'min_impurity_split': 0.5306122448979591}

clf = DecisionTreeClassifier(criterion='entropy', min_impurity_split=0.002857142857142857)
model=clf.fit(X_train, y_train)
train_score = clf.score(X_train, y_train)
test_score = clf.score(X_test, y_test)
print('train score: {0}; test score: {1}'.format(train_score, test_score))# 导出 titanic.dot 文件
with open("titanic.dot", 'w') as f:f = export_graphviz(clf, out_file=f)# 1. 在电脑上安装 graphviz
# 2. 运行 `dot -Tpng titanic.dot -o titanic.png`
# 3. 在当前目录查看生成的决策树 titanic.png

train score: 0.9901685393258427; test score: 0.776536312849162

def read_dataset(fname):# 指定第一列作为行索引data = pd.read_csv(fname, index_col=0) # 丢弃无用的数据data.drop(['Name', 'Ticket', 'Cabin'], axis=1, inplace=True)# 处理性别数据data['Sex'] = (data['Sex'] == 'male').astype('int')# 处理登船港口数据labels = data['Embarked'].unique().tolist()data['Embarked'] = data['Embarked'].apply(lambda n: labels.index(n))# 处理缺失数据data = data.fillna(0)return datatrain = read_dataset('datasets/titanic/test.csv')

x_test = train.values

clf = DecisionTreeClassifier(criterion='entropy', min_impurity_split=0.002857142857142857)
# clf.fit(x_test)
ans=model.predict(x_test)

tab_2=pd.DataFrame({'Survived':ans},index=train.index)

tab_2.to_csv('1.csv')

决策树_预测泰坦尼可号幸存者相关推荐

Spark：基于PySpark的逻辑回归和决策树模型对泰旦尼克号幸存者预测的机器学习流程
pyspark的ML回顾下文章目录官网文档环境泰坦尼克号数据分析泰坦尼克号数据清洗整理 Spark ML Pipeline Titanic幸存者预测:逻辑回归LR模型模型训练模型预测 T ...
机器学习代码实战——决策树（预测泰坦尼号船员生存情况）
文章目录 1.实验目的 2.数据预处理 3.导入必要模块 4.训练+计算模型得分 1.实验目的 1.建立决策树模型以根据某些参数预测泰坦尼克号人是否得以生存 2.在泰坦尼克数据中,使用以下各列构建一个 ...
袋装决策树_袋装树是每个数据科学家需要的机器学习算法
袋装决策树袋装树木介绍 (Introduction to Bagged Trees) Without diving into the specifics just yet, it's importa ...
数据分享|PYTHON用决策树分类预测糖尿病和可视化实例
全文下载链接:http://tecdat.cn/?p=23848 在本文中,决策树是对例子进行分类的一种简单表示.它是一种有监督的机器学习技术,数据根据某个参数被连续分割.决策树分析可以帮助解决分类和 ...
python实现决策树建模预测并验证评估
实现功能: python实现数据读取.数据清洗.数据编码.数据降维分析.数据集划分.(具体参见前几篇文章),决策树建模预测并验证评估. 实现代码: # 导入需要的库 import pandas as ...
有关糖尿病模型建立的论文_预测糖尿病结果的模型比较
有关糖尿病模型建立的论文项目主题 (Subject of the Project) The dataset is primarily used for predicting the onset of ...
arima 预测模型_预测未来：学习使用Arima模型进行预测
arima 预测模型 XTS对象 (XTS Objects) If you're not using XTS objects to perform your forecasting in R, the ...
机器学习决策树_机器学习-决策树 Decision Tree
咱们正式进入了机器学习的模型的部分,虽然现在最火的的机器学习方面的库是Tensorflow, 但是这里还是先简单介绍一下另一个数据处理方面很火的库叫做sklearn.其实咱们在前面已经介绍了一点点sk ...
决策树留一法python代码_从实例中归纳决策树_人工智能一
从实例中归纳决策树_人工智能一 18.3.3 从实例中归纳决策树布尔决策树的一个实例是由一个输入属性向量X以及一个唯一的布尔输出值y组成的.一个实例集合(X1,y1),-,(X12,y12)如图18 ...
python中如何画出决策树_使用Python绘制决策树
决策树为字典格式,示例如下: {'tearRate': {'reduced': 'no lenses', 'normal': {' astigmatic': {'yes': {' prescript' ...

决策树_预测泰坦尼可号幸存者

决策树_预测泰坦尼可号幸存者相关推荐

最新文章

热门文章