动手数据分析-模型建立与评估

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from IPython.display import Image   #展示图片

from IPython.core.interactiveshell import InteractiveShell
InteractiveShell.ast_node_interactivity=‘all‘


%matplotlib inline

plt.rcParams[‘font.sans-serif‘] = [‘SimHei‘]  # 用来正常显示中文标签
plt.rcParams[‘axes.unicode_minus‘] = False  # 用来正常显示负号
plt.rcParams[‘figure.figsize‘] = (10, 6)  # 设置输出图片大小

1 # 对分类变量进行填充
2 train[‘Cabin‘] = train[‘Cabin‘].fillna(‘NA‘)
3 train[‘Embarked‘] = train[‘Embarked‘].fillna(‘S‘)

1 # 对连续变量进行填充
2 train[‘Age‘] = train[‘Age‘].fillna(train[‘Age‘].mean())

# 检查缺失值比例
train.isnull().sum().sort_values(ascending=False)

1 # 取出所有的输入特征
2 data = train[[‘Pclass‘,‘Sex‘,‘Age‘,‘SibSp‘,‘Parch‘,‘Fare‘, ‘Embarked‘]]
3 data = pd.get_dummies(data)

#写入代码
from sklearn.model_selection import train_test_split
# 在机器学习中，该函数可按照用户设定的比例，随机将样本集合划分为训练集 和测试集，并返回划分好的训练集和测试集数据。


# 一般先取出X和y后再切割，有些情况会使用到未切割的，这时候X和y就可以用,x是清洗好的数据，y是我们要预测的存活数据‘Survived‘
X = data
y = train[‘Survived‘]


# 对数据集进行切割
X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=0)

# 查看数据形状
X_train.shape, X_test.shape

1 #写入代码
2 
3 from sklearn.linear_model import LogisticRegression
4 from sklearn.ensemble import RandomForestClassifier

1 #写入代码
2 # 默认参数逻辑回归模型
3 lr = LogisticRegression()
4 lr.fit(X_train, y_train)

#写入代码
# 查看训练集和测试集score值
print("Training set score: {:.2f}".format(lr.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(lr.score(X_test, y_test)))

# 调整参数后的逻辑回归模型
lr2 = LogisticRegression(C=100)
lr2.fit(X_train, y_train)

print("Training set score: {:.2f}".format(lr2.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(lr2.score(X_test, y_test)))

# 默认参数的随机森林分类模型
rfc = RandomForestClassifier()
rfc.fit(X_train, y_train)

print("Training set score: {:.2f}".format(rfc.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(rfc.score(X_test, y_test)))



# 调整参数后的随机森林分类模型
rfc2 = RandomForestClassifier(n_estimators=100, max_depth=5)
rfc2.fit(X_train, y_train)

print("Training set score: {:.2f}".format(rfc2.score(X_train, y_train)))
print("Testing set score: {:.2f}".format(rfc2.score(X_test, y_test)))

from sklearn.model_selection import cross_val_score

lr = LogisticRegression(C=100)
scores = cross_val_score(lr, X_train, y_train, cv=10)


scores

# 平均交叉验证分数
print("Average cross-validation score: {:.2f}".format(scores.mean()))

from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report

# 训练模型
lr = LogisticRegression(C=100)
lr.fit(X_train, y_train)

# 模型预测结果
pred = lr.predict(X_train)


# 混淆矩阵
confusion_matrix(y_train, pred)

# 精确率、召回率以及f1-score
print(classification_report(y_train, pred))

from sklearn.metrics import roc_curve

fpr, tpr, thresholds = roc_curve(y_test, lr.decision_function(X_test))
plt.plot(fpr, tpr, label="ROC Curve")
plt.xlabel("FPR")
plt.ylabel("TPR (recall)")
# 找到最接近于0的阈值
close_zero = np.argmin(np.abs(thresholds))
plt.plot(fpr[close_zero], tpr[close_zero], ‘o‘, markersize=10, label="threshold zero", fillstyle="none", c=‘k‘, mew=2)
plt.legend(loc=4)