数据挖掘实践（28）：算法基础（六）Random Forest(随机森林)算法（集成学习）（二）基于随机森林的医疗费用分析与建模预估

1 基于随机森林的医疗费用分析与建模预估

import warnings
warnings.filterwarnings('ignore') # 忽视警告

import pandas as pd
from matplotlib import pyplot as plt
import seaborn as sns
from sklearn.ensemble import RandomForestRegressor
from sklearn.preprocessing import LabelEncoder, StandardScaler
from sklearn.model_selection import train_test_split
import numpy as np
import sklearn.metrics

#1.加载数据，并进行分析¶
df = pd.read_csv('./data/insurance.csv')
#剔除缺失值
df = df.dropna()
df.head()

df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 1338 entries, 0 to 1337
Data columns (total 7 columns):
age         1338 non-null int64
sex         1338 non-null object
bmi         1338 non-null float64
children    1338 non-null int64
smoker      1338 non-null object
region      1338 non-null object
charges     1338 non-null float64
dtypes: float64(2), int64(2), object(3)
memory usage: 83.6+ KB

#查看数据分布状况
df.describe() # 从年龄能看出，平均在39岁

 age:年龄 sex：性别 bmi：身体质量指数 children：zi smoker region charges

#查看不同维度之间的相关性，倒置的手法
df.corr()

# 注：bmi（Body Mass Index）为身体质量指数，这里省略小数点来区间化特征，方便做数据分析
df['bmi_int'] = df['bmi'].apply(lambda x: int(x))


variables=['sex','smoker','region','age','bmi_int','children']

print('数据分布分析：')
"""
参数    说明
by    指定列名(axis=0或’index’)或索引值(axis=1或’columns’)
axis    若axis=0或’index’，则按照指定列中数据大小排序；若axis=1或’columns’，则按照指定索引中数据大小排序，默认axis=0
ascending    是否按指定列的数组升序排列，默认为True，即升序排列
inplace    是否用排序后的数据集替换原来的数据，默认为False，即不替换
na_position    {‘first’,‘last’}，设定缺失值的显示位置
"""
for v in variables:
    df = df.sort_values(by=[v])
    df[v].value_counts().plot(kind = 'bar')
    plt.title(v)
    plt.show()

数据分布分析：

 

 

 

 

 

• 0：代表没孩子 1：代表1个孩子......

#对类别型变量进行编码
le_sex = LabelEncoder()
le_smoker = LabelEncoder()
le_region = LabelEncoder()

df['sex'] = le_sex.fit_transform(df['sex'])
df['smoker'] = le_smoker.fit_transform(df['smoker'])
df['region'] = le_region.fit_transform(df['region']) # 0 1 2 3 

df['region']

172     0
1150    0
195     1
581     1
1196    1
       ..
937     1
425     2
1245    3
1085    3
932     3
Name: region, Length: 1338, dtype: int64

variables=['sex','smoker','region','age','bmi','children']  # 选择特征
X=df[variables]        # 导入特征数据
sc=StandardScaler()
X=sc.fit_transform(X)  # 对数据进行标准化处理
Y=df['charges']        # 导入标签数据

# 使用sklearn.model_selection库自动对数据进行训练集与测试集的分割
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.2)

# 使用import的随机森林模型，并设置不同的树的数量进行试验，参考值为200
regressor = RandomForestRegressor(n_estimators=200)
# 使用fit函数对X_train,y_train进行拟合
regressor.fit(X_train,y_train)

#prediction and evaluation
y_train_pred = regressor.predict(X_train) #对X_train进行预测
y_test_pred = regressor.predict(X_test) # 对X_test进行预测

#计算相应的MAE和RMSE，得到价格的平均绝对值损失
print('RandomForestRegressor evaluating result:')
print("Train MAE: ", sklearn.metrics.mean_absolute_error(y_train ,y_train_pred ))
print("Train RMSE: ", np.sqrt(sklearn.metrics.mean_squared_error(y_train,y_train_pred)))
print("Test MAE: ", sklearn.metrics.mean_absolute_error(y_test ,y_test_pred))
print("Test RMSE: ", np.sqrt(sklearn.metrics.mean_squared_error(y_test, y_test_pred)))

RandomForestRegressor evaluating result:
Train MAE:  944.9813798049196
Train RMSE:  1764.1825891298656
Test MAE:  2993.187358598303
Test RMSE:  5603.299343502578

# 简单可视化模型，查看各个特征在随机森林中的重要度

importances = regressor.feature_importances_
std = np.std([tree.feature_importances_ for tree in regressor.estimators_],axis=0)# 代表行
indices = np.argsort(importances)[::-1]

importance_list = []
#       shape[1]:代表一维矩阵
for f in range(X.shape[1]):
    variable = variables[indices[f]] # index，就是序列号
    importance_list.append(variable)
    print("%d.%s(%f)" % (f + 1, variable, importances[indices[f]]))

# Plot the feature importances of the forest
plt.figure()
plt.title("Feature importance")
plt.bar(importance_list, importances[indices],
       color="r", yerr=std[indices], align="center")
plt.show()

特征重要度排序


1.smoker(0.643205)
2.bmi(0.197045)
3.age(0.123219)
4.children(0.016878)
5.region(0.014015)
6.sex(0.005639)