项目一：医疗费用预估
今天开始准备记录自己看过或者参加的项目，并把其中的一些细节在代码中写出来。
开始，载入需要用的库和数据：
import warnings
warnings.filterwarnings('ignore')
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
df = pd.read_csv('./insurance.csv')
df = df.dropna(how='all')
df.describe()
得到数据分布情况：
df.head()
#查看不同维度之间的相关性
df.corr()
corrMatrix=df.corr()
sns.set(font_scale=1.10)
plt.figure(figsize=(8, 8))
sns.heatmap(corrMatrix, vmax=.8, linewidths=0.01,
square=True,annot=True,cmap='viridis',linecolor="white")
plt.title('Correlation between video num and retain');
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：')
for v in variables:
df = df.sort_values(by=[v])
df[v].value_counts().plot(kind = 'bar')
plt.title(v)
plt.show()
print('平均医疗开销分析：')
for v in variables:
group_df = df.groupby(pd.Grouper(key=v)).mean()
group_df = group_df.sort_index()
group_df.plot(y = ['charges'],kind = 'bar')
plt.show()
print('两两变量分析：')
variables = ['sex','smoker','region','age','bmi_int','children','charges']
sns_plot = sns.pairplot(df[variables])
plt.show()
print('建模与评估nn')
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'])
variables = ['sex','smoker','region','age','bmi','children']
X = df[variables]
sc = StandardScaler()
X = sc.fit_transform(X)
Y = df['charges']
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.2)
regressor = RandomForestRegressor(n_estimators = 200)
regressor.fit(X_train,y_train)
y_train_pred = regressor.predict(X_train)
y_test_pred = regressor.predict(X_test)
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)))
print('特征重要度排序n')
importances = regressor.feature_importances_
std = np.std([tree.feature_importances_ for tree in regressor.estimators_],axis=0)
indices = np.argsort(importances)[::-1]
importance_list = []
for f in range(X.shape[1]):
variable = variables[indices[f]]
importance_list.append(variable)
print("%d.%s(%f)" % (f + 1, variable, importances[indices[f]]))
plt.figure()
plt.title("feature importance")
plt.bar(importance_list, importances[indices],
color="r", yerr=std[indices], align="center")
plt.show()
print('在新数据上进行预测nn')
billy = ['male','yes','southeast',25,30.5,2]
print('Billy - ',str(billy))
billy[0] = le_sex.transform([billy[0]])[0]
billy[1] = le_smoker.transform([billy[1]])[0]
billy[2] = le_region.transform([billy[2]])[0]
X = sc.transform([billy])
cost_for_billy = regressor.predict(X)[0]
print('Billy的医疗开销 = ',cost_for_billy,'nn')
dennis = ['female','no','southeast',45,19,0]
print('Dennis - ',str(dennis))
dennis[0] = le_sex.transform([dennis[0]])[0]
dennis[1] = le_smoker.transform([dennis[1]])[0]
dennis[2] = le_region.transform([dennis[2]])[0]
X = sc.transform([dennis])
cost_for_dennis = regressor.predict(X)[0]
print('Dennis的医疗开销 = ',cost_for_dennis)
完。
相关知识
项目一：医疗费用预估
中国宠物医疗项目可行性研究报告
【宠物医疗加盟费】宠物医疗加盟费多少钱？总投资15.7万元！
宠物医院费用详解：宠物治疗项目及收费标准一览
宠物医疗费用全解析：让您的毛孩健康又省钱
宠物店创业项目简介选项目,项目找资源
宠物医疗费用控制如何合理规划宠物医疗支出
宠物的医疗费用是多少？
宠物医疗平台项目商业计划书PPT
在宠物店工作的员工谁来承担狗狗受伤的医疗费用？
网址: 项目一：医疗费用预估 https://m.mcbbbk.com/newsview333523.html
| 上一篇: 狗狗社交实例，考考大家能否分辨！ |
下一篇: 日韩宠物研究报告：发展史给我们带 |
