bosd_cade

# 防止不必要的警告
import warnings
warnings.filterwarnings("ignore")

# 引入数据科学基础包
import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt
import pandas as pd
import scipy.stats as st
import seaborn as sns
## 设置属性防止画图中文乱码
mpl.rcParams['font.sans-serif'] = [u'SimHei']
mpl.rcParams['axes.unicode_minus'] = False

# 引入机器学习，预处理，模型选择，评估指标
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import r2_score

# 引入本次所使用的波士顿数据集
from sklearn.datasets import load_boston

# 引入算法
from sklearn.linear_model import RidgeCV, LassoCV, LinearRegression, ElasticNet
#对比SVC，是svm的回归形式
from sklearn.svm import SVR
# 集成算法
from sklearn.ensemble import RandomForestRegressor, GradientBoostingRegressor
from xgboost import XGBRegressor

# 载入波士顿房价数据集
boston = load_boston()

# x是特征，y是标签
x = boston.data
y = boston.target

# 查看相关属性
print('特征的列名')
print(boston.feature_names)
print("样本数据量:%d, 特征个数：%d" % x.shape)
print("target样本数据量:%d" % y.shape[0])

# 转化为dataframe形式
x = pd.DataFrame(boston.data, columns=boston.feature_names)
print(x.head())


# 对标签的分布进行可视化
# no_1 = sns.distplot(tuple(y), kde=False, fit=st.norm)
sns.distplot(tuple(y), kde=False, fit=st.norm)
# print(no_1)