XGBOOST算法之一特征分析

仅仅记录一下简单的特征分析法：

数据集仍是：Pima印第安人糖尿病数据集

主要是：数据分布、散点图、相关性矩阵分析等

代码如下：

from operator import index
from numpy import loadtxt
from numpy import sort
from matplotlib import pyplot
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

# #----------------------Load Data-----------------------------------------------

dataset = loadtxt(r'C:\Users\Administrator\Desktop\pima-indians-diabetes.csv', delimiter=",",skiprows=1)

# #--------------------- array转化为DataFrame,并添加列名# -----------------------------------
data = np.array(dataset)
df = pd.DataFrame(data=data[0:,0:],
                   columns=['pregnants','Plasma_glucose_concentration','blood_pressure','Triceps_skin_fold_thickness','serum_insulin','BMI','Diabetes_pedigree_function','Age','Target'
] )


# #---------------------绘制数据的分布情况-----------------------------------------
df.hist(figsize=(16,14)) 

# #----------------------散点图分析-----------------------------------------------

sns.pairplot(df,hue = "Target")


# #----------------------Correlation computer-------------------------------------
figure, ax = plt.subplots(figsize=(12, 12))
sns.heatmap(df.corr(), square=True, annot=True, ax=ax)

plt.show()

最后结果：

标签：#----------------------,plt,df,numpy,XGBOOST,算法,ax,import,特征分析
来源： https://blog.csdn.net/zhaomengszu/article/details/123615582