基于随机森林的红葡萄酒分析

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import GridSearchCV
import warnings
warnings.filterwarnings('ignore')

try:
    wine = pd.read_csv('winequality-red.csv',sep = ';')
except:
    print('cannot find the file!')
    
print(wine.info())
wine.describe()

wine.duplicated().sum() #检查是否有重复行
#删除重复记录
wine = wine.drop_duplicates()
wine.describe()
#查看quality目标属性具体每一类有多少值
wine.quality.value_counts()

#绘制饼图,直观看目标属性每一类的比例
wine.quality.value_counts().plot(kind = 'pie',autopct ='%.2f' )
#查看目标属性quality和其他特征属性的皮尔逊相关系数
win