葡萄酒数据分析

• 引入包，查看数据

import pandas as pd
import matplotlib.pyplot as plt
# 支持中文
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False  # 用来正常显示负号
read_df = pd.read_csv('winequality-red.csv',sep=';')
white_df = pd.read_csv('winequality-white.csv',sep=';')
white_df.head()

read_df.head()

• 新增颜色列

import numpy as np
# 为红葡萄酒数据框创建颜色数组
color_red = np.repeat(0,read_df.shape[0])

# 为白葡萄酒数据框创建颜色数组
color_white = np.repeat(1,white_df.shape[0])

read_df['color'] = color_red
white_df['color'] = color_white

• 合并红白葡萄酒数据集

wine_df = read_df.append(white_df)
wine_df.info()
wine_df.to_csv('winequality_edited.csv',index=False)
wine_df.to_csv('winequality_edited1.csv')

• 可