葡萄酒数据可视化分析

必应壁纸供图

数据集：https://download.csdn.net/download/weixin_53742691/87982219

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

wine = pd.read_csv("wine_quality/wine_edited.csv")
wine.head()

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality	color	alcohol_level	acidity_level
0	7.4	0.70	0.00	1.9	0.076	11.0	34.0	0.9978	3.51	0.56	9.4	5	red	low	low
1	7.8	0.88	0.00	2.6	0.098	25.0	67.0	0.9968	3.20	0.68	9.8	5	red	low	mod_high
2	7.8	0.76	0.04	2.3	0.092	15.0	54.0	0.9970	3.26	0.65	9.8	5	red	low	medium
3	11.2	0.28	0.56	1.9	0.075	17.0	60.0	0.9980	3.16	0.58	9.8	6	red	low	mod_high
4	7.4	0.70	0.00	1.9	0.076	11.0	34.0	0.9978	3.51	0.56	9.4	5	red	low	low

wine.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 6497 entries, 0 to 6496
Data columns (total 15 columns):
 #   Column                Non-Null Count  Dtype  
---  ------                --------------  -----  
 0   fixed acidity         6497 non-null   float64
 1   volatile acidity      6497 non-null   float64
 2   citric acid           6497 non-null   float64
 3   residual sugar        6497 non-null   float64
 4   chlorides             6497 non-null   float64
 5   free sulfur dioxide   6497 non-null   float64
 6   total sulfur dioxide  6497 non-null   float64
 7   density               6497 non-null   float64
 8   pH                    6497 non-null   float64
 9   sulphates             6497 non-null   float64
 10  alcohol               6497 non-null   float64
 11  quality               6497 non-null   int64  
 12  color                 6497 non-null   object 
 13  alcohol_level         6497 non-null   object 
 14  acidity_level         6496 non-null   object 
dtypes: float64(11), int64(1), object(3)
memory usage: 761.5+ KB

单一变量的可视化

sns.countplot(x='color',data=wine);

​

​

sns.countplot(x='acidity_level',data=wine);

sns.countplot(x='quality',data=wine);

sns.color_palette()

base_color = sns.color_palette()[0]
sns.countplot(x='color',data=wine,color=base_color);

sns.countplot(x='quality',data=wine,color=base_color);

sns.countplot(y='acidity_level',data=wine,color=base_color);

 wine.acidity_level.value_counts()

high        1717
mod_high    1643
low         1574
medium      1562
Name: acidity_level, dtype: int64

ph_order = wine.acidity_level.value_counts().index
sns.countplot(y='acidity_level',data=wine,color=base_color,order=ph_order);

sns.countplot(x='acidity_level',data=wine,color=base_color,order=ph_order);

sns.countplot(x='acidity_level',data=wine,color=base_color,order=ph_order);

acidity_class = wine['acidity_level'].value_counts()
locs,lables = plt.xticks()

for i in range(len(locs)):
    put_string = acidity_class[i]
    plt.text(locs[i],put_string-100,put_string,color='white',ha='center')

sns.countplot(y='acidity_level',data=wine,color=base_color,order=ph_order);

acidity_class = wine['acidity_level'].value_counts()
locs,lables = plt.yticks()

for i in range(len(locs)):
    put_string = acidity_class[i]
    plt.text(put_string+100,locs[i],put_string,ha='center')

alcohol_data = wine.alcohol_level.value_counts().reset_index()
alcohol_data = alcohol_data.rename(columns={'index':'alcohol_level','alcohol_level':'alcohol_counts'})
alcohol_data

	alcohol_level	alcohol_counts
0	high	3320
1	low	3177

sns.barplot(x='alcohol_level',y='alcohol_counts',data=alcohol_data,color=base_color);

plt.pie(alcohol_data.alcohol_counts,labels=alcohol_data.alcohol_level,startangle=90)
plt.show()

acidity_class = wine['acidity_level'].value_counts().reset_index()
acidity_class = acidity_class.rename(columns={'index':'acidity_level','acidity_level':'level_counts'})
acidity_class

	acidity_level	level_counts
0	high	1717
1	mod_high	1643
2	low	1574
3	medium	1562

plt.pie(acidity_class.level_counts,labels=acidity_class.acidity_level,startangle=90)
plt.show()

plt.pie(acidity_class.level_counts,labels=acidity_class.acidity_level,startangle=90,wedgeprops={'width':0.4})
plt.show()

wine.describe()

	fixed acidity	volatile acidity	citric acid	residual sugar	chlorides	free sulfur dioxide	total sulfur dioxide	density	pH	sulphates	alcohol	quality
count	6497.000000	6497.000000	6497.000000	6497.000000	6497.000000	6497.000000	6497.000000	6497.000000	6497.000000	6497.000000	6497.000000	6497.000000
mean	7.215307	0.339666	0.318633	5.443235	0.056034	30.525319	115.744574	0.994697	3.218501	0.531268	10.491801	5.818378
std	1.296434	0.164636	0.145318	4.757804	0.035034	17.749400	56.521855	0.002999	0.160787	0.148806	1.192712	0.873255
min	3.800000	0.080000	0.000000	0.600000	0.009000	1.000000	6.000000	0.987110	2.720000	0.220000	8.000000	3.000000
25%	6.400000	0.230000	0.250000	1.800000	0.038000	17.000000	77.000000	0.992340	3.110000	0.430000	9.500000	5.000000
50%	7.000000	0.290000	0.310000	3.000000	0.047000	29.000000	118.000000	0.994890	3.210000	0.510000	10.300000	6.000000
75%	7.700000	0.400000	0.390000	8.100000	0.065000	41.000000	156.000000	0.996990	3.320000	0.600000	11.300000	6.000000
max	15.900000	1.580000	1.660000	65.800000	0.611000	289.000000	440.000000	1.038980	4.010000	2.000000	14.900000	9.000000

plt.hist(data=wine,x='pH')
plt.show()

import numpy as np
bin_edges = np.arange(wine.pH.min(),wine.pH.max()+0.05,0.05)
len(bin_edges )

27

plt.hist(data=wine,x='pH',bins=bin_edges)
plt.show()

bin_edges = np.arange(0.0,0.125+0.005,0.005)
plt.hist(data=wine,x='chlorides',bins=bin_edges)
plt.xlim((0.0,0.125))
plt.show()