In [ ]:
#summarize the relationship between two numeric variables via python
In [ ]:
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
In [ ]:
df= pd.read_csv('winequality.csv')
df.head()
Out[ ]:
| fixed acidity | volatile acidity | citric acid | residual sugar | chlorides | free sulfur dioxide | total sulfur dioxide | density | pH | sulphates | alcohol | quality | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 7.4 | 0.70 | 0.00 | 1.9 | 0.076 | 11.0 | 34.0 | 0.9978 | 3.51 | 0.56 | 9.4 | 5 |
| 1 | 7.8 | 0.88 | 0.00 | 2.6 | 0.098 | 25.0 | 67.0 | 0.9968 | 3.20 | 0.68 | 9.8 | 5 |
| 2 | 7.8 | 0.76 | 0.04 | 2.3 | 0.092 | 15.0 | 54.0 | 0.9970 | 3.26 | 0.65 | 9.8 | 5 |
| 3 | 11.2 | 0.28 | 0.56 | 1.9 | 0.075 | 17.0 | 60.0 | 0.9980 | 3.16 | 0.58 | 9.8 | 6 |
| 4 | 7.4 | 0.70 | 0.00 | 1.9 | 0.076 | 11.0 | 34.0 | 0.9978 | 3.51 | 0.56 | 9.4 | 5 |
In [ ]:
# display the relationship between fixed acidity and alcohol
In [ ]:
plt.figure(figsize=(5,3))
sns.scatterplot(data=df, x='fixed acidity', y='alcohol')
#plt.title('Relationship between Fixed Acidity and Alcohol')
#plt.xlabel('Fixed Acidity')
#plt.ylabel('Alcohol')
plt.show()
In [ ]:
#histplot
plt.figure(figsize=(5,3))
sns.histplot(data=df, x='fixed acidity', y='alcohol')
plt.show()
In [ ]:
#kdeplot
plt.figure(figsize=(5,3))
sns.kdeplot(data=df, x='fixed acidity', y='alcohol')
plt.show()
In [ ]:
#stacking technique
plt.figure(figsize=(5,3))
#sns.histplot(data=df, x='fixed acidity', y='alcohol')
sns.scatterplot(data=df, x='fixed acidity', y='alcohol', color='skyblue')
sns.histplot(data=df, x='fixed acidity', y='alcohol', color ='lightblue', pthresh=0.2)
sns.kdeplot(data=df, x='fixed acidity', y='alcohol', color='lightgreen')
plt.show()
In [ ]:
#jointplot with regression line
#plt.figure(figsize=(5,3))
sns.jointplot(data=df, x='fixed acidity', y='alcohol', kind='reg')
plt.show()
In [ ]:
In [ ]:
#jointplot with hex
#plt.figure(figsize=(5,3))
sns.jointplot(data=df, x='fixed acidity', y='alcohol', kind='hex')
plt.show()
In [ ]:
# identify the relationship between sulphate and alcohol across quality
In [ ]:
plt.figure(figsize=(5,5))
sns.kdeplot(data=df, x='sulphates', y='alcohol', hue='quality', palette='bwr', levels=3)
plt.show()
In [ ]:
#donut chart
prod= ['iphone', 'ipad']
color= ['skyblue', 'grey']
sales= [300,100]
In [ ]:
plt.figure(figsize=(5,5))
plt.pie(sales, labels=prod, colors=color, autopct='%.1f%%', wedgeprops={'width': 0.5},
startangle=90, explode=(0,0.1), shadow=True)
plt.show()
In [ ]: