8. 用Seaborn破解diamonds数据集的辛普森悖论

 In[95]: pd.DataFrame(index=['Student A', 'Student B'], 
                      data={'Raw Score': ['50/100', '80/100'], 
                            'Percent Correct':[50,80]}, columns=['Raw Score', 'Percent Correct'])
Out[95]:

 In[96]: pd.DataFrame(index=['Student A', 'Student B'], 
                      data={'Difficult': ['45/95', '2/5'], 
                            'Easy': ['5/5', '78/95'],
                            'Difficult Percent': [47, 40],
                            'Easy Percent' : [100, 82],
                            'Total Percent':[50, 80]}, 
                      columns=['Difficult', 'Easy', 'Difficult Percent', 'Easy Percent', 'Total Percent'])
Out[96]:

#  读取diamonds数据集
 In[97]: diamonds = pd.read_csv('data/diamonds.csv')
         diamonds.head()
Out[97]:

#  将cut、color、clarity列变为有序类型
 In[98]: cut_cats = ['Fair', 'Good', 'Very Good', 'Premium', 'Ideal']
         color_cats = ['J', 'I', 'H', 'G', 'F', 'E', 'D']
         clarity_cats = ['I1', 'SI2', 'SI1', 'VS2', 'VS1', 'VVS2', 'VVS1', 'IF']
         diamonds['cut'] = pd.Categorical(diamonds['cut'],
                                          categories=cut_cats, 
                                          ordered=True)
         diamonds['color'] = pd.Categorical(diamonds['color'],
                                            categories=color_cats, 
                                            ordered=True)
         diamonds['clarity'] = pd.Categorical(diamonds['clarity'],
                                              categories=clarity_cats, 
                                              ordered=True)
 In[99]: fig, (ax1, ax2, ax3) = plt.subplots(1, 3, figsize=(14,4))
         sns.barplot(x='color', y='price', data=diamonds, ax=ax1)
         sns.barplot(x='cut', y='price', data=diamonds, ax=ax2)
         sns.barplot(x='clarity', y='price', data=diamonds, ax=ax3)
         fig.suptitle('Price Decreasing with Increasing Quality?')
Out[98]: Text(0.5,0.98,'Price Decreasing with Increasing Quality?')

#  画出每种钻石颜色和价格的关系
 In[100]: sns.factorplot(x='color', y='price', col='clarity',
                         col_wrap=4, data=diamonds, kind='bar')
Out[100]: <seaborn.axisgrid.FacetGrid at 0x11b61d5f8>

#  用克拉值取代价格
 In[101]: sns.factorplot(x='color', y='carat', col='clarity',
                         col_wrap=4, data=diamonds, kind='bar')
Out[101]: <seaborn.axisgrid.FacetGrid at 0x11e42eef0>

 In[102]: fig, (ax1, ax2, ax3) = plt.subplots(1, 3, figsize=(14,4))
          sns.barplot(x='color', y='carat', data=diamonds, ax=ax1)
          sns.barplot(x='cut', y='carat', data=diamonds, ax=ax2)
          sns.barplot(x='clarity', y='carat', data=diamonds, ax=ax3)
          fig.suptitle('Diamond size decreases with quality')
Out[102]: Text(0.5,0.98,'Diamond size decreases with quality')

#  下图显示钻石越大，价格越高
 In[103]: diamonds['carat_category'] = pd.qcut(diamonds.carat, 5)
          from matplotlib.cm import Greys
          greys = Greys(np.arange(50,250,40))
          g = sns.factorplot(x='clarity', y='price', data=diamonds,
                             hue='carat_category', col='color', 
                             col_wrap=4, kind='point') # , palette=greys)
          g.fig.suptitle('Diamond price by size, color and clarity',
                         y=1.02, size=20)
Out[103]: Text(0.5,1.02,'Diamond price by size, color and clarity')

更多

#  用seaborn更高级的PairGrid构造器，对二元变量作图
 In[104]: g = sns.PairGrid(diamonds,size=5,
                           x_vars=["color", "cut", "clarity"],
                           y_vars=["price"])
          g.map(sns.barplot)
          g.fig.suptitle('Replication of Step 3 with PairGrid', y=1.02)
Out[104]: Text(0.5,1.02,'Replication of Step 3 with PairGrid')