[Pandas Day8]分类数据

ex8-1

import pandas as pd
import numpy as np
df = pd.read_csv('data/Earthquake.csv')
# print(df.head())
# 将深度分为七个等级：[0,5,10,15,20,30,50,np.inf]，请以深度等级Ⅰ,Ⅱ,Ⅲ,Ⅳ,Ⅴ,Ⅵ,Ⅶ为索引并按照由浅到深的顺序进行排序
df_a = df.copy()
df_a['深度'] = pd.cut(df_a['深度'], [-1e-10,5,10,15,20,30,50,np.inf],labels=['Ⅰ','Ⅱ','Ⅲ','Ⅳ','Ⅴ','Ⅵ','Ⅶ'])
print(df_a.set_index('深度').sort_index().head())

# 将烈度分为4个等级：[0,3,4,5,np.inf]，依次对南部地区的深度和烈度等级建立多级索引排序
df_a['烈度'] = pd.cut(df_a['烈度'], [-1e-10,3,4,5,np.inf],labels=['Ⅰ','Ⅱ','Ⅲ','Ⅳ'])
print(df_a.set_index(['深度','烈度']).sort_index().head())

ex8-2

import pandas as pd
import numpy as np
foo = pd.Categorical(['a', 'b'], categories=['a', 'b', 'c'])
bar = pd.Categorical(['d', 'e'], categories=['d', 'e', 'f'])
print(pd.crosstab(foo, bar))

def my_crosstab(foo,bar):
    num = len(foo)
    s1 = pd.Series([i for i in list(foo.categories.union(set(foo)))],name='1nd var')
    s2 = [i for i in list(bar.categories.union(set(bar)))]
    df = pd.DataFrame({i:[0]*len(s1) for i in s2},index=s1)
    for i in range(num):
        df.at[foo[i],bar[i]] += 1
    return df.rename_axis('2st var',axis=1)
print(my_crosstab(foo,bar))