python_转换为数值类型&map映射&分桶&factorize

python_类型转换&map映射

Transforming Data Using a Function or Mapping
# 利⽤函数或映射进⾏数据转换
# 对于许多数据集，你可能希望根据数组、Series或DataFrame列
# 中的值来实现转换⼯作。我们来看看下⾯这组有关⾁类的数据
data = pd.DataFrame({'food': ['bacon', 'pulled pork', 'bacon',
'Pastrami', 'corned beef', 'Bacon',
'pastrami', 'honey ham', 'nova lox'],
'ounces': [4, 3, 12, 6, 7.5, 8, 3, 5, 6]})
data
food ounces
0 bacon 4.0
1 pulled pork 3.0
2 bacon 12.0
3 Pastrami 6.0
4 corned beef 7.5
5 Bacon 8.0
6 pastrami 3.0
7 honey ham 5.0
8 nova lox 6.0
meat_to_animal = {
'bacon': 'pig',
'pulled pork': 'pig',
'pastrami': 'cow',
'corned beef': 'cow',
'honey ham': 'pig',
'nova lox': 'salmon'
}
映射
# 使⽤Series的str.lower⽅法，将
# 各个值转换为⼩写：
lowercased = data['food'].str.lower()
lowercased
# Series的map⽅法可以接受⼀个函数或含有映射关系的字典型对 映射
# 象
data['animal'] = lowercased.map(meat_to_animal)
data
food ounces animal
0 bacon 4.0 pig
1 pulled pork 3.0 pig
2 bacon 12.0 pig
3 Pastrami 6.0 cow
4 corned beef 7.5 cow
5 Bacon 8.0 pig
6 pastrami 3.0 cow
7 honey ham 5.0 pig
8 nova lox 6.0 salmon
# 使用lambda类型映射
# 使⽤map是⼀种实现元素级转换以及其他数据清理⼯作的便捷⽅
data['food'].map(lambda x: meat_to_animal[x.lower()])
# 使用lambda类型映射
# 使⽤map是⼀种实现元素级转换以及其他数据清理⼯作的便捷⽅
data['food'].map(lambda x: meat_to_animal[x.lower()])

案例二

import pandas as pd
df = pd.DataFrame([
['green', 'M', 10.1, 'class1'],
['red', 'L', 13.5, 'class2'],
['blue', 'XL', 15.3, 'class1']])

df.columns = ['color', 'size', 'prize', 'class label']
df
color size prize class label
0 green M 10.1 class1
1 red L 13.5 class2
2 blue XL 15.3 class1
size_mapping = {
'XL': 3,
'L': 2,
'M': 1}
df['size'] = df['size'].map(size_mapping)
# df['size_b'] = df['size'].map(size_mapping)
df
color size prize class label
0 green 1 10.1 1
1 red 2 13.5 0
2 blue 3 15.3 1
ab=enumerate(set(df['class label']))
print(ab)
<enumerate object at 0x000001F65EB16678>
# set 去除重复值
# enumerate 枚举，增加一列排序值
# 然后map映射
class_mapping = {label:idx for idx,label in enumerate(set(df['class label']))}
df['class label'] = df['class label'].map(class_mapping)
df
df
color size prize class label size_b
0 green 1 10.1 1 1
1 red 2 13.5 0 2
2 blue 3 15.3 1 3

案例三，通过pd.factorize 函数

labels, uniques = pd.factorize(['b', 'b', 'a', 'c', 'b'])
labels
array([0, 0, 1, 2, 0], dtype=int64)
uniques
array(['b', 'a', 'c'], dtype=object)
labels, uniques = pd.factorize(['b', 'b', 'a', 'c', 'b'], sort=True)
labels
array([1, 1, 0, 2, 1], dtype=int64)
>>> labels, uniques = pd.factorize(['b', 'b', 'a', 'c', 'b'], sort=True)
>>> labels
array([1, 1, 0, 2, 1])
>>>
array(['a', 'b', 'c'], dtype=object)
uniques
array(['a', 'b', 'c'], dtype=object)

​