pandas系列8-分类类型categories

import numpy as np
import pandas as pd
from pandas import Series, DataFrame

results = (pd.Series(draws)
    .groupby(bins)
    .agg(['count', 'min', 'max'])
    .reset_index())

values = pd.Series(['apple', 'orange', 'apple', 'apple'] * 2)
pd.unique(values)  # 选取唯一值

array(['apple', 'orange'], dtype=object)

pd.value_counts(values)   # 计算每个值出现的频率

apple     6
orange    2
dtype: int64

values = pd.Series([0, 1, 0, 0] * 2)
dim = pd.Series(['apple', 'orange'])

print(values)
print(dim)

0    0
1    1
2    0
3    0
4    0
5    1
6    0
7    0
dtype: int64
0     apple
1    orange
dtype: object

dim.take(values)   # take方法

0     apple
1    orange
0     apple
0     apple
0     apple
1    orange
0     apple
0     apple
dtype: object

fruits = ['apple', 'orange', 'apple', 'apple'] * 2
N = len(fruits)

df = pd.DataFrame({'fruit': fruits,
                   'basket_id': np.arange(N),
                   'count': np.random.randint(3, 15, size=N),   # 生成3-15随机整数
                   'weight': np.random.uniform(0, 4, size=N)},  # 生成0-4的数 
                  columns=['basket_id', 'fruit', 'count', 'weight'])
df

# 转换成分类
fruit_cat = df['fruit'].astype('category')
fruit_cat

0     apple
1    orange
2     apple
3     apple
4     apple
5    orange
6     apple
7     apple
Name: fruit, dtype: category
Categories (2, object): [apple, orange]

print(type(fruit_cat))   # S型数据
<class 'pandas.core.series.Series'>

c = fruit_cat.valuest
type(c)  # c是⼀个pandas.Categorical实例

pandas.core.arrays.categorical.Categorical

# 分类对象有categories和codes属性
print(c.categories)  # categories是具体的分类
print(c.codes)   # codes是里面的0、1值

Index(['apple', 'orange'], dtype='object')
[0 1 0 0 0 1 0 0]

df

# 将列转换成分类
df['fruit'] = df['fruit'].astype("category")
df.fruit

0     apple
1    orange
2     apple
3     apple
4     apple
5    orange
6     apple
7     apple
Name: fruit, dtype: category
Categories (2, object): [apple, orange]

# 通过Python其他序列创建分类
my_categories = pd.Categorical(['foo', 'bar', 'baz', 'foo', 'bar'])
my_categories

[foo, bar, baz, foo, bar]
Categories (3, object): [bar, baz, foo]

# 通过from_codes构建分类
categories = ['foo', 'bar', 'baz']
codes = [0, 1, 2, 0, 0, 1]
my_cats_2 = pd.Categorical.from_codes(codes, categories)  # from_codes构造器
my_cats_2

[foo, bar, baz, foo, foo, bar]
Categories (3, object): [foo, bar, baz]

# 无序的分类实例通过as_ordered进行排序
my_cats_2.as_ordered()

[foo, bar, baz, foo, foo, bar]
Categories (3, object): [foo < bar < baz]

# 创建分类的实例直接指定顺序: ordered=True
ordered_cat = pd.Categorical.from_codes(codes, categories,
                                        ordered=True)
ordered_cat

[foo, bar, baz, foo, foo, bar]
Categories (3, object): [foo < bar < baz]

np.random.seed(12345)
draws = np.random.randn(1000)
draws[:5]

array([-0.20470766,  0.47894334, -0.51943872, -0.5557303 ,  1.96578057])

bins = pd.qcut(draws, 4)
bins

[(-0.684, -0.0101], (-0.0101, 0.63], (-0.684, -0.0101], (-0.684, -0.0101], (0.63, 3.928], ..., (-0.0101, 0.63], (-0.684, -0.0101], (-2.9499999999999997, -0.684], (-0.0101, 0.63], (0.63, 3.928]]
Length: 1000
Categories (4, interval[float64]): [(-2.9499999999999997, -0.684] < (-0.684, -0.0101] < (-0.0101, 0.63] < (0.63, 3.928]]

bins = pd.qcut(draws, 4, labels=['Q1', 'Q2', 'Q3', 'Q4'])
bins

[Q2, Q3, Q2, Q2, Q4, ..., Q3, Q2, Q1, Q3, Q4]
Length: 1000
Categories (4, object): [Q1 < Q2 < Q3 < Q4]

bins.codes[:10]

array([1, 2, 1, 1, 3, 3, 2, 2, 3, 3], dtype=int8)

# groupby 提取汇总信息
bins = pd.Series(bins, name="quratile")
results = (pd.Series(draws)
          .groupby(bins)
          .agg(["count", "min", "max"])
          .reset_index())
results

bins = pd.Series(bins, name="quratile")
result = (pd.Series(draws)
          .groupby(bins)
          .agg(["count", "min", "max"]))
result

results["quratile"]

0    Q1
1    Q2
2    Q3
3    Q4
Name: quratile, dtype: category
Categories (4, object): [Q1 < Q2 < Q3 < Q4]

N = 10000000
draws = pd.Series(np.random.randn(N))
labels = pd.Series(['foo', 'bar', 'baz', 'qux'] * (N // 4))

categories = labels.astype("category")
categories.memory_usage()  # 分类占用内存少

10000272

labels.memory_usage()   # 非分类占用内存多

80000080

%time _ = labels.astype('category')

Wall time: 444 ms

s = pd.Series(['a', 'b', 'c', 'd'] * 2)
cat_s = s.astype('category')  # 如何转换成分类
cat_s

0    a
1    b
2    c
3    d
4    a
5    b
6    c
7    d
dtype: category
Categories (4, object): [a, b, c, d]

# cat属性提供分类方法的入口
cat_s.cat.codes

0    0
1    1
2    2
3    3
4    0
5    1
6    2
7    3
dtype: int8

cat_s.cat.categories

Index(['a', 'b', 'c', 'd'], dtype='object')

# 实际分类超出给定数据集中的个数，通过set_catgories实现
actual_categories = ['a', 'b', 'c', 'd', 'e']
cat_s2 = cat_s.cat.set_categories(actual_categories)
cat_s2

0    a
1    b
2    c
3    d
4    a
5    b
6    c
7    d
dtype: category
Categories (5, object): [a, b, c, d, e]

# 统计每个类的分类值
cat_s.value_counts()

d    2
c    2
b    2
a    2
dtype: int64

cat_s2.value_counts()

d    2
c    2
b    2
a    2
e    0
dtype: int64

#  remove_unused_categories()
cat_s3 = cat_s[cat_s.isin(['a', 'b'])]
cat_s3

0    a
1    b
4    a
5    b
dtype: category
Categories (4, object): [a, b, c, d]

cat_s.isin(['a', 'b'])

0     True
1     True
2    False
3    False
4     True
5     True
6    False
7    False
dtype: bool

# 查看分类，变成2个
cat_s3.cat.remove_unused_categories()

0    a
1    b
4    a
5    b
dtype: category
Categories (2, object): [a, b]

cat_s = pd.Series(['a', 'b', 'c', 'd'] * 2, dtype='category')
pd.get_dummies(cat_s)

cat_s

0    a
1    b
2    c
3    d
4    a
5    b
6    c
7    d
dtype: category
Categories (4, object): [a, b, c, d]