Python 8

mapping transform, str.title, str.upper, 일부 변경, 배열 > 카테고리 조건분류, np.sign(x), random.permutation, take, sample, One-Hot Encoding(get_dummies), .dat file, split, enumerate, add_prefix, set_option, strip, (index, find, count, replace)

mapping transform¶

In [1]:

import numpy as np
import pandas as pd

In [2]:

data = pd.DataFrame(np.arange(12).reshape((3, 4)), index=['Ohio', 'Colorado', 'New York'], columns=['one', 'two', 'three', 'four'])
data

Out[2]:

	one	two	three	four
Ohio	0	1	2	3
Colorado	4	5	6	7
New York	8	9	10	11

In [3]:

transform = lambda x: x[:3].upper()
#display(data.columns.map(transform))
display(data.index.map(transform))
display(data.index)
display(data)

Index(['OHI', 'COL', 'NEW'], dtype='object')

Index(['Ohio', 'Colorado', 'New York'], dtype='object')

	one	two	three	four
Ohio	0	1	2	3
Colorado	4	5	6	7
New York	8	9	10	11

In [4]:

data.index = data.index.map(transform)
data

Out[4]:

	one	two	three	four
OHI	0	1	2	3
COL	4	5	6	7
NEW	8	9	10	11

str.title, str.upper

• str.title : 문장처럼 첫문자만 대문자화
• str.upper : 항목 전체를 대문자화

https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.Series.str.swapcase.html

In [5]:

data.rename(index=str.title, columns=str.upper)

Out[5]:

	ONE	TWO	THREE	FOUR
Ohi	0	1	2	3
Col	4	5	6	7
New	8	9	10	11

일부 변경

In [6]:

data.rename(index={'OHIO':'INDIANA'}, columns={'three':'peekaboo'})

Out[6]:

	one	two	peekaboo	four
OHI	0	1	2	3
COL	4	5	6	7
NEW	8	9	10	11

배열 > 카테고리 조건분류¶

In [7]:

ages = [20, 22, 25, 27, 21, 23, 37, 31, 61, 45, 41, 32]

pd.cut

In [22]:

#18~25, 26~35, 36~60, 60이상

bins = [18,26,36,60,100] # 자를 경계
cats = pd.cut(ages,bins) # right=True(default) : (,]
cats

Out[22]:

[(18, 26], (18, 26], (18, 26], (26, 36], (18, 26], ..., (26, 36], (60, 100], (36, 60], (36, 60], (26, 36]]
Length: 12
Categories (4, interval[int64]): [(18, 26] < (26, 36] < (36, 60] < (60, 100]]

In [23]:

# 나눈 계층값을 0~n으로 지정
# 0~n 까지의 값으로 변경
cats.codes # 0~3

Out[23]:

array([0, 0, 0, 1, 0, 0, 2, 1, 3, 2, 2, 1], dtype=int8)

In [24]:

cats.categories

Out[24]:

IntervalIndex([(18, 26], (26, 36], (36, 60], (60, 100]],
              closed='right',
              dtype='interval[int64]')

In [25]:

pd.value_counts(cats)

Out[25]:

(18, 26]     5
(36, 60]     3
(26, 36]     3
(60, 100]    1
dtype: int64

In [26]:

# right=False : [,)
cats = pd.cut(ages,[18,26,36,61,100], right=False)
cats

Out[26]:

[[18, 26), [18, 26), [18, 26), [26, 36), [18, 26), ..., [26, 36), [61, 100), [36, 61), [36, 61), [26, 36)]
Length: 12
Categories (4, interval[int64]): [[18, 26) < [26, 36) < [36, 61) < [61, 100)]

In [27]:

group_names = ['Youth','YoungAdult','MiddleAged','Senior']
pd.cut(ages,bins,labels=group_names)

Out[27]:

['Youth', 'Youth', 'Youth', 'YoungAdult', 'Youth', ..., 'YoungAdult', 'Senior', 'MiddleAged', 'MiddleAged', 'YoungAdult']
Length: 12
Categories (4, object): ['Youth' < 'YoungAdult' < 'MiddleAged' < 'Senior']

In [28]:

data = np.random.rand(20)
print(data)
pd.cut(data, 4, precision=2, labels=['lowest','low','high','highest'])

[0.56843069 0.30254945 0.49730879 0.68326291 0.91669867 0.10892895
 0.49549179 0.23283593 0.43686066 0.75154299 0.48089213 0.79772841
 0.28270293 0.43341824 0.00975735 0.34079598 0.68927201 0.86936929
 0.26780382 0.45674792]

Out[28]:

['high', 'low', 'high', 'high', 'highest', ..., 'low', 'high', 'highest', 'low', 'low']
Length: 20
Categories (4, object): ['lowest' < 'low' < 'high' < 'highest']

In [29]:

data = pd.DataFrame(np.random.randn(1000,4))
data.head()

Out[29]:

	0	1	2	3
0	0.738600	-0.507776	0.227991	-1.740421
1	-0.534505	-0.937749	-1.486301	-0.029363
2	-1.237142	0.075986	-1.945198	-0.234840
3	-1.814567	0.059636	-0.397631	0.267998
4	0.890952	0.025341	-0.598142	-1.230504

In [30]:

data.describe()

Out[30]:

	0	1	2	3
count	1000.000000	1000.000000	1000.000000	1000.000000
mean	-0.011442	0.013205	0.028648	0.008134
std	1.026796	0.973519	0.998007	1.038934
min	-3.170364	-3.784642	-3.146325	-3.411796
25%	-0.708385	-0.627578	-0.661498	-0.713016
50%	0.012511	0.015492	0.050225	0.004004
75%	0.746445	0.658925	0.703221	0.760504
max	2.938272	3.190904	3.039147	3.375219

In [31]:

col = data[2]
col[np.abs(col) > 3]

Out[31]:

197    3.039147
416   -3.146325
Name: 2, dtype: float64

In [51]:

# ★
data[ (np.abs(data)>3) .any(1) ]
#data[ (np.abs(data)>3) ].dropna(thresh=1).fillna(0)#.max()#.min()#.count()#.mean()#.std()
#data[ (np.abs(data)>3) ].dropna(thresh=1).isnull()

Out[51]:

	0	1	2	3
19	0.758383	-3.784642	-1.219263	-0.369502
59	0.753059	0.858625	0.241787	-3.411796
197	1.045804	1.145826	3.039147	-0.489863
222	-0.660346	-0.732768	1.989074	3.344321
238	-2.610590	-0.620662	0.026520	-3.256768
388	-3.170364	0.079760	0.077850	0.877214
416	0.059133	0.389149	-3.146325	0.954444
445	0.991565	3.190904	0.057445	0.359985
466	0.784626	-1.549977	0.370359	3.238048
840	-3.130360	1.642567	-0.398491	0.523445
857	-0.084178	0.578835	1.869249	3.375219
915	-1.351265	1.018378	0.208455	-3.198062

In [56]:

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

np.random.seed(123)
df = DataFrame({'col_1': np.random.randint(20, size=20), 'col_2': np.random.randn(20)})
df

factor_col_1 = pd.cut(df.col_1, 4)
factor_col_1

grouped_col_1 = df.col_1.groupby(factor_col_1)
display(grouped_col_1) # SeriesGroupBy
grouped_col_1.agg(['count', 'mean', 'std', 'min', 'max'])

<pandas.core.groupby.generic.SeriesGroupBy object at 0x0C47CF10>

Out[56]:

	count	mean	std	min	max
col_1
(-0.019, 4.75]	8	1.125	1.457738	0	4
(4.75, 9.5]	2	7.500	2.121320	6	9
(9.5, 14.25]	4	12.750	1.892969	10	14
(14.25, 19.0]	6	17.000	1.788854	15	19

In [57]:

def summary_func(group):
    return {'count': group.count(), 'mean': group.mean(), 'std': group.std(), 'min': group.min(), 'max': group.max()}

grouped_col_1.apply(summary_func)

Out[57]:

col_1                
(-0.019, 4.75]  count     8.000000
                mean      1.125000
                std       1.457738
                min       0.000000
                max       4.000000
(4.75, 9.5]     count     2.000000
                mean      7.500000
                std       2.121320
                min       6.000000
                max       9.000000
(9.5, 14.25]    count     4.000000
                mean     12.750000
                std       1.892969
                min      10.000000
                max      14.000000
(14.25, 19.0]   count     6.000000
                mean     17.000000
                std       1.788854
                min      15.000000
                max      19.000000
Name: col_1, dtype: float64

In [69]:

test = grouped_col_1.apply(summary_func).unstack()
test.unstack().shape
test

Out[69]:

	count	mean	std	min	max
col_1
(-0.019, 4.75]	8.0	1.125	1.457738	0.0	4.0
(4.75, 9.5]	2.0	7.500	2.121320	6.0	9.0
(9.5, 14.25]	4.0	12.750	1.892969	10.0	14.0
(14.25, 19.0]	6.0	17.000	1.788854	15.0	19.0

numpy.sign(x)

• -1 if x < 0
• 0 if x = 0
• 1 if x > 0

In [70]:

# np.abs(data)가 3보다 큰 애들을 3으로 고정시킴
data[np.abs(data)>3] = np.sign(data)*3
data.describe()

Out[70]:

	0	1	2	3
count	1000.000000	1000.000000	1000.000000	1000.000000
mean	-0.011141	0.013799	0.028755	0.008043
std	1.025897	0.970161	0.997434	1.033362
min	-3.000000	-3.000000	-3.000000	-3.000000
25%	-0.708385	-0.627578	-0.661498	-0.713016
50%	0.012511	0.015492	0.050225	0.004004
75%	0.746445	0.658925	0.703221	0.760504
max	2.938272	3.000000	3.000000	3.000000

In [71]:

np.sign(data).head()

Out[71]:

	0	1	2	3
0	1.0	-1.0	1.0	-1.0
1	-1.0	-1.0	-1.0	-1.0
2	-1.0	1.0	-1.0	-1.0
3	-1.0	1.0	-1.0	1.0
4	1.0	1.0	-1.0	-1.0

random.permutation

In [73]:

df = pd.DataFrame(np.arange(5 * 4).reshape((5, 4)))
display(np.random.permutation(df)) # inplace=False <-> np.random.shuffle() - inplace=True
display(df)

array([[ 0,  1,  2,  3],
       [ 4,  5,  6,  7],
       [ 8,  9, 10, 11],
       [12, 13, 14, 15],
       [16, 17, 18, 19]])

	0	1	2	3
0	0	1	2	3
1	4	5	6	7
2	8	9	10	11
3	12	13	14	15
4	16	17	18	19

take : Return the elements in the given positional indices along an axis.

In [86]:

sampler = np.random.permutation(5)#(4)
sampler

Out[86]:

array([2, 4, 3, 0, 1])

In [116]:

df.take(sampler)#, axis=1)

Out[116]:

	0	1	2	3
2	8	9	10	11
4	16	17	18	19
3	12	13	14	15
0	0	1	2	3
1	4	5	6	7

sample : Return a random sample of items from an axis of object.

In [120]:

display(df.sample(n=3, random_state=1))
display(df.sample(n=3, axis=1))
df.sample(n=3)

	0	1	2	3
2	8	9	10	11
1	4	5	6	7
4	16	17	18	19

	3	2	1
0	3	2	1
1	7	6	5
2	11	10	9
3	15	14	13
4	19	18	17

Out[120]:

	0	1	2	3
3	12	13	14	15
4	16	17	18	19
2	8	9	10	11

In [121]:

choices = pd.Series([5, 7, -1, 6, 4])
draws = choices.sample(n=10, replace=True)
draws

Out[121]:

1    7
2   -1
2   -1
2   -1
1    7
3    6
2   -1
3    6
1    7
1    7
dtype: int64

One-Hot Encoding (전처리)¶

!(https://teddylee777.github.io/machine-learning/python-numpy%EB%A1%9C-one-hot-encoding-%EC%89%BD%EA%B2%8C%ED%95%98%EA%B8%B0)

In [122]:

df = pd.DataFrame({'key': ['b', 'b', 'a', 'c', 'a', 'b'], 'data1': range(6)})
df

Out[122]:

	key	data1
0	b	0
1	b	1
2	a	2
3	c	3
4	a	4
5	b	5

In [123]:

pd.get_dummies(df['key'])

Out[123]:

	a	b	c
0	0	1	0
1	0	1	0
2	1	0	0
3	0	0	1
4	1	0	0
5	0	1	0

In [127]:

dummies = pd.get_dummies(df['key'], prefix='key')
dummies

Out[127]:

	key_a	key_b	key_c
0	0	1	0
1	0	1	0
2	1	0	0
3	0	0	1
4	1	0	0
5	0	1	0

In [134]:

#df_with_dummy = df['data1'].join(dummies) # error:'Series' object has no attribute 'join'
df_with_dummy = df[['data1']].join(dummies)
df_with_dummy

Out[134]:

	data1	key_a	key_b	key_c
0	0	0	1	0
1	1	0	1	0
2	2	1	0	0
3	3	0	0	1
4	4	1	0	0
5	5	0	1	0

In [137]:

# ★★
display(df[['data1']])
display(df['data1'])

	data1
0	0
1	1
2	2
3	3
4	4
5	5

0    0
1    1
2    2
3    3
4    4
5    5
Name: data1, dtype: int64

In [135]:

test = dummies.join(df['data1'])
test

Out[135]:

	key_a	key_b	key_c	data1
0	0	1	0	0
1	0	1	0	1
2	1	0	0	2
3	0	0	1	3
4	1	0	0	4
5	0	1	0	5

.dat file¶

In [146]:

mnames = ['movie_id', 'title', 'genres']
movies = pd.read_table('files/movies.dat', sep='::', header=None, names=mnames) # header=None > affect movie_id
movies[:10]

Out[146]:

	movie_id	title	genres
0	1	Toy Story (1995)	Animation|Children's|Comedy
1	2	Jumanji (1995)	Adventure|Children's|Fantasy
2	3	Grumpier Old Men (1995)	Comedy|Romance
3	4	Waiting to Exhale (1995)	Comedy|Drama
4	5	Father of the Bride Part II (1995)	Comedy
5	6	Heat (1995)	Action|Crime|Thriller
6	7	Sabrina (1995)	Comedy|Romance
7	8	Tom and Huck (1995)	Adventure|Children's
8	9	Sudden Death (1995)	Action
9	10	GoldenEye (1995)	Action|Adventure|Thriller

In [148]:

movies.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3883 entries, 0 to 3882
Data columns (total 3 columns):
 #   Column    Non-Null Count  Dtype 
---  ------    --------------  ----- 
 0   movie_id  3883 non-null   int64 
 1   title     3883 non-null   object
 2   genres    3883 non-null   object
dtypes: int64(1), object(2)
memory usage: 60.7+ KB

split

In [147]:

all_genres = []
for x in movies.genres:
    all_genres.extend(x.split('|'))
genres = pd.unique(all_genres)
genres

Out[147]:

array(['Animation', "Children's", 'Comedy', 'Adventure', 'Fantasy',
       'Romance', 'Drama', 'Action', 'Crime', 'Thriller', 'Horror',
       'Sci-Fi', 'Documentary', 'War', 'Musical', 'Mystery', 'Film-Noir',
       'Western'], dtype=object)

In [149]:

# genres를 unique했으므로 genres에 따라 movies 목록을 뽑아내는 작업
zero_matrix = np.zeros((len(movies),len(genres)))
dummies = pd.DataFrame(zero_matrix, columns = genres)
dummies

Out[149]:

	Animation	Children's	Comedy	Adventure	Fantasy	Romance	Drama	Action	Crime	Thriller	Horror	Sci-Fi	Documentary	War	Musical	Mystery	Film-Noir	Western
0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
4	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
3878	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3879	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3880	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3881	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3882	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

3883 rows × 18 columns

In [152]:

gen = movies.genres[0]
gen.split('|') # ['Animation', "Children's", 'Comedy']
dummies.columns.get_indexer(gen.split('|')) # ['Animation'=0, "Children's"=1, 'Comedy'=2]

Out[152]:

array([0, 1, 2], dtype=int32)

enumerate 함수

리스트가 있는 경우 순서와 리스트의 값을 전달하는 기능
enumerate는 “열거하다”라는 뜻이다. 이 함수는 순서가 있는 자료형(리스트, 튜플, 문자열)을 입력으로 받아 인덱스 값을 포함하는 enumerate 객체를 리턴한다.
보통 enumerate 함수는 아래 예제처럼 for문과 함께 자주 사용된다.

In [153]:

for i, gen in enumerate(movies.genres):
    indices = dummies.columns.get_indexer(gen.split('|'))
    dummies.iloc[i, indices] = 1
dummies

Out[153]:

	Animation	Children's	Comedy	Adventure	Fantasy	Romance	Drama	Action	Crime	Thriller	Horror	Sci-Fi	Documentary	War	Musical	Mystery	Film-Noir	Western
0	1.0	1.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	0.0	1.0	0.0	1.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	0.0	0.0	1.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3	0.0	0.0	1.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
4	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
3878	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3879	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3880	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3881	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3882	0.0	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

3883 rows × 18 columns

add_prefix(suffix)

In [157]:

movies_windic = movies.join(dummies.add_prefix('Genre_')) # add_suffix
#movies_windic.iloc[0]
movies_windic

Out[157]:

	movie_id	title	genres	Genre_Animation	Genre_Children's	Genre_Comedy	Genre_Adventure	Genre_Fantasy	Genre_Romance	Genre_Drama	...	Genre_Crime	Genre_Thriller	Genre_Horror	Genre_Sci-Fi	Genre_Documentary	Genre_War	Genre_Musical	Genre_Mystery	Genre_Film-Noir	Genre_Western
0	1	Toy Story (1995)	Animation|Children's|Comedy	1.0	1.0	1.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	2	Jumanji (1995)	Adventure|Children's|Fantasy	0.0	1.0	0.0	1.0	1.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	3	Grumpier Old Men (1995)	Comedy|Romance	0.0	0.0	1.0	0.0	0.0	1.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3	4	Waiting to Exhale (1995)	Comedy|Drama	0.0	0.0	1.0	0.0	0.0	0.0	1.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
4	5	Father of the Bride Part II (1995)	Comedy	0.0	0.0	1.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
3878	3948	Meet the Parents (2000)	Comedy	0.0	0.0	1.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3879	3949	Requiem for a Dream (2000)	Drama	0.0	0.0	0.0	0.0	0.0	0.0	1.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3880	3950	Tigerland (2000)	Drama	0.0	0.0	0.0	0.0	0.0	0.0	1.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3881	3951	Two Family House (2000)	Drama	0.0	0.0	0.0	0.0	0.0	0.0	1.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3882	3952	Contender, The (2000)	Drama|Thriller	0.0	0.0	0.0	0.0	0.0	0.0	1.0	...	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

3883 rows × 21 columns

pd.set_option

https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.set_option.html

In [172]:

# set_option을 할 경우 지금 DataFrame뿐 아니라 이후에 출력되는 DataFrame도 영향이 가므로 주의
pd.set_option('display.max_columns',6)
#pd.set_option('display.max_rows',2)
pd.set_option('display.max_rows',2)
movies_windic = movies.join(dummies.add_prefix('Genre_'))
movies_windic.head()

Out[172]:

	movie_id	title	genres	...	Genre_Mystery	Genre_Film-Noir	Genre_Western
0	1	Toy Story (1995)	Animation|Children's|Comedy	...	0.0	0.0	0.0
...	...	...	...	...	...	...	...
4	5	Father of the Bride Part II (1995)	Comedy	...	0.0	0.0	0.0

5 rows × 21 columns

get_dummies (one-hot encoding)¶

In [173]:

np.random.seed(12345)
values = np.random.rand(10)
values

Out[173]:

array([0.92961609, 0.31637555, 0.18391881, 0.20456028, 0.56772503,
       0.5955447 , 0.96451452, 0.6531771 , 0.74890664, 0.65356987])

In [183]:

pd.set_option('display.max_columns', None)
pd.set_option('display.max_rows', None)

bins = [0,0.2,0.4,0.6,0.8,1]

display(pd.cut(values, bins))
display(pd.get_dummies(pd.cut(values, bins)))

[(0.8, 1.0], (0.2, 0.4], (0.0, 0.2], (0.2, 0.4], (0.4, 0.6], (0.4, 0.6], (0.8, 1.0], (0.6, 0.8], (0.6, 0.8], (0.6, 0.8]]
Categories (5, interval[float64]): [(0.0, 0.2] < (0.2, 0.4] < (0.4, 0.6] < (0.6, 0.8] < (0.8, 1.0]]

	(0.0, 0.2]	(0.2, 0.4]	(0.4, 0.6]	(0.6, 0.8]	(0.8, 1.0]
0	0	0	0	0	1
1	0	1	0	0	0
2	1	0	0	0	0
3	0	1	0	0	0
4	0	0	1	0	0
5	0	0	1	0	0
6	0	0	0	0	1
7	0	0	0	1	0
8	0	0	0	1	0
9	0	0	0	1	0

split, strip¶

https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.Series.str.strip.html

In [184]:

val = 'a,b, guide'
val.split(',')

Out[184]:

['a', 'b', ' guide']

In [191]:

# 공백 사라짐
pieces = list(x.strip() for x in val.split(','))
pieces

Out[191]:

['a', 'b', 'guide']

In [192]:

# unpacking
first, second, third = pieces
first + '::' + second + '::' + third

Out[192]:

'a::b::guide'

In [193]:

'::'.join(pieces)

Out[193]:

'a::b::guide'

In [194]:

'guide' in val

Out[194]:

True

index, find, count, replace¶

In [195]:

val.index(',')

Out[195]:

1

In [196]:

# 없으면 음수값 반환
val.find(':')

Out[196]:

-1

In [197]:

val.count(",")

Out[197]:

2

In [198]:

val.replace(',', '::')

Out[198]:

'a::b:: guide'

In [199]:

val.replace(',', '')

Out[199]:

'ab guide'