[빅데이터분석기사] 작업형1 - 시계열 데이터 1

실습 환경 - Google Colab

시계열 데이터 (Datetime)¶

In [ ]:

# 데이터 생성(실습 전 실행)
import pandas as pd
data = {
    'Date1': ['2024-02-17', '2024-02-18', '2024-02-19'],
    'Date2': ['2024:02:17', '2024:02:18', '2024:02:19'],
    'Date3': ['24/02/17', '24/02/18', '24/02/19'],
    'Date4': ['02/17/2024', '02/18/2024', '02/19/2024'],
    'Date5': ['17-Feb-2024', '18-Feb-2024', '19-Feb-2024'],
    'Date6': ['2024년02월17일', '2024년02월18일', '2024년02월19일'],
    'DateTime1': ['24-02-17 11:45:30', '24-02-18 12:55:45', '24-02-19 13:30:15'],
    'DateTime2': ['2024-02-17 11-45-30', '2024-02-18 12-55-45', '2024-02-19 13-30-15'],
    'DateTime3': ['02/17/2024 11:45:30 AM', '02/18/2024 12:55:45 PM', '02/19/2024 01:30:15 PM'],
    'DateTime4': ['17 Feb 2024 11:45:30', '18 Feb 2024 12:55:45', '19 Feb 2024 13:30:15']
}

df = pd.DataFrame(data)
df.to_csv("date.csv", index=False)
df

Out[ ]:

	Date1	Date2	Date3	Date4	Date5	Date6	DateTime1	DateTime2	DateTime3	DateTime4
0	2024-02-17	2024:02:17	24/02/17	02/17/2024	17-Feb-2024	2024년02월17일	24-02-17 11:45:30	2024-02-17 11-45-30	02/17/2024 11:45:30 AM	17 Feb 2024 11:45:30
1	2024-02-18	2024:02:18	24/02/18	02/18/2024	18-Feb-2024	2024년02월18일	24-02-18 12:55:45	2024-02-18 12-55-45	02/18/2024 12:55:45 PM	18 Feb 2024 12:55:45
2	2024-02-19	2024:02:19	24/02/19	02/19/2024	19-Feb-2024	2024년02월19일	24-02-19 13:30:15	2024-02-19 13-30-15	02/19/2024 01:30:15 PM	19 Feb 2024 13:30:15

In [ ]:

# 데이터 불러오기
df = pd.read_csv('date.csv')
df

Out[ ]:

	Date1	Date2	Date3	Date4	Date5	Date6	DateTime1	DateTime2	DateTime3	DateTime4
0	2024-02-17	2024:02:17	24/02/17	02/17/2024	17-Feb-2024	2024년02월17일	24-02-17 11:45:30	2024-02-17 11-45-30	02/17/2024 11:45:30 AM	17 Feb 2024 11:45:30
1	2024-02-18	2024:02:18	24/02/18	02/18/2024	18-Feb-2024	2024년02월18일	24-02-18 12:55:45	2024-02-18 12-55-45	02/18/2024 12:55:45 PM	18 Feb 2024 12:55:45
2	2024-02-19	2024:02:19	24/02/19	02/19/2024	19-Feb-2024	2024년02월19일	24-02-19 13:30:15	2024-02-19 13-30-15	02/19/2024 01:30:15 PM	19 Feb 2024 13:30:15

In [ ]:

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3 entries, 0 to 2
Data columns (total 10 columns):
 #   Column     Non-Null Count  Dtype 
---  ------     --------------  ----- 
 0   Date1      3 non-null      object
 1   Date2      3 non-null      object
 2   Date3      3 non-null      object
 3   Date4      3 non-null      object
 4   Date5      3 non-null      object
 5   Date6      3 non-null      object
 6   DateTime1  3 non-null      object
 7   DateTime2  3 non-null      object
 8   DateTime3  3 non-null      object
 9   DateTime4  3 non-null      object
dtypes: object(10)
memory usage: 368.0+ bytes

자료형 변경¶

• pd.to_datetime(df['컬럼명'])

In [ ]:

# Date1
df = pd.read_csv("date.csv")
print(df['Date1'])

df['Date1'] = pd.to_datetime(df['Date1'])
print(df['Date1'])

0    2024-02-17
1    2024-02-18
2    2024-02-19
Name: Date1, dtype: object
0   2024-02-17
1   2024-02-18
2   2024-02-19
Name: Date1, dtype: datetime64[ns]

In [ ]:

# Date2 (year 4자리: %Y)
df = pd.read_csv("date.csv")
print(df['Date2'])

df['Date2'] = pd.to_datetime(df['Date2'], format='%Y:%m:%d')
print(df['Date2'])

0    2024:02:17
1    2024:02:18
2    2024:02:19
Name: Date2, dtype: object
0   2024-02-17
1   2024-02-18
2   2024-02-19
Name: Date2, dtype: datetime64[ns]

In [ ]:

# Date3 (year 2자리: %y)
df = pd.read_csv("date.csv")
print(df['Date3'])

df['Date3'] = pd.to_datetime(df['Date3'], format='%y/%m/%d')
print(df['Date3'])

0    24/02/17
1    24/02/18
2    24/02/19
Name: Date3, dtype: object
0   2024-02-17
1   2024-02-18
2   2024-02-19
Name: Date3, dtype: datetime64[ns]

In [ ]:

# Date4
df = pd.read_csv("date.csv")
print(df['Date4'])

df['Date4'] = pd.to_datetime(df['Date4'], format='%m/%d/%Y')
print(df['Date4'])

0    02/17/2024
1    02/18/2024
2    02/19/2024
Name: Date4, dtype: object
0   2024-02-17
1   2024-02-18
2   2024-02-19
Name: Date4, dtype: datetime64[ns]

In [ ]:

# Date5
df = pd.read_csv("date.csv")
print(df['Date5'])

df['Date5'] = pd.to_datetime(df['Date5'])
print(df['Date5'])

0    17-Feb-2024
1    18-Feb-2024
2    19-Feb-2024
Name: Date5, dtype: object
0   2024-02-17
1   2024-02-18
2   2024-02-19
Name: Date5, dtype: datetime64[ns]

In [ ]:

# Date6
df = pd.read_csv("date.csv")
print(df['Date6'])

df['Date6'] = pd.to_datetime(df['Date6'], format='%Y년%m월%d일')
print(df['Date6'])

0    2024년02월17일
1    2024년02월18일
2    2024년02월19일
Name: Date6, dtype: object
0   2024-02-17
1   2024-02-18
2   2024-02-19
Name: Date6, dtype: datetime64[ns]

In [ ]:

# DateTime1
df = pd.read_csv("date.csv")
print(df['DateTime1'])

df['DateTime1'] = pd.to_datetime(df['DateTime1'], format='%y-%m-%d %H:%M:%S')
print(df['DateTime1'])

0    24-02-17 11:45:30
1    24-02-18 12:55:45
2    24-02-19 13:30:15
Name: DateTime1, dtype: object
0   2024-02-17 11:45:30
1   2024-02-18 12:55:45
2   2024-02-19 13:30:15
Name: DateTime1, dtype: datetime64[ns]

In [ ]:

# DateTime2
df = pd.read_csv("date.csv")
print(df['DateTime2'])

df['DateTime2'] = pd.to_datetime(df['DateTime2'], format='%Y-%m-%d %H-%M-%S')
print(df['DateTime2'])

0    2024-02-17 11-45-30
1    2024-02-18 12-55-45
2    2024-02-19 13-30-15
Name: DateTime2, dtype: object
0   2024-02-17 11:45:30
1   2024-02-18 12:55:45
2   2024-02-19 13:30:15
Name: DateTime2, dtype: datetime64[ns]

In [ ]:

# DateTime3
df = pd.read_csv("date.csv")
print(df['DateTime3'])

df['DateTime3'] = pd.to_datetime(df['DateTime3'])
print(df['DateTime3'])

0    02/17/2024 11:45:30 AM
1    02/18/2024 12:55:45 PM
2    02/19/2024 01:30:15 PM
Name: DateTime3, dtype: object
0   2024-02-17 11:45:30
1   2024-02-18 12:55:45
2   2024-02-19 13:30:15
Name: DateTime3, dtype: datetime64[ns]

In [ ]:

# DateTime4
df = pd.read_csv("date.csv")
print(df['DateTime4'])

df['DateTime4'] = pd.to_datetime(df['DateTime4'])
print(df['DateTime4'])

0    17 Feb 2024 11:45:30
1    18 Feb 2024 12:55:45
2    19 Feb 2024 13:30:15
Name: DateTime4, dtype: object
0   2024-02-17 11:45:30
1   2024-02-18 12:55:45
2   2024-02-19 13:30:15
Name: DateTime4, dtype: datetime64[ns]

In [ ]:

# 자료형 확인
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3 entries, 0 to 2
Data columns (total 10 columns):
 #   Column     Non-Null Count  Dtype         
---  ------     --------------  -----         
 0   Date1      3 non-null      object        
 1   Date2      3 non-null      object        
 2   Date3      3 non-null      object        
 3   Date4      3 non-null      object        
 4   Date5      3 non-null      object        
 5   Date6      3 non-null      object        
 6   DateTime1  3 non-null      object        
 7   DateTime2  3 non-null      object        
 8   DateTime3  3 non-null      object        
 9   DateTime4  3 non-null      datetime64[ns]
dtypes: datetime64[ns](1), object(9)
memory usage: 368.0+ bytes

• datetime 자료형으로 변경하면 dt를 사용할 수 있다.

In [ ]:

# 년, 월, 일, 시간, 분, 초 추출
df['year'] = df['DateTime4'].dt.year
df['month'] = df['DateTime4'].dt.month
df['day'] = df['DateTime4'].dt.day
df['hour'] = df['DateTime4'].dt.hour
df['minute'] = df['DateTime4'].dt.minute
df['second'] = df['DateTime4'].dt.second

In [ ]:

df.iloc[:,-6:]

Out[ ]:

	year	month	day	hour	minute	second
0	2024	2	17	11	45	30
1	2024	2	18	12	55	45
2	2024	2	19	13	30	15

In [ ]:

#요일 dayofweek 0:월, 1:화, 2:수, 3:목, 4:금, 5:토, 6:일
df['DateTime4'].dt.dayofweek

Out[ ]:

0    5
1    6
2    0
Name: DateTime4, dtype: int32

In [ ]:

# 주말 5:토, 6:일
df['is주말'] = df['DateTime4'].dt.dayofweek >= 5
df

Out[ ]:

	Date1	Date2	Date3	Date4	Date5	Date6	DateTime1	DateTime2	DateTime3	DateTime4	year	month	day	hour	minute	second	is주말
0	2024-02-17	2024:02:17	24/02/17	02/17/2024	17-Feb-2024	2024년02월17일	24-02-17 11:45:30	2024-02-17 11-45-30	02/17/2024 11:45:30 AM	2024-02-17 11:45:30	2024	2	17	11	45	30	True
1	2024-02-18	2024:02:18	24/02/18	02/18/2024	18-Feb-2024	2024년02월18일	24-02-18 12:55:45	2024-02-18 12-55-45	02/18/2024 12:55:45 PM	2024-02-18 12:55:45	2024	2	18	12	55	45	True
2	2024-02-19	2024:02:19	24/02/19	02/19/2024	19-Feb-2024	2024년02월19일	24-02-19 13:30:15	2024-02-19 13-30-15	02/19/2024 01:30:15 PM	2024-02-19 13:30:15	2024	2	19	13	30	15	False

In [ ]:

# [참고] 기간 to_period()
print(df['DateTime4'].dt.to_period('Y'))
print(df['DateTime4'].dt.to_period('Q'))
print(df['DateTime4'].dt.to_period('M'))
print(df['DateTime4'].dt.to_period('D'))
print(df['DateTime4'].dt.to_period('H'))

0    2024
1    2024
2    2024
Name: DateTime4, dtype: period[A-DEC]
0    2024Q1
1    2024Q1
2    2024Q1
Name: DateTime4, dtype: period[Q-DEC]
0    2024-02
1    2024-02
2    2024-02
Name: DateTime4, dtype: period[M]
0    2024-02-17
1    2024-02-18
2    2024-02-19
Name: DateTime4, dtype: period[D]
0    2024-02-17 11:00
1    2024-02-18 12:00
2    2024-02-19 13:00
Name: DateTime4, dtype: period[H]

---

참고

https://inf.run/PoyjH

[퇴근후딴짓] 빅데이터 분석기사 실기 (작업형1,2,3) | 퇴근후딴짓 - 인프런