pandas 如何在时间序列数据上“get_dummies”

如果我有一些时间序列数据：（弥补一些）

import numpy as np
import pandas as pd
np.random.seed(11)

rows,cols = 50000,2
data = np.random.rand(rows,cols) 
tidx = pd.date_range('2019-01-01', periods=rows, freq='H') 
df = pd.DataFrame(data, columns=['Temperature','Value'], index=tidx)

我该如何利用get_dummies？只是看着熊猫文档，我不知道我是否可以应用到我如何制作一种热编码。

例如，我知道如何制作虚拟变量来表示一周时间变量的唯一方法是一种非常笨重的冗余代码方法。有人可以给我建议如何做得更好吗？

#create dummy variables
df['month'] = df.index.month
df['year'] = df.index.year
df['day_of_week'] = df.index.dayofweek
df['hour'] = df.index.strftime('%H').astype('int')

df['hour_0'] = np.where(df['hour'].isin([0]), 1, 0)
df['hour_1'] = np.where(df['hour'].isin([1]), 1, 0)
df['hour_2'] = np.where(df['hour'].isin([2]), 1, 0)
df['hour_3'] = np.where(df['hour'].isin([3]), 1, 0)
df['hour_4'] = np.where(df['hour'].isin([4]), 1, 0)
df['hour_5'] = np.where(df['hour'].isin([5]), 1, 0)
df['hour_6'] = np.where(df['hour'].isin([6]), 1, 0)
df['hour_7'] = np.where(df['hour'].isin([7]), 1, 0)
df['hour_8'] = np.where(df['hour'].isin([8]), 1, 0)
df['hour_9'] = np.where(df['hour'].isin([9]), 1, 0)
df['hour_10'] = np.where(df['hour'].isin([10]), 1, 0)
df['hour_11'] = np.where(df['hour'].isin([11]), 1, 0)
df['hour_12'] = np.where(df['hour'].isin([12]), 1, 0)
df['hour_13'] = np.where(df['hour'].isin([13]), 1, 0)
df['hour_14'] = np.where(df['hour'].isin([14]), 1, 0)
df['hour_15'] = np.where(df['hour'].isin([15]), 1, 0)
df['hour_16'] = np.where(df['hour'].isin([16]), 1, 0)
df['hour_17'] = np.where(df['hour'].isin([17]), 1, 0)
df['hour_18'] = np.where(df['hour'].isin([18]), 1, 0)
df['hour_19'] = np.where(df['hour'].isin([19]), 1, 0)
df['hour_20'] = np.where(df['hour'].isin([20]), 1, 0)
df['hour_21'] = np.where(df['hour'].isin([21]), 1, 0)
df['hour_22'] = np.where(df['hour'].isin([22]), 1, 0)
df['hour_23'] = np.where(df['hour'].isin([23]), 1, 0)

df['monday'] = np.where(df['day_of_week'].isin([0]), 1, 0)
df['tuesday'] = np.where(df['day_of_week'].isin([1]), 1, 0)
df['wednesday'] = np.where(df['day_of_week'].isin([2]), 1, 0)
df['thursday'] = np.where(df['day_of_week'].isin([3]), 1, 0)
df['friday'] = np.where(df['day_of_week'].isin([4]), 1, 0)
df['saturday'] = np.where(df['day_of_week'].isin([5]), 1, 0)
df['sunday'] = np.where(df['day_of_week'].isin([6]), 1, 0)

df['january'] = np.where(df['month'].isin([1]), 1, 0)
df['february'] = np.where(df['month'].isin([2]), 1, 0)
df['march'] = np.where(df['month'].isin([3]), 1, 0)
df['april'] = np.where(df['month'].isin([4]), 1, 0)
df['may'] = np.where(df['month'].isin([5]), 1, 0)
df['june'] = np.where(df['month'].isin([6]), 1, 0)
df['july'] = np.where(df['month'].isin([7]), 1, 0)
df['august'] = np.where(df['month'].isin([8]), 1, 0)
df['september'] = np.where(df['month'].isin([9]), 1, 0)
df['october'] = np.where(df['month'].isin([10]), 1, 0)
df['november'] = np.where(df['month'].isin([11]), 1, 0)
df['december'] = np.where(df['month'].isin([12]), 1, 0)

df['year19'] = np.where(df['year'].isin([2019]), 1, 0)
df['year20'] = np.where(df['year'].isin([2020]), 1, 0)
df['year21'] = np.where(df['year'].isin([2021]), 1, 0)
df['year22'] = np.where(df['year'].isin([2022]), 1, 0)
df['year23'] = np.where(df['year'].isin([2023]), 1, 0)
df['year24'] = np.where(df['year'].isin([2024]), 1, 0)

然后我正在尝试 ML 算法的最终数据框将是：

df2 = df[['Temperature', 'Value', 
            'hour_0' , 'hour_1' , 'hour_2' , 'hour_3' , 'hour_4' , 'hour_5' , 'hour_6' ,
            'hour_7' , 'hour_8' , 'hour_9' , 'hour_10' , 'hour_11' , 'hour_12' , 'hour_13' , 
            'hour_14' , 'hour_15' , 'hour_16' , 'hour_17' , 'hour_18' , 'hour_19' , 'hour_20' , 
            'hour_21' , 'hour_22' , 'hour_23' , 
            'monday' , 'tuesday' , 'wednesday' , 'thursday' , 'friday' , 'saturday' , 'sunday' , 
            'january' , 'february' , 'march' , 'april' , 'may' , 'june' , 'july' , 'august' , 
            'september' , 'october' , 'november' , 'december' , 
            'year19' , 'year20' , 'year21' , 'year22' , 'year23' , 'year24']]

EDIT更新的代码尝试

import numpy as np
import pandas as pd
np.random.seed(11)

rows,cols = 50000,2
data = np.random.rand(rows,cols) 
tidx = pd.date_range('2019-01-01', periods=rows, freq='H') 
df = pd.DataFrame(data, columns=['Temperature','Value'], index=tidx)

df['hour'] = df.index.strftime('%H').astype('int')
df['day_of_week'] = df.index.dayofweek
df['month'] = df.index.month
df['year'] = df.index.year

hour_dummies = pd.get_dummies(df['hour'], prefix='hour')

day_mapping = {0: 'monday', 1: 'tuesday', 2: 'wednesday', 3: 'thursday', 4: 'friday', 5: 'saturday', 6: 'sunday'}
day_dummies = pd.get_dummies(df['day_of_week'].map(day_mapping))

month_mapping = {0: 'jan', 1: 'feb', 2: 'mar', 3: 'apr', 4: 'may', 5: 'jun', 6: 'jul',
                 7: 'aug', 8: 'sep', 9: 'oct', 10: 'nov', 11: 'dec'}
month_dummies = pd.get_dummies(df['month'].map(month_mapping))

year_mapping = {0: 'year_2019', 1: 'year_2020', 2: 'year_2021', 3: 'year_2022', 4: 'year_2023', 5: 'year_2024'}
year_dummies = pd.get_dummies(df['year'].map(year_mapping))

df = df.join(hour_dummies)
df = df.join(day_dummies)
df = df.join(month_dummies)
df = df.join(year_dummies)

可以从时间索引中提取对应的信息，然后使用pd.get_dummies。例如

# day name
day_names = pd.get_dummies(df.index.day_name())

# hours
hours = pd.get_dummies(df.index.hour, prefix='hour')

# months
months = pd.get_dummies(df.index.month_name())

# year
years = pd.get_dummies(df.index.year, prefix='year')

进而concat:

df = pd.concat((df, hours, day_names), axis=1)