如何从大型数据集的单个列中切分字符串？

import pandas as pd

# 创建示例数据
data = {
    'id': [1, 2, 3],
    'info': ['name:John,age:30', 'name:Jane,age:25', 'name:Tom,age:40']
}

df = pd.DataFrame(data)

# 切分字符串
df[['name', 'age']] = df['info'].str.split(',', expand=True)

# 进一步切分
df['name'] = df['name'].str.split(':').str[1]
df['age'] = df['age'].str.split(':').str[1]

print(df)

   id               info  name age
0   1  name:John,age:30  John  30
1   2  name:Jane,age:25  Jane  25
2   3    name:Tom,age:40   Tom  40

SELECT
    id,
    SUBSTRING_INDEX(SUBSTRING_INDEX(info, ',', 1), ':', -1) AS name,
    SUBSTRING_INDEX(SUBSTRING_INDEX(info, ',', -1), ':', -1) AS age
FROM
    users;

from pyspark.sql import SparkSession
from pyspark.sql.functions import split, col

# 创建SparkSession
spark = SparkSession.builder.appName("StringSplitExample").getOrCreate()

# 创建示例数据
data = [
    (1, 'name:John,age:30'),
    (2, 'name:Jane,age:25'),
    (3, 'name:Tom,age:40')
]

columns = ['id', 'info']

df = spark.createDataFrame(data, columns)

# 切分字符串
df = df.withColumn('name', split(col('info'), ',')[0])
df = df.withColumn('age', split(col('info'), ',')[1])

# 进一步切分
df = df.withColumn('name', split(col('name'), ':')[1])
df = df.withColumn('age', split(col('age'), ':')[1])

df.show()

+---+---------------+----+---+
| id|           info|name|age|
+---+---------------+----+---+
|  1|name:John,age:30|John| 30|
|  2|name:Jane,age:25|Jane| 25|
|  3|  name:Tom,age:40| Tom| 40|
+---+---------------+----+---+

library(tidyverse)

# 创建示例数据
data <- tibble(
  id = c(1, 2, 3),
  info = c('name:John,age:30', 'name:Jane,age:25', 'name:Tom,age:40')
)

# 切分字符串
data <- data %>%
  separate(info, into = c("name", "age"), sep = ",") %>%
  separate(name, into = c("name_label", "name"), sep = ":") %>%
  separate(age, into = c("age_label", "age"), sep = ":") %>%
  select(-name_label, -age_label)

print(data)

# A tibble: 3 × 3
     id name  age  
  <dbl> <chr> <chr>
1     1 John  30   
2     2 Jane  25   
3     3 Tom   40