提取特定单元格的值并将其填充到pyspark dataframe中的NA值

cell_value = df.select("column_name").collect()[0][0]

df_filled = df.fillna(cell_value)

# 导入必要的库
from pyspark.sql import SparkSession

# 创建SparkSession对象
spark = SparkSession.builder.getOrCreate()

# 创建DataFrame对象
data = [("Alice", 25, 100),
        ("Bob", None, 200),
        ("Charlie", 30, None)]
df = spark.createDataFrame(data, ["name", "age", "salary"])

# 提取特定单元格的值
cell_value = df.select("age").collect()[0][0]

# 填充NA值
df_filled = df.fillna(cell_value)

# 打印填充后的DataFrame
df_filled.show()

+-------+----+------+
|   name| age|salary|
+-------+----+------+
|  Alice|  25|   100|
|    Bob|  25|   200|
|Charlie|  30|   100|
+-------+----+------+