PYTHON

create spark dataframe in python

spark.createDataFrame(["10","11","13"], "string").toDF("age")

create spark dataframe from pandas

import numpy as np
import pandas as pd

# Enable Arrow-based columnar data transfers
spark.conf.set("spark.sql.execution.arrow.enabled", "true")

# Generate a pandas DataFrame
pdf = pd.DataFrame(np.random.rand(100, 3))

# Create a Spark DataFrame from a pandas DataFrame using Arrow
df = spark.createDataFrame(pdf)

Create spark dataframe in python

spark.createDataFrame([("10", ), ("11", ), ("13",  )], ["age"])