PYTHON

convert pandas dataframe to spark dataframe

import pandas as pd
from pyspark.sql import SparkSession

filename = <'path to file'>
spark = SparkSession.build.appName('pandasToSpark').getOrCreate()
# Assuming file is csv
pandas_df = pd.read_csv(filename)
spark_df = spark.CreateDataFrame(pandas_df)

spark to pandas

pandas_df = spark_df.select("*").toPandas()

dataframe pandas to spark

from pyspark.sql import SparkSession
#Create PySpark SparkSession
spark = SparkSession.builder 
    .master("local[1]") 
    .appName("SparkByExamples.com") 
    .getOrCreate()
#Create PySpark DataFrame from Pandas
sparkDF=spark.createDataFrame(pandasDF) 
sparkDF.printSchema()
sparkDF.show()

#Outputs below schema & DataFrame

root
 |-- Name: string (nullable = true)
 |-- Age: long (nullable = true)

+------+---+
|  Name|Age|
+------+---+
| Scott| 50|
|  Jeff| 45|
|Thomas| 54|
|   Ann| 34|
+------+---+

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)

spark to pandas

pandas_df = some_df.toPandas()

spark df to pandas df

some_df = sc.parallelize([
 ("A", "no"),
 ("B", "yes"),
 ("B", "yes"),
 ("B", "no")]
 ).toDF(["user_id", "phone_number"])
pandas_df = some_df.toPandas()

convert spark dataframe to pandas

# Convert Spark DataFrame back to a Pandas DataFrame using Arrow
pandasDF = sparkDF.select("*").toPandas()