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)create dataframe pyspark
from datetime import datetime, date
import pandas as pd
from pyspark.sql import Row
df = spark.createDataFrame([
Row(a=1, b=2., c='string1', d=date(2000, 1, 1), e=datetime(2000, 1, 1, 12, 0)),
Row(a=2, b=3., c='string2', d=date(2000, 2, 1), e=datetime(2000, 1, 2, 12, 0)),
Row(a=4, b=5., c='string3', d=date(2000, 3, 1), e=datetime(2000, 1, 3, 12, 0))
])
dfCopyright © 2021 Codeinu
Forgot your account's password or having trouble logging into your Account? Don't worry, we'll help you to get back your account. Enter your email address and we'll send you a recovery link to reset your password. If you are experiencing problems resetting your password contact us
