pvmehta.com

from pyspark.sql.functions import col, lit# File location and typefile_location = “/FileStore/tables/sales_data_part1.csv”file_type = “csv”# CSV optionsinfer_schema = “false”first_row_is_header = “true”delimiter = “,”# The applied options are for CSV files. For other file types, these will # be ignored.df = spark.read.format(file_type) .option(“inferSchema”, infer_schema) .option(“header”, first_row_is_header) .option(“sep”, delimiter) .load(file_location)display(df)# Adding new column with and with default values. #…

Read More “Add new columns in dataframe” »

# Databricks notebook source   %sqlcreate database if not exists abcdb   %sqluse abcdb   %sqlcreate table student (id int , name string)   %sqlinsert into studentselect 1 as id, ‘user1’ as name   %sqlselect * from student   spark.sql(“create database if not exists xyzdb”)spark.sql(“use xyzdb”)   # Use three double quotes (“””) if SQL…

Read More “Getting started with notebook” »

from pyspark.sql.functions import col   # File location and type file_location = “/FileStore/tables/sales_data_part1.csv” file_type = “csv” # CSV options infer_schema = “false” first_row_is_header = “true” delimiter = “,” # The applied options are for CSV files. For other file types, these will be ignored. df = spark.read.format(file_type)   .option(“inferSchema”, infer_schema)   .option(“header”, first_row_is_header)   .option(“sep”,…

Read More “Read CSV file using PySpark” »

# Databricks notebook source import pandas as pd # preapre dataframe df_h=pd.read_csv(“https://people.sc.fsu.edu/~jburkardt/data/csv/zillow.csv”) #Print dataframe df_h #define custom columns columns = [“Srno”, “SQFT”, “BR”, “Baths”, “Zipcode”, “YearBuilt”, “ListPrice”] df_h=pd.read_csv(“https://people.sc.fsu.edu/~jburkardt/data/csv/zillow.csv”, header=None, names=columns) #Print dataframe df_h # show top 10 rows df_h.head(10) # show last 10 rows df_h.tail(10) #Print dataframe df_h #Drop non-needed columns, column names are case…

Read More “Read CSV File using Python” »