Milind Jagre milindjagre

## post31.sql
create table post31 (
id int,
name string,
gender string
)
partitioned by (year int, month int)
row format delimited
fields terminated by ','
stored as textfile;

## post31.csv

          
            1
            tina
            F
            2000
            1

            
              2
              jerry
              M
              1997
              5

            
              3
              tom
              M
              1996
              5

            
              4
              wonder woman
              F
              1586
              10

            
              5
              scoobydoo
              M
              1991
              3

            
              6
              donald duck
              M
              1995
              6

            
              7
              pink panther
              F
              1997
              8

            
              8
              oggy
              M
              2010
              10

            
              9
              shinchan
              M
              2005
              1

## post30.csv

          
            1
            tina
            F

            
              2
              jerry
              M

            
              3
              tom
              M

            
              4
              wonder woman
              F

            
              5
              scoobydoo
              M

            
              6
              donald duck
              M

            
              7
              pink panther
              F

            
              8
              oggy
              M

            
              9
              shinchan
              M

## post29.sql
create table post29(
id int,
name string,
gender string
)
row format delimited
fields terminated by ','
stored as textfile;

## post28.sql
select * from categories;

## Data.csv

          
            Country
            Age
            Salary
            Purchased

            
              France
              44
              72000
              No

            
              Spain
              27
              48000
              Yes

            
              Germany
              30
              54000
              No

            
              Spain
              38
              61000
              No

            
              Germany
              40
              
              Yes

            
              France
              35
              58000
              Yes

            
              Spain
              
              52000
              No

            
              France
              48
              79000
              Yes

            
              Germany
              50
              83000
              No

## data_preprocessing.R
#  DATA PREPROCESSING

# setting the working directory
setwd("C:\\Users\\User\\Desktop\\blog\\3 ML Data Preprocessing\\R")

# IMPORTING THE DATASET
dataset = read.csv("Data.csv")
# viewing the imported dataset
View(dataset)

## data_preprocessing.py
# -*- coding: utf-8 -*-
"""
This python file demonstrates the concepts
we are going to cover in Data Preprocessing

"""

# IMPORTING THE LIBRARIES
# numpy contains mathematical operations
import numpy as np

## post27.pig
-- this pig script demonstrates how to invoke an UDF in Apache PIG

-- LOAD command is used to load data from post27.csv into input_data pig relation
input_data = LOAD '/hdpcd/input/post27/post27.csv' USING PigStorage(',');

-- we need to register the jar file first with REGISTER command
REGISTER /usr/hdp/2.3.0.0-2557/pig/piggybank.jar;

-- defining an alias for the fully qualified class name UPPER
DEFINE upper org.apache.pig.piggybank.evaluation.string.UPPER;

## post27.csv

          
            1
            Richard
            Hernandez
            XXXXXXXXX
            XXXXXXXXX
            6303 Heather Plaza
            Brownsville
            TX
            78521

            
              526
              Kimberly
              Barrett
              XXXXXXXXX
              XXXXXXXXX
              7988 High Jetty
              Brownsville
              TX
              78521
	create table post31 (
	id int,
	name string,
	gender string
	)
	partitioned by (year int, month int)
	row format delimited
	fields terminated by ','
	stored as textfile;
1	tina	F	2000	1
2	jerry	M	1997	5
3	tom	M	1996	5
4	wonder woman	F	1586	10
5	scoobydoo	M	1991	3
6	donald duck	M	1995	6
7	pink panther	F	1997	8
8	oggy	M	2010	10
9	shinchan	M	2005	1
	create table post29(
	id int,
	name string,
	gender string
	)
	row format delimited
	fields terminated by ','
	stored as textfile;
Country	Age	Salary	Purchased
France	44	72000	No
Spain	27	48000	Yes
Germany	30	54000	No
Spain	38	61000	No
Germany	40		Yes
France	35	58000	Yes
Spain		52000	No
France	48	79000	Yes
Germany	50	83000	No
	# DATA PREPROCESSING

	# setting the working directory
	setwd("C:\\Users\\User\\Desktop\\blog\\3 ML Data Preprocessing\\R")

	# IMPORTING THE DATASET
	dataset = read.csv("Data.csv")
	# viewing the imported dataset
	View(dataset)
	# -- coding: utf-8 --
	"""
	This python file demonstrates the concepts
	we are going to cover in Data Preprocessing

	"""

	# IMPORTING THE LIBRARIES
	# numpy contains mathematical operations
	import numpy as np
	-- this pig script demonstrates how to invoke an UDF in Apache PIG

	-- LOAD command is used to load data from post27.csv into input_data pig relation
	input_data = LOAD '/hdpcd/input/post27/post27.csv' USING PigStorage(',');

	-- we need to register the jar file first with REGISTER command
	REGISTER /usr/hdp/2.3.0.0-2557/pig/piggybank.jar;

	-- defining an alias for the fully qualified class name UPPER
	DEFINE upper org.apache.pig.piggybank.evaluation.string.UPPER;
	1	Richard	Hernandez	XXXXXXXXX	XXXXXXXXX	6303 Heather Plaza	Brownsville	TX	78521
	526	Kimberly	Barrett	XXXXXXXXX	XXXXXXXXX	7988 High Jetty	Brownsville	TX	78521