Santosh Gouda sgouda0412

## prediction_example.py
#!/usr/bin/python
# -*- coding: utf8 -*-

# SAMPLE SUBMISSION TO THE BIG DATA HACKATHON 13-14 April 2013 'Influencers in a Social Network'
# .... more info on Kaggle and links to go here
#
# written by Ferenc Huszár, PeerIndex

from sklearn import linear_model
from sklearn.metrics import auc_score

## delete_write_idempotency.py
import pandas as pd
import os
import shutil


def extract(path: str = "s3://my_bucket_name/file0.parquet") -> pd.DataFrame:
  df = pd.read_parquet(path)
  return df


## exploratory_data_analysis.py
import pandas as pd
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
import missingno
import warnings
warnings.filterwarnings("ignore")
%matplotlib inline

## cohort.py
## Importing libraries
import numpy as np
import pandas as pd
import datetime as dt
import seaborn as sns
import matplotlib.pyplot as plt

#For inline Chart Display
%matplotlib inline

## redshift_redshift.py
from pyspark.context import SparkContext
from awsglue.context import GlueContext
from pyspark.sql import SQLContext

sc = SparkContext()
glueContext = GlueContext(sc)
spark = glueContext.spark_session

# EXTRACT: Reading parquet data

## Amazon Redshfit
Files for amazon redshift sql queries with aws lambda

## Google Colab SSH
#CODE

#Generate root password
import random, string
password = ''.join(random.choice(string.ascii_letters + string.digits) for i in range(20))

#Download ngrok
! wget -q -c -nc https://bin.equinox.io/c/4VmDzA7iaHb/ngrok-stable-linux-amd64.zip
! unzip -qq -n ngrok-stable-linux-amd64.zip
#Setup sshd

## basic.csv

          
            COMMAND
            FUNCTIONALITY

            
              ls
              Lists all files and directories in the present working directory

            
              ls -R
              Lists files in sub-directories as well

            
              ls -a
              Lists hidden files as well

            
              ls -al
              Lists files and directories with detailed information.

            
              ls 'path' | more
              Show listing one screen at a time

            
              cd or cd ~
              Navigate to HOME directory

            
              cd ..
              Move one level up

            
              cd
              To change to a particular directory

            
              cd /
              Move to the root directory

## advanced.csv

          
            COMMAND
            FUNCTIONALITY

            
              grep -v ‘^$’ filename > new_filename
              Remove Blank Lines in a file

            
              ls -l | grep '^-' | awk '/^-/ {if ($5 !=0 ) print $9 }'
              Display zero byte size files

            
              sed 's/honey/pasta/n' < filename
              Replace the nth occurrence of the word 'honey' with 'pasta' in a file

            
              echo 'string' | tr [a-z] [A-Z]
              command to convert a string from lower case to upper case

            
              grep -i 'search string' filename
              Search for a given string in a file (case in-sensitive search)

            
              cal 03 2022
              Display the calendar for the month march in the year 2022

            
              find -atime n -type f
              List the files that are accessed n days ago in the current directory

            
              find -mtime n -type f
              List the files that were modified n days ago in the current directory

            
              find -ctime n -type f
              List the files that were changed n days ago in the current directory

## ml_pipeline.py
from datetime import timedelta
# The DAG object; we'll need this to instantiate a DAG
from airflow import DAG
# Operators; we need this to operate!
from airflow.operators.bash_operator import BashOperator
from airflow.utils.dates import days_ago
# These args will get passed on to each operator
# You can override them on a per-task basis during operator initialization
default_args = {
    'owner': 'Binh Phan',
	#!/usr/bin/python
	# -- coding: utf8 --

	# SAMPLE SUBMISSION TO THE BIG DATA HACKATHON 13-14 April 2013 'Influencers in a Social Network'
	# .... more info on Kaggle and links to go here
	#
	# written by Ferenc Huszár, PeerIndex

	from sklearn import linear_model
	from sklearn.metrics import auc_score
	import pandas as pd
	import os
	import shutil


	def extract(path: str = "s3://my_bucket_name/file0.parquet") -> pd.DataFrame:
	df = pd.read_parquet(path)
	return df
	import pandas as pd
	import numpy as np
	import matplotlib
	import matplotlib.pyplot as plt
	import seaborn as sns
	import missingno
	import warnings
	warnings.filterwarnings("ignore")
	%matplotlib inline
	## Importing libraries
	import numpy as np
	import pandas as pd
	import datetime as dt
	import seaborn as sns
	import matplotlib.pyplot as plt

	#For inline Chart Display
	%matplotlib inline
	from pyspark.context import SparkContext
	from awsglue.context import GlueContext
	from pyspark.sql import SQLContext

	sc = SparkContext()
	glueContext = GlueContext(sc)
	spark = glueContext.spark_session

	# EXTRACT: Reading parquet data
	#CODE

	#Generate root password
	import random, string
	password = ''.join(random.choice(string.ascii_letters + string.digits) for i in range(20))

	#Download ngrok
	! wget -q -c -nc https://bin.equinox.io/c/4VmDzA7iaHb/ngrok-stable-linux-amd64.zip
	! unzip -qq -n ngrok-stable-linux-amd64.zip
	#Setup sshd
	COMMAND	FUNCTIONALITY
	ls	Lists all files and directories in the present working directory
	ls -R	Lists files in sub-directories as well
	ls -a	Lists hidden files as well
	ls -al	Lists files and directories with detailed information.
	ls 'path' \| more	Show listing one screen at a time
	cd or cd ~	Navigate to HOME directory
	cd ..	Move one level up
	cd	To change to a particular directory
	cd /	Move to the root directory
	COMMAND	FUNCTIONALITY
	grep -v ‘^$’ filename > new_filename	Remove Blank Lines in a file
	ls -l \| grep '^-' \| awk '/^-/ {if ($5 !=0 ) print $9 }'	Display zero byte size files
	sed 's/honey/pasta/n' < filename	Replace the nth occurrence of the word 'honey' with 'pasta' in a file
	echo 'string' \| tr [a-z] [A-Z]	command to convert a string from lower case to upper case
	grep -i 'search string' filename	Search for a given string in a file (case in-sensitive search)
	cal 03 2022	Display the calendar for the month march in the year 2022
	find -atime n -type f	List the files that are accessed n days ago in the current directory
	find -mtime n -type f	List the files that were modified n days ago in the current directory
	find -ctime n -type f	List the files that were changed n days ago in the current directory
	from datetime import timedelta
	# The DAG object; we'll need this to instantiate a DAG
	from airflow import DAG
	# Operators; we need this to operate!
	from airflow.operators.bash_operator import BashOperator
	from airflow.utils.dates import days_ago
	# These args will get passed on to each operator
	# You can override them on a per-task basis during operator initialization
	default_args = {
	'owner': 'Binh Phan',