Pawan Trivedi d0r1h

## Chunking.py
"""
csv_chunk_processor.py
======================
Production-ready, memory-efficient CSV processor with UUID-aware chunking.

Core guarantee
--------------
ALL rows belonging to a single UUID are ALWAYS written to the same chunk file.
A UUID's rows are NEVER split across two chunks.

## SparkML_Titanic.py
from pyspark.sql import SparkSession
from pyspark.sql.functions import col, mean
from pyspark.sql.types import DoubleType
from pyspark.ml import Pipeline
from pyspark.ml.feature import VectorAssembler, StringIndexer
from pyspark.ml.classification import LogisticRegression
from pyspark.ml.evaluation import BinaryClassificationEvaluator, MulticlassClassificationEvaluator

spark = SparkSession.builder.getOrCreate()
print(f" spark version {spark.version}")

## venv.md

      
              1 file
            
          
              0 forks
            
          
                0 comments
              
            
              0 stars
            
          
                d0r1h
                / venv.md
            
            
              Created
              November 22, 2021 00:28
            
              
                Creating Virtual Environment for Python application 
              
          
    Using Python3
sudo apt install python3.8-venv
python3 -m venv env_name

source env_name/bin/activate


## index.html
<!DOCTYPE html>
<html lang="en">

<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>C02</title>

</head>

## app.py
import pickle
import jsonify
import requests
import numpy as np
import pandas as pd
from sklearn.linear_model import LinearRegression
from flask import Flask, render_template, request
from sklearn.model_selection import train_test_split


## haproxy.cfg.j2
#---------------------------------------------------------------------
# Example configuration for a possible web application.  See the
# full configuration options online.
#
#   https://www.haproxy.org/download/1.8/doc/configuration.txt
#
#---------------------------------------------------------------------

#---------------------------------------------------------------------
# Global settings

## reverseproxy.yml
- hosts: proxyserver
  tasks:
          - name: installing haproxy program
            package:
                    name: haproxy


          - name: configuring hapoxy
            template:
                    dest: /etc/haproxy/haproxy.cfg
	"""
	csv_chunk_processor.py
	======================
	Production-ready, memory-efficient CSV processor with UUID-aware chunking.

	Core guarantee
	--------------
	ALL rows belonging to a single UUID are ALWAYS written to the same chunk file.
	A UUID's rows are NEVER split across two chunks.
	from pyspark.sql import SparkSession
	from pyspark.sql.functions import col, mean
	from pyspark.sql.types import DoubleType
	from pyspark.ml import Pipeline
	from pyspark.ml.feature import VectorAssembler, StringIndexer
	from pyspark.ml.classification import LogisticRegression
	from pyspark.ml.evaluation import BinaryClassificationEvaluator, MulticlassClassificationEvaluator

	spark = SparkSession.builder.getOrCreate()
	print(f" spark version {spark.version}")
	<!DOCTYPE html>
	<html lang="en">

	<head>
	<meta charset="UTF-8">
	<meta name="viewport" content="width=device-width, initial-scale=1.0">
	<title>C02</title>

	</head>
	import pickle
	import jsonify
	import requests
	import numpy as np
	import pandas as pd
	from sklearn.linear_model import LinearRegression
	from flask import Flask, render_template, request
	from sklearn.model_selection import train_test_split
	#---------------------------------------------------------------------
	# Example configuration for a possible web application. See the
	# full configuration options online.
	#
	# https://www.haproxy.org/download/1.8/doc/configuration.txt
	#
	#---------------------------------------------------------------------

	#---------------------------------------------------------------------
	# Global settings
	- hosts: proxyserver
	tasks:
	- name: installing haproxy program
	package:
	name: haproxy


	- name: configuring hapoxy
	template:
	dest: /etc/haproxy/haproxy.cfg