QuantVI

## SQL_Window_Functions.SQL
SELECT
  *,
  row_number () over () AS Row_N
FROM Summer_Medals
ORDER BY Row_N ASC;
--------------------

SELECT
  Year,
  row_number() over() AS Row_N

## prob_calculator.py
import copy
import random
# Consider using the modules imported above.

class Hat:
    def __init__(self, **kwargs):
        self.d = kwargs
        self.contents = [
            key for key, val in kwargs.items() for num in range(val)
        ]

## assorted_python_blurbs.py
# Within a Jupyter Notebook
import sys
sys.path.append("C:/somewhere/else/not/in/the/tree/of/this/jpfile")
# Now we can import Windows directories as packages, and refer to Python files within them
  # the folder jpyfile need not have an __init__.py file in it
  # folders that we import from within jpfile should
from folder_w_in_jpfile import my_modular_code
  # folder_w_in_jpfile contains an __init__.py file whihc can be empty
  # my_modular_code is a file my_modular_code.py with any other Python code you've written.
# This snippet is for when there are issues with

## ss_simple_segments_full_1_hardcode_pid1731.sql
--	Query to breakout events into legacy segmentation

CREATE TEMPORARY FUNCTION rank AS 'ABCxyz.QWERTY.hadoop.hive.udf.Rank';
SET mapred.map.output.compression.codec = ABCxyz.hadoop.compression.lzo.LzopCodec;
SET hive.cli.print.header = TRUE;
SET mapred.job.priority = HIGH;

SET partnerid = 1731;
SET golivedate = "2014-03-01";
--	abandondate is 15 days before golivedate

## clicks_per_day_w_7d_csum_advsql2.sql
SELECT
	day,
	clicks,
	SUM(clicks) OVER (order by day range between '7 days' preceding and current row) accumulated_clicks
FROM
	datamart.fact_network_stats_daily
WHERE
	network_id = 72
	AND affiliate_country_code = 'FR'
	AND banner_currency_id = 1

## revenue_by_client_advsql2.sql
WITH
revenue_by_client
AS
(
	SELECT
		f.day,
		c.client_country_name,
		c.client_name,
		SUM(f.revenue * er.rate) revenue_euro
	FROM

## quick_split_batch.py
# Editing to be able to split all files in a directory

import sys
import os # for getting the list of all files in the directory, when we use batch mode
import re # to find file matching a particular handle/pattern

a = sys.argv[0]
print '\n', sys.argv


## output_status_distrib_w_conf_status_min_max.json
{
  "hits": {
    "hits": [],
    "total": 123928,
    "max_score": 0.0
  },
  "_shards": {
    "successful": 20,
    "failed": 0,
    "total": 20

## total_room_Rate_ranges.json
{   "size": 0,
    "query": {
        "term": {"propertyId":"{{property_id}}"}
    },
    "aggs" : {
        "zero_or_not": {
            "range" : {
                "field" : "totalRoomRateInPropertyCurrency",
                "ranges" : [
                    {"from": 0, "to" : 0.1 },

## status_distrib_w_conf_status_min_max.json
{   "size": 0,
    "query": {
        "term": {"propertyId":"{{property_id}}"}
    },
    "aggs": {
        "pms_status_code": {
            "terms" : { "field" : "confirmationStatus"},
            "aggs": {
                "conf_status": {
                    "terms" : { "field" : "statusCode"},
	SELECT
	*,
	row_number () over () AS Row_N
	FROM Summer_Medals
	ORDER BY Row_N ASC;
	--------------------

	SELECT
	Year,
	row_number() over() AS Row_N
	import copy
	import random
	# Consider using the modules imported above.

	class Hat:
	def __init__(self, **kwargs):
	self.d = kwargs
	self.contents = [
	key for key, val in kwargs.items() for num in range(val)
	]
	# Within a Jupyter Notebook
	import sys
	sys.path.append("C:/somewhere/else/not/in/the/tree/of/this/jpfile")
	# Now we can import Windows directories as packages, and refer to Python files within them
	# the folder jpyfile need not have an __init__.py file in it
	# folders that we import from within jpfile should
	from folder_w_in_jpfile import my_modular_code
	# folder_w_in_jpfile contains an __init__.py file whihc can be empty
	# my_modular_code is a file my_modular_code.py with any other Python code you've written.
	# This snippet is for when there are issues with
	-- Query to breakout events into legacy segmentation

	CREATE TEMPORARY FUNCTION rank AS 'ABCxyz.QWERTY.hadoop.hive.udf.Rank';
	SET mapred.map.output.compression.codec = ABCxyz.hadoop.compression.lzo.LzopCodec;
	SET hive.cli.print.header = TRUE;
	SET mapred.job.priority = HIGH;

	SET partnerid = 1731;
	SET golivedate = "2014-03-01";
	-- abandondate is 15 days before golivedate
	SELECT
	day,
	clicks,
	SUM(clicks) OVER (order by day range between '7 days' preceding and current row) accumulated_clicks
	FROM
	datamart.fact_network_stats_daily
	WHERE
	network_id = 72
	AND affiliate_country_code = 'FR'
	AND banner_currency_id = 1
	WITH
	revenue_by_client
	AS
	(
	SELECT
	f.day,
	c.client_country_name,
	c.client_name,
	SUM(f.revenue * er.rate) revenue_euro
	FROM
	# Editing to be able to split all files in a directory

	import sys
	import os # for getting the list of all files in the directory, when we use batch mode
	import re # to find file matching a particular handle/pattern

	a = sys.argv[0]
	print '\n', sys.argv
	{
	"hits": {
	"hits": [],
	"total": 123928,
	"max_score": 0.0
	},
	"_shards": {
	"successful": 20,
	"failed": 0,
	"total": 20
	{ "size": 0,
	"query": {
	"term": {"propertyId":"{{property_id}}"}
	},
	"aggs" : {
	"zero_or_not": {
	"range" : {
	"field" : "totalRoomRateInPropertyCurrency",
	"ranges" : [
	{"from": 0, "to" : 0.1 },