mneedham

pip install confluent-kafka avro urllib3 requests fastavro

mneedham

# Dataset: https://www.kaggle.com/datasets/wilmerarltstrmberg/recipe-dataset-over-2m

import duckdb

db1 = duckdb.connect('db1.duck.db')
db2 = duckdb.connect('db2.duck.db')

db1.sql("""
CREATE OR REPLACE TABLE recipes AS 
FROM read_csv_auto('recipes_data.csv', header=True)

mneedham

Intro to Window Functions

Queries based on the Citi bikes dataset using DuckDB.

Associated YouTube video: https://youtu.be/u9AtW5P0m5c

Import data

CREATE OR REPLACE TABLE bikeStations AS
FROM read_csv_auto('data/*.csv', types={"station_id": "VARCHAR"}) 

mneedham

SQL Aggregate vs Aggregate Window Functions

Queries based on the Citi bikes dataset using DuckDB.

Associated YouTube video: https://www.youtube.com/watch?v=KTIBhsIoCvk

Load the data

CREATE OR REPLACE TABLE bikeStations AS

mneedham

import duckdb
import pandas as pd

con = duckdb.connect('atp-matches.db')

con.sql("INSTALL httpfs")
con.sql("LOAD httpfs")

csv_files = [
    f"https://raw.githubusercontent.com/JeffSackmann/tennis_atp/master/atp_matches_{year}.csv"

mneedham

CREATE CONSTRAINT ON(u:User)
ASSERT u.id IS unique;
:param keysToKeep => ["name", "username", "bio", "following", "followers"];
CALL apoc.load.json("https://gist.github.com/mneedham/3c6a59fb5e7d87e20a2f5f1ae4fa2920/raw/9d7c57997c09b3a105556adb6c6f1819792a4db4/query.json")
YIELD value
MERGE (u:User {id: value.user.id })
SET u += value.user
FOREACH (following IN value.following |  
  MERGE (f1:User {id: following})  
  MERGE (u)-[:FOLLOWS]->(f1))

mneedham

CREATE OR REPLACE TABLE players
AS SELECT * FROM read_csv_auto('atp_players.csv', SAMPLE_SIZE=-1);

CREATE OR REPLACE TABLE rankings AS 
select * 
from 'atp_rankings_*.csv';

SELECT player_id, name_first, name_last
FROM players 
LIMIT 5;

mneedham

# Headless service to provide DNS lookup
apiVersion: v1
kind: Service
metadata:
  labels:
    app: neo4j
  name: neo4j
spec:
  clusterIP: None
  ports:

mneedham

import json
import os
import luigi
import requests

from collections import Counter
from luigi.contrib.external_program import ExternalProgramTask

class Meetup(luigi.WrapperTask):
    def run(self):

mneedham

# Dataset from https://blogs.oracle.com/bigdataspatialgraph/intuitive-explanation-of-personalized-page-rank-and-its-application-in-recommendation

import operator

import networkx as nx

G = nx.Graph()

G.add_nodes_from(["John", "Mary", "Jill", "Todd",
                  "iPhone5", "Kindle Fire", "Fitbit Flex Wireless", "Harry Potter", "Hobbit"])