maltzsama

WITH daily_sales AS (
    SELECT
        p.producer_id,
        EXTRACT(DOW FROM s.purchase_date::DATE) AS day_of_week,
        EXTRACT(YEAR FROM s.purchase_date::DATE) AS year,
        COUNT(s.purchase_id) AS total_sales
    FROM
        "case".sales s
    JOIN "case".products p ON
        p.product_id = s.product_id

maltzsama

Clearing all cache from a Windows system can help improve performance and free up disk space. Here are the steps to clear various types of cache on Windows:

1. Clear Temporary Files Cache

1. Press Windows + R to open the Run dialog box.
2. Type temp and press Enter. This will open the Temp folder.
3. Select all files and folders (Ctrl + A) and press Delete. You may need administrator permissions for some files.
4. Repeat the process with %temp% in the Run dialog box.

2. Clear System Cache

1. Press Windows + R to open the Run dialog box.

maltzsama

use std::fs::File;
use parquet::arrow::arrow_reader::ParquetRecordBatchReaderBuilder;

fn main(){
    let file_path = "Flights_1m.parquet";
    let file = File::open(file_path).unwrap();
    // let builder = ParquetRecordBatchReaderBuilder::try_new(file).unwrap();
    let builder = ParquetRecordBatchReaderBuilder::try_new(file).unwrap();
    println!("Converted arrow schema is: {}", builder.schema());
    let mut reader = builder.build().unwrap();

maltzsama

WITH RECURSIVE
  cpf(digits, len) AS (
    SELECT ARRAY[CAST(FLOOR(RANDOM() * 10) AS INTEGER)], 1
    UNION ALL
    SELECT digits || CAST(FLOOR(RANDOM() * 10) AS INTEGER), len + 1
    FROM cpf
    WHERE len < 9
  ),
  cpf_with_first_verifier(digits, len) AS (
    SELECT digits || (CASE WHEN 11 - MOD(SUM((10 - i + 1) * v), 11) >= 10 THEN 0 ELSE 11 - MOD(SUM((10 - i + 1) * v), 11) END), len + 1

maltzsama

Exercicio - 1

Baseado na api da FIPE Crie um script python capaz de salvar os dados retornados do endereço de marcas em uma tabela SQLite

Tabela:

• id
• name

recomendação: usar a biblioteca requests do python

maltzsama

O erro "TypeError: cannot pickle 'SSLContext' object" ocorre quando você está tentando serializar um objeto SSLContext, que não é serializável por padrão no PySpark.

Para contornar esse erro, você pode definir uma função personalizada para converter cada linha em JSON usando a biblioteca json do Python. Aqui está um exemplo de como fazer isso:

from pyspark.sql import SparkSession
import json

# Função para converter uma linha em JSON
def row_to_json(row):

maltzsama

from pyspark.sql import SparkSession
import boto3

# Configurar a sessão Spark
spark = SparkSession.builder.getOrCreate()

# Criar DataFrame com dados de exemplo
data = [("mensagem1",), ("mensagem2",), ("mensagem3",)]
df = spark.createDataFrame(data, ["message"])

maltzsama

from pyspark.sql import SparkSession

def init_spark():
  spark = SparkSession.builder.config("spark.jars", "/postgresql-42.5.4.jar")\
    .master("local").appName("PySpark_Postgres_test").getOrCreate()

  sc = spark.sparkContext
  return spark,sc

def main():

maltzsama

-- create delta table on athena
CREATE EXTERNAL TABLE cliente
LOCATION 's3://bucket_name/cliente/'
TBLPROPERTIES ('table_type' = 'DELTA')

maltzsama

#!/usr/bin/env python
# -*- coding: utf-8 -*-
def min_time(string):
    count = 0
    position = 0
    string = string.lower()
    for element in range(len(string)):
        unicode_value = ord(string[element]) - 97
        first_distance = abs(position - unicode_value)
        second_distance = 26 - abs(position - unicode_value)