Dataset: Air Pollution At São Paulo, Brazil, Since 2013

About this Dataset

Air Pollution At São Paulo, Brazil, Since 2013

Content

This is an historical series for all CETESB air pollution measurement stations since May, 2013. This represents all coverage of the kind associated with the State of São Paulo, Brazil.

The values on the rows represents the index of pollution, where 0-50 is 'good', 50-100 is 'moderate', 100-150 is 'bad', and 150+ is 'horrible', all of which according to some CETESB definition.

Also, I've included data containing raw addresses for the measurements stations, which could be used for an geospatial analysis

Acknowledgements

Thanks CETESB for providing the data in an very hard way to make it easily available for data analysis. I needed two days of webscraping to get all of that.

Inspiration

You have the entire air pollution data for the biggest Brazilian state since 2013. Is there any inspiration needed?

Tables

Estacoes Cetesb

@kaggle.danlessa_air_pollution_at_so_paulo_brazil_since_2013.estacoes_cetesb

15.52 KB
61 rows
15 columns


CREATE TABLE estacoes_cetesb (
  "data" TIMESTAMP,
  "efeito" VARCHAR,
  "endereco" VARCHAR,
  "id" BIGINT,
  "indice" DOUBLE,
  "msgsaude" VARCHAR,
  "municipio" VARCHAR,
  "nome" VARCHAR,
  "poluente" VARCHAR,
  "qualidade" VARCHAR,
  "situacao_rede" VARCHAR,
  "tipo_rede" VARCHAR,
  "x" DOUBLE,
  "y" DOUBLE,
  "id2" BIGINT
);

Cetesb

@kaggle.danlessa_air_pollution_at_so_paulo_brazil_since_2013.cetesb

24.4 MB
3355416 rows
12 columns


CREATE TABLE cetesb (
  "unnamed_0" BIGINT,
  "time" TIMESTAMP,
  "id" BIGINT,
  "mp10" DOUBLE,
  "trs" DOUBLE,
  "o3" DOUBLE,
  "no2" DOUBLE,
  "co" DOUBLE,
  "mp2_5" DOUBLE,
  "so2" DOUBLE,
  "benzeno" DOUBLE,
  "tolueno" DOUBLE
);