Бесплатный Apache Parquet Viewer онлайн – открывайте и изучайте файлы Parquet

# Installation: pip install pandas
import pandas as pd

df = pd.read_parquet('path/to/file.parquet')
print(df.head())

# Installation: pip install duckdb
import duckdb

# Query directly from the file
result = duckdb.sql("SELECT * FROM 'path/to/file.parquet' LIMIT 10").fetchdf()
print(result)

# Installation: pip install clickhouse-connect
import clickhouse_connect

client = clickhouse_connect.get_client(host='localhost', port=8123)
query = "SELECT * FROM file('path/to/file.parquet') LIMIT 10"
result = client.query(query).result_set
print(result)

// Installation: npm install parquetjs
const parquet = require('parquetjs');

async function readParquet() {
    let reader = await parquet.ParquetReader.openFile('example.parquet');
    let cursor = reader.getCursor();
    let record = null;
    while (record = await cursor.next()) {
        console.log(record);
    }
    await reader.close();
}

// Required dependencies: parquet-avro, parquet-hadoop
import org.apache.hadoop.fs.Path;
import org.apache.parquet.hadoop.ParquetReader;
import org.apache.parquet.avro.AvroParquetReader;
import org.apache.avro.generic.GenericRecord;

Path path = new Path("example.parquet");
try (ParquetReader<GenericRecord> reader = AvroParquetReader.<GenericRecord>builder(path).build()) {
    GenericRecord record;
    while ((record = reader.read()) != null) {
        System.out.println(record);
    }
}