File Downloads

{entity}_{platform}_{date_or_range}_{random_id}.parquet.gz

fills_polymarket_2024-01-15_a7k9m2b1.parquet.gz
markets_kalshi_2024-01-10_to_2024-01-15_x3l8n9q2.parquet.gz
markets_polymarket_2024-01_m7q1k3n5.parquet.gz

import pandas as pd

df = pd.read_parquet('fills_polymarket_2024-01-15_a7k9m2b1.parquet.gz')

print(df.head())
print(df.dtypes)
print(df.describe())

import polars as pl

df = pl.read_parquet('fills_polymarket_2024-01-15_a7k9m2b1.parquet.gz')

print(df.head())
print(df.schema)
print(df.describe())

import polars as pl

df = pl.read_parquet('fills_polymarket_2024-01-15_a7k9m2b1.parquet.gz')

# High-value fills
high_value = df.filter(pl.col('size') > 1000)
print(high_value)

# Group by platform and sum size
by_platform = df.groupby('platform').agg(pl.col('size').sum())
print(by_platform)

import { readParquet } from 'parquet-wasm';
import fs from 'fs';
import { gunzipSync } from 'zlib';

const compressed = fs.readFileSync('fills_polymarket_2024-01-15_a7k9m2b1.parquet.gz');
const buffer = gunzipSync(compressed);
const table = readParquet(buffer);

console.log(table.schema);
console.log(`Total rows: ${table.numRows}`);

import pandas as pd

# Weekly export (created every Monday)
fills = pd.read_parquet('fills_polymarket_2024-01-14_w2k7m1n3.parquet.gz')

print(f"Total fills: {len(fills)}")
print(fills.groupby('platform')['size'].sum())

import pandas as pd

# Monthly markets export (created on 1st of month)
markets = pd.read_parquet('markets_kalshi_2024-01_m7q1k3n5.parquet.gz')

print(f"Total markets: {len(markets)}")
print(markets.groupby('category')['status'].value_counts())