13 lines
460 B
Python
13 lines
460 B
Python
import pyarrow.parquet as pq
|
|
import pandas as pd
|
|
t = pq.read_table("/mnt/d/PaperTrader/research/hl_data/minutes/20260415/15.parquet")
|
|
print("SCHEMA:"); print(t.schema)
|
|
df = t.to_pandas()
|
|
print("SHAPE:", df.shape)
|
|
print("HEAD:")
|
|
print(df.head(3).to_string())
|
|
for c in df.columns:
|
|
print(f" {c}: dtype={df[c].dtype} nunique={df[c].nunique() if df[c].nunique() < 50 else '>50'}")
|
|
if "coin" in df.columns:
|
|
print("COINS:", sorted(df["coin"].unique())[:30])
|