chdb-datastore

# Change this:
import pandas as pd
# To this:
import chdb.datastore as pd
# Everything else stays the same.

pip install chdb

1. "I have a file/database and want to analyze it with pandas"
   → DataStore.from_file() / from_mysql() / from_s3() etc.
   → See references/connectors.md

2. "I need to join data from different sources"
   → Create DataStores from each source, use .join()
   → See examples/examples.md #3-5

3. "My pandas code is too slow"
   → import chdb.datastore as pd — change one line, keep the rest

4. "I need raw SQL queries"
   → Use the chdb-sql skill instead

from datastore import DataStore
 
# Local file (auto-detects .parquet, .csv, .json, .arrow, .orc, .avro, .tsv, .xml)
ds = DataStore.from_file("sales.parquet")
 
# Database
ds = DataStore.from_mysql(host="db:3306", database="shop", table="orders", user="root", password="pass")
 
# Cloud storage
ds = DataStore.from_s3("s3://bucket/data.parquet", nosign=True)
 
# URI shorthand — auto-detects source type
ds = DataStore.uri("mysql://root:pass@db:3306/shop/orders")

result = ds[ds["age"] > 25]                                          # filter
result = ds[["name", "city"]]                                        # select columns
result = ds.sort_values("revenue", ascending=False)                  # sort
result = ds.groupby("dept")["salary"].mean()                         # groupby
result = ds.assign(margin=lambda x: x["profit"] / x["revenue"])     # computed column
ds["name"].str.upper()                                               # string accessor
ds["date"].dt.year                                                   # datetime accessor
result = ds1.join(ds2, on="id")                                      # join
result = ds.head(10)                                                 # preview
print(ds.to_sql())                                                   # see generated SQL

from datastore import DataStore
 
customers = DataStore.from_mysql(host="db:3306", database="crm", table="customers", user="root", password="pass")
orders = DataStore.from_file("orders.parquet")
 
result = (orders
    .join(customers, left_on="customer_id", right_on="id")
    .groupby("country")
    .agg({"amount": "sum", "rating": "mean"})
    .sort_values("sum", ascending=False))
print(result)

source = DataStore.from_mysql(host="db:3306", database="shop", table="orders", user="root", password="pass")
target = DataStore("file", path="summary.parquet", format="Parquet")
 
target.insert_into("category", "total", "count").select_from(
    source.groupby("category").select("category", "sum(amount) AS total", "count() AS count")
).execute()