与 pandas 的关键区别

import pandas as pd

df = pd.read_csv("data.csv")  # Loads entire file NOW
result = df[df['age'] > 25]   # Filters NOW
grouped = result.groupby('city')['salary'].mean()  # Aggregates NOW

from chdb import datastore as pd

ds = pd.read_csv("data.csv")  # Just records the source
result = ds[ds['age'] > 25]   # Just records the filter
grouped = result.groupby('city')['salary'].mean()  # Just records

# Execution happens here:
print(grouped)        # Executes when displaying
df = grouped.to_df()  # Or when converting to pandas

df['col']           # Returns pd.Series
df[['a', 'b']]      # Returns pd.DataFrame
df[df['x'] > 10]    # Returns pd.DataFrame
df.groupby('x')     # Returns DataFrameGroupBy

ds['col']           # Returns ColumnExpr (lazy)
ds[['a', 'b']]      # Returns DataStore (lazy)
ds[ds['x'] > 10]    # Returns DataStore (lazy)
ds.groupby('x')     # Returns LazyGroupBy

# Get pandas DataFrame
df = ds.to_df()
df = ds.to_pandas()

# Get pandas Series from column
series = ds['col'].to_pandas()

# Or trigger execution
print(ds)  # Automatically converts for display

df = pd.read_csv("data.csv")
print(df.head())  # Always same order as file

ds = pd.read_csv("data.csv")
print(ds.head())  # Matches file order

# Filter preserves order
ds_filtered = ds[ds['age'] > 25]  # Same order as pandas

df.drop(columns=['col'], inplace=True)  # Modifies df
df.fillna(0, inplace=True)              # Modifies df
df.rename(columns={'old': 'new'}, inplace=True)

ds = ds.drop(columns=['col'])           # Returns new DataStore
ds = ds.fillna(0)                       # Returns new DataStore
ds = ds.rename(columns={'old': 'new'})  # Returns new DataStore

df = df.set_index('id')
df.loc['user123']           # Label-based access
df.loc['a':'z']             # Label-based slicing
df.reset_index()
df.index.name = 'user_id'

# Basic operations work
ds.loc[0:10]               # Integer position
ds.iloc[0:10]              # Same as loc for DataStore

# For pandas-style index operations, convert first
df = ds.to_df()
df = df.set_index('id')
df.loc['user123']

import pandas as pd
from chdb import datastore as ds

pdf = pd.DataFrame({'a': [1, 2, 3]})
dsf = ds.DataFrame({'a': [1, 2, 3]})

# This doesn't work as expected
pdf == dsf  # pandas doesn't know DataStore

# Solution: convert DataStore to pandas
pdf.equals(dsf.to_pandas())  # True

# DataStore.equals() also works
dsf.equals(pdf)  # Compares with pandas DataFrame

df['col'].dtype  # int64, float64, object, datetime64, etc.

ds['col'].dtype  # Int64, Float64, String, DateTime, etc.

# Types are converted when going to pandas
df = ds.to_df()
df['col'].dtype  # Now pandas type

# Force specific type
ds['col'] = ds['col'].astype('int64')

df = pd.read_csv("huge.csv")  # 10GB in memory!

ds = pd.read_csv("huge.csv")  # Just metadata
ds = ds.filter(ds['year'] == 2024)  # Still just metadata

# Only filtered result is loaded
df = ds.to_df()  # Maybe only 1GB now

# May see ClickHouse-style errors
# "Code: 62. DB::Exception: Syntax error..."

# View the SQL to debug
print(ds.to_sql())

# See execution plan
ds.explain()

# Enable debug logging
from chdb.datastore.config import config
config.enable_debug()