pandas からの移行

# Before (pandas)
import pandas as pd

# After (DataStore)
from chdb import datastore as pd

# All these work the same
df = pd.read_csv("data.csv")
df = pd.read_parquet("data.parquet")
df = pd.read_json("data.json")
df = pd.read_excel("data.xlsx")

# Boolean indexing
df[df['age'] > 25]
df[(df['age'] > 25) & (df['city'] == 'NYC')]

# query() method
df.query('age > 25 and salary > 50000')

# Column selection
df['name']
df[['name', 'age']]

# Row selection
df.head(10)
df.tail(10)
df.iloc[0:100]

# GroupBy
df.groupby('city')['salary'].mean()
df.groupby(['city', 'dept']).agg({'salary': ['sum', 'mean']})

df.sort_values('salary', ascending=False)
df.sort_values(['city', 'age'])

df['name'].str.upper()
df['name'].str.contains('John')
df['name'].str.len()

df['date'].dt.year
df['date'].dt.month
df['date'].dt.dayofweek

df.to_csv("output.csv")
df.to_parquet("output.parquet")
df.to_json("output.json")

# Executes immediately
result = df[df['age'] > 25]
print(type(result))  # pandas.DataFrame

# Builds query, doesn't execute yet
result = ds[ds['age'] > 25]
print(type(result))  # DataStore (lazy)

# Executes when you need the data
print(result)        # Triggers execution
df = result.to_df()  # Triggers execution

df.drop(columns=['col'], inplace=True)

ds = ds.drop(columns=['col'])  # Assign the result

# This may not work as expected
df == ds  # pandas doesn't know DataStore

# Do this instead
df.equals(ds.to_pandas())

# pandas preserves order
df = pd.read_csv("data.csv")

# DataStore - use sort for guaranteed order
ds = pd.read_csv("data.csv")
ds = ds.sort('id')  # Explicit ordering

# pandas
import pandas as pd
df = pd.read_csv("data.csv")
result = df[df['amount'] > 100].groupby('category')['amount'].sum()
result.to_csv("output.csv")

# DataStore - same code works!
from chdb import datastore as pd
df = pd.read_csv("data.csv")
result = df[df['amount'] > 100].groupby('category')['amount'].sum()
result.to_csv("output.csv")

from chdb import datastore as pd

# Fast DataStore operations
ds = pd.read_csv("large_data.csv")
ds = ds.filter(ds['date'] >= '2024-01-01')
ds = ds.filter(ds['amount'] > 100)

# Convert to pandas for specific features
df = ds.to_df()
df_pivoted = df.pivot_table(...)  # pandas-specific

from chdb import datastore as pd
import pandas

# Start with DataStore for fast filtering
ds = pd.read_csv("huge_file.csv")  # 10M rows
ds = ds.filter(ds['year'] == 2024)  # Fast SQL filter
ds = ds.select('col1', 'col2', 'col3')  # Column pruning

# Convert for pandas-specific operations
df = ds.to_df()  # Now only ~100K rows
result = df.apply(complex_custom_function)  # pandas

from chdb.datastore.config import config
config.enable_debug()

# View the SQL being generated
ds.filter(ds['x'] > 10).explain()

# Bad: Multiple small executions
for i in range(1000):
    result = ds.filter(ds['id'] == i).to_df()

# Good: Single execution
result = ds.filter(ds['id'].isin(ids)).to_df()

# Check types
print(ds.dtypes)

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

# Keep both imports
import pandas as pd
from chdb import datastore as ds

# Compare results
pdf = pd.read_csv("data.csv")
dsf = ds.read_csv("data.csv")

# Verify they match
assert pdf.equals(dsf.to_pandas())

from chdb import datastore as pd

# Let DataStore handle the heavy lifting
ds = pd.read_csv("data.csv")
ds = ds.filter(ds['year'] == 2024)  # SQL

# Convert for custom work
df = ds.to_df()
result = df.apply(my_custom_function)

from chdb import datastore as ds
import pandas as pd

# DataStore to pandas
df = ds_result.to_pandas()

# pandas to DataStore  
ds = ds.DataFrame(pd_result)

def test_my_function():
    result = my_function()
    expected = pd.DataFrame(...)
    pd.testing.assert_frame_equal(result.to_pandas(), expected)

from chdb import datastore as pd

ds = pd.read_csv("data.csv")
ds.head()  # Displays nicely in Jupyter