import duckdb

def compare_schemas(file1, file2):
    """
    Compare schemas of two datasets and find differences.
    Args:
        file1 (str): Path to the first dataset (CSV/Parquet).
        file2 (str): Path to the second dataset (CSV/Parquet).
    Returns:
        list: Schema differences.
    """
    con = duckdb.connect()
    schema1 = con.execute(f"DESCRIBE SELECT * FROM read_csv_auto('{file1}')").fetchall()
    schema2 = con.execute(f"DESCRIBE SELECT * FROM read_csv_auto('{file2}')").fetchall()
    return {"file1_schema": schema1, "file2_schema": schema2}

# Example Usage
differences = compare_schemas("data1.csv", "data2.csv")
print(differences)
Copy code

#!/bin/bash
function remove_duplicates() {
    input_file="$1"  # Input CSV file with duplicates
    output_file="$2" # Deduplicated output CSV file
    # Use DuckDB to remove duplicate rows and write the cleaned data to a new CSV file.
    duckdb -c "COPY (SELECT DISTINCT * FROM read_csv_auto('$input_file')) TO '$output_file' (FORMAT CSV, HEADER TRUE);"
}

#Usage remove_duplicates "input_data.csv" "cleaned_data.csv"
Copy code

import duckdb

def query_json(file_path, query):
    """
    Query JSON data directly using DuckDB.
    Args:
        file_path (str): Path to the JSON file.
        query (str): SQL query to execute on the JSON data.
    Returns:
        pandas.DataFrame: Query results as a Pandas DataFrame.
    """
    con = duckdb.connect()
    # Execute the query on the JSON file and fetch the results as a Pandas DataFrame.
    df = con.execute(f"SELECT * FROM read_json_auto('{file_path}') WHERE {query}").df()
    return df

# Example Usage
result = query_json("./json/query_20min.json", "scheduled = true")
print(result)
Copy code

-- For more info on DSVs (I'm not the author): https://matthodges.com/posts/2024-08-12-csv-bad-dsv-good/
CREATE OR REPLACE MACRO read_dsv(path_spec)
 AS TABLE
(
with _lines as (
    select 
        filename
        ,regexp_split_to_array(content, '\x1e') as content
    from read_text(path_spec )
)
, _cleanup as (
    select 
        filename
        ,regexp_split_to_array(content[1],'\x1f') as header
        ,generate_subscripts(content[2:],1) as linenum
        ,unnest((content[2:]).list_filter(x -> trim(x) != '').list_transform(x -> x.regexp_split_to_array('\x1f'))) as line
    from _lines
)
select
    filename
    ,linenum
    ,unnest(map_entries(map(header, line)), recursive := true) as kv
from _cleanup
);
Copy code

-- You can use the same path specification as you would with read_text or read_csv, this includes globbing.
-- Trying to include the pivot statement in the macro isn't possible, as you then have to explicitly define the column values (which defeats the purpose of this implementation)
pivot read_dsv("C:\Temp\csv\*.csv")
on key
using first(value)
group by filename, linenum
order by filename, linenum
Copy code

SELECT 
    COLUMNS(t1.*) AS 't1_\0',
    COLUMNS(t2.*) AS 't2_\0'
FROM range(10) t1 
JOIN range(10) t2 ON t1.range = t2.range
Copy code

// generate_series(start, stop, step)
// get all even numbers, starting at 0 up to and including 100
SELECT * FROM generate_series(0,100,2);
Copy code

// range(start, stop, step)
// get all even numbers, starting at 0 up to and including 98
SELECT * FROM range(0,100,2);
Copy code

// Using range() as a column value instead of a table
// in your SQL statement will return an array of the
// numbers in the range
SELECT range(0,100,2)
Copy code