pdet

import duckdb
import time

def gen_tpch():
	con = duckdb.connect()
	con.execute("CALL dbgen(sf=20);")
	con.execute("COPY lineitem to 'lineitem.csv'")
	con.execute("COPY lineitem to 'lineitem.parquet'")
	con.execute("COPY lineitem TO 'lineitem_zstd.parquet' (FORMAT 'parquet', CODEC 'zstd', COMPRESSION_LEVEL 1);")

pdet

import threading
import psutil
import resource
import duckdb
import pyarrow as pa
import os
import time

def create_db():
    con = duckdb.connect("duck.db")

pdet

import duckdb
import pyarrow as pa
import pandas as pd
import time

def time_function(function):
	res = []
	for i in range (0,5):
		start_time = time.monotonic()
		ans = function()

pdet

import duckdb
import pyarrow as pa
import pandas as pd
import time
import pyarrow.compute as pc

def time_function(function):
  res = []
  for i in range (0,5):
    start_time = time.monotonic()

pdet

# Files used in the example: 
# !wget "https://d37ci6vzurychx.cloudfront.net/trip-data/yellow_tripdata_2016-01.parquet"
# !wget "https://d37ci6vzurychx.cloudfront.net/trip-data/yellow_tripdata_2016-02.parquet"

import duckdb
from duckdb.typing import *
import torch
import torch.nn as nn
import pyarrow as pa 

pdet

import torch
import torch.nn as nn
import duckdb
import pyarrow as pa 
import matplotlib.pyplot as plt

class LinearRegression(nn.Module):
    def __init__(self, input_dim, output_dim):
        super(LinearRegression, self).__init__()
        self.linear = nn.Linear(input_dim, output_dim)