BexTuychiev

This is a test gist. 13894950uijklakd#$%^&*'\\./

BexTuychiev

import optuna
import xgboost as xgb
from sklearn.metrics import mean_squared_error # or any other metric
from sklearn.model_selection import train_test_split

# Load the dataset
X, y = ... # load your  own
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Define the objective function for Optuna

BexTuychiev

import pandas as pd
import numpy as np
import string

# Set the desired number of rows and columns
num_rows = 10_000_000
num_cols = 10
chunk_size = 100_000

# Define an empty DataFrame to store the chunks

BexTuychiev

import time

import datatable as dt
import pandas as pd
import polars as pl

# Define a DataFrame to store the results
results_df = pd.DataFrame(
    columns=["Function", "Library", "Runtime (s)"]
)

BexTuychiev

import os
import random
import time

import numpy as np
import pandas as pd
from faker import Faker

# Set seed for reproducibility
random.seed(42)

BexTuychiev

FROM nvidia/cuda:11.2.0-runtime-ubuntu20.04

# install utilities
RUN apt-get update && \
   apt-get install --no-install-recommends -y curl

ENV CONDA_AUTO_UPDATE_CONDA=false \
   PATH=/opt/miniconda/bin:$PATH
RUN curl -sLo ~/miniconda.sh https://repo.anaconda.com/miniconda/Miniconda3-py38_4.9.2-Linux-x86_64.sh \
   && chmod +x ~/miniconda.sh \

BexTuychiev

$ dvc remove dvclive.dvc models.dvc
$ rm -rf dvclive models
$ git add - all
$ git commit -m "Remove all experiments"
$ git tag "cnn32"

BexTuychiev

$ dvc add models dvclive
$ git commit -am "exp: CNN All layers, 0.992 val accuracy"

BexTuychiev

$ git add - all
$ git commit -m "Update train.py to use a DVCLive logger"
$ git tag cnn-all-layers
$ python src/train.py

BexTuychiev

# Set the parameters
params = {
  "image_width": 30,
  "image_height": 30,
  "batch_size": 32,
  "learning_rate": 0.001,
  "n_epochs": 10
}

logger.log_params(params)