BexTuychiev

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

import lightning as L

from torch.utils.data import DataLoader
from torchvision import datasets, transforms
from lightning.pytorch.callbacks import ModelCheckpoint

BexTuychiev

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

# Device configuration
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

BexTuychiev

import pandas as pd
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.ensemble import RandomForestRegressor
import gradio as gr

# Load the diamonds dataset

BexTuychiev

import json

import pandas as pd
from joblib import dump
from sklearn.linear_model import SGDRegressor
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder, StandardScaler

BexTuychiev

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder, OrdinalEncoder, StandardScaler


def preprocess_data(data_path, test_size=0.2, target_name="price"):
    """
    Loads data, splits into train/test, performs normalization and one-hot encoding,
    saves preprocessed data with targets as CSV files.

BexTuychiev

import pandas as pd
from xgboost import XGBClassifier
from pathlib import Path
from sklearn.preprocessing import LabelEncoder
from google.cloud import storage
import joblib


# Path to your CSV file in GCS bucket
gcs_path = "gs://vertex-tutorial-bucket-bex"

BexTuychiev

Feature	Jupyter Notebooks	Databricks Notebooks
Platform	Open-source, runs locally or on cloud platforms	Exclusive to the Databricks platform
Collaboration and Sharing	Limited collaboration features, manual sharing	Built-in collaboration, real-time concurrent editing
Execution	Relies on local or external servers	Execution on Databricks clusters
Integration with Big Data	Can be integrated with Spark, requires additional configurations	Native integration with Apache Spark, optimized for big data
Built-in Features	External tools/extensions for version control, collaboration, and visualization	Integrated with Databricks-specific features like Delta Lake, built-in support for collaboration and analytics tools
Cost and Scaling	Local installations are often free, cloud-based solutions may have costs	Paid service, costs depend on usage, scales seamlessly with Databricks clusters
Ease of Use	Familiar and widely used in the data science commun

BexTuychiev

import pandas as pd
import seaborn as sns

# Load the dataset from Seaborn
diamonds = sns.load_dataset("diamonds")

# Create a Pandas DataFrame
df = pd.DataFrame(diamonds)

# Save the DataFrame directly as a Parquet file

BexTuychiev

import pandas as pd
import seaborn as sns

# Load the dataset from Seaborn
diamonds = sns.load_dataset("diamonds")

# Create a Pandas DataFrame
df = pd.DataFrame(diamonds)

# Save the DataFrame directly as a Parquet file

BexTuychiev

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