datavudeja

# conda activate bert-github

#%%
import pandas as pd
import numpy as np
import os
import glob
import pathlib
from tqdm import tqdm
from bs4 import BeautifulSoup

datavudeja

# Splits the values and expands them in multiple numbered columns
temp_df = df[column].str.split("|", expand=True).fillna('')

# One-Hot encodes all the values for each column
temp_df = pd.get_dummies(temp_df).astype('uint8')

# Removes the "N_" prefixe for each column to expose duplicates
temp_df = remove_prefixes(temp_df)

# Merges the duplicate columns

datavudeja

#! /usr/bin/env python3

# Usage:
#  $ python3 this.py > output.csv
#  $ nkf --overwrite --oc=UTF-8-BOM output.csv

import glob
import hashlib
import os
import sys

datavudeja

import pandas as pd
import hashlib

def hash_dataframe(df):
    """
    Generate a hash for a DataFrame using the SHA-256 algorithm.
    
    This function creates a hash for each row of the DataFrame using pandas' `hash_pandas_object` 
    and then hashes the resulting array of row hashes using `hashlib.sha256`.
    

datavudeja

import pandas as pd
import json

def readJson(filename,) -> dict:
    """ 
    Reads a json file and returns a dictionary
    """
    file = open(filename, 'r')
    data = file.read()
    file.close()

datavudeja

#2022-07-25 Argparse Parse from Command Line

"C:\<Entwicklung>\WORK_JUPYTER\root\tools\argparse_template.py"

""" template code for argparse """

datavudeja

import pandas as pd
import pyodbc

class DataImporter:
    """
    This Python class takes in a pandas DataFrame from a CSV file and a SQL Server connection string, as 
    well as a name for the SQL table where the data will be imported. The class compares the columns of 
    the DataFrame to those in the SQL table and ensures that at least 50% of the fields match. If there 
    are missing fields, the class adds them to the SQL table using the same naming convention as existing 
    fields. All new fields are created as varchar fields by default. Once the SQL table has all the fields 

datavudeja

import pandas as pd


@pd.api.extensions.register_series_accessor("nullsafe")
class NullSafeSeriesAccessor:
    """
    Null-safe comparison accessor for Pandas Series.

    This is equivalent to a null-safe equal operator in SQL (<=>) where

datavudeja

# This example is copied verbatim from one of the codebases I contribute to.
# Unfortunately, I can't copy it, so I tried to extract the scenario as it was,
# as an example that I could share publicly.
#
# I'm sure the example could be simplified, but I thought it would be better to
# show it as it is, and leave any conclusions to whomever is going to read it.
#

from typing import Union, TypeVar, Callable
from typing_extensions import TypeAlias, Literal, overload

datavudeja

"""Unit conversion"""

from dataclasses import dataclass
from functools import total_ordering
from enum import Enum
from typing import Callable, NamedTuple

class UnitDesc(NamedTuple):
    """Unit description"""
    scale: float