7effrey89

# %%
!pip install mltable

# %%
# AML to query delta table in lakehouse to pandas dataframe
from mltable import from_delta_lake

#url = "https://onelake.dfs.fabric.microsoft.com/ws_ramboll_data/bronze.Lakehouse/Tables/taxidatacsv"
abfs = "abfss://[email protected]/bronze.Lakehouse/Tables/taxidatacsv"
df2 = from_delta_lake(abfs).to_pandas_dataframe()

7effrey89

trigger:
  branches:
    include:
      - main

variables:
  pWorkspaceId: '<GUID OF FABRIC WORKSPACE>' #My Fabric Workspace ID
  pPipelineId: '<GUID OF FABRIC PIPELINE IN WORKSPACE>' #My Fabric Pipeline ID

stages:

7effrey89

trigger:
  branches:
    include:
      - main

variables:
  resourceGroupName: '<Name of Resource Group>' # My Resource Group Name
  dataFactoryName: '<Name of ADF instance>' # My Data Factory Name
  pipelineName: '<Name of Pipeline>' # My Data Factory Pipeline Name

7effrey89

from azure.storage.filedatalake import DataLakeServiceClient
from azure.identity import ClientSecretCredential

# Service principal credentials
app = "<app Registration Name>"    # App Registration Name
tenant_id = '<tenant_id>'          # Directory (tenant) ID
client_id = '<client_id>'          # Application (client) ID
client_secret = '<client_secret>'  # Client secret

# Storage account name

7effrey89

# Script to create searchable PDF from scan PDF or images using Azure Form Recognizer / Document Intelligence
#
# USAGE:
#   python Untitled-1.py <input_file> [-o <output_file>]
#
# ARGUMENTS:
#   <input_file>   Path to your PDF or image file (jpg, jpeg, tif, tiff, bmp, png).
#   -o <output_file> (optional) Name for the output searchable PDF.
#                    If omitted, output will be <input_file>.ocr.pdf
#

7effrey89

using Azure;
using Azure.AI.Translation.Document;

/// <summary>
/// This program demonstrates how to use Azure's Document Translation service to translate documents
/// stored in an Azure Blob Storage container from one language to another.
/// It authenticates using a custom endpoint and resource key, then submits a translation job,
/// waits for completion, and prints the status and results for each document.
/// https://learn.microsoft.com/en-us/azure/ai-services/translator/document-translation/how-to-guides/use-rest-api-programmatically?tabs=csharp
/// https://learn.microsoft.com/en-us/dotnet/api/overview/azure/ai.translation.document-readme?view=azure-dotnet

7effrey89

7effrey89

import os
import re

files_folder = "/lakehouse/default/Files/input"
csv_files = []

for root, dirs, files in os.walk(files_folder):
    for file in files:
        if file.endswith('.csv'):
            csv_files.append(os.path.join(root, file))

7effrey89

7effrey89