NYC Taxi and Limousine Commission – Fahrtenaufzeichnungen für „Green Taxi“

# This is a package in preview.
from azureml.opendatasets import NycTlcGreen

from datetime import datetime
from dateutil import parser


end_date = parser.parse('2018-06-06')
start_date = parser.parse('2018-05-01')
nyc_tlc = NycTlcGreen(start_date=start_date, end_date=end_date)
nyc_tlc_df = nyc_tlc.to_pandas_dataframe()

nyc_tlc_df.info()

# Pip install packages
import os, sys

!{sys.executable} -m pip install azure-storage-blob
!{sys.executable} -m pip install pyarrow
!{sys.executable} -m pip install pandas

# Azure storage access info
azure_storage_account_name = "azureopendatastorage"
azure_storage_sas_token = r""
container_name = "nyctlc"
folder_name = "green"

from azure.storage.blob import BlockBlobServicefrom azure.storage.blob import BlobServiceClient, BlobClient, ContainerClient

if azure_storage_account_name is None or azure_storage_sas_token is None:
    raise Exception(
        "Provide your specific name and key for your Azure Storage account--see the Prerequisites section earlier.")

print('Looking for the first parquet under the folder ' +
      folder_name + ' in container "' + container_name + '"...')
container_url = f"https://{azure_storage_account_name}.blob.core.windows.net/"
blob_service_client = BlobServiceClient(
    container_url, azure_storage_sas_token if azure_storage_sas_token else None)

container_client = blob_service_client.get_container_client(container_name)
blobs = container_client.list_blobs(folder_name)
sorted_blobs = sorted(list(blobs), key=lambda e: e.name, reverse=True)
targetBlobName = ''
for blob in sorted_blobs:
    if blob.name.startswith(folder_name) and blob.name.endswith('.parquet'):
        targetBlobName = blob.name
        break

print('Target blob to download: ' + targetBlobName)
_, filename = os.path.split(targetBlobName)
blob_client = container_client.get_blob_client(targetBlobName)
with open(filename, 'wb') as local_file:
    blob_client.download_blob().download_to_stream(local_file)

# Read the parquet file into Pandas data frame
import pandas as pd

print('Reading the parquet file into Pandas data frame')
df = pd.read_parquet(filename)

# you can add your filter at below
print('Loaded as a Pandas data frame: ')
df

Für diese Kombination aus Plattform und Paket ist kein Beispiel verfügbar.

# This is a package in preview.
# You need to pip install azureml-opendatasets in Databricks cluster. https://video2.skills-academy.com/azure/data-explorer/connect-from-databricks#install-the-python-library-on-your-azure-databricks-cluster
from azureml.opendatasets import NycTlcGreen

from datetime import datetime
from dateutil import parser


end_date = parser.parse('2018-06-06')
start_date = parser.parse('2018-05-01')
nyc_tlc = NycTlcGreen(start_date=start_date, end_date=end_date)
nyc_tlc_df = nyc_tlc.to_spark_dataframe()

display(nyc_tlc_df.limit(5))

Für diese Kombination aus Plattform und Paket ist kein Beispiel verfügbar.

# Azure storage access info
blob_account_name = "azureopendatastorage"
blob_container_name = "nyctlc"
blob_relative_path = "green"
blob_sas_token = r""

# Allow SPARK to read from Blob remotely
wasbs_path = 'wasbs://%s@%s.blob.core.windows.net/%s' % (blob_container_name, blob_account_name, blob_relative_path)
spark.conf.set(
  'fs.azure.sas.%s.%s.blob.core.windows.net' % (blob_container_name, blob_account_name),
  blob_sas_token)
print('Remote blob path: ' + wasbs_path)

# SPARK read parquet, note that it won't load any data yet by now
df = spark.read.parquet(wasbs_path)
print('Register the DataFrame as a SQL temporary view: source')
df.createOrReplaceTempView('source')

# Display top 10 rows
print('Displaying top 10 rows: ')
display(spark.sql('SELECT * FROM source LIMIT 10'))

# This is a package in preview.
from azureml.opendatasets import NycTlcGreen

from datetime import datetime
from dateutil import parser


end_date = parser.parse('2018-06-06')
start_date = parser.parse('2018-05-01')
nyc_tlc = NycTlcGreen(start_date=start_date, end_date=end_date)
nyc_tlc_df = nyc_tlc.to_spark_dataframe()

# Display top 5 rows
display(nyc_tlc_df.limit(5))

# Display data statistic information
display(nyc_tlc_df, summary = True)

Für diese Kombination aus Plattform und Paket ist kein Beispiel verfügbar.

# Azure storage access info
blob_account_name = "azureopendatastorage"
blob_container_name = "nyctlc"
blob_relative_path = "green"
blob_sas_token = r""

# Allow SPARK to read from Blob remotely
wasbs_path = 'wasbs://%s@%s.blob.core.windows.net/%s' % (blob_container_name, blob_account_name, blob_relative_path)
spark.conf.set(
  'fs.azure.sas.%s.%s.blob.core.windows.net' % (blob_container_name, blob_account_name),
  blob_sas_token)
print('Remote blob path: ' + wasbs_path)

# SPARK read parquet, note that it won't load any data yet by now
df = spark.read.parquet(wasbs_path)
print('Register the DataFrame as a SQL temporary view: source')
df.createOrReplaceTempView('source')

# Display top 10 rows
print('Displaying top 10 rows: ')
display(spark.sql('SELECT * FROM source LIMIT 10'))