File piu grande copia incolla.

Si ma la libreria Azurel è già presente ecco la risposta.
Grazie

OK ecco il percorso allegato della installazione

import subprocess
import codecs
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
import os
import re
import time
import atexit
import seaborn as sns
import matplotlib.pyplot as plt

from pyspark import SparkConf
from pyspark import SparkContext
from pyspark import SQLContext
import pyspark.sql.functions as F
from pyspark.sql.functions import concat, col, udf, lag, date_add, explode, lit, unix_timestamp
from pyspark.sql.functions import month, weekofyear, dayofmonth
from pyspark.sql.types import *
from pyspark.sql.types import DateType
from pyspark.sql.dataframe import *
from pyspark.sql.window import Window
from pyspark.sql import Row
from pyspark.ml.classification import *
from pyspark.ml.feature import StringIndexer, OneHotEncoder, VectorAssembler, VectorIndexer
from pyspark.ml.feature import StandardScaler, PCA, RFormula
from pyspark.ml import Pipeline, PipelineModel

start_time = time.time()

from pyspark import SQLContext
# Import data from Azure Blob Storage
dataFile = "wasb://sampledata@pysparksampledata.blob.core.windows.net/sampledata.csv"
dataFileSep = ','
df = SQLContext.read.csv(dataFile, header=True, sep=dataFileSep, inferSchema=True, nanValue="", mode='PERMISSIVE')

# Import data from the home directory on your machine 
# dataFile = '/home/katlin/Desktop/PysparkExample/sampledata.csv'

AttributeError Traceback (most recent call last)
<ipython-input-2-feb6a732221b> in <module>()
3 dataFile = "wasb://sampledata@pysparksampledata.blob.core.windows.net/sampledata.csv"
4 dataFileSep = ','
----> 5 df = SQLContext.read.csv(dataFile, header=True, sep=dataFileSep, inferSchema=True, nanValue="", mode='PERMISSIVE')
6
7 # Import data from the home directory on your machine

AttributeError: 'property' object has no attribute 'csv'
sia in Jupyter che in Pynthon mi da lo stesso erroe sopra riportatoGrazie

## Setup our environment by importing required libraries

import time

import os

import glob

import urllib




# Read csv file from URL directly

import pandas as pd




# For Azure blob storage access

from azure.storage.blob import BlockBlobService

from azure.storage.blob import PublicAccess




# For creating some preliminary EDA plots.

%matplotlib inline

import matplotlib.pyplot as plt

from ggplot import *




from datetime import datetime




# Setup the pyspark environment

from pyspark.sql import SparkSession




# For logging model evaluation parameters back into the

# AML Workbench run history plots.

import logging

from azureml.logging import get_azureml_logger




amllog = logging.getLogger("azureml")

amllog.level = logging.INFO




# Turn on cell level logging.

%azureml history on

%azureml history show




# Time the notebook execution.

# This will only make sense if you "Run All" cells

tic = time.time()




logger = get_azureml_logger() # logger writes to AMLWorkbench runtime view

spark = SparkSession.builder.getOrCreate()




# Telemetry

logger.log('amlrealworld.predictivemaintenance.data_ingestion','true')




mi da il seguente errore:

Traceback (most recent call last)
<ipython-input-1-089d6c991973> in <module>()
25 # AML Workbench run history plots.
26 import logging
---> 27 from azureml.logging import get_azureml_logger
28
29 amllog = logging.getLogger("azureml")

ImportError: No module named logging

sia in Python 2.7.14 che jupyter, anche se il logging è stato installato regolarmente Grazie

Per il seguente file in Python 2.7.14 e Jupyther
import
subprocess


import
codecs


import sys


reload(sys)


sys.setdefaultencoding('utf-8')


import os


import re


import time


import
atexit


import
seaborn as sns


import
matplotlib.pyplot as plt





from
pyspark import SparkConf


from
pyspark import SparkContext


from
pyspark import SQLContext


import
pyspark.sql.functions as F


from
pyspark.sql.functions import concat, col, udf, lag, date_add, explode, lit,
unix_timestamp


from
pyspark.sql.functions import month, weekofyear, dayofmonth


from
pyspark.sql.types import *


from
pyspark.sql.types import DateType


from
pyspark.sql.dataframe import *


from
pyspark.sql.window import Window


from
pyspark.sql import Row


from
pyspark.ml.classification import *


from
pyspark.ml.feature import StringIndexer, OneHotEncoder, VectorAssembler,
VectorIndexer


from
pyspark.ml.feature import StandardScaler, PCA, RFormula


from
pyspark.ml import Pipeline, PipelineModel


start_time = time.time()





from
pyspark import SQLContext


# Import
data from Azure Blob Storage


dataFile =
"wasb://sampledata@pysparksampledata.blob.core.windows.net/sampledata.csv"


dataFileSep
= ','


df =
SQLContext.read.csv(dataFile, header=True, sep=dataFileSep, inferSchema=True,
nanValue="", mode='PERMISSIVE')


# Import
data from the home directory on your machine


# dataFile
= '/home/katlin/Desktop/PysparkExample/sampledata.csv'


Utilizzo
sia Juyiter che Pythno 2.7.14 e RIcevo il seguente messaggio di errore:





---------------------------------------------------------------------------


AttributeError Traceback (most
recent call last)


<ipython-input-2-feb6a732221b>
in <module>()


3 dataFile =
"wasb://sampledata@pysparksampledata.blob.core.windows.net/sampledata.csv"


4 dataFileSep = ','


----> 5
df = SQLContext.read.csv(dataFile, header=True, sep=dataFileSep,
inferSchema=True, nanValue="", mode='PERMISSIVE')


6


7 # Import data from the home directory
on your machine


Attribute Error: 'property' object has no
attribute 'csv'

Sto utilizzando : Python 3.6.0 sotto Wind7; ne seguente programma:



#!/usr/bin/python 3

import gi

gi.require_version('Gtk', '3.0')

from gi.repository import Gtk

class SpinnerAnimation(Gtk.Window):







mi da il seguente errore:

JoB\Spinner\Spinner..py", line 3, in <module>

gi.require_version('Gtk', '3.0')

AttributeError: module 'gi' has no attribute 'require_version'





mi sembra di capire che manca la libreria Gtk 3 , ma dove posso scaricarla e come installarla ?

Grazie.