I currently have a data frame that has address details of certain place. I want to use Google geocode API key to find the coordinates - Latitude and Longitude in order to plot a map. Does anybody know how to do this? I have tried the below code but it is returning 'Error, skipping address...' on all the lines of addresses.
I would greatly appreciate any help!
import pandas as pd
import os
from geopy import geocoders
from geopy.geocoders import GoogleV3
API_KEY = os.getenv("API1234")
g = GoogleV3(api_key=API_KEY)
loc_coordinates = []
loc_address = []
for address in df.Address:
try:
inputAddress = Address
location = g.geocode(inputAddress, timeout=15)
loc_coordinates.append((location.latitude, location.longitude))
loc_Address.append(inputAddress)
except:
print('Error, skipping address...')
df_geocodes = pd.DataFrame({'coordinate':loc_coordinates,'address':loc_address})
You had some typos: Address instead of address, loc_Address instead of loc_address.
But what is df.Address ?
Try this:
import pandas as pd
import os
from geopy import geocoders
from geopy.geocoders import GoogleV3
API_KEY = os.getenv("API1234")
g = GoogleV3(api_key=API_KEY)
loc_coordinates = []
loc_address = []
for address in df.Address:
try:
inputAddress = address
location = g.geocode(inputAddress, timeout=15)
loc_coordinates.append((location.latitude, location.longitude))
loc_address.append(inputAddress)
except Exception as e:
print('Error, skipping address...', e)
df_geocodes = pd.DataFrame({'coordinate':loc_coordinates,'address':loc_address})
Related
I'am trying to display all sharepoint's list name but i'am getting this error :
No handlers could be found for logger "office365.runtime.auth.saml_token_provider.SamlTokenProvider._process_service_token_response"
This is my code :
from office365.runtime.auth.authentication_context import AuthenticationContext
from office365.sharepoint.client_context import ClientContext
url = 'https://abc.sharepoint.com/sites/siteName/'
ctx_auth = AuthenticationContext(url)
if ctx_auth.acquire_token_for_user(username='username#abc.com'
,password ='password'):
ctx = ClientContext(url, ctx_auth)
lists = ctx.web.lists
ctx.load(lists)
ctx.execute_query()
for l in lists:
print(l.properties["Title"])
Thanks
I tested below code here with python 2.7 and it works well.
from office365.runtime.auth.authentication_context import AuthenticationContext
from office365.sharepoint.client_context import ClientContext
tenant_url= "https://company.sharepoint.com"
site_url="https://company.sharepoint.com/sites/sname"
ctx_auth = AuthenticationContext(tenant_url)
if ctx_auth.acquire_token_for_user("abc#company.onmicrosoft.com","mypassword"):
ctx = ClientContext(site_url, ctx_auth)
lists = ctx.web.lists
ctx.load(lists)
ctx.execute_query()
for l in lists:
print(l.properties["Title"])
else:
print(ctx_auth.get_last_error())
Result:
If this is related to ADFS, please refer to this closed question:
https://github.com/vgrem/Office365-REST-Python-Client/issues/85
BR
Well i found a solution to get data for specific sharepoint List
from shareplum import Site
from shareplum import Office365
import json
import csv
import pandas
authcookie = Office365('https://abc.sharepoint.com/', username='username', password='password').GetCookies()
site = Site('https://abc.sharepoint.com/sites/SitesName/', authcookie=authcookie)
sp_list = site.List('ListName')
#print(sp_list)
data = sp_list.GetListItems(fields=['FieldName1','FieldName2'])
c = pandas.read_json(json.dumps(data)).to_csv("output.csv")
I am trying to obtain the image data from the following website.
However, I am getting a list of data that contains the links that are not needed. I want to apply the filter so that I can only get the data that starts with /PIAimages. How to apply the filter to do that?
import requests
from bs4 import BeautifulSoup
import csv
result = []
response = requests.get("https://www.ikea.com/sa/en/catalog/products/00361049/")
assert response.ok
page = BeautifulSoup(response.text, "html.parser")
for des in page.find_all('img'):
image= des.get('src')
print(image)
Expected output:
/PIAimages/0531313_PE647261_S1.JPG
/PIAimages/0513228_PE638849_S1.JPG
/PIAimages/0618875_PE688687_S1.JPG
/PIAimages/0325432_PE517964_S1.JPG
/PIAimages/0690287_PE723209_S1.JPG
/PIAimages/0513996_PE639275_S1.JPG
/PIAimages/0325450_PE517970_S1.JPG
Actual output:
/ms/img/header/ikea-logo.svg
/ms/en_SA/img/header/ikea-store.png
/ms/img/header/main_menu_shadow.gif
/sa/en/images/products/strandmon-wing-chair-beige__0513996_PE639275_S4.JPG
/PIAimages/0531313_PE647261_S1.JPG
/PIAimages/0513228_PE638849_S1.JPG
/PIAimages/0618875_PE688687_S1.JPG
/PIAimages/0325432_PE517964_S1.JPG
/PIAimages/0690287_PE723209_S1.JPG
/PIAimages/0513996_PE639275_S1.JPG
/PIAimages/0325450_PE517970_S1.JPG
/ms/img/static/loading.gif
/ms/img/static/stock_check_green.gif
/ms/img/ads/services/ways_to_shop/20172_otav20a_assembly_20x20.jpg
/ms/en_SA/img/icons/picking-with-delivery.jpg
/ms/img/ads/services/ways_to_shop/20172_otav24a_pickingdelivery_20x20.jpg
/sa/en/images/products/strandmon-wing-chair-beige__0739100_PH147003_S4.JPG
https://smetrics.ikea.com/b/ss/ikeaallnojavascriptprod/5/?c8=sa&pageName=nojavascript
Use If clause then append data into list.
import requests
from bs4 import BeautifulSoup
result = []
response = requests.get("https://www.ikea.com/sa/en/catalog/products/00361049/")
assert response.ok
page = BeautifulSoup(response.text, "html.parser")
for des in page.find_all('img'):
image= des.get('src')
if 'PIAimages' in image:
result.append(image)
print(result)
OR use regular expression.This is much faster.
import requests
import re
from bs4 import BeautifulSoup
result = []
response = requests.get("https://www.ikea.com/sa/en/catalog/products/00361049/")
assert response.ok
page = BeautifulSoup(response.text, "html.parser")
for des in page.find_all('img', src=re.compile("PIAimages")):
image= des.get('src')
result.append(image)
print(result)
I think it faster and more concise to use css attribute = value selector with starts with operator. You specify the start substring for the src in the selector so only qualifying elements are returned.
import requests
from bs4 import BeautifulSoup
response = requests.get("https://www.ikea.com/sa/en/catalog/products/00361049/")
page = BeautifulSoup(response.text, "lxml")
images = [item['src'] for item in page.select('img[src^=\/PIAimages]')]
print(images)
I am getting result from BigQuery using the following code:
from google.oauth2 import service_account
from google.cloud import bigquery
credential = service_account.Credentials.from_service_account_file(SERVICE_ACCOUNT_FILE)
scoped_credential = credential.with_scopes(BIG_QUERY_SCOPE)
client = bigquery.Client(project="XX-XX",credentials=scoped_credential)
query_results = client.run_sync_query(query_detail)
query_results.use_legacy_sql = False
query_results.run()
iterator = query_results.fetch_data()
rows = iterator.query_result.rows
But it only returns up-to 50000 rows. I tried to paginate while fetching data, but failed to figure out how to do it:
page_token = query_results.page_token
iterator = query_results.fetch_data(max_results=500, page_token=page_token)
I could not find out how to get the updated page_token.
Thanks,
I think you are close. Try running this code now:
data = list(query_results.fetch_data()) # changed from `iterator` to `data` the variable name
The management of page tokens is done automatically for you.
I need some help regarding the error in code. My Code consists of retrieving the zomato reviews and storing it in HDFS and again reading it performing Recommender Analtyics on it. I am getting a problem regarding my function is not recognizing in pyspark code. I am not entirely pasting the code as it might be confusing so i am writing a small similar use case for your easy understanding.
I am trying to read a file from local and converting it to dataframe from rdd and performing some operations and again converting it to rdd and performing map operation to have delimiter by '|' and then save it to HDFS.
When i try to call self.filter_data(y) in lambda func of check function its not recognizing and giving me error as
Exception: It appears that you are attempting to reference
SparkContext from a broadcast variable, action, or transformation.
SparkContext can only be used on the driver, not in code that it run
on workers. For more information, see SPARK-5063.
****CAN ANY ONE HELP ME WHY MY FILTER_DATA FUNCTION IS NOT RECOGNISING? SHOULD I NEED TO ADD ANY THING OR ANY THING WRONG IN THE WAY I AM CALLING. PLEASE HELP ME. THANKS IN ADVANCE****
INPUT VALUE
starting
0|0|ffae4f|0|https://b.zmtcdn.com/data/user_profile_pictures/565/aed32fa2eb18bb4a5a3ba426870fd565.jpg?fit=around%7C100%3A100&crop=100%3A100%3B%2A%2C%2A|https://www.zomato.com/akellaram87?utm_source=api_basic_user&utm_medium=api&utm_campaign=v2.1|2.5|FFBA00|Well...|unknown|16946626|2017-08-01T00-25-43.455182Z|30059877|Have been here for a quick bite for lunch, ambience and everything looked good, food was okay but presentation was not very appealing. We or...|2017-04-15 16:38:38|Big Foodie|6|Venkata Ram Akella|akellaram87|Bad Food|0.969352505662|0|0|0|0|0|0|1|1|0|0|1|0|0|0.782388212399
ending
starting
1|0|ffae4f|0|https://b.zmtcdn.com/data/user_profile_pictures/4d1/d70d7a57e1bfdf296ff4db3d8daf94d1.jpg?fit=around%7C100%3A100&crop=100%3A100%3B%2A%2C%2A|https://www.zomato.com/users/sm4-2011696?utm_source=api_basic_user&utm_medium=api&utm_campaign=v2.1|1|CB202D|Avoid!|unknown|16946626|2017-08-01T00-25-43.455182Z|29123338|Giving a 1.0 rating because one cannot proceed with writing a review, without rating it. This restaurant deserves a 0 star rating. The qual...|2017-01-04 10:54:53|Big Foodie|4|Sm4|unknown|Bad Service|0.964402034541|0|1|0|0|0|0|0|1|0|0|0|1|0|0.814540622345
ending
My code:
if __name__== '__main__':
import os,logging,sys,time,pandas,json;from subprocess
import PIPE,Popen,call;from datetime import datetime, time, timedelta
from pyspark import SparkContext, SparkConf
conf = SparkConf().setAppName('test')
sc = SparkContext(conf = conf,pyFiles=['/bdaas/exe/nlu_project/spark_classifier.py','/bdaas/exe/spark_zomato/other_files/spark_zipcode.py','/bdaas/exe/spark_zomato/other_files/spark_zomato.py','/bdaas/exe/spark_zomato/conf_files/spark_conf.py','/bdaas/exe/spark_zomato/conf_files/date_comparision.py'])
from pyspark.sql import Row, SQLContext,HiveContext
from pyspark.sql.functions import lit
sqlContext = HiveContext(sc)
import sys,logging,pandas as pd
import spark_conf
n = new()
n.check()
class new:
def __init__(self):
print 'entered into init'
def check(self):
data = sc.textFile('file:///bdaas/src/spark_dependencies/classifier_data/final_Output.txt').map(lambda x: x.split('|')).map(lambda z: Row(restaurant_id=z[0], rating = z[1], review_id = z[2],review_text = z[3],rating_color = z[4],rating_time_friendly=z[5],rating_text=z[6],time_stamp=z[7],likes=z[8],comment_count =z[9],user_name = z[10],user_zomatohandle=z[11],user_foodie_level = z[12],user_level_num=z[13],foodie_color=z[14],profile_url=z[15],profile_image=z[16],retrieved_time=z[17]))
data_r = sqlContext.createDataFrame(data)
data_r.show()
d = data_r.rdd.collect()
print d
data_r.rdd.map(lambda x: list(x)).map(lambda y: self.filter_data(y)).collect()
print data_r
def filter_data(self,y):
s = str()
for i in y:
print i.encode('utf-8')
if i != '':
s = s + i.encode('utf-8') + '|'
print s[0:-1]
return s[0:-1]
Code snippet
from dbinit import session
from geoalchemy2 import Geometry, func
result = session.query(func.ST_AsText('POINT(100 100)'))
How to retrieve the data from this result object?
I have figured out the solution.
re = result.all()