In [1]:
import pandas as pd
import numpy as np
In [ ]:
alldata = pd.read_csv('2008.csv')
In [3]:
data_100k = alldata[:100000]
In [6]:
data_100k[:30]
Out[6]:
In [7]:
import sys
In [8]:
sys.path
Out[8]:
In [9]:
data_100k.to_csv('./2008_100k.csv')
In [33]:
import dropbox
import re
import time
from firebase import firebase
from IPython.display import IFrame
def publish_gatherplot(p, dataname):
filename = str(time.time())+'.csv'
p.index.name = 'indexPandas'
p.to_csv(filename)
access_token = 'vwezSddRAD0AAAAAAAA0K2kAPqcpKnsShlfAPyIxSAYG0l2GxKfx5vtEkSyCeNOk'
client = dropbox.client.DropboxClient(access_token)
f = open(filename,'rb')
response = client.put_file('./gatherplot/' + filename,f)
print "uploaded:", response
response = client.share('./gatherplot/' + filename, short_url=False)
print 'Shared:', response
url = response['url']
match = re.search(r'https://www\.dropbox\.com/s/(.+)\?dl=0', url)
if match:
# print match.group(1)
download_url = 'https://dl.dropboxusercontent.com/s/' + match.group(1)
print download_url
aFirebase = firebase.FirebaseApplication('https://gatherplot-dev.firebaseio.com',None)
new_csv = {'name':dataname,
'uploader':"google:110953151430048855242",
'uploaderName': "Deok Gun Park",
'url': download_url }
result = aFirebase.post('/csv',new_csv)
print result
return 'https://gatherplot-dev.firebaseapp.com/#/load/' + result['name']
In [38]:
# data_30k = alldata[:30000]
data_10k = alldata.loc[np.random.choice(alldata.index, 10000, replace=False)]
url = publish_gatherplot(data_10k, "2008 Airline On-time Performance random 10K data")
IFrame(url, 900,900)
Out[38]:
In [35]:
data_30k.head()
Out[35]:
In [ ]: