profiledate re-validation

profiledate re-validation.ipynb

profiledate re-validation.py

# coding: utf-8

# ### [Bug 1271391](https://bugzilla.mozilla.org/show_bug.cgi?id=1271391) - Validate Fennec Date header & creation date

# In[9]:

import ujson as json
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import plotly.plotly as py
import datetime as dt
from uuid import UUID
import re
import email.utils as eut

from moztelemetry import get_pings, get_pings_properties, get_one_ping_per_client, get_clients_history

get_ipython().magic(u'pylab inline')


# The Date header landed [2016-05-10](https://hg.mozilla.org/mozilla-central/rev/fdece96f5cf5). This is available in ``"meta/Date"``.
# 
# The ping creation date field and timezone (``created`` and ``tz``) also landed 2016-05-10, bumping the core ping version to 5 - see:
# * https://hg.mozilla.org/mozilla-central/rev/cd0c3acb37e0
# * https://hg.mozilla.org/mozilla-central/rev/40958aebbb80

# In[46]:

submission_dates = ("20160524", "20160414")
pings5 = get_pings(sc,
                   app="Fennec",
                   channel="nightly",
                   doc_type="core",
                   source_version="5",
                   submission_date="20160521",
                   fraction=1.0)
pings6 = get_pings(sc,
                   app="Fennec",
                   channel="nightly",
                   doc_type="core",
                   source_version="6",
                   submission_date="20160521",
                   fraction=1.0)


# In[50]:

merged = pings5 + pings6
properties = ['meta/Date', 'meta/submissionDate', 'clientId', 'created', 'tz']
pings = get_pings_properties(merged, properties)


# In[51]:

pings.first()


# ### Validate

# In[52]:

def valid_date_header(p):
    date_pattern = '^\D+, \d{1,2} \D+ \d{4,4} \d\d:\d\d:\d\d GMT\\+00:00$'
    return re.match(date_pattern, p['meta/Date']) != None

valid_date_header(pings.first())


# In[54]:

def ping_check(ping):
    props = {
        'meta/Date': [unicode],
        'meta/submissionDate': [unicode],
        'clientId': [unicode],
        'created': [unicode],
        'tz': [int, long]
    }

    for k,types in props.iteritems():
        if not k in ping:
            return 'missing field: ' + prop
        if type(ping[k]) not in types:
            return 'wrong type for ' + k

    if not valid_date_header(ping):
        return 'invalid date header'

    return ''


# In[55]:

results = pings.map(lambda p: (ping_check(p), p))


# In[57]:

results.countByKey()


# In[62]:

grouped = results.groupByKey().map(lambda t: t[1])
grouped.cache()


# In[63]:

grouped.collect()


# In[ ]: