Bug 1355712 - Validate new hour-precision (sub)SessionStart Dates

Bug 1355712 - Validate new hour-precision (sub)SessionStart Dates.ipynb

Bug 1355712 - Validate new hour-precision (sub)SessionStart Dates.py

# coding: utf-8

# In[26]:

sc.defaultParallelism


# In[27]:

from moztelemetry.dataset import Dataset
from moztelemetry import get_pings_properties
from dateutil import parser

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


# In[30]:

pings = Dataset.from_source("telemetry")     .where(docType='main')     .where(submissionDate=lambda d: d >= "20170406")     .where(appUpdateChannel="nightly")     .records(sc, sample=1)


# In[31]:

pings.count()


# In[32]:

subset = get_pings_properties(pings, ["application/buildId", "meta/submissionDate", "payload/info/sessionStartDate", "payload/info/subsessionStartDate"])


# In[33]:

filtered = subset.filter(lambda p: p["application/buildId"] > "20170406000000").persist()


# In[34]:

filtered.take(10)


# In[35]:

filtered.count()


# In[36]:

filtered.map(lambda p: parser.parse(p["payload/info/sessionStartDate"]).time()).countByValue()


# In[37]:

filtered.map(lambda p: parser.parse(p["payload/info/subsessionStartDate"]).time()).countByValue()


# In[ ]: