Bug 1274975 - Validate moving the clientId loading earlier during startup

Bug 1274975 - Validate moving the clientId loading earlier during startup.ipynb

Bug 1274975 - Validate moving the clientId loading earlier during startup.py

# coding: utf-8

# In[1]:

import datetime as dt
import matplotlib.pyplot as plt
import ujson as json
import pandas as pd
import numpy as np
import copy as cp

from moztelemetry import get_pings, get_pings_properties, get_one_ping_per_client, get_clients_history


# ### How many crash pings with no client id the week before 1233986 landed?

# In[13]:

build_ids = ("20160622000000", "20160628999999")
submission_dates = ("20160622", "20160628")
crash_pings = get_pings(sc,
                        app="Firefox",
                        channel="nightly",
                        build_id=build_ids,
                        submission_date=submission_dates,
                        doc_type="crash",
                        schema="v4",
                        fraction=1.0)


# In[14]:

crash_pings_count = crash_pings.count()
crash_pings_count


# In[15]:

subset = get_pings_properties(crash_pings, ["meta/clientId",
                                            "meta/submissionDate"])


# In[16]:

crash_pings_no_clientid = subset.filter(lambda p: not p.get("meta/clientId", None))


# In[17]:

no_clientid_count = crash_pings_no_clientid.count()
no_clientid_count


# ### How many crash pings with no client id the after 1233986 landed?

# In[18]:

build_ids = ("20160629000000", "20160705030222")
submission_dates = ("20160629", "20160706")
crash_pings = get_pings(sc,
                        app="Firefox",
                        channel="nightly",
                        build_id=build_ids,
                        submission_date=submission_dates,
                        doc_type="crash",
                        schema="v4",
                        fraction=1.0)


# In[19]:

crash_pings_count = crash_pings.count()
crash_pings_count


# In[20]:

subset = get_pings_properties(crash_pings, ["meta/clientId",
                                            "meta/submissionDate"])


# In[21]:

crash_pings_no_clientid = subset.filter(lambda p: not p.get("meta/clientId", None))


# In[22]:

no_clientid_count = crash_pings_no_clientid.count()
no_clientid_count


# In[ ]: