In [ ]:

    

import os
import pandas as pd
import re
import subprocess
import sys
import matplotlib as mpl
mpl.use('Agg') 
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns

%matplotlib inline


    

In [ ]:

    

sys.path.append('../code/')

from database_comparisons import Database, DatabaseComparison


    

In [ ]:

    

# for Waffle, until the default Java is set to 8:
#java="/usr/lib/jvm/java-8-oracle/jre/bin/java"
# for badger, set java = 'java'
java='java'


    

In [ ]:

    

! pwd


    

In [ ]:

    

! ls -l ../jars/*.jar


    

In [ ]:

    

! ls -l ../data_mining_Neo4j_v2_3_2/databases/


    

In [ ]:

    

dbc = DatabaseComparison(desc_string='50M')
dbc.make_dbs([0.005, 0.0075, 0.01, 0.0125, 0.015, 0.02, 0.025, 0.03, 0.035, 0.04, 0.045, 0.05, 0.055, 0.06])


    

In [ ]:

    

dbc.summary


    

In [ ]:

    

dbc.databases


    

In [ ]:

    

p = dbc.plot_db_construction_time_vs_n_nodes()


    

In [ ]:

    

p = dbc.plot_db_construction_time_vs_cutoff()


    

In [ ]:

    

p = dbc.plot_base(x='cutoff', y='edges', color='k', logy=True, figsize=(4.5, 2.5))


    

In [ ]:

    

p = dbc.plot_base(x='cutoff', y='edges', color='k', logy=True, figsize=(4.5, 2.5))


    

In [ ]:

    

#dbc.make_dbs([0.001, 0.003])


    

In [ ]:

    

dbc.make_dbs([0.0125])


    

In [ ]:

    

dbc.make_dbs([0.0075])


    

In [ ]: