def address_types():
ip_only_1 = session.execute(
"select count(*) from nodes_1_channel where total_ip > 0 and total_addresses=total_ip"
).scalar()
ip_only_5_10 = session.execute(
"select count(*) from nodes_5_10_channels where total_ip > 0 and total_addresses=total_ip"
).scalar()
ip_only_best_connected = session.execute(
"select count(*) from nodes_best_connected where total_ip > 0 and total_addresses=total_ip"
).scalar()
tor_only_1 = session.execute(
"select count(*) from nodes_1_channel where total_tor > 0 and total_addresses=total_tor"
).scalar()
tor_only_5_10 = session.execute(
"select count(*) from nodes_5_10_channels where total_tor > 0 and total_addresses=total_tor"
).scalar()
tor_only_best_connected = session.execute(
"select count(*) from nodes_best_connected where total_tor > 0 and total_addresses=total_tor"
).scalar()
both_1 = session.execute(
"select count(*) from nodes_1_channel where total_tor > 0 and total_ip > 0"
).scalar()
both_5_10 = session.execute(
"select count(*) from nodes_5_10_channels where total_tor > 0 and total_ip > 0"
).scalar()
both_best_connected = session.execute(
"select count(*) from nodes_best_connected where total_tor > 0 and total_ip > 0"
).scalar()
node_types = np.array([
'Nodes with 1 channel', 'Nodes with 5-10 channels',
'Nodes with higest number\n of channels in the network'
])
ip_only = np.array([ip_only_1, ip_only_5_10, ip_only_best_connected])
tor_only = np.array([tor_only_1, tor_only_5_10, tor_only_best_connected])
both = np.array([both_1, both_5_10, both_best_connected])
total_1 = ip_only_1 + tor_only_1 + both_1
total_5_10 = ip_only_5_10 + tor_only_5_10 + both_5_10
total_best = ip_only_best_connected + tor_only_best_connected + both_best_connected
total = [total_1, total_5_10, total_best]
proportion_ip = np.true_divide(ip_only, total) * 100
proportion_tor = np.true_divide(tor_only, total) * 100
proportion_both = np.true_divide(both, total) * 100
df = DataFrame([proportion_ip, proportion_tor,
proportion_both]).transpose()
df.index = node_types
df.columns = [
'IP addresses only', 'Onion addresses only', 'Both kinds of addresses'
]
print(df)
plot = df.plot(kind='bar', stacked=True)
save_plot(plot, 'address_types.png', tilt_x_labels=True)
def connection_successes():
successes = dict(
list(
session.execute(
"select category, count(*) as successes from connects where success=True group by category"
)))
#failure = dict(list(session.execute("select category, count(*) as total from connects where success=False group by category")))
refused = dict(
list(
session.execute(
"select category, count(*) from connects where connectresult like '%refused%' group by category"
)))
no_tor_circuit = dict(
list(
session.execute(
"select category, count(*) from connects where connectresult like '%in progress%' group by category"
)))
timeout = dict(
list(
session.execute(
"select category, count(*) from connects where connectresult like '%timed out%' group by category"
)))
df_refused = DataFrame(refused.items(),
columns=['category', 'Connection refused'])
df_timeout = DataFrame(timeout.items(), columns=['category', 'Timeout'])
df_tor = DataFrame(no_tor_circuit.items(),
columns=['category', 'Unable to establish Tor circuit'])
df = DataFrame(successes.items(),
columns=['category', 'Connection succeeded'])
dfe = df.merge(df_refused, how='left').merge(df_timeout, how='left').merge(
df_refused, how='left').merge(df_tor, how='left')
dfe = dfe.fillna(0)
dfe.index = [
'Nodes with 1 open channel', 'Nodes with 5-10 open channels',
'Nodes with higest number\n of channels in the network'
]
def normalize(x):
total = sum(x[1:])
x[1:] *= 100
x[1:] /= total
return x
df3 = dfe.apply(normalize, axis=1)
plot = df3.plot(kind='bar', stacked=True, color='gryb')
save_plot(plot, 'connection_success', tilt_x_labels=True)
def connection_times():
durations = list(
session.execute(
"select extract(second from connected_after) from connects"))
df = DataFrame(durations, columns=['Connection time (s)'])
plot = df.plot(kind='hist')
save_plot(plot, 'connection_times')
def success_rate_combined():
total = total_attempts_by_amount()
attempt1_success = session.execute(
"select amount_usd, count(*) from payments where success=True and attempts=1 group by amount_usd order by amount_usd asc"
)
successes = DataFrame(attempt1_success, index=total.index)[[1]]
successes /= total / 100
successes.columns = ['Success on first attempt']
attemptany_success = session.execute(
"select amount_usd, count(*) from payments where success=True group by amount_usd order by amount_usd asc"
)
successes_retries = DataFrame(attemptany_success, index=total.index)[[1]]
successes_retries /= total / 100
successes_retries.columns = ['Success after at most 25 attempts']
combined = successes.join(successes_retries)
plot = combined.plot(kind='bar')
save_plot(plot, 'payment_success_rate', tilt_x_labels=True)
print(combined)
def attempts_hist():
avgs = session.execute(
"select amount_usd, round(avg(attempts), 2) from payments where success=True group by amount_usd order by amount_usd asc"
)
df = DataFrame(avgs)
df[[1]] = df[[1]].astype(float)
df[[1]] -= 1 # Display retries instead of attempts
df.columns = ['', 'Average number of retires before success']
df.index = ['USD 0.01', 'USD 1.00', 'USD 10.00']
plot = df.plot(kind='bar')
print(df)
save_plot(plot, 'avg_attempts', tilt_x_labels=True)
def connection_failure_reasons():
refused = session.execute(
"select count(*) from connects where connectresult like '%refused%'"
).scalar()
no_tor_circuit = session.execute(
"select count(*) from connects where connectresult like '%in progress%'"
).scalar()
timeout = session.execute(
"select count(*) from connects where connectresult like '%timed out%'"
).scalar()
index = [
'TCP Connection refused', 'Unable to establish Tor circuit', 'Timeout',
'Other error'
]
df = DataFrame(
{'Connection errors': [refused, no_tor_circuit, timeout, 1]},
index=index)
plot = df.plot(kind='pie', y='Connection errors', labels=None)
plot.set_ylabel('')
save_plot(plot, 'connection_errors')
def success_by_route_length():
data = session.execute(
"select route_length, count(case success when True then 1 end)::float/count(*)*100 as success_rate, count(case route_length when route_length then 1 end) as count from payments group by route_length "
"order by route_length asc")
data = list(data)
data = {
'Hop count': [d['route_length'] for d in data],
'Success rate, %': [d['success_rate'] for d in data],
'Number of probes with this route length': [d['count'] for d in data]
}
df = DataFrame(data)
df = df.set_index(['Hop count'])
plot = df.plot(kind='bar',
secondary_y='Number of probes with this route length')
save_plot(plot, 'success_by_hops')
def failures():
data = session.execute(
"select failcodename from payments where success=False and failcodename is not null"
)
df = DataFrame(data)
df = df.groupby([0]).size()
errors = {
'WIRE_UNKNOWN_NEXT_PEER': 'Unknown next peer',
'WIRE_TEMPORARY_CHANNEL_FAILURE': 'Temporary channel failure',
'WIRE_TEMPORARY_NODE_FAILURE': 'Temporary node failure',
'WIRE_FEE_INSUFFICIENT': 'Insufficient fee',
'WIRE_REQUIRED_NODE_FEATURE_MISSING': 'Insufficient channel capacity',
'WIRE_CHANNEL_DISABLED': 'Channel disabled'
}
df.index = [errors.get(e, e) for e in df.index]
plt.pie(df)
plt.legend(labels=df.index)
plt.savefig(fname='payment_errors.png')
def visible_nodes():
nodes_over_time = list(
session.execute(
"select extract (epoch from delay) as secs, to_char(delay, 'HH24 hrs, MI mnutes, ss secs') as time, total_nodes from gossip_most order by time asc"
))
df = DataFrame(nodes_over_time,
columns=['secs', 'Time', 'Nodes in the local network view'])
df = df.set_index(['secs'])
def human_readable_interval(x):
time = x['Time']
components = time.split(', ')
nonzero = [c for c in components if not c.startswith('00 ')]
x['Time'] = ", ".join(nonzero)
return x
df = df.apply(human_readable_interval, axis=1)
df = df.set_index(['Time'])
print(df)
plot = df.plot(kind='line', x_compat=True)
# plot.get_figure().savefig('gossip.png')
save_plot(plot, 'gossip', tilt_x_labels=60)
def total_attempts_by_amount():
total = session.execute(
"select amount_usd, count(*) from payments group by amount_usd order by amount_usd asc"
)
total = DataFrame(total, index=['USD 0.01', 'USD 1', 'USD 10'])[[1]]
return total
