def rcot_hyperparameter_tuning():
"""Runs the experiment for tuning the hyperparameters of the non-linear causal model using RCOT.
This function creates causal models using the RCOT test for a variety of different alphas and numbers of random
Fourier transformations (num_f). The results are plotted as network and timeseries graphs. The maximum lag is 1.
"""
var_names = [
"dayOfYear", "minuteOfYear", "minuteOfDay", "dayOfWeek", "isWeekend",
"humidity_sensor", "temperature", "precip_intensity", "cloud_cover",
"p1", "p2", "dew_point", "wind_speed"
]
tau_min = 0
tau_max = 1
dataframe, var_list = generate_dataframe(var_names,
start_index=0,
end_index=2000)
print(f"Variable names: {var_names}")
num_fs = [2**n for n in range(1, 14)]
for num_f in num_fs:
ci_test = RCOT(significance='analytic', num_f=num_f)
test_alphas(dataframe,
ci_test, [0.05, 0.1, 0.2],
var_names,
tau_min=tau_min,
tau_max=tau_max)
def prior_knowledge():
"""Runs the experiment for incorporating prior knowledge into the non-linear causal model using RCOT.
This function creates causal models using the RCOT test for a variety of alphas and small range of random Fourier
transformations (num_f). It further limits the solution space by limiting the selected_links used in the PCMCI
algorithm, which effectively enforced independencies in the result. The results are plotted as network and
timeseries graphs. The maximum lag is 1.
"""
var_names = [
"dayOfYear", "minuteOfYear", "minuteOfDay", "dayOfWeek", "isWeekend",
"humidity_sensor", "temperature", "precip_intensity", "cloud_cover",
"p1", "p2", "dew_point", "wind_speed"
]
tau_min = 0
tau_max = 24
dataframe, var_list = generate_dataframe(var_names,
start_index=0,
end_index=2000)
print(f"Variable names: {var_names}")
num_fs = [2**9, 2**10]
for num_f in num_fs:
ci_test = RCOT(significance='analytic', num_f=num_f)
test_alphas(dataframe,
ci_test, [0.05, 0.1, 0.2],
var_names,
tau_min=tau_min,
tau_max=tau_max,
selected_links=generate_links_from_prior_knowledge(
var_names, tau_min, tau_max))
def rcot(request):
return RCOT(mask_type=None,
significance='analytic',
fixed_thres=None,
sig_samples=500,
sig_blocklength=3,
confidence='bootstrap',
conf_lev=0.9,
conf_samples=10000,
conf_blocklength=1,
num_f=25,
approx="lpd4",
seed=42)
def pcmci_causality(data, dt, index, headers, T_data, N_data, maxlag):
T = T_data
N = N_data
tau_max = maxlag
# Verbosity:
# 0 - nothing
# 1 - final graph only
# 2 - everything
verbose_max = 2
verbose = 2
print("======")
# print(list(data)) # got 100 records as itertools.chain object, not numpy df
data = np.array(list(data))
print("data len is ")
print(len(data))
# data = np.fromiter(data, float)
# print(data)
# Initialize dataframe object, specify time axis and variable names
dataframe = pp.DataFrame(data, datatime=dt, var_names=headers)
print(dataframe.var_names)
rcot = RCOT(significance='analytic')
pcmci_rcot = PCMCI(dataframe=dataframe, cond_ind_test=rcot, verbosity=0)
pcmci_rcot.verbosity = 1
results = pcmci_rcot.run_pcmci(tau_max=tau_max, pc_alpha=0.05)
# Print results
print("p-values")
print(results['p_matrix'].round(3))
print("MCI partial correlations")
print(results['val_matrix'].round(2))
# print("inside def pcmci_causality")
# output edges
result_arr = []
# result_arr.append(["effect","cause"])
for index_cause, item in enumerate(results['p_matrix']):
print("index is")
print(index)
print("item is")
print(item)
print("cause is")
cause = headers[index_cause]
print(headers[index_cause])
for index_effect, arr in enumerate(item):
print("effect arr is ")
print(arr)
print("effect name is")
effect = headers[index_effect]
print(headers[index_effect])
for arrItem in arr:
if arrItem < 0.05 and cause != effect:
result_arr.append([effect, cause, index])
print("{} caused by {}".format(effect, cause))
break
with open("pcmci_para_out{}.csv".format(index), "w", newline='') as f:
for row in result_arr:
f.write("%s\n" % ','.join(str(col) for col in row))
# print(pcmci)
return result_arr
def test(dataframes,max_lags=[4],alpha=[None],tests=['ParCorr'],limit=1):
''' This function performs the PCMCI algorithm for all the dataframes received as parameters, given the hyper-parameters of the conditional
independence test
Args:
dataframes: A list of TIGRAMITE dataframes
max_lags: Maximum number of lags to consider for the laggd time series
alpha: Significance level to perform the parent test
tests: A list of conditional independence test to be performed
limit: A limit for the instances to be considered
Returns:
'''
test_results = []
random.shuffle(dataframes)
total = limit*len(max_lags)*len(alpha)*len(tests)
data_frame_iter = iter(dataframes)
tests_to_evaluate=[]
if 'RCOT' in tests:
rcot = RCOT()
tests_to_evaluate.append(['RCOT',rcot])
if 'GPDC' in tests:
gpdc = GPDC()
tests_to_evaluate.append(['GPDC', gpdc])
if 'ParCorr' in tests:
parcorr = ParCorr(significance='analytic')
tests_to_evaluate.append(['ParCorr',parcorr])
if 'CMIknn' in tests:
cmiknn = CMIknn()
tests_to_evaluate.append(['CMIknn',cmiknn])
unique_complexities = list(set(l[1] for l in dataframes))
counts = {}
for i in unique_complexities:
counts[i] = 0
for test in tests_to_evaluate:
stop = False
for l in max_lags:
for a in alpha:
while not stop:
try:
i = random.sample(dataframes,1)[0]
if counts[i[1]] < limit:
print('evaluating: ' + str(i[3]))
start = time.time()
pcmci = PCMCI(
dataframe=i[2],
cond_ind_test=test[1],
verbosity=0)
# correlations = pcmci.get_lagged_dependencies(tau_max=20)
pcmci.verbosity = 1
results = pcmci.run_pcmci(tau_max=l, pc_alpha=a)
time_lapse = round(time.time() - start, 2)
q_matrix = pcmci.get_corrected_pvalues(p_matrix=results['p_matrix'], fdr_method='fdr_bh')
valid_parents = list(pcmci.return_significant_parents(pq_matrix=q_matrix,
val_matrix=results['val_matrix'],
alpha_level=a)['parents'].values())
flat_list = []
for sublist in valid_parents:
for item in sublist:
flat_list.append(item)
valid_links = len(flat_list)
test_results.append([i[3], i[0], i[1], l,test[0],a,valid_links,time_lapse])
results_df = pd.DataFrame(test_results,
columns=['representation', 'complexity', 'sample_size', 'max_lag','test','alpha','valid_links_at_alpha',
'learning_time'])
print('results ready to be saved')
results_df.to_csv(
'results/performance_sample_sizes.csv',
index=False)
counts[i[1]] += 1
if all(value == limit for value in counts.values()):
stop = True
except:
print('Hoopla!')
pass
for i in unique_complexities:
counts[i] = 0
def pcmci_causality(data, dt, index, headers, T_data, N_data, maxlag):
T = T_data
N = N_data
# Run settings
# there is another tau_max in lagged dependencies that might be much longer!
tau_max = maxlag
# Verbosity:
# 0 - nothing
# 1 - final graph only
# 2 - everything
verbose_max = 2
verbose = 2
print("======")
# print(list(data)) # got 100 records as itertools.chain object, not numpy df
# Initialize dataframe object, specify time axis and variable names
dataframe = pp.DataFrame(data, datatime=dt, var_names=headers)
print(dataframe.var_names)
rcot = RCOT(significance='analytic')
pcmci_rcot = PCMCI(dataframe=dataframe, cond_ind_test=rcot, verbosity=0)
pcmci_rcot.verbosity = 1
results = pcmci_rcot.run_pcmci(tau_max=tau_max, pc_alpha=0.05)
# Print results
print("p-values")
print(results['p_matrix'].round(3))
print("MCI partial correlations")
print(results['val_matrix'].round(2))
# Save results to file
# p_matrix = results['p_matrix']
# with open("p-values_baseline.csv", "w") as csv_file:
# writer = csv.writer(csv_file, delimiter=",", quotechar="|", quoting=csv.QUOTE_MINIMAL)
# # [[[1 2 3]]] Three brackets to get through.
# for sector in p_matrix:
# print("sector: ", sector)
# for row in sector:
# print("row: ", row)
# writer.writerow(row)
# writer.writerow([])
#
# print("inside def pcmci_causality")
# output edges
result_arr = []
for index_cause, item in enumerate(results['p_matrix']):
# print("index is")
# print(index)
# print("item is")
# print(item)
# print("cause is")
cause = headers[index_cause]
# print(headers[index_cause])
for index_effect, arr in enumerate(item):
# print("effect arr is ")
# print(arr)
# print("effect name is")
effect = headers[index_effect]
# print(headers[index_effect])
for arrItem in arr:
if arrItem < 0.05 and cause != effect:
result_arr.append([effect, cause, index])
print("{} caused by {}".format(effect, cause))
break
with open("pcmci_baseline_out.csv", "w", newline='') as f:
for row in result_arr:
f.write("%s\n" % ','.join(str(col) for col in row))
# print(pcmci)
print(result_arr)
return result_arr