val_matrix = results['val_matrix']
with open("val-values.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 val_matrix:
print("sector: ", sector)
for row in sector:
print("row: ", row)
writer.writerow(row)
writer.writerow([])
q_matrix = pcmci.get_corrected_pvalues(p_matrix=results['p_matrix'],
fdr_method='fdr_bh')
pcmci.print_significant_links(p_matrix=results['p_matrix'],
q_matrix=q_matrix,
val_matrix=results['val_matrix'],
alpha_level=0.01)
link_matrix = pcmci.return_significant_parents(
pq_matrix=q_matrix, val_matrix=results['val_matrix'],
alpha_level=0.01)['link_matrix']
graph = tp.plot_graph(
val_matrix=results['val_matrix'],
link_matrix=link_matrix,
var_names=headers,
link_colorbar_label='cross-MCI',
node_colorbar_label='auto-MCI',
def run_PCMCI(ex, outdic_actors, s, df_splits, map_proj):
#=====================================================================================
#
# 4) PCMCI-algorithm
#
#=====================================================================================
# save output
if ex['SaveTF'] == True:
# from contextlib import redirect_stdout
orig_stdout = sys.stdout
# buffer print statement output to f
if sys.version[:1] == '3':
sys.stdout = f = io.StringIO()
elif sys.version[:1] == '2':
sys.stdout = f = open(os.path.join(ex['fig_subpath'], 'old.txt'),
'w+')
#%%
# amount of text printed:
verbosity = 3
# alpha level for independence test within the pc procedure (finding parents)
pc_alpha = ex['pcA_sets'][ex['pcA_set']]
# alpha level for multiple linear regression model while conditining on parents of
# parents
alpha_level = ex['alpha_level_tig']
print('run tigramite 4, run.pcmci')
print(('alpha level(s) for independence tests within the pc procedure'
'(finding parents): {}'.format(pc_alpha)))
print((
'alpha level for multiple linear regression model while conditining on parents of '
'parents: {}'.format(ex['alpha_level_tig'])))
# Retrieve traintest info
traintest = df_splits
# load Response Variable class
RV = ex[ex['RV_name']]
# create list with all actors, these will be merged into the fulldata array
allvar = ex['vars'][0]
var_names_corr = []
actorlist = []
cols = [[RV.name]]
for var in allvar[:]:
print(var)
actor = outdic_actors[var]
if actor.ts_corr[s].size != 0:
ts_train = actor.ts_corr[s].values
actorlist.append(ts_train)
# create array which numbers the regions
var_idx = allvar.index(var)
n_regions = actor.ts_corr[s].shape[1]
actor.var_info = [[i + 1, actor.ts_corr[s].columns[i], var_idx]
for i in range(n_regions)]
# Array of corresponing regions with var_names_corr (first entry is RV)
var_names_corr = var_names_corr + actor.var_info
cols.append(list(actor.ts_corr[s].columns))
index_dates = actor.ts_corr[s].index
var_names_corr.insert(0, RV.name)
# stack actor time-series together:
fulldata = np.concatenate(tuple(actorlist), axis=1)
print(('There are {} regions in total'.format(fulldata.shape[1])))
# add the full 1D time series of interest as first entry:
fulldata = np.column_stack((RV.RVfullts, fulldata))
df_data = pd.DataFrame(fulldata, columns=flatten(cols), index=index_dates)
if ex['import_prec_ts'] == True:
var_names_full = var_names_corr.copy()
for d in ex['precursor_ts']:
path_data = d[1]
if len(path_data) > 1:
path_data = ''.join(list(path_data))
# skip first col because it is the RV ts
df_data_ext = func_fc.load_hdf5(
path_data)['df_data'].iloc[:, 1:].loc[s]
cols_ts = np.logical_or(df_data_ext.dtypes == 'float64',
df_data_ext.dtypes == 'float32')
cols_ext = list(df_data_ext.columns[cols_ts])
# cols_ext must be of format '{}_{int}_{}'
lab_int = 100
for i, c in enumerate(cols_ext):
char = c.split('_')[1]
if char.isdigit():
pass
else:
cols_ext[i] = c.replace(char, str(lab_int)) + char
lab_int += 1
df_data_ext = df_data_ext[cols_ext]
to_freq = ex['tfreq']
if to_freq != 1:
start_end_date = (ex['sstartdate'], ex['senddate'])
start_end_year = (ex['startyear'], ex['endyear'])
df_data_ext = functions_pp.time_mean_bins(df_data_ext,
to_freq,
start_end_date,
start_end_year,
seldays='part')[0]
# df_data_ext = functions_pp.time_mean_bins(df_data_ext,
# ex, ex['tfreq'],
# seldays='part')[0]
# Expand var_names_corr
n = var_names_full[-1][0] + 1
add_n = n + len(cols_ext)
n_var_idx = var_names_full[-1][-1] + 1
for i in range(n, add_n):
var_names_full.append([i, cols_ext[i - n], n_var_idx])
df_data = df_data.merge(df_data_ext,
left_index=True,
right_index=True)
else:
var_names_full = var_names_corr
bool_train = traintest.loc[s]['TrainIsTrue']
bool_RV_train = np.logical_and(bool_train, traintest.loc[s]['RV_mask'])
dates_train = traintest.loc[s]['TrainIsTrue'][bool_train].index
dates_RV_train = traintest.loc[s]['TrainIsTrue'][bool_RV_train].index
RVfull_train = RV.RVfullts.sel(time=dates_train)
datesfull_train = pd.to_datetime(RVfull_train.time.values)
data = df_data.loc[datesfull_train].values
print((data.shape))
# get RV datamask (same shape als data)
data_mask = [
True if d in dates_RV_train else False for d in datesfull_train
]
data_mask = np.repeat(data_mask, data.shape[1]).reshape(data.shape)
# add traintest mask to fulldata
# dates_all = pd.to_datetime(RV.RVfullts.index)
# dates_RV = pd.to_datetime(RV.RV_ts.index)
dates_all = pd.to_datetime(RV.RVfullts.time.values)
dates_RV = pd.to_datetime(RV.RV_ts.time.values)
df_data['TrainIsTrue'] = [
True if d in datesfull_train else False for d in dates_all
]
df_data['RV_mask'] = [True if d in dates_RV else False for d in dates_all]
# ======================================================================================================================
# tigramite 3
# ======================================================================================================================
T, N = data.shape # Time, Regions
# ======================================================================================================================
# Initialize dataframe object (needed for tigramite functions)
# ======================================================================================================================
dataframe = pp.DataFrame(data=data,
mask=data_mask,
var_names=var_names_full)
# ======================================================================================================================
# pc algorithm: only parents for selected_variables are calculated
# ======================================================================================================================
parcorr = ParCorr(significance='analytic',
mask_type='y',
verbosity=verbosity)
#==========================================================================
# multiple testing problem:
#==========================================================================
pcmci = PCMCI(dataframe=dataframe,
cond_ind_test=parcorr,
selected_variables=None,
verbosity=4)
# selected_variables : list of integers, optional (default: range(N))
# Specify to estimate parents only for selected variables. If None is
# passed, parents are estimated for all variables.
# ======================================================================================================================
#selected_links = dictionary/None
results = pcmci.run_pcmci(tau_max=ex['tigr_tau_max'],
pc_alpha=pc_alpha,
tau_min=0,
max_combinations=ex['max_comb_actors'])
q_matrix = pcmci.get_corrected_pvalues(p_matrix=results['p_matrix'],
fdr_method='fdr_bh')
pcmci.print_significant_links(p_matrix=results['p_matrix'],
q_matrix=q_matrix,
val_matrix=results['val_matrix'],
alpha_level=alpha_level)
# returns all parents, not just causal precursors (of lag>0)
sig = rgcpd.return_sign_parents(pcmci,
pq_matrix=q_matrix,
val_matrix=results['val_matrix'],
alpha_level=alpha_level)
all_parents = sig['parents']
# link_matrix = sig['link_matrix']
links_RV = all_parents[0]
df = rgcpd.bookkeeping_precursors(links_RV, var_names_full)
#%%
rgcpd.print_particular_region_new(links_RV, var_names_corr, s,
outdic_actors, map_proj, ex)
#%%
if ex['SaveTF'] == True:
if sys.version[:1] == '3':
fname = f's{s}_' + ex['params'] + '.txt'
file = io.open(os.path.join(ex['fig_subpath'], fname), mode='w+')
file.write(f.getvalue())
file.close()
f.close()
elif sys.version[:1] == '2':
f.close()
sys.stdout = orig_stdout
return df, df_data
T, N = data.shape
# Initialize dataframe object
dataframe = pp.DataFrame(data)
#%%
rcot = RCOT2(significance=parameters['cond_ind_test.significance'],
num_f=parameters['cond_ind_test.num_f'])
pcmci = PCMCI(dataframe,
cond_ind_test=rcot,
selected_variables=parameters['selected_variables'],
var_names=parameters['var_names'],
verbosity=10)
q_matrix = pcmci.get_corrected_pvalues(p_matrix=p_matrix, fdr_method='fdr_bh')
q_matrix_tsbh = pcmci.get_corrected_pvalues(p_matrix=p_matrix, fdr_method='fdr_tsbh')
#%% print results
pcmci._print_significant_links(
p_matrix = p_matrix,
q_matrix = q_matrix,
val_matrix = val_matrix,
alpha_level = 0.1)
#%% get selected parents and fit linear model
q_0 = 0.05
parameters['q_0'] = q_0
parameters['q_matrix'] = q_matrix
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 run_pcmci(data, data_mask, var_names, path_outsub2, s, tau_min=0, tau_max=1,
pc_alpha=None, alpha_level=0.05, max_conds_dim=4, max_combinations=1,
max_conds_py=None, max_conds_px=None, verbosity=4):
#%%
if path_outsub2 is not False:
txt_fname = os.path.join(path_outsub2, f'split_{s}_PCMCI_out.txt')
# from contextlib import redirect_stdout
orig_stdout = sys.stdout
# buffer print statement output to f
sys.stdout = f = io.StringIO()
#%%
# ======================================================================================================================
# tigramite 4
# ======================================================================================================================
T, N = data.shape # Time, Regions
# ======================================================================================================================
# Initialize dataframe object (needed for tigramite functions)
# ======================================================================================================================
dataframe = pp.DataFrame(data=data, mask=data_mask, var_names=var_names)
# ======================================================================================================================
# pc algorithm: only parents for selected_variables are calculated
# ======================================================================================================================
parcorr = ParCorr(significance='analytic',
mask_type='y',
verbosity=verbosity)
#==========================================================================
# multiple testing problem:
#==========================================================================
pcmci = PCMCI(dataframe=dataframe,
cond_ind_test=parcorr,
selected_variables=None,
verbosity=verbosity)
# selected_variables : list of integers, optional (default: range(N))
# Specify to estimate parents only for selected variables. If None is
# passed, parents are estimated for all variables.
# ======================================================================================================================
#selected_links = dictionary/None
results = pcmci.run_pcmci(tau_max=tau_max, pc_alpha=pc_alpha, tau_min=tau_min,
max_conds_dim=max_conds_dim,
max_combinations=max_combinations,
max_conds_px=max_conds_px,
max_conds_py=max_conds_py)
q_matrix = pcmci.get_corrected_pvalues(p_matrix=results['p_matrix'], fdr_method='fdr_bh')
pcmci.print_significant_links(p_matrix=results['p_matrix'],
q_matrix=q_matrix,
val_matrix=results['val_matrix'],
alpha_level=alpha_level)
#%%
if path_outsub2 is not False:
file = io.open(txt_fname, mode='w+')
file.write(f.getvalue())
file.close()
f.close()
sys.stdout = orig_stdout
return pcmci, q_matrix, results
def caus_gpdc(data, var_names):
import numpy as np
import matplotlib as mpl
from matplotlib import pyplot as plt
import sklearn
import tigramite
from tigramite import data_processing as pp
from tigramite import plotting as tp
from tigramite.pcmci import PCMCI
from tigramite.independence_tests import ParCorr, GPDC, CMIknn, CMIsymb
from tigramite.models import LinearMediation, Prediction
data_mask_row = np.zeros(len(data))
for i in range(68904):
if (i % 72) < 30 or (i % 72) > 47:
data_mask_row[i] = True
data_mask = np.zeros(data.shape)
data_mask[:, 0] = data_mask_row
data_mask[:, 1] = data_mask_row
data_mask[:, 2] = data_mask_row
data_mask[:, 9] = data_mask_row
data_mask[:, 10] = data_mask_row
data_mask[:, 11] = data_mask_row
dataframe = pp.DataFrame(data, mask=data_mask)
datatime = np.arange(len(data))
# tp.plot_timeseries(data, datatime, var_names, use_mask=True,
# mask=data_mask, grey_masked_samples='data')
gpdc = GPDC(significance='analytic',
gp_params=None,
use_mask=True,
mask_type='y')
gpdc.generate_and_save_nulldists(sample_sizes=range(495, 501),
null_dist_filename='dc_nulldists.npz')
gpdc.null_dist_filename = 'dc_nulldists.npz'
pcmci_gpdc = PCMCI(dataframe=dataframe,
cond_ind_test=gpdc,
var_names=var_names,
verbosity=1)
# correlations = pcmci.get_lagged_dependencies(tau_max=20)
# lag_func_matrix = tp.plot_lagfuncs(val_matrix=correlations,
# setup_args={'var_names':var_names,
# 'x_base':5, 'y_base':.5})
results = pcmci_gpdc.run_pcmci(tau_max=6, tau_min=1, pc_alpha=0.01)
# print("p-values")
# print (results['p_matrix'].round(3))
# print("MCI partial correlations")
# print (results['val_matrix'].round(2))
q_matrix = pcmci_gpdc.get_corrected_pvalues(p_matrix=results['p_matrix'],
fdr_method='fdr_bh')
pcmci_gpdc._print_significant_links(p_matrix=results['p_matrix'],
q_matrix=q_matrix,
val_matrix=results['val_matrix'],
alpha_level=0.01)
link_matrix = pcmci_gpdc._return_significant_parents(
pq_matrix=q_matrix, val_matrix=results['val_matrix'],
alpha_level=0.01)['link_matrix']
tp.plot_time_series_graph(
val_matrix=results['val_matrix'],
link_matrix=link_matrix,
var_names=var_names,
link_colorbar_label='MCI',
)
return results, link_matrix