[plt.setp(item.xaxis.get_label(), 'size', 40) for item in axes.ravel()]
corr = df.corr().as_matrix()
for i, j in zip(*plt.np.triu_indices_from(axes, k=1)):
axes[i, j].annotate("%.3f" %corr[i,j], (0.8, 0.8), xycoords='axes fraction', ha='center', va='center', size=45)
plt.show()
if __name__ == '__main__':
# data preparation
file = '3222'
data_preparation = DataPreparation(file)
logs = data_preparation.logs_preparation()
rules = data_preparation.rules_preparation()
indicators = data_preparation.indexes_preparation(rules)
rules_ids = data_preparation.rules_to_ids(rules)
# frequent patterns
spam = SPAM(file)
spam.set_max_gap(1)
spam.set_min_pattern_length(2)
spam.set_max_pattern_length(3)
spam.spam_algorithm(logs, 0.5)
#unusual patterns
ind = str(indicators.loc[0][0])
logs = logs.reset_index()
unusual_patterns = UnusualPatterns(file, spam.result, indicators, logs, rules_ids)
prefix_s_step, s_temp_bitmap)
# recursively try to extend that pattern
if self.max_pattern_length > size_current_prefix:
self.dfs_pruning(prefix_s_step, s_temp_bitmap, s_temp,
s_temp, s_temp[pos],
size_current_prefix + 1)
# Save the results in a file
def write_to_file(self, file):
results_to_strings = self.result.apply(
lambda sequence: " -1 ".join(str(x) for x in sequence['Pattern']) +
" -1 #SUP: " + str(sequence['SUP']),
axis=1)
results_to_strings.to_csv('../results-SPAM/' + self.file + '-out.txt',
index=False,
header=None)
if __name__ == '__main__':
f = 'test1'
l = DataPreparation(f)
logs = l.logs_preparation()
s = SPAM(f)
#s.set_max_gap(1)
s.set_min_pattern_length(2)
s.set_max_pattern_length(3)
s.spam_algorithm(logs, 0.4)
s.write_to_file(f)
