From c298bde8700f6c665ada136beba3647f72eb2894 Mon Sep 17 00:00:00 2001
From: steve <steve@the-phi.com>
Date: Wed, 22 Feb 2017 14:51:12 -0600
Subject: [PATCH] ML bug fix, @TODO: apply regression on folders and have
 report generated

---
 src/utils/agents/data-collector.py | 4 +++-
 src/utils/agents/learner.py        | 8 +++++---
 src/utils/ml.py                    | 4 +++-
 3 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/src/utils/agents/data-collector.py b/src/utils/agents/data-collector.py
index 4aeaace..39fe528 100644
--- a/src/utils/agents/data-collector.py
+++ b/src/utils/agents/data-collector.py
@@ -26,6 +26,7 @@ class ICollector(Thread) :
 		self.lock 	= RLock()
 		self.factory	= DataSourceFactory()
 		self.init()
+		self.name = 'data-collector@'+self.id
 	def init(self):
 		
 		
@@ -78,12 +79,13 @@ class ICollector(Thread) :
 				label	= thread.getName()
 				row	= {}
 				if label == 'folders':
-					row[id]	= data
+					row = [ dict({"id":self.id}, **_row) for _row in data]
 				else:
 					label = id
 					row = data
 				self.lock.acquire()
 				store = self.factory.instance(type=write_class,args=read_args)
+				
 				store.write(label=label,row=row)
 				self.lock.release()
 			if 'MONITOR_CONFIG_PATH' in os.environ :
diff --git a/src/utils/agents/learner.py b/src/utils/agents/learner.py
index 26c78bf..1c7bb36 100644
--- a/src/utils/agents/learner.py
+++ b/src/utils/agents/learner.py
@@ -41,6 +41,7 @@ class Anomalies(Thread) :
 		pass
 	def stop(self):
 		self.quit = True
+            
 	def run(self):
 		DELAY = self.config['delay'] * 60
 		reader 	= self.factory.instance(type=self.rclass,args=self.rw_args)
@@ -52,15 +53,16 @@ class Anomalies(Thread) :
 		while self.quit == False :
 			print ' *** ',self.name, ' ' , str(datetime.today())
 			for app in self.apps:
-				print '\t',str(datetime.today()),' ** ',app
+				print '\t',app,str(datetime.today()),' ** ',app
 				logs = ML.Filter('label',app,rdata)
+				
 				if logs :
 					handler = AnomalyDetection()
 					value 	= handler.learn(logs,'label',app,features,yo)
-					print value
 					if value is not None:
 						value = dict(value,**{"features":features})
-						r[id][app] = value
+						value = dict({"id":self.id},**value)
+						#r[id][app] = value
 						self.lock.acquire()
 						writer = self.factory.instance(type=self.wclass,args=self.rw_args)
 						writer.write(label='learn',row=value)
diff --git a/src/utils/ml.py b/src/utils/ml.py
index ff6faea..287919e 100644
--- a/src/utils/ml.py
+++ b/src/utils/ml.py
@@ -209,6 +209,7 @@ class AnomalyDetection:
 		sigma = info['parameters']['cov']
 		xu	= info['parameters']['mean']
 		epsilon = info['performance']['epsilon']
+		
 		return self.gPx(xu,sigma,xo,epsilon)
 	"""
 		This function computes performance metrics i.e precision, recall and f-score
@@ -228,7 +229,8 @@ class AnomalyDetection:
 			tn += 1 if (test[i][1] == labels[i] and test[i][1] == 0) else 0
 		precision = tp / (tp + fp) if tp + fp > 0 else 1
 		recall	= tp / (tp + fn) if tp  + fp > 0 else 1
-		fscore 	= (2 * precision * recall)/ (precision + recall)
+		
+		fscore 	= (2 * precision * recall)/ ((precision + recall) if (precision + recall) > 0  else 1)
 		return {"precision":precision,"recall":recall,"fscore":fscore}
 
 	"""