From 2e26b9521050fb2f840b74746d6ad551b4cefa0b Mon Sep 17 00:00:00 2001
From:  <hamed@DESKTOP-SG54322.localdomain>
Date: Wed, 5 Dec 2018 18:01:45 -0800
Subject: [PATCH] Geometric mean line

---
 src/analyzer/plot.py             | 44 ++++++++++++++++++++++++++++++++
 src/analyzer/tunerloganalyzer.py | 24 +++++++++++------
 2 files changed, 60 insertions(+), 8 deletions(-)
 create mode 100644 src/analyzer/plot.py

diff --git a/src/analyzer/plot.py b/src/analyzer/plot.py
new file mode 100644
index 0000000..fde99e0
--- /dev/null
+++ b/src/analyzer/plot.py
@@ -0,0 +1,44 @@
+import numpy as np
+import matplotlib.pyplot as plt
+IMAGEDIR = "report/pics/"
+
+def generateHistograms(X, header):
+	global IMAGEDIR
+	for i, c in enumerate(X.T):
+		plt.hist(c)
+		plt.savefig(IMAGEDIR + header[i] + "-hist.pdf")
+		plt.clf()
+
+def generateScatterPlot(X, Y, header):
+	global IMAGEDIR
+	for i, feature in enumerate(X.T):
+		values = np.unique(feature)
+		values = np.sort(values)
+		geomean = []
+		for value in values:
+			a =Y[np.where(feature == value)]
+			a = np.array(map(lambda x :  x**(1.0/len(a)), a))
+			geomean.append(a.prod())
+		plt.plot(feature, Y, 'r.')
+		for ii in range(0, len(geomean)-1):
+			print(values[ii:ii + 2])
+			print(geomean[ii:ii + 2])
+			plt.plot(values[ii:ii + 2], geomean[ii:ii + 2], 'bo-')
+		plt.savefig(IMAGEDIR + header[i] + "-scat.pdf")
+		plt.clf()
+
+def plot(data, header):
+	global IMAGEDIR
+	header=header[6:-1]
+	data = np.array(data)
+	X = data[:, 6:-4]
+	X[X==''] = '-1'
+	X = X.astype(np.float)
+	Y = data[:, -2]
+	Y = Y.astype(np.float)
+	generateHistograms(X, header)
+	generateScatterPlot(X, Y, header)
+
+	
+
+
diff --git a/src/analyzer/tunerloganalyzer.py b/src/analyzer/tunerloganalyzer.py
index d4e52cc..8f8f395 100644
--- a/src/analyzer/tunerloganalyzer.py
+++ b/src/analyzer/tunerloganalyzer.py
@@ -2,7 +2,7 @@ import re
 import argparse
 import sys
 import os
-
+import plot as pl
 
 class AutoTunerArgParser:
 	def __init__(self):
@@ -60,10 +60,13 @@ def printHeader(file):
 def dump(file, row):
 	global TUNABLEHEADER
 	mystr=""
+	data = []
 	for i in range(len(TUNABLEHEADER)):
 		mystr += row[TUNABLEHEADER[i]]+ ","
-	print "mystr is:"+ mystr
+		data.append(row[TUNABLEHEADER[i]])
+	print ("mystr is:"+ mystr)
 	print >>file, mystr
+	return data
 
 def loadTunerInfo(row, filename):
 	with open(filename) as f:
@@ -99,6 +102,7 @@ def analyzeLogs(file):
 	argprocess = AutoTunerArgParser()
 	printHeader(file)
 	rows = []
+	data = []
 	for i in range(argprocess.getRunNumber()):
 		row = {"DECOMPOSEORDER" : "",
 			"MUSTREACHGLOBAL" : "",
@@ -126,9 +130,9 @@ def analyzeLogs(file):
 		loadTunerInfo(row, argprocess.getFolder()+"/tuner"+str(i)+"used")
 		loadSolverTime(row, argprocess.getFolder()+"/log"+str(i))
 		loadProblemName(row, argprocess.getFolder()+"/problem"+str(i))
-		dump(file, row)
+		data.append(dump(file, row))
 		rows.append(row)
-	return rows
+	return rows, data
 
 def tunerNumberAnalysis(file, rows):
 	global TUNABLEHEADER
@@ -146,17 +150,21 @@ def tunerNumberAnalysis(file, rows):
 			tunernumber[mystr] += "-" + str(row["TUNERNUMBER"])
 
 	problems = set(map(lambda x: x["PROBLEM"], rows))
-	print "Number of repititive tuners"
+	print ("Number of repititive tuners")
 	for key in tunercount:
 		if tunercount[key] > 1:
-			print key + "(ids:" + tunernumber[key]  + ") = #" + str(tunercount[key])
-
+			print (key + "(ids:" + tunernumber[key]  + ") = #" + str(tunercount[key]))
 
+def transformDataset(rows):
+	print(rows)
 def main():
+	global TUNABLEHEADER
 	file = open("tuner.csv", "w")
-	rows = analyzeLogs(file)
+	rows, data = analyzeLogs(file)
 	tunerNumberAnalysis(file, rows)
 	file.close()
+	#transformDataset(data)
+	pl.plot(data, TUNABLEHEADER)
 	return
 
 if __name__ == "__main__":
-- 
2.34.1