upload

+from optparse import OptionParser
+import re
+from collections import defaultdict as df
+import os
+import random
+from pandas import DataFrame as DF
+import matplotlib.pyplot as plt
+
+# Objective
+# Drawn figures of grid reports 
+#
+# Input parameters
+# --inputPath=PATH              Path of inputfiles
+# --outputPath=PATH             Path to place output figures
+# --figureName            single run specific name figure, multifigure first part of name
+# --inputFile             Use it for a single report
+# --version		  CRF-script version of reports
+#
+# Output
+# training and test data set
+#
+# Examples
+# python figures-reports.py
+# --inputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/reports/
+# --outputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/figures/
+# --figureName FiguresGrid
+# --inputFile report_Run1_v11.txt
+# -version v11
+
+# python figures-reports.py --inputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/reports/ --outputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/figures/ --figureName FiguresGrid_v1 --inputFile report_Run1_v11.txt ..version v11
+__author__ = 'egaytan'
+
+####################################################################################
+#                                   FUNCTIONS                                      #
+####################################################################################
+def Filter(rfile, options,v):
+  if options[0]=='all':
+    if rfile[0:6]=='report' and rfile[-7:-4]==v: return(True)
+  elif rfile in options:
+    return(True)
+  return(False)
+
+####################################################################################
+#                                   MAIN PROGRAM                                  #
+####################################################################################
+
+if __name__ == '__main__':
+    # Defining parameters
+    parser = OptionParser()
+    parser.add_option('--inputPath',  dest='inputPath',   help='Path of output from CoreNLP',           metavar='PATH')
+    parser.add_option('--outputPath', dest='outputPath',  help='Path to place output figures',          metavar='PATH')
+    parser.add_option('--figureName', dest='figureName',  help='Specific or first part of figurename',  metavar='FILE')
+    parser.add_option('--version', dest='version',  help='script version',  metavar='FILE')    
+    parser.add_option('--inputFile',  dest='inputFile',   help='Use it for a specific report files',            metavar='FILE', default='all,')
+
+    (options, args) = parser.parse_args()
+    if len(args) > 0:
+        parser.error('Any parameter given.\nFor multi input files be sure to seprate the filenames by coma')
+        sys.exit(1)
+
+    print('-------------------------------- PARAMETERS --------------------------------')
+    print('Path of output from CoreNLP: ' + str(options.inputPath))
+    print('Path to place output figures: ' + str(options.outputPath))
+    print('Specific or first part of figurename: ' + str(options.figureName))
+    print('CRF-script version: ' + str(options.version))   
+
+    print('-------------------------------- PROCESSING --------------------------------')
+
+    rawInputRepotsList = str(options.inputFile).split(',')
+    reportFileList = [ rfile for rfile in os.listdir(options.inputPath) if Filter(rfile, rawInputRepotsList, str(options.version)) ]
+    scores = df(dict)
+    #CV={}
+    print('Report files: ' + str(options.inputFile  ))
+    print('\n'.join(reportFileList))
+    print('----------------------------------- NOTE -----------------------------------')
+    print('\n-------- All chosen report files should be in inputPath given---------------\n')
+
+    print('------------------------------- SAVING DATA --------------------------------\n')
+    for report in reportFileList:
+      with open(os.path.join(options.inputPath, report), 'r') as File:
+        string = File.read()
+        scores[report[7:11]]['CV']=re.findall('best\sCV\sscore\:(\d+\.\d+)', string)[0]
+        summaryScores = re.findall('avg\s\/\stotal\s+(\d+\.\d+)\s+(\d+\.\d+)\s+(\d+\.\d+)', string)[0]        
+        scores[report[7:11]]['precision']=summaryScores[0]
+        scores[report[7:11]]['recall']=summaryScores[1]
+        scores[report[7:11]]['f1-score']=summaryScores[2]       
+    
+    print(DF(scores).T)
+    scoresTable = DF(scores).T
+    
+    imageName=os.path.join(options.outputPath, options.figureName)    
+    ylab = "score",
+    fig = plt.figure()
+    plt.grid(False)
+    plt.rcParams.update({'font.size': 15})
+    fig.set_figheight(13)
+    fig.set_figwidth(20)
+    plt.xlabel("Runs")    
+    plt.ylabel("score")    
+    plt.xticks(range(8),scoresTable["CV"].index)
+    plt.plot(scoresTable['CV'], "--", color="red", label="CV")    
+    plt.plot(scoresTable['precision'], color="blue", label="precision")   
+    plt.plot(scoresTable['f1-score'], color="orange", label="F1")    
+    plt.plot(scoresTable['recall'], color="g", label="recall")
+    plt.legend(loc='lower right')
+    plt.tight_layout()
+    fig.savefig(imageName, pad_inches=0.5)    
+        
+
+
+
+
+

+
+python3 training_validation_v10.py --inputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/data-sets --trainingFile training-data-set-70.txt --testFile test-data-set-30.txt --outputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/ --Gridname Run1 --version _v10 > ../outputs/Run1_v10.txt
+python3 training_validation_v10.py --inputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/data-sets --trainingFile training-data-set-70.txt --testFile test-data-set-30.txt --outputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/ --Gridname Run2 --version _v10 --S1 > ../outputs/Run2_v10.txt
+python3 training_validation_v10.py --inputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/data-sets --trainingFile training-data-set-70.txt --testFile test-data-set-30.txt --outputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/ --Gridname Run3 --version _v10 --S2 > ../outputs/Run3_v10.txt
+python3 training_validation_v10.py --inputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/data-sets --trainingFile training-data-set-70.txt --testFile test-data-set-30.txt --outputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/ --Gridname Run4 --version _v10 --S1 --S2 > ../outputs/Run4_v10.txt
+python3 training_validation_v10.py --inputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/data-sets --trainingFile training-data-set-70.txt --testFile test-data-set-30.txt --outputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/ --Gridname Run5 --version _v10 --S3 > ../outputs/Run5_v10.txt
+python3 training_validation_v10.py --inputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/data-sets --trainingFile training-data-set-70.txt --testFile test-data-set-30.txt --outputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/ --Gridname Run6 --version _v10 --S1 --S3 > ../outputs/Run6_v10.txt
+python3 training_validation_v10.py --inputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/data-sets --trainingFile training-data-set-70.txt --testFile test-data-set-30.txt --outputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/ --Gridname Run7 --version _v10 --S2 --S3 > ../outputs/Run7_v10.txt
+python3 training_validation_v10.py --inputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/data-sets --trainingFile training-data-set-70.txt --testFile test-data-set-30.txt --outputPath /home/egaytan/automatic-extraction-growth-conditions/CRF/ --Gridname Run8 --version _v10 --S1 --S2 --S3 > ../outputs/Run8_v10.txt
+
+