diff --git a/.gitignore b/.gitignore
index d91d394..90728e7 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,4 +1,5 @@
final/
result/
+result*/
result_backup/
.idea
\ No newline at end of file
diff --git a/.idea/workspace.xml b/.idea/workspace.xml
index 60f4bca..37260fb 100644
--- a/.idea/workspace.xml
+++ b/.idea/workspace.xml
@@ -15,10 +15,12 @@
-
+
+
-
+
+
@@ -33,7 +35,7 @@
-
+
@@ -45,7 +47,7 @@
-
+
@@ -53,11 +55,23 @@
-
-
+
+
-
+
+
+
+
+
+
+
+
+
+
+
+
+
@@ -65,13 +79,13 @@
-
-
+
+
-
-
+
+
-
+
@@ -81,7 +95,7 @@
-
+
@@ -104,17 +118,36 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
@@ -154,6 +187,8 @@
+
+
@@ -174,8 +209,6 @@
-
-
@@ -186,7 +219,7 @@
-
+
@@ -205,24 +238,6 @@
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
@@ -259,7 +274,7 @@
-
+
@@ -272,7 +287,25 @@
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
@@ -467,18 +500,18 @@
-
@@ -496,7 +529,7 @@
-
+
@@ -506,12 +539,12 @@
-
+
-
+
@@ -533,15 +566,92 @@
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
@@ -638,13 +748,6 @@
-
-
-
-
-
-
-
@@ -652,14 +755,6 @@
-
-
-
-
-
-
-
-
@@ -675,12 +770,20 @@
-
+
-
+
+
+
+
+
+
+
+
+
-
+
@@ -688,32 +791,58 @@
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
+
+
-
-
-
-
-
-
-
-
-
-
\ No newline at end of file
diff --git a/classifier.py b/classifier.py
index 15e047b..8bc4749 100644
--- a/classifier.py
+++ b/classifier.py
@@ -31,7 +31,7 @@ def data_preprocess(project_name, methold_name = ''):
train_target = []
x_id = []
for r in cur.fetchall():
- train_data.append(helper.filter_str(repr(r[1])+"\n"+repr(r[2])))
+ train_data.append(helper.filter_str(repr(r[1])+".\n"+repr(r[2])))
train_target.append(r[0])
x_id.append(r[3])
print("data length is : ", len(train_target))
diff --git a/classifier.pyc b/classifier.pyc
index 749fd68..a6ae919 100644
Binary files a/classifier.pyc and b/classifier.pyc differ
diff --git a/get_analysis_result.py b/get_analysis_result.py
index 046f6bc..6056b9a 100644
--- a/get_analysis_result.py
+++ b/get_analysis_result.py
@@ -149,22 +149,15 @@ def analysis_process(project_id,method):
return count_improve*1.0/int(result_set[0][-1]),r1,\
result_set[0][-1],result_set[0][final_threshold]
-
-method = 'svm'
-final_path = 'final/'
-helper.mkdir(final_path)
-f_proj_id = file('proj_id.csv', 'r')
-reader = csv.reader(f_proj_id)
-f_all_precision = file(final_path + 'precision_'+method+'.csv','w')
-writer_final = csv.writer(f_all_precision)
-precision_improve = []
-precision_machine = []
-p_id = []
-writer_final.writerow(['proj_id','issue_count','proj_name','improve_prec','improve_prec_part','mechine_prec','num_sample','num_hard'])
-
-line = ['6','500']
-for line in reader:
- # classifier_process(line[0])
+def handle_project(line):
+ method = 'svm'
+ final_path = 'final/'
+ helper.mkdir(final_path)
+ f_all_precision = file(final_path + 'precision_'+method+'.csv','a')
+ writer_final = csv.writer(f_all_precision)
+ precision_improve = []
+ precision_machine = []
+ p_id = []
print(line[0])
p_id.append(line[0])
@@ -186,8 +179,22 @@ for line in reader:
# data = (line[0],line[1],proj_name,analysis_process(line[0]),helper.get_precision(line[0]),et,et_1000,rf,nb,lrl1,lrl2,adaboost)
data = (line[0],line[1],proj_name,temp[0],temp[1],helper.get_precision(line[0],method),temp[2],temp[3])
writer_final.writerow(data)
+ # classifier_process(line[0])
+ f_all_precision.close()
-
-
+f_proj_id = file('proj_id.csv', 'r')
+reader = csv.reader(f_proj_id)
+# line = ['6','500']
+method = 'svm'
+final_path = 'final/'
+helper.mkdir(final_path)
+f_all_precision = file(final_path + 'precision_'+method+'.csv','a')
+writer_final = csv.writer(f_all_precision)
+writer_final.writerow(['proj_id','issue_count','proj_name','improve_prec','improve_prec_part','mechine_prec','num_sample','num_hard'])
f_all_precision.close()
+for line in reader:
+ writer_final = csv.writer(f_all_precision)
+
+ handle_project(line)
+
f_proj_id.close()
\ No newline at end of file
diff --git a/read me.txt b/read me.txt
new file mode 100644
index 0000000..6c788e0
--- /dev/null
+++ b/read me.txt
@@ -0,0 +1,5 @@
+classifier.py:对数据进行预处理，包括stemming，去除数字，特殊字符，TFIDF计算
+sentence_classifier.py:分类程序，包括直接使用svm，对hard部分的特殊处理，结果统计与持久化
+dao:数据库访问方法
+helper:一些复杂方法的实现
+get_analysis_result/get_feature_analysis_result:对分类结果的分析
\ No newline at end of file
diff --git a/sentence_classifier.py b/sentence_classifier.py
index 415fd74..7402187 100644
--- a/sentence_classifier.py
+++ b/sentence_classifier.py
@@ -7,7 +7,7 @@ from sklearn.cross_validation import KFold
from time import time
import csv
# from itertools import *
-# import dao
+import dao
import sys
import helper
diff --git a/sentence_classifier2.py b/sentence_classifier2.py
new file mode 100644
index 0000000..2bc148d
--- /dev/null
+++ b/sentence_classifier2.py
@@ -0,0 +1,429 @@
+# import traceback
+import nltk
+import numpy as np
+from sklearn import svm
+from sklearn import metrics
+from sklearn.cross_validation import KFold
+from time import time
+import csv
+# from itertools import *
+import dao
+
+import sys
+import helper
+import classifier
+
+reload(sys)
+sys.setdefaultencoding("utf-8")
+
+__author__ = 'mac'
+import cPickle as pickle
+
+
+def classifier_project_by_id(proj_id):
+ # project_name = repr(proj_id)
+ project_name = proj_id
+ methold_name = 'svm'
+
+ path = 'result/'+project_name+'/'
+ helper.mkdir(path)
+ path_analysis = path + methold_name + '/analysis/'
+ helper.mkdir(path_analysis)
+ path_data = path + methold_name + '/data/'
+ helper.mkdir(path_data)
+ csv_result = file(path_analysis + 'precision_method.csv', 'wb')
+ writer_result = csv.writer(csv_result)
+
+ feature_csv_result = file(path_analysis + 'feature_precision_method.csv', 'wb')
+ feature_writer_result = csv.writer(feature_csv_result)
+
+ csv_path = file(path_analysis + 'sentence_split.csv', 'wb')
+ writer = csv.writer(csv_path)
+ writer.writerow(['id','diff','y_test','pred','sentence_pred','sentence_pred_0','sentence_pred_1','sentence'])
+
+
+ csv_classifier = file(path_analysis + 'classifier_info.csv', 'wb')
+ writer_classifier = csv.writer(csv_classifier)
+ writer_classifier.writerow(['classifier infomation for project:',repr(project_name)])
+
+ threshold = []
+ break_count = 20 # cut the different, len(threshold)
+ change_break = 20 # cut the condition for changing class
+
+ for ind_c_th in range(1,break_count+1):
+ threshold.append(ind_c_th*1.0/break_count)
+
+ count_base = [0]*break_count
+ right_base = [0]*break_count
+ count_base2 = [0]*break_count
+ right_base2 = [0]*break_count
+
+ feature_count_base = [0]*break_count
+ feature_pred_base = [0]*break_count
+ feature_right_base = [0]*break_count
+ feature_count_base2 = [0]*break_count
+ feature_pred_base2 = [0]*break_count
+ feature_right_base2 = [0]*break_count
+
+
+ right_mine1 = [([0] * change_break) for i in range(break_count)]
+ right_mine2 = [([0] * change_break) for i in range(break_count)]
+ right_mine3 = [([0] * change_break) for i in range(break_count)]
+ right_mine4 = [([0] * change_break) for i in range(break_count)]
+
+ feature_right_mine1 = [([0] * change_break) for i in range(break_count)]
+ feature_right_mine2 = [([0] * change_break) for i in range(break_count)]
+ feature_right_mine3 = [([0] * change_break) for i in range(break_count)]
+ feature_right_mine4 = [([0] * change_break) for i in range(break_count)]
+
+ feature_count_mine1 = [([0] * change_break) for i in range(break_count)]
+ feature_count_mine2 = [([0] * change_break) for i in range(break_count)]
+ feature_count_mine3 = [([0] * change_break) for i in range(break_count)]
+ feature_count_mine4 = [([0] * change_break) for i in range(break_count)]
+
+
+ X,y,x_id_before,vect = classifier.data_preprocess(project_name,methold_name) # first time run, get tf-idf of train data
+ # X,y,x_id_before,vect = helper.get_tfidf_data(project_name) # fellow methold run, to get tf-idf store in disk
+ f_train_data = path + 'train_data.pkl'
+ train_data = helper.get_pickle_record(f_train_data)
+
+
+ # get tf-idf matirx of train data
+ # print('get data: ')
+ # f_train = path +'train.pkl'
+ # f_target = path + 'target.pkl'
+ # f_id = path + 'id.pkl'
+ # f_vect = path + 'vect.pkl'
+ # X = helper.get_pickle_record(f_train)
+ # y = helper.get_pickle_record(f_target)
+ # x_id = helper.get_pickle_record(f_id)
+ # vect = helper.get_pickle_record(f_vect)
+ # print('done')
+
+ y = np.array(y)
+ x_id = np.array(x_id_before)
+
+ results = []
+ kf = KFold(len(y), n_folds=10)
+
+
+ def change_flag(flag,ind_threshold,ind_change,j,sentences_count):
+ flag_t = False
+ if j == 0 or j == 1 or j == sentences_count:
+ flag[ind_threshold][ind_change]=True
+ else:
+ # todo: according to possision to decide whether to change flag
+ if sentences_count >= 4 and (j-1 <=1 or sentences_count-j <=1):
+ flag_t = True
+ if sentences_count >= 4 and (abs((j-1)*1.0/(sentences_count-j)) <= 1.0/3 or abs((sentences_count-j)*1.0/(j-1)) <= 1.0/3):
+ flag_t = True
+ if flag_t:
+ flag[ind_threshold][ind_change]=True
+
+ def data_process(change_flag_set,ind_threshold,status):
+ if status:
+ for ind_change in range(change_break):
+ if not change_flag_set[0][ind_threshold][ind_change]:
+ right_mine1[ind_threshold][ind_change] = right_mine1[ind_threshold][ind_change] + 1
+ if not change_flag_set[1][ind_threshold][ind_change]:
+ right_mine2[ind_threshold][ind_change] = right_mine2[ind_threshold][ind_change] + 1
+ if not change_flag_set[2][ind_threshold][ind_change]:
+ right_mine3[ind_threshold][ind_change] = right_mine3[ind_threshold][ind_change] + 1
+ if not change_flag_set[3][ind_threshold][ind_change]:
+ right_mine4[ind_threshold][ind_change] = right_mine4[ind_threshold][ind_change] + 1
+ if not status:
+ for ind_change in range(change_break):
+ if change_flag_set[0][ind_threshold][ind_change]:
+ right_mine1[ind_threshold][ind_change] = right_mine1[ind_threshold][ind_change] + 1
+ if change_flag_set[1][ind_threshold][ind_change]:
+ right_mine2[ind_threshold][ind_change] = right_mine2[ind_threshold][ind_change] + 1
+ if change_flag_set[2][ind_threshold][ind_change]:
+ right_mine3[ind_threshold][ind_change] = right_mine3[ind_threshold][ind_change] + 1
+ if change_flag_set[3][ind_threshold][ind_change]:
+ right_mine4[ind_threshold][ind_change] = right_mine4[ind_threshold][ind_change] + 1
+
+ def data_process2(change_flag_set,ind_threshold,status):
+ for ind_change in range(change_break):
+ if change_flag_set[0][ind_threshold][ind_change] and not status:
+ feature_right_mine1[ind_threshold][ind_change] = feature_right_mine1[ind_threshold][ind_change] + 1
+ if change_flag_set[1][ind_threshold][ind_change] and not status:
+ feature_right_mine2[ind_threshold][ind_change] = feature_right_mine2[ind_threshold][ind_change] + 1
+ if change_flag_set[2][ind_threshold][ind_change] and not status:
+ feature_right_mine3[ind_threshold][ind_change] = feature_right_mine3[ind_threshold][ind_change] + 1
+ if change_flag_set[3][ind_threshold][ind_change] and not status:
+ feature_right_mine4[ind_threshold][ind_change] = feature_right_mine4[ind_threshold][ind_change] + 1
+
+
+ turn_count = 0
+ print("start training:")
+ # ten-fold traning
+ for train_index, test_index in kf:
+ X_train, X_test = X[train_index], X[test_index]
+ y_train, y_test = y[train_index], y[test_index]
+ x_id_train, x_id_test = x_id[train_index], x_id[test_index]
+ turn_count = turn_count+1
+ print('turn '+ repr(turn_count) +':')
+ writer_classifier.writerow(['------------------------------'])
+ writer_classifier.writerow(['turn ', repr(turn_count) ,':'])
+ # print('='*80)
+ ###############################################################################
+ # Benchmark classifiers
+ def benchmark(clf):
+ print('_' * 80)
+ print("Training: ")
+ print(clf)
+ t0 = time()
+ clf.fit(X_train, y_train)
+ train_time = time() - t0
+ print("train time: %0.3fs" % train_time)
+ writer_classifier.writerow(["train time:", train_time])
+
+ t0 = time()
+ pred = clf.predict(X_test)
+
+ test_time = time() - t0
+ print("test time: %0.3fs" % test_time)
+ writer_classifier.writerow(["test time:", test_time])
+
+ score = metrics.accuracy_score(y_test, pred)
+ print("accuracy: %0.3f" % score)
+ writer_classifier.writerow(["accuracy:", score])
+
+ probability = clf.predict_proba(X_test)
+
+ f_mechine = path_data + 'mechine_' + repr(turn_count)
+ with open(f_mechine, 'w') as f:
+ pickle.dump(clf, f)
+
+
+ np.save(path_data + "y_test_"+repr(turn_count),y_test)
+ np.save(path_data + "pred_"+repr(turn_count),pred)
+ np.save(path_data + "x_id_"+repr(turn_count),x_id_test)
+ np.save(path_data + "probability_"+repr(turn_count),probability)
+
+ tokenizer = nltk.data.load('tokenizers/punkt/english.pickle')
+
+ for ind in range(len(pred)):
+ # reset flag for each test data
+ change_flag1 = [([False] * change_break) for i in range(break_count)]
+ change_flag2 = [([False] * change_break) for i in range(break_count)]
+ change_flag3 = [([False] * change_break) for i in range(break_count)]
+ change_flag4 = [([False] * change_break) for i in range(break_count)]
+ change_flag_set = [change_flag1,change_flag2,change_flag3,change_flag4]
+
+ # diff = np.sort(probability[ind:ind+1])[:1,-1:][0][0]-np.sort(probability[ind:ind+1],)[:1,-2:-1][0][0]
+ # get sentence info and split it
+ # issue = dao.get_info_by_id(x_id_test[ind])
+ # for temp in issue:
+ # issue_title = temp[0]
+ # issue_body = temp[1]
+ info = helper.get_info_by_id(x_id_test[ind],x_id_before,train_data)
+ # issue_title = issue[1]
+ # issue_body = issue[2]
+ # info = issue_title + '.\n' + issue_body
+ # info = ''.join(ifilterfalse(unicode.isdigit, info))
+ info = helper.filter_str(info)
+
+ sentences = tokenizer.tokenize(info)
+ x_test = vect.transform(sentences)
+ x_pred = clf.predict(x_test)
+ x_prob = clf.predict_proba(x_test)
+ diff = probability[ind:ind+1,0][0]-probability[ind:ind+1,1][0]
+
+ # get num of sentences for dividing body (without title)
+ sentences_count = len(x_pred)-1
+ # record split information
+ if len(x_pred)>0:
+ for j in range(len(x_pred)):
+ if(helper.word_count(sentences[j])>3):
+ # data format : ['id','diff','y_test','pred','sentence_pred','sentence_pred_0','sentence_pred_1','sentence']
+ data = (x_id_test[ind],diff,y_test[ind],pred[ind],x_pred[j],x_prob[j:j+1,0][0],x_prob[j:j+1,1][0],sentences[j])
+
+ writer.writerow(data)
+
+ for ind_threshold in range(break_count):
+ if abs(diff) <= threshold[ind_threshold]:
+ count_base[ind_threshold] = count_base[ind_threshold] + 1
+ if int(y_test[ind]) == 1:
+ feature_count_base[ind_threshold] = feature_count_base[ind_threshold] +1
+ if int(pred[ind]) == 1:
+ feature_pred_base[ind_threshold] = feature_pred_base[ind_threshold] + 1
+
+ if y_test[ind] == pred[ind]:
+ right_base[ind_threshold] = right_base[ind_threshold] + 1
+ if int(y_test[ind]) == 1:
+ feature_right_base[ind_threshold] = feature_right_base[ind_threshold] + 1
+ if ind_threshold == 0:
+ low_threshold = -0.1
+ else:
+ low_threshold = threshold[ind_threshold]- 1.0/break_count
+ if abs(diff) <= threshold[ind_threshold] and abs(diff) > low_threshold:
+ count_base2[ind_threshold] = count_base2[ind_threshold] + 1
+ if int(y_test[ind]) == 1:
+ feature_count_base2[ind_threshold] = feature_count_base2[ind_threshold] +1
+ if int(pred[ind]) == 1:
+ feature_pred_base2[ind_threshold] = feature_pred_base2[ind_threshold] + 1
+
+ if y_test[ind] == pred[ind]:
+ right_base2[ind_threshold] = right_base2[ind_threshold] + 1
+ if int(y_test[ind]) == 1:
+ feature_right_base2[ind_threshold] = feature_right_base2[ind_threshold] + 1
+
+ # flag for diff
+ flag = 'zero'
+ if diff > 0:
+ flag = "+"
+ elif diff < 0:
+ flag = "-"
+ # print("id:"+repr(x_id[ind]))
+ if len(x_pred)>0:
+ for j in range(len(x_pred)):
+ if(helper.word_count(sentences[j])>3):
+ # recording which to change
+ for ind_change in range(change_break):
+ if pred[ind] == 0 and x_prob[j:j+1,1][0] > ind_change*1.0/change_break:
+ change_flag(change_flag_set[0],ind_threshold,ind_change,j,sentences_count)
+ if pred[ind] == 0 and x_prob[j:j+1,1][0] > ind_change*1.0/change_break and flag != '+':
+ change_flag(change_flag_set[1],ind_threshold,ind_change,j,sentences_count)
+ if pred[ind] == 0 and x_prob[j:j+1,1][0] > ind_change*1.0/change_break and flag == '-':
+ change_flag(change_flag_set[2],ind_threshold,ind_change,j,sentences_count)
+ # if pred[ind] == 1 and x_prob[j:j+1,0][0] > ind_change*1.0/change_break and flag == '+':
+ # change_flag(change_flag_set[3],ind_threshold,ind_change)
+
+ status = (y_test[ind] == pred[ind])
+ data_process(change_flag_set,ind_threshold,status)
+ for ind_change in range(change_break):
+ if change_flag_set[0][ind_threshold][ind_change]:
+ feature_count_mine1[ind_threshold][ind_change] = feature_count_mine1[ind_threshold][ind_change] + 1
+ if change_flag_set[1][ind_threshold][ind_change]:
+ feature_count_mine2[ind_threshold][ind_change] = feature_count_mine2[ind_threshold][ind_change] + 1
+ if change_flag_set[2][ind_threshold][ind_change]:
+ feature_count_mine3[ind_threshold][ind_change] = feature_count_mine3[ind_threshold][ind_change] + 1
+ if change_flag_set[3][ind_threshold][ind_change]:
+ feature_count_mine4[ind_threshold][ind_change] = feature_count_mine4[ind_threshold][ind_change] + 1
+
+ data_process2(change_flag_set,ind_threshold,status)
+
+ # issue.close()
+ clf_descr = str(clf).split('(')[0]
+
+ return clf_descr, score, train_time, test_time
+##############################################
+ results.append(benchmark(svm.SVC(kernel='linear',probability=True)))
+
+ results = [[x[i] for x in results] for i in range(4)]
+ clf_names, score, training_time, test_time = results
+
+ info_len = len(score)
+ training_time = np.array(training_time).sum() / info_len
+ test_time = np.array(test_time).sum() / info_len
+ score_all = np.array(score).sum()/ info_len
+ print("accuracy for all: %0.3f" % score_all)
+ writer_classifier.writerow(['------------------------------'])
+ writer_classifier.writerow(["traning time for all:", training_time])
+ writer_classifier.writerow(["test time for all:", test_time])
+ writer_classifier.writerow(["accuracy for all:", score_all])
+
+ # write result
+ writer_result.writerow(['base count for all:'])
+ writer_result.writerow([n for n in count_base])
+ writer_result.writerow(['base right count for all:'])
+ writer_result.writerow([n for n in right_base])
+
+ writer_result.writerow(['base count for threshold:'])
+ writer_result.writerow([n for n in count_base2])
+ writer_result.writerow(['base right count for threshold:'])
+ writer_result.writerow([n for n in right_base2])
+
+
+ feature_writer_result.writerow(['base count for all:'])
+ feature_writer_result.writerow([n for n in feature_count_base])
+ feature_writer_result.writerow(['base right count for all:'])
+ feature_writer_result.writerow([n for n in feature_right_base])
+ feature_writer_result.writerow(['base pred count for all:'])
+ feature_writer_result.writerow([n for n in feature_pred_base])
+
+ feature_writer_result.writerow(['base count for threshold:'])
+ feature_writer_result.writerow([n for n in feature_count_base2])
+ feature_writer_result.writerow(['base right count for threshold:'])
+ feature_writer_result.writerow([n for n in feature_right_base2])
+ feature_writer_result.writerow(['base pred count for threshold:'])
+ feature_writer_result.writerow([n for n in feature_pred_base2])
+
+ writer_result.writerow(['right count of mine method 1 for each threshold:'])
+ for i in range(break_count):
+ writer_result.writerow([l for l in right_mine1[i]])
+ writer_result.writerow(['right count of mine method 2 for each threshold:'])
+ for i in range(break_count):
+ writer_result.writerow([l for l in right_mine2[i]])
+ writer_result.writerow(['right count of mine method 3 for each threshold:'])
+ for i in range(break_count):
+ writer_result.writerow([l for l in right_mine3[i]])
+ writer_result.writerow(['right count of mine method 4 for each threshold:'])
+ for i in range(break_count):
+ writer_result.writerow([l for l in right_mine4[i]])
+
+
+ feature_writer_result.writerow(['right count of mine method 1 for each threshold:'])
+ for i in range(break_count):
+ feature_writer_result.writerow([l for l in feature_right_mine1[i]])
+ feature_writer_result.writerow(['right count of mine method 2 for each threshold:'])
+ for i in range(break_count):
+ feature_writer_result.writerow([l for l in feature_right_mine2[i]])
+ feature_writer_result.writerow(['right count of mine method 3 for each threshold:'])
+ for i in range(break_count):
+ feature_writer_result.writerow([l for l in feature_right_mine3[i]])
+ feature_writer_result.writerow(['right count of mine method 4 for each threshold:'])
+ for i in range(break_count):
+ feature_writer_result.writerow([l for l in feature_right_mine4[i]])
+
+ feature_writer_result.writerow(['change count of mine method 1 for each threshold:'])
+ for i in range(break_count):
+ feature_writer_result.writerow([l for l in feature_count_mine1[i]])
+ feature_writer_result.writerow(['change count of mine method 2 for each threshold:'])
+ for i in range(break_count):
+ feature_writer_result.writerow([l for l in feature_count_mine2[i]])
+ feature_writer_result.writerow(['change count of mine method 3 for each threshold:'])
+ for i in range(break_count):
+ feature_writer_result.writerow([l for l in feature_count_mine3[i]])
+ feature_writer_result.writerow(['change count of mine method 4 for each threshold:'])
+ for i in range(break_count):
+ feature_writer_result.writerow([l for l in feature_count_mine4[i]])
+
+ csv_result.close()
+ csv_path.close()
+ csv_classifier.close()
+
+
+# classifier_project_by_id('6')
+
+# break_id = 961
+# projects = dao.get_project()
+# flag_break = True
+# csv_project = file('project_id.csv', 'wb')
+# writer_project = csv.writer(csv_project)
+# for project in projects:
+# print('do classifier for project:'+ repr(project[0]))
+# if project[0] == break_id:
+# flag_break = True
+#
+# if project[1] > 500 and flag_break:
+# try:
+# classifier_project_by_id(project[0])
+# writer_project.writerow(project)
+# except:
+# f=open("log.txt",'a')
+# f.writelines("project:\t"+repr(project[0])+'\n')
+# f.flush()
+# f.close()
+#
+# csv_project.close()
+# projects.close()
+
+f_proj_id = file('proj_id.csv', 'r')
+reader = csv.reader(f_proj_id)
+for line in reader:
+ classifier_project_by_id(line[0])
+
+ print(line[0])
+dao.close()
\ No newline at end of file
diff --git a/test.py b/test.py
new file mode 100644
index 0000000..e69de29