def main(maxFeatures=30, maxDepth=8): print "maxFeatures:", maxFeatures print "maxDepth :", maxDepth baseDir = globalConst.BASE_DIR params = { "max_depth": maxDepth, "subsample": 0.5, "verbose": 2, "random_state": 0, "min_samples_split": 20, "min_samples_leaf": 20, "max_features": maxFeatures, "n_estimators": 500, "learning_rate": 0.05, } #'n_estimators': 12000, 'learning_rate': 0.002} clf = GradientBoostingClassifier(**params) # NOTE: first pass, no orderFile; 2nd pass, use orderfiles test = Classify( trainFile=baseDir + "workspace/trainMetrics.csv", orderFile=useIfExists(baseDir + "/moby/corr32.csv") ) test.validate(clf=clf, nFolds=2, featureImportance=True, outFile=baseDir + "moby/trainPredictions.csv") test.testAndOutput( clf=clf, testFile=baseDir + "workspace/testMetrics.csv", orderFile=useIfExists(baseDir + "/moby/testCorr32.csv"), outfile=baseDir + "moby/testPredictions.sub", ) # NOTE .sub, not .csv
def cl(self): self.cl = Classify() a = self.cl.classify_r1() self.textEdit_2.setText(a + ' >>') b = self.cl.classify_r2(a) self.textEdit_2.append(b) self.textEdit_3.setText("Tweet Classfied")
def main(): path = "data/yellow-small.csv" dry_run = False # parse tags if len(sys.argv) == 2: if sys.argv[1] == DRY_RUN: dry_run = True else: path = sys.argv[1] if len(sys.argv) == 3 and sys.argv[2] == DRY_RUN: dry_run = True path = sys.argv[1] # parse input im = Importer(path) im.parse_data() # build tree tree = DecisionTree(im) tree.build_tree(THRESH) print(tree.tree_to_json()) # classify data classify = Classify(path, tree.tree) classify.check_data(dry_run)
def main(model='production.pkl'): # setup classify = Classify(ARTIFACT_PATH, model) ## CONTROL LOOPS ## while not rover.isDeadZone(): if not rover.isOverride(): # run this guy at 1Hz start = timer() # classify camera images camera_imgs = rover.getImgs() camera_preds = [] # may have to convert images here or change classify class for img in camera_imgs: camera_preds.append(classify.predict(img)) # confirm we are onlyhot running at 1Hz # and check if we are running over if timer() - start > 1: print('--BELOW 1HZ') print(timer() - start) while timer() - start < 1: pass while rover.isDeadZone(): # run this guy at 1Hz start = timer() # do stuff here signal = rover.getSignalStrength() while timer() - start < 1: pass
def main(): baseDir = '/Users/nkridler/Desktop/whale/' params = {'max_depth':8, 'subsample':0.5, 'verbose':2, 'random_state':0 'min_samples_split':20, 'min_samples_leaf':20, 'max_features':30, 'n_estimators': 500, 'learning_rate': 0.05} #'n_estimators': 12000, 'learning_rate': 0.002} clf = GradientBoostingClassifier(**params) test = Classify(baseDir+'workspace/trainMetrics.csv') test.validate(clf,nFolds=2,featureImportance=True)
def main(): baseDir = '/home/nick/whale/' params = {'max_depth':8, 'subsample':0.5, 'verbose':2, 'random_state':0, 'min_samples_split':20, 'min_samples_leaf':20, 'max_features':30, 'n_estimators': 12000, 'learning_rate': 0.002} clf = GradientBoostingClassifier(**params) # Generate a submission with corr32 and all metrics test = Classify(trainFile=baseDir+'workspace/trainMetrics.csv', orderFile=baseDir+'moby/corr32.csv') test.testAndOutput(clf=clf, testFile=baseDir+'workspace/testMetrics.csv', orderFile=baseDir+'moby/testCorr32.csv', outfile='submit32.sub') # Generate a submission with corr64 and no time metrics noTime = np.array(range(150) + range(385,448)) test = Classify(trainFile=baseDir+'workspace/trainMetrics.csv', orderFile=baseDir+'moby/corr64.csv', useCols=noTime) test.testAndOutput(clf=clf, testFile=baseDir+'workspace/testMetrics.csv', orderFile=baseDir+'moby/testCorr64.csv', outfile='submit64.sub') # Blend s32 = np.loadtxt('submit32.sub',delimiter=',') s64 = np.loadtxt('submit64.sub',delimiter=',') sub_ = 0.5*s32 + 0.5*s64 np.savetxt('blend.sub',sub_,delimiter=',')
def predictor(self): if self.sc == None: self.sc = scraper(self.keyword).results self.articles = len(self.sc) for i in self.sc: value = Classify(i["title"]).classify() self.score += value self.final_pred = self.score / self.articles
def predictor(self): sc = scraper(self.keyword).results self.articles = len(sc) for i in sc: value = Classify(i["title"]).classify() if value == "Positive": self.score += 1 self.final_pred = self.score / self.articles
def cl(self): global flag if (flag == 1): #From Twitter self.cl = Classify() a = self.cl.classify_r1() self.textEdit_2.setText(a + ' >>') if (flag == 0): #From File self.cl = Classify_FileTweet() a = self.cl.classify_r1() self.textEdit_2.setText(a + ' >>')
def main(maxFeatures=30, maxDepth=8): print "maxFeatures:", maxFeatures print "maxDepth :", maxDepth baseDir = globalConst.BASE_DIR params = { 'max_depth': maxDepth, 'subsample': 0.5, 'verbose': 2, 'random_state': 0, 'min_samples_split': 20, 'min_samples_leaf': 20, 'max_features': maxFeatures, 'n_estimators': 500, 'learning_rate': 0.05 } #'n_estimators': 12000, 'learning_rate': 0.002} clf = GradientBoostingClassifier(**params) # NOTE: first pass, no orderFile; 2nd pass, use orderfiles test = Classify(trainFile=baseDir + 'workspace/trainMetrics.csv', orderFile=useIfExists(baseDir + '/moby/corr32.csv')) test.validate(clf=clf, nFolds=2, featureImportance=True, outFile=baseDir + 'moby/trainPredictions.csv') test.testAndOutput(clf=clf, testFile=baseDir + 'workspace/testMetrics.csv', orderFile=useIfExists(baseDir + '/moby/testCorr32.csv'), outfile=baseDir + 'moby/testPredictions.sub') # NOTE .sub, not .csv
def cl(self): global flag if (flag == 1): #From Twitter self.cl = Classify() a = self.cl.classify_r1() self.textEdit_2.setText(a + ' >>') b = self.cl.classify_r2(a) self.textEdit_2.append(b + ' >>') c = self.cl.classify_r3(b) self.textEdit_2.append(c + ' >>') d = self.cl.classify_r4(c) self.textEdit_2.append(d) if (flag == 0): #From File self.cl = Classify_FileTweet() a = self.cl.classify_r1() self.textEdit_2.setText(a + ' >>') b = self.cl.classify_r2(a) self.textEdit_2.append(b + ' >>') c = self.cl.classify_r3(b) self.textEdit_2.append(c + ' >>') d = self.cl.classify_r4(c) self.textEdit_2.append(d)
def main(self, args, command): ''' Parameters ---------- Output ------ ''' self._check_general(args) self._logging_setup(args) logging.info("Running command: %s" % ' '.join(command)) if args.subparser_name == self.DATA: self._check_data(args) d = Data() d.do() if args.subparser_name == self.ANNOTATE: self._check_annotate(args) a = Annotate(# Define inputs and outputs args.output, # Define type of annotation to be carried out args.ko, args.pfam, args.tigrfam, args.cog, args.hypothetical, # Cutoffs args.evalue, args.bit, args.id, args.aln_query, args.aln_reference, args.cascaded, args.c, # Parameters args.threads, args.parallel, args.suffix) a.do(args.genome_directory, args.protein_directory, args.genome_files, args.protein_files) elif args.subparser_name == self.CLASSIFY: self._check_classify(args) c = Classify() c.do(args.custom_modules, args.cutoff, args.genome_and_annotation_file, args.genome_and_annotation_matrix, args.output) elif args.subparser_name == self.ENRICHMENT: self._check_enrichment(args) e = Enrichment() e.do(# Inputs args.annotation_matrix, args.annotation_file, args.metadata, args.modules, args.abundances, args.do_all, args.do_ivi, args.do_gvg, args.do_ivg, args.pval_cutoff, args.proportions_cutoff, args.threshold, args.multi_test_correction, args.output) elif args.subparser_name == self.COMPARE: self._check_compare(args) c = Compare() c.do(args.enrichm_annotate_output) elif(args.subparser_name == NetworkAnalyser.PATHWAY or args.subparser_name == NetworkAnalyser.EXPLORE or args.subparser_name == NetworkAnalyser.TRAVERSE): self._check_network(args) na=NetworkAnalyser(args.metadata) na.do(args.matrix, args.transcriptome, args.metabolome, args.depth, args.filter, args.limit, args.queries, args.subparser_name, args.starting_compounds, args.steps, args.number_of_queries, args.output) logging.info('Done!')
def save_feedback(): if request.method == 'POST': ques_1 = request.form.get('ques_1') ques_2 = request.form.get('ques_2') ques_3 = request.form.get('ques_3') ques_4 = request.form.get('ques_4') opinion = request.form.get('opinion') teacher = request.form.get('teacher') teacher_obj = Teacher.query.filter(Teacher.name == teacher).one() positive_score = Classify(opinion).classify() if positive_score > 0.75: feedback_obj = Feedback(ques_1=ques_1, ques_2=ques_2, ques_3=ques_3, ques_4=ques_4, opinion=opinion, teacher=teacher_obj) db.session.add(feedback_obj) db.session.commit() return make_response("Feedback Posted Successfully!") else: return make_response( "Invalid Feedback. Please check your language quality") else: query_1 = [ Feedback.query.filter(Feedback.ques_1.in_([1])).count(), Feedback.query.filter(Feedback.ques_1.in_([2])).count(), Feedback.query.filter(Feedback.ques_1.in_([3])).count(), Feedback.query.filter(Feedback.ques_1.in_([4])).count(), Feedback.query.filter(Feedback.ques_1.in_([5])).count() ] query_2 = [ Feedback.query.filter(Feedback.ques_2.in_([1])).count(), Feedback.query.filter(Feedback.ques_2.in_([2])).count(), Feedback.query.filter(Feedback.ques_2.in_([3])).count(), Feedback.query.filter(Feedback.ques_2.in_([4])).count(), Feedback.query.filter(Feedback.ques_2.in_([5])).count() ] query_3 = [ Feedback.query.filter(Feedback.ques_3.in_([1])).count(), Feedback.query.filter(Feedback.ques_3.in_([2])).count(), Feedback.query.filter(Feedback.ques_3.in_([3])).count(), Feedback.query.filter(Feedback.ques_3.in_([4])).count(), Feedback.query.filter(Feedback.ques_3.in_([5])).count() ] query_4 = [ Feedback.query.filter(Feedback.ques_4.in_([1])).count(), Feedback.query.filter(Feedback.ques_4.in_([2])).count(), Feedback.query.filter(Feedback.ques_4.in_([3])).count(), Feedback.query.filter(Feedback.ques_4.in_([4])).count(), Feedback.query.filter(Feedback.ques_4.in_([5])).count() ] opinion_1 = [] for i in Feedback.query.all(): opinion_1.append(i.opinion) resp = { "query_1": query_1, "query_2": query_2, "query_3": query_3, "ques_4": query_4, "opinion": opinion_1 } return jsonify(resp)
class Ui_MainWindow(object): def fromfile(self): self.fromfile = TweetFetch() f = self.fromfile.fetchFromFile() self.textEdit.setText(f) self.textEdit_3.setText("Tweet Fetched from file") def fromtwitter(self): self.fromtwitter = TweetFetch() self.fromtwitter.status() f = self.fromtwitter.fetchFromTwitter() self.textEdit.setText(f) self.textEdit_3.setText("Tweet Fetched from Twitter") def cl(self): self.cl = Classify() a = self.cl.classify_r1() self.textEdit_2.setText(a + ' >>') b = self.cl.classify_r2(a) self.textEdit_2.append(b) self.textEdit_3.setText("Tweet Classfied") def setupUi(self, MainWindow): MainWindow.setObjectName("MainWindow") MainWindow.resize(579, 458) self.centralwidget = QtWidgets.QWidget(MainWindow) self.centralwidget.setObjectName("centralwidget") self.pushButton = QtWidgets.QPushButton(self.centralwidget) self.pushButton.setGeometry(QtCore.QRect(30, 140, 151, 27)) self.pushButton.setObjectName("pushButton") self.pushButton.clicked.connect(self.fromfile) self.pushButton_2 = QtWidgets.QPushButton(self.centralwidget) self.pushButton_2.setGeometry(QtCore.QRect(90, 300, 85, 27)) self.pushButton_2.setObjectName("pushButton_2") self.pushButton_2.clicked.connect(self.cl) self.textEdit = QtWidgets.QTextEdit(self.centralwidget) self.textEdit.setGeometry(QtCore.QRect(220, 130, 301, 101)) self.textEdit.setObjectName("textEdit") self.textEdit.setReadOnly(True) self.textEdit_2 = QtWidgets.QTextEdit(self.centralwidget) self.textEdit_2.setGeometry(QtCore.QRect(220, 250, 301, 171)) self.textEdit_2.setObjectName("textEdit_2") self.textEdit_2.setReadOnly(True) self.line = QtWidgets.QFrame(self.centralwidget) self.line.setGeometry(QtCore.QRect(0, 230, 611, 16)) self.line.setFrameShape(QtWidgets.QFrame.HLine) self.line.setFrameShadow(QtWidgets.QFrame.Sunken) self.line.setObjectName("line") self.label = QtWidgets.QLabel(self.centralwidget) self.label.setGeometry(QtCore.QRect(20, 10, 541, 20)) font = QtGui.QFont() font.setPointSize(10) self.label.setFont(font) self.label.setObjectName("label") self.textEdit_3 = QtWidgets.QTextEdit(self.centralwidget) self.textEdit_3.setGeometry(QtCore.QRect(220, 60, 301, 41)) self.textEdit_3.setObjectName("textEdit_3") self.textEdit_3.setReadOnly(True) self.label_2 = QtWidgets.QLabel(self.centralwidget) self.label_2.setGeometry(QtCore.QRect(10, 70, 181, 20)) font = QtGui.QFont() font.setPointSize(10) font.setItalic(False) self.label_2.setFont(font) self.label_2.setObjectName("label_2") self.line_2 = QtWidgets.QFrame(self.centralwidget) self.line_2.setGeometry(QtCore.QRect(0, 110, 601, 16)) self.line_2.setFrameShape(QtWidgets.QFrame.HLine) self.line_2.setFrameShadow(QtWidgets.QFrame.Sunken) self.line_2.setObjectName("line_2") self.pushButton_3 = QtWidgets.QPushButton(self.centralwidget) self.pushButton_3.setGeometry(QtCore.QRect(30, 200, 151, 27)) self.pushButton_3.setObjectName("pushButton_3") self.pushButton_3.clicked.connect(self.fromtwitter) MainWindow.setCentralWidget(self.centralwidget) self.statusbar = QtWidgets.QStatusBar(MainWindow) self.statusbar.setObjectName("statusbar") MainWindow.setStatusBar(self.statusbar) self.retranslateUi(MainWindow) QtCore.QMetaObject.connectSlotsByName(MainWindow) def retranslateUi(self, MainWindow): _translate = QtCore.QCoreApplication.translate MainWindow.setWindowTitle(_translate("MainWindow", "MainWindow")) self.pushButton.setText( _translate("MainWindow", "Fetch Tweet from File")) self.pushButton_2.setText(_translate("MainWindow", "Classify")) self.label.setText( _translate( "MainWindow", "Welcome to Twitter Classifier! This system classifies tweet into 3 level deep cateorization" )) self.label_2.setText( _translate("MainWindow", "Status of Processing Request")) self.pushButton_3.setText( _translate("MainWindow", "Fetch Tweet from Twitter"))
def main(): parser = argparse.ArgumentParser( description="process all JSON files in the given directory" "outputting the results in the given filename") parser.add_argument("parse_dir", help="enter the directory to parse") parser.add_argument( "output_file", help="enter the file where the results will be written") parser.add_argument("-v", "--verbose", action="store_true", help="set verbose output") parser.add_argument("-s", "--skip", action="store_true", help="skip parsing the files") args = parser.parse_args() if args.verbose: printer = Printer(True) else: printer = Printer(False) p_dir = args.parse_dir output_file = args.output_file if not args.skip: printer.standard_output( 'Chosen directory %s. Wait for file: %s to be generated' % (p_dir, output_file)) printer.standard_output('verbose is set to: %r' % printer.get_verbose()) printer.write_file(output_file, '', 'w') parsing = Parser(printer) parsing.parse_files(p_dir, output_file) in_dir = "docs/" in_file = "classify.json" classifier = Classify(printer) classifier.classify(output_file, in_dir, in_file) type = 'apis' cat_dir = 'docs/randep-binary-maps/%s/' % type grap_dir = 'docs/randep-binary-maps/graphs/' plotter = Plot() regex = re.compile(r'^(.*?)[-|\.]json') for (dir_path, dir_names, file_names) in walk(cat_dir): for i, name in enumerate(file_names): if name.endswith('.json'): # only get the proper name of the file file_name = re.match(regex, name).group(1) printer.line_comment("Generate graph from json file: " + name) api_names, start_times, end_times, state_names, state_starts, state_ends, class_names, class_starts, \ class_ends, state_dict = \ classifier.get_api_data(dir_path + name, type) plotter.plots(grap_dir + 'apis/' + file_name, api_names, start_times, end_times) plotter.plots(grap_dir + 'states/' + file_name, state_names, state_starts, state_ends) plotter.plots(grap_dir + 'classes/' + file_name, class_names, class_starts, class_ends) for state in state_dict: plotter.plots( grap_dir + 'states/api_per_state/' + file_name + '-' + state, state_dict[state]['apis'], state_dict[state]['starts'], state_dict[state]['ends'])