Exemplo n.º 1
0
 def __init__(self, name='Meta-DecisionTree', commands=[]):
     """ Initializes the TransitivityInt model.
     Parameters
     ----------
     name : str
         Unique name of the model. Will be used throughout the ORCA
         framework as a means for identifying the model.
     """
     SentimentAnalyzer.initialize()
     self.parameter = {}
     self.componentKeys = Keys.person + Keys.task
     super().__init__(name, ['misinformation'], ['single-choice'], commands)
Exemplo n.º 2
0
 def __init__(self, name='Fast-Frugal-Tree', commands = []):
     """ Initializes the TransitivityInt model.
     Parameters
     ----------
     name : str
         Unique name of the model. Will be used throughout the ORCA
         framework as a means for identifying the model.
     """
     SentimentAnalyzer.initialize()
     self.parameter = {}
     #self.parameter['thresh'] = 10
     self.componentKeys = ['Exciting_Party_Combined', 'Familiarity_Party_Combined', 'Partisanship_Party_Combined','Worrying_Party_Combined','Importance_Party_Combined',  'Partisanship_All_Combined', 'Partisanship_All_Partisan']
     super().__init__(name, ['misinformation'], ['single-choice'], commands)
Exemplo n.º 3
0
 def __init__(self, name='Fast-Frugal-Tree-ZigZag(Z+)', commands=[]):
     """ Initializes the model.
     Parameters
     ----------
     name : str
         Unique name of the model. Will be used throughout the ORCA
         framework as a means for identifying the model.
     """
     SentimentAnalyzer.initialize()
     self.parameter = {}
     #self.parameter['thresh'] = 1
     self.fft = None
     self.lastnode = None
     self.componentKeys = Keys.person + Keys.task
     super().__init__(name, ['misinformation'], ['single-choice'], commands)
Exemplo n.º 4
0
    def toDFFormat(self, trialList):
        featList = []
        for item in trialList:
            if item.conservatism < 3.5:
                componentKeys = [a.replace('Party','Democrats') for a in self.componentKeys]
            if item.conservatism > 3.5:
                componentKeys = [a.replace('Party','Republicans') for a in self.componentKeys]
            newPars = [item.birep, item.conservatism, item.gender, #int(item.truthful), 
                item.crt, item.cons, item.accimp] 
            newPars += [item.itemComponents[a] for a in componentKeys] + [SentimentAnalyzer.analysis(item)[a] for a in SentimentAnalyzer.relevant]                     
            newPars += [item.panas[a] for a in item.panas.keys()] + [item.media[a] for a in item.media.keys()]
            featList.append(newPars)

        compKeys = [a[:3] + a.split('_')[1][:1] + a.split('_')[2][:1] for a in self.componentKeys]
        media = ['Media1_Some people t','Media1_In presenting','Media3_1_To what ext','Media3_2_To what ext','Media3_3_To what ext','Media3_11_To what ex','Media3_12_To what ex'] 
        panas = ['PANAS_' + str(i) for i in range(1, 21)]
        cat_columns = ['ct','Gender'] #'truthful']
        nr_columns = ['crt', 'cons','AccImp'] + compKeys  + SentimentAnalyzer.relevant + panas + media
        data_columns = ['response'] + cat_columns + nr_columns
        data = pd.DataFrame(data=featList, columns=data_columns)
        for col in cat_columns:
            data[col] = data[col].astype('category')
            for col in nr_columns:
                if data[col].dtype != 'float' and data[col].dtype != 'int':
                    print('type error: ' + data[col])
                    data.loc[data[col] == '?', col] = np.nan
                    data[col] = data[col].astype('float')
        data['response'] = data['response'].apply(lambda x: True if x==1 else False).astype(bool)
        return data
Exemplo n.º 5
0
 def predictS(self, trial):
     analysis = SentimentAnalyzer.analysis(trial)
     p = 0
     for a in self.relevant:
         p += analysis[a] * self.parameter[a]
     #print(p)
     return 1 if self.thresh < p else 0
Exemplo n.º 6
0
def itemsList(source):
    itemsList = []
    linecount = 0
    indcount = 0
    line1 = True
    lines = open('/home/hippo/git/news-reasoning/benchmarks/misinformation/' +
                 source + '.csv')
    ind = {}
    for line in lines:
        listLine = line.replace('\r', '').replace('\n', '').split(',')
        if line1:
            line1 = False
            for key in listLine:
                ind[key] = indcount
                indcount += 1
            continue
        panasPos = [
            'PANAS_' + str(i) for i in [1, 3, 5, 9, 10, 14, 16, 17, 19]
        ]
        panasNeg = [
            'PANAS_' + str(i) for i in [2, 4, 6, 7, 8, 11, 12, 13, 15, 18, 20]
        ]
        personfeatures = {
            'crt': float(listLine[ind['crt']]),
            'conservatism': listLine[ind['conservatism']],
            'ct': int(listLine[ind['ct']]),
            'education': int(listLine[ind['education']]),
            'gender': listLine[ind['gender']],
            'accimp': float(listLine[ind['accimp']]),
            'panasPos': float(listLine[ind['panasPos']]),
            'panasNeg': float(listLine[ind['panasNeg']]),
            'reaction_time': float(listLine[ind['reaction_time']])
        }
        taskfeatures = {}
        os.chdir(
            "/home/hippo/git/news-reasoning/benchmarks/misinformation/data/study2"
        )
        for modelfile in glob.glob("with*"):
            no = False
            for a in ['ecision', 'Pers', 'inear', 'ecommend', 'Tree']:
                if a in modelfile:
                    no = True
            if no:
                continue
            taskfeatures[modelfile] = float(listLine[ind[modelfile]])

        if Keys.person == None:
            Keys.person = [a for a in personfeatures.keys()]
        if Keys.task == None:
            SentimentAnalyzer.initialize()
            Keys.task = [
                a for a in taskfeatures.keys() if 'ikelihood' not in a
            ]
            Keys.task += [a for a in SentimentAnalyzer.relevant]

        linecount += 1
        itemsList.append(
            Item(listLine[ind['id']],
                 listLine[ind['domain']],
                 listLine[ind['task']],
                 listLine[ind['response_type']],
                 listLine[ind['choices']],
                 listLine[ind['trial']],
                 float(listLine[ind['crt']]),
                 bool('T' in listLine[ind['realnews']]),
                 bool('T' in listLine[ind['acc']]),
                 bool('T' in listLine[ind['birep']]),
                 str(listLine[ind['response']]),
                 persFeat=personfeatures,
                 taskFeat=taskfeatures))
    return itemsList
Exemplo n.º 7
0
def itemsList(source):
    itemsList = []
    linecount = 0
    indcount = 0
    line1 = True
    lines = open(
        '/home/hippo/git/news-reasoning/benchmarks/misinformation/data/' +
        source + '.csv')
    ind = {}
    for line in lines:
        listLine = line.replace('\r', '').replace('\n', '').split(',')
        if line1:
            line1 = False
            for key in listLine:
                ind[key] = indcount
                indcount += 1
            continue

        linecount += 1
        if listLine[ind['_accurate']] == '':
            continue

        crtresults = []
        itemComponents = {}
        panas = {}
        media = {}
        if 'DemRep_C_current' in ind.keys():
            if '' == listLine[ind['DemRep_C_current']]:
                continue
            conservatism = float(listLine[ind['DemRep_C_current']])
        elif 'Conservatism' in ind.keys():
            conservatism = float(listLine[ind['Conservatism']]) * 7 / 5
        elif 'Conserv' in ind.keys():
            try:
                conservatism = float(listLine[ind['Conserv']]) * 7 / 5
            except:
                continue
        if '' == conservatism:
            continue
        for item in ind.keys():
            if item in [
                    'Exciting_Democrats_Combined',
                    'Exciting_Republicans_Combined',
                    'Familiarity_Democrats_Combined',
                    'Familiarity_Republicans_Combined',
                    'Importance_Democrats_Combined',
                    'Importance_Republicans_Combined',
                    'Likelihood_Democrats_Combined',
                    'Likelihood_Republicans_Combined',
                    'Partisanship_All_Combined', 'Partisanship_All_Partisan',
                    'Partisanship_Democrats_Combined',
                    'Partisanship_Republicans_Combined',
                    'Worrying_Democrats_Combined',
                    'Worrying_Republicans_Combined'
            ]:  #'Sharing_Democrats_Combined', 'Sharing_Republicans_Combined',
                itemComponents[item] = float(listLine[ind[item]])
            elif 'CRT1' in item or 'CRT3' in item:
                crtresults.append(
                    float(listLine[ind[item]] in item.split('_')[1].split(':')
                          [1:]))
            elif 'PANAS' in item and 'Inst' not in item:
                if listLine[ind[item]] == '':
                    #logstr('One panas error', listLine[ind['id']], item)
                    panas[item.split('_T')[0]] = None
                    continue
                panas[item.split('_T')[0]] = float(listLine[ind[item]])
            elif 'AccImp_How important' in item:
                accimp = float(listLine[ind[item]])
            elif 'Gender_What' in item:
                gender = float(listLine[ind[item]])
            elif 'Sex' == item:
                try:
                    gender = float(listLine[ind[item]])
                except:
                    gender = 'NoInfo'

        crt = sum(crtresults) / len(crtresults)
        panasPos = [
            'PANAS_' + str(i) for i in [1, 3, 5, 9, 10, 14, 16, 17, 19]
        ]
        panasNeg = [
            'PANAS_' + str(i) for i in [2, 4, 6, 7, 8, 11, 12, 13, 15, 18, 20]
        ]
        for a in ['_RT_2_Timing-Last Click', '_RT_accurate', '_A_RT_accurate']:
            if a not in ind.keys():
                continue
            try:
                react_time = float(listLine[ind[a]])
            except:
                react_time = 'NoInfo'
        if react_time == 'NoInfo':
            continue
        for a in ['ClintonTrump', 'POTUS2016_Who did yo']:
            if a not in ind.keys():
                continue
            try:
                ct = int(listLine[ind[a]])
            except:
                ct = 'NoInfo'
                print('ct:', listLine[ind[a]])
        for a in ['Education', 'Education_What is th']:
            if a not in ind.keys():
                continue
            try:
                edu = int(listLine[ind[a]])
            except:
                edu = 'NoInfo'
        if 'AccImp_How important' not in ind.keys():
            accimp = 'NoInfo'

        personfeatures = {
            'crt':
            float(crt),
            'conservatism':
            conservatism,
            'ct':
            ct,
            'education':
            edu,
            'gender':
            gender,
            'accimp':
            accimp,
            'panasPos':
            sum(panas[a] for a in panasPos
                if panas[a] != None) if len(panas.keys()) > 0 else 'NoInfo',
            'panasNeg':
            sum(panas[a] for a in panasNeg
                if panas[a] != None) if len(panas.keys()) > 0 else 'NoInfo',
            'reaction_time':
            react_time
        }
        nokeys = []
        #        for a in personfeatures.keys():
        #            if personfeatures[a] == 'NoInfo':
        #                nokeys.append(a)
        #        for a in nokeys:
        #            personfeatures.pop(a)
        taskfeatures = {}
        for a in itemComponents.keys():
            if conservatism >= 3.5:
                if 'Democrats' in a:
                    continue
                else:
                    key = a.replace('Republicans', 'Party')
            elif conservatism <= 3.5:
                if 'Republicans' in a:
                    continue
                else:
                    key = a.replace('Democrats', 'Party')
            taskfeatures[key] = itemComponents[a]
        if Keys.person == None:
            Keys.person = [a for a in personfeatures.keys()]
        if Keys.task == None:
            SentimentAnalyzer.initialize()
            Keys.task = [
                a for a in taskfeatures.keys() if 'ikelihood' not in a
            ]
            Keys.task += [a for a in SentimentAnalyzer.relevant]

        newItem = Item(listLine[ind['id']],
                       listLine[ind['domain']],
                       listLine[ind['task']],
                       listLine[ind['response_type']],
                       listLine[ind['choices']],
                       listLine[ind['sequence']],
                       float(crt),
                       bool(int(listLine[ind['truthful']])),
                       bool(int(listLine[ind['_accurate']])),
                       bool(int(listLine[ind['binaryResponse']])),
                       str(listLine[ind['response']]),
                       persFeat=personfeatures,
                       taskFeat=taskfeatures)

        itemsList.append(newItem)
    return itemsList