Python arff.load方法代码示例

# 需要导入模块: import arff [as 别名]
# 或者: from arff import load [as 别名]
def read_arff(file_path, misplaced_list):
    misplaced = False
    for item in misplaced_list:
        if item in file_path:
            misplaced = True

    file = arff.load(open(file_path))
    data_value = np.asarray(file['data'])
    attributes = file['attributes']

    X = data_value[:, 0:-2]
    if not misplaced:
        y = data_value[:, -1]
    else:
        y = data_value[:, -2]
    y[y == 'no'] = 0
    y[y == 'yes'] = 1
    y = y.astype('float').astype('int').ravel()

    if y.sum() > len(y):
        print(attributes)
        raise ValueError('wrong sum')

    return X, y, attributes 

# 需要导入模块: import arff [as 别名]
# 或者: from arff import load [as 别名]
def gsCreation():
	#We load ARFF files countaining ratings
	print("Reading individual ratings...")
	rGoldIndiv = openingRatingIndividual()
	print("Computing inter-rater agreement on raw...")
	seq = []
	for i in range(v.nAn):
		seq.append(i)
	#We take the combination list for each rater
	combnk = combinListe(seq,2)
	#We get the names of files
	files = listFiles()
	#We compute the agreement between each rater of this list
	ra = ratersAgreement(rGoldIndiv, combnk, files)
	#We compute the agreement of each rater
	aRa = raterAgreement(ra, combnk, files)
	#print aRa
	#print sum(aRa)
	print("Perform CCC centring...")
	cccCentring(ra, combnk, files, aRa, rGoldIndiv)
#End gsCreation 

# 需要导入模块: import arff [as 别名]
# 或者: from arff import load [as 别名]
def load_iot():
    """ Loads iot data

    Sensor stream contains information (temperature, humidity, light, and sensor voltage) collected from 54 sensors deployed
    in Intel Berkeley Research Lab. The whole stream contains consecutive information recorded over a 2 months
    period (1 reading per 1-3 minutes). I used the sensor ID as the class label, so the learning task of the stream is
    to correctly identify the sensor ID (1 out of 54 sensors) purely based on the sensor data and the corresponding recording
    time.

    While the data stream flow over time, so does the concepts underlying the stream. For example, the lighting during
    the working hours is generally stronger than the night, and the temperature of specific sensors (conference room)
    may regularly rise during the meetings.

    Returns
    -------
    pandas DataFrame
    """
    dataset = arff.load(open(reduce(os.path.join, _IOT_PATH, _get_datapath())))
    columns = [i[0] for i in dataset['attributes']]
    return pd.DataFrame(dataset['data'], columns=columns) 

# 需要导入模块: import arff [as 别名]
# 或者: from arff import load [as 别名]
def load_bci():
    """ Loads BCI data

    Contains measurements from 64 EEG sensors on the scalp of a single participant. 
    The purpose of the recording is to determine from the electrical brain activity when the participant is paying attention.

    Returns
    -------
    A tuple containing four numpy arrays
        train features
        train labels
        test features
        test labels
    """

    npzfile = np.load(reduce(os.path.join, _BCI_PATH, _get_datapath()))
    return npzfile['train_X'], npzfile['train_y'], npzfile['test_X'], npzfile['test_y'] 

# 需要导入模块: import arff [as 别名]
# 或者: from arff import load [as 别名]
def main(opts):
    for ai, afile in tqdm.tqdm(enumerate(opts.arff_files), total=len(opts.arff_files)):
        with open(afile) as af:
            data = arff.load(af)
            attrs = [at[0] for at in data['attributes']]
            f0_idx = attrs.index('F0_sma')
            data = data['data']
            array = []
            X = []
            for dpoint in data:
                # ignore name, timestamp and class
                f0_val = dpoint[f0_idx]
                if f0_val > 0:
                    dpoint[f0_idx] = np.log(f0_val)
                else:
                    dpoint[f0_idx] = -1e10
                array.append(dpoint[2:-1])
            array = np.array(array, dtype=np.float32)
            lf0, _ = interpolation(array[:, -1], -1e10)
            array[:, -1] = lf0
            if opts.out_stats is not None:
                X.append(array)
            npfile = os.path.splitext(afile)[0]
            np.save(os.path.join(npfile), array.T)
    if opts.out_stats is not None:
        X = np.concatenate(X, axis=0)
        mn = np.mean(X, axis=0)
        sd = np.std(X, axis=0)
        with open(opts.out_stats, 'wb') as out_f:
            pickle.dump({'mean':mn, 'std':sd}, out_f) 

# 需要导入模块: import arff [as 别名]
# 或者: from arff import load [as 别名]
def create_dataframe(data_path=None, records=None, features=None):
        if data_path:
            ds = DataFrame({'data_path': data_path})
            ds.load(features = features)
        else:
            ds = DataFrame({})
            ds.load_records(records, features=features)

        return ds 

# 需要导入模块: import arff [as 别名]
# 或者: from arff import load [as 别名]
def cccCentring(ra, combnk, files, aRa, rGoldIndiv):
	for i in range(len(v.eName)):
		for f, fname in enumerate(files[i][0]):
			meanByF = []
			wghRater = []
			csv = rGoldIndiv[v.eName[i]][f]
			#Firstly we compute the mean of all raters for each file
			for a in range(v.nAn):
				#We get the mean
				meanRatersF = np.nanmean(csv[:,a+1])
				meanByF.append(meanRatersF)	
				#We take the weight of the rater in this file
				wghRater.append(aRa[a][i][f])
			#Now we calculate the ponderate mean of all raters
			pondMean = np.sum(np.multiply(meanByF,wghRater))/np.sum(aRa[:,i,f])
			#We have the mean of all raters, we need the total mean of the file
			meanF = np.nanmean(csv[:,1:])
			#Now we will center each prediction according to the mean
			output = []
			#We prepare the ARFF file, we get the template
			data = arff.load(open(v.arffTempPath,'rb'))
			for line in range(len(csv)-1):
				meanLine = np.nanmean(csv[line+1,1:])
				newGs = meanLine-meanF+pondMean
				#We replace the values in the ARFF template
				data["data"][line][0] = fname.replace(".csv","")
				data["data"][line][1] = round(csv[line+1,0],2)
				data["data"][line][2] = round(newGs,6)
			#We write the csv in the Gold Standard folder
			f = open(v.agsc[i]+fname.replace(".csv",".arff"), "w")
			f.write(arff.dumps(data))	
	return None
#End cccCentring 

# 需要导入模块: import arff [as 别名]
# 或者: from arff import load [as 别名]
def restaurObject(addr):
	f = open(addr,"rb")
	obj = cPickle.load(f)
	f.close()
	return obj
#End restaurObject

#Augment the tab to take context 

# 需要导入模块: import arff [as 别名]
# 或者: from arff import load [as 别名]
def unimodalPredPrep(wSize, wStep, nMod):
	feats = {}
	#We need the number of line for a wStep of v.tsp
	trainLen = len(arff.load(open(v.descNorm[nMod]+"train_"+str(wSize)+"_"+str(v.tsp)+".arff","rb"))['data'])
	#We open corresponding files
	for s in v.part:	
		feats[s] = arff.load(open(v.descNorm[nMod]+s+"_"+str(wSize)+"_"+str(wStep)+".arff","rb"))
		#We put to 0 NaN values
		feats[s] = arffNan(feats[s])
		#We transform it in array
		feats[s] = np.array(feats[s]['data'])
		#We resample it to be at a wSize of v.tsp
		feats[s] = resamplingTab(feats[s], trainLen)
	return feats, trainLen
#End unimodalPredPrep 

# 需要导入模块: import arff [as 别名]
# 或者: from arff import load [as 别名]
def concArff(sourceD, fNames, destinationD, fileName):
	try :
		fNames = sorted(fNames)
		warnings.filterwarnings('ignore', category=UnicodeWarning)
		arffs = {}
		long = 0
		b = 0
		#We verify that the file dont already exist
		if (not os.path.isfile(destinationD+fileName)) :
			for i in range(len(fNames)):
				if (os.path.isfile(sourceD+fNames[i])):
					#We search for the corresponding descriptor with the parameters
					if (i == 0):
						arffs = arff.load(open(sourceD+fNames[i],"rb"))
						long = len(arffs['data'])
					else :
						d = arff.load(open(sourceD+fNames[i],"rb"))
						if (len(d['data']) != long):
							while(len(d['data']) != long):
								lastInd = len(d['data'])-1
								if (len(d['data']) > long):
									del(d['data'][lastInd])
								else :
									d['data'].append(d['data'][lastInd])
						arffs['data'] += d['data']
				else:
					b = 1
		else :
			b = 2
		if (b == 0):
			f = open(destinationD+fileName, "w")
			arffs = removeColArff(arffs)
			f.write(arff.dumps(arffs))
		return b
	except KeyboardInterrupt:
		os.remove(destinationD+fileName)
		raise
#End concatenationArff : Return 0 if the file is written, 1 if one of the files was missing, 2 if the file already exists

#Concatenation of golds standards per partition (test/dev/train) 

# 需要导入模块: import arff [as 别名]
# 或者: from arff import load [as 别名]
def load_dataset_dump(filename):
    """Loads a compressed data set dump

    Parameters
    ----------
    filename : str
        path to dump file, if without .bz2 ending, the .bz2 extension will be appended.

    Returns
    -------
    X : `array_like`, :class:`numpy.matrix` or :mod:`scipy.sparse` matrix, shape=(n_samples, n_features)
        input feature matrix
    y : `array_like`, :class:`numpy.matrix` or :mod:`scipy.sparse` matrix of `{0, 1}`, shape=(n_samples, n_labels)
        binary indicator matrix with label assignments
    names of attributes: List[str]
        list of attribute names for `X` columns
    names of labels: List[str]
        list of label names for `y` columns
    """

    if not os.path.exists(filename):
        raise IOError("File {} does not exist, use load_dataset to download file".format(filename))

    if filename[-4:] != '.bz2':
        filename += ".bz2"

    with bz2.BZ2File(filename, "r") as file_handle:
        data = pickle.load(file_handle)

    return data['X'], data['y'], data['features'], data['labels'] 

# 需要导入模块: import arff [as 别名]
# 或者: from arff import load [as 别名]
def read_ARFF2(file, label_col = None):
    data = arff.load(open(file,'r'))
    
    data = pd.DataFrame(data['data'])
    
    X=data
    y=None
    X,y =_data_to_matrix(X,label_col)

    return X,y 

# 需要导入模块: import arff [as 别名]
# 或者: from arff import load [as 别名]
def load(self, features=None, nrows=None):
        self.categoricals = {}
        self.transforms_log = [[],[],[],[]]

        import csv
        from io import StringIO

        path = self.options['data_path']
        if isinstance(path, StringIO):
            path.seek(0)
            self.df = pd.read_csv(path, encoding='utf-8', escapechar="\\", usecols=features, na_values=['?'], nrows=nrows)
            if self.options.get("targetFeature") in self.df.columns:
                self.dropna([self.options["targetFeature"]])
        else:
            if path.startswith("jdbc:"):
                import psycopg2
                from psycopg2.extensions import parse_dsn
                path = path.replace('sslfactory=org.postgresql.ssl.NonValidatingFactory&', '')
                ary = path.split('tablename')
                path = ary[0]
                tablename = ary[1]
                dataset_name = tablename

                self.dbconn_args = parse_dsn(path[5:])
                conn = psycopg2.connect(**self.dbconn_args)
                self.df = pd.read_sql("select * from %s"%tablename, con=conn)
            else:
                path, remote_path = self._check_remote_path()
                try:
                    self.df = self.load_from_file(path, features=features, nrows=nrows)
                except:
                    if remote_path:
                        logging.exception("Loading local file failed. Download it again...")
                        self.options['data_path'] = remote_path
                        path, remote_path = self._check_remote_path(force_download=True)
                        self.df = self.load_from_file(path, features=features, nrows=nrows)
                    else:
                        raise

                self.dataset_name = os.path.basename(path)

            if self.options.get("targetFeature") in self.df.columns:
                self.dropna([self.options["targetFeature"]])
        return self