Merge branch 'ChemometricMethods' into ResultGeneration

.gitignore

@@ -6,3 +6,11 @@ __pycache__/
 *.png
 
 *.res
+
+cythonModules/build/
+
+*.c
+
+*.pyd
+
+*.html

chemometricMethods.py

+import numpy as np
+import cv2
+from sklearn.preprocessing import StandardScaler
+from sklearn.decomposition import PCA
+from sklearn.cluster import DBSCAN
+from scipy import spatial
+from itertools import combinations
+from random import sample
+
+import time
+import sys
+sys.path.append("C://Users//xbrjos//Desktop//Python")
+from gepard.analysis.particleContainer import ParticleContainer
+from gepard.analysis import particleAndMeasurement as pm
+from methods import SubsamplingMethod
+
+
+def get_pca(data: np.ndarray, numComp: int = 2) -> np.ndarray:
+    try:
+        standardizedData = StandardScaler().fit_transform(data.copy())
+    except ValueError:
+        print('first standardscaler attempt failed, retrying..')
+        print('datashape', data.shape)
+        print('unique:', np.unique(data))
+        raise
+    pca = PCA(n_components=numComp)
+    princComp: np.ndarray = pca.fit_transform(np.transpose(standardizedData))
+    return princComp
+
+
+def do_DBSCAN_clustering(data: np.ndarray, eps: float = 0.1, min_samples: int = 10) -> tuple:
+    """
+    Does DBSCAN clustering and finds noisy data
+    :param data: The input array
+    :param eps:
+    :param min_samples:
+    :return: Cluster labels for each point in the dataset given to fit(). Noisy samples are given the label -1.
+    """
+    assert data.shape[1] == 2
+    standardizedData = StandardScaler().fit_transform(data)
+    db = DBSCAN(eps=eps, min_samples=min_samples).fit(standardizedData)
+    return db.labels_, db.core_sample_indices_
+
+
+def get_n_points_closest_to_point(points: np.ndarray, n: int, refPoint: np.ndarray) -> list:
+    """
+    Returns a list with indices of n points that are closest to the indicated refPoint
+    :param points: np.ndarray, cols: x, y, rows: individual points
+    :param n: number of points to return
+    :param refPoint: np.array([x, y]) of reference point
+    :return: list of point indices
+    """
+    distancesToPoints: np.ndarray = np.linalg.norm(points - refPoint, axis=1)
+    sortedIndices = np.argsort(distancesToPoints)
+    return list(sortedIndices[:n])
+
+
+class ChemometricSubsampling(SubsamplingMethod):
+    def __init__(self, particleContainer: ParticleContainer, desiredFraction: float):
+        super(ChemometricSubsampling, self).__init__(particleContainer, desiredFraction)
+
+    @property
+    def label(self) -> str:
+        return 'Chemometric Selection'
+
+    def apply_subsampling_method(self) -> list:
+        vectors: np.ndarray = self._get_particle_featurematrix()
+        try:
+            princComps: np.ndarray = get_pca(vectors)
+        except ValueError:
+            print('numParticles:', len(self.particleContainer.particles))
+            print('input featurematrix shape', vectors.shape)
+        clusterLabels, coreIndices = do_DBSCAN_clustering(princComps)
+        indices: list = self._get_indices_from_clusterLabels(princComps, clusterLabels, coreIndices)
+
+        selectedParticles: list = []
+        for particle in self.particleContainer.particles:
+            if particle.index in indices:
+                selectedParticles.append(particle)
+
+        return selectedParticles
+
+    def _get_particle_featurematrix(self) -> np.ndarray:
+        """
+        :return: np.ndarray, numRows: Features, numCols: Particles
+        """
+        vectors: list = []
+        for particle in self.particleContainer.particles:
+            extractor: FeatureExtractor = FeatureExtractor(particle)
+            vectors.append(extractor.get_characteristic_vector())
+        vectors: np.ndarray = np.transpose(np.array(vectors))
+        assert vectors.shape == (11, len(self.particleContainer.particles)), f'wrong featureMat-shape: {vectors.shape}'
+        return vectors
+
+    def equals(self, otherMethod) -> bool:
+        equals: bool = False
+        if type(otherMethod) == ChemometricSubsampling and otherMethod.fraction == self.fraction:
+            equals = True
+        return equals
+
+    def _get_indices_from_clusterLabels(self, points: np.ndarray, labels: np.ndarray, centerIndices: np.ndarray) -> list:
+        indices: list = []
+        allIndices: np.ndarray = np.arange(len(labels))
+        numPointsPerCluster: dict = self._get_numPoints_per_cluster(labels)
+
+        for clusterIndex in set(labels):
+            indToAppend: list = []
+            nPoints: int = int(numPointsPerCluster[clusterIndex])
+            indicesInCluster: np.ndarray = allIndices[labels == clusterIndex]
+            if clusterIndex == -1:
+                for ind in sample(list(indicesInCluster), nPoints):
+                    # assert ind not in indices
+                    indices.append(ind)
+            else:
+                clusterPoints: np.ndarray = points[indicesInCluster]
+                centerPoint: np.ndarray = np.mean(clusterPoints, axis=0)
+                indicesToSelect: list = get_n_points_closest_to_point(clusterPoints, nPoints, centerPoint)
+                for ind in indicesToSelect:
+                    origInd = indicesInCluster[ind]
+                    indices.append(origInd)
+
+        assert len(set(indices)) == len(indices), f'The calculated indices contain duplicates, ' \
+                                                  f'num duplicates: {len(indices) - len(set(indices))}'
+        return indices
+
+    def _get_numPoints_per_cluster(self, labels: np.ndarray, noiseAmpFactor: float = 5) -> dict:
+        """
+        MP Particles are expected to be the minority of all particles. So, if datapoints were classified as noise
+        (i.e., label = -1), it is likely that MP is in there. The abundancy of points taken from the noise is multiplied
+        by the noiseAmpFactor
+        :param labels:
+        :param noiseAmpFactor:
+        :return: A dictionary with keys = cluster index (i.e., label) and value = number of points to take from that
+        """
+        pointsPerCluster: dict = {}
+        if type(labels) != np.ndarray:
+            labels = np.array(labels)
+        individualLabels: set = set(labels)
+        numPointsToSelect = round(len(labels) * self.fraction)
+        if numPointsToSelect == 0:
+            numPointsToSelect = 1
+
+        numNoisePoints = len(labels[labels == -1])
+        numClusteredPoints = len(labels) - numNoisePoints
+
+        # # get max noiseAmpFactor
+        if noiseAmpFactor > 1/self.fraction:
+            noiseAmpFactor = 1/self.fraction
+
+        numAmpPoints = numClusteredPoints + numNoisePoints*noiseAmpFactor
+        fractionPerCluster = np.clip(numPointsToSelect / numAmpPoints, 0.0, 1.0)
+
+        tooFewPoints = numPointsToSelect < len(individualLabels)
+
+        totalPointsAdded = 0
+        for ind in individualLabels:
+            if ind > -1:
+
+                if not tooFewPoints:
+                    pointsToAdd = round(fractionPerCluster * len(labels[labels == ind]))
+                else:
+                    pointsToAdd = 1 if totalPointsAdded < numPointsToSelect else 0
+
+                pointsPerCluster[ind] = pointsToAdd
+                totalPointsAdded += pointsToAdd
+
+        # fill up the rest with noisePoints
+        if numNoisePoints > 0:
+            diff: float = np.clip(numPointsToSelect - totalPointsAdded, 0, numNoisePoints)
+            pointsPerCluster[-1] = diff
+            totalPointsAdded += diff
+
+        # just in case too many points were selected (due to rounding errors), keep on deleting until it matches
+        while totalPointsAdded > numPointsToSelect:
+            indexWithHighestCount = None
+            maxCount = 0
+            for index in pointsPerCluster.values():
+                if pointsPerCluster[index] > maxCount:
+                    maxCount = pointsPerCluster[index]
+                    indexWithHighestCount = index
+
+            pointsPerCluster[indexWithHighestCount] -= 1
+            totalPointsAdded -= 1
+
+        if not abs(totalPointsAdded - numPointsToSelect) <= 1:
+            print('error')
+        # assert abs(totalPointsAdded - numPointsToSelect) <= 1
+        for clusterIndex in pointsPerCluster.keys():
+            assert 0 <= pointsPerCluster[clusterIndex] <= len(labels[labels == clusterIndex])
+        return pointsPerCluster
+
+
+class FeatureExtractor(object):
+    def __init__(self, particle: pm.Particle):
+        super(FeatureExtractor, self).__init__()
+        self.particle: pm.Particle = particle
+
+    def get_characteristic_vector(self) -> np.ndarray:
+        log_hu: np.ndarray = self._get_log_hu_moments()
+        color: np.ndarray = self._get_color_hash(self.particle.color, desiredLength=4)
+        vector: np.ndarray = np.hstack((log_hu, color))
+        if len(vector) != 11:
+            print('error')
+        assert len(vector) == 7 + 4, f'wrong feature vector: {vector} with shape: {vector.shape}'
+        return vector
+
+    def _get_log_hu_moments(self) -> np.ndarray:
+        moments: dict = cv2.moments(self.particle.contour)
+        resultMoments: np.ndarray = np.zeros((7, 1))
+        for index, mom in enumerate(cv2.HuMoments(moments)):
+            if mom != 0:
+                resultMoments[index] = -1 * np.copysign(1.0, mom) * np.log10(abs(mom))
+            else:
+                resultMoments[index] = 0
+
+        return resultMoments[:, 0]
+
+    def _get_color_hash(self, color: str, desiredLength: int = 4) -> np.ndarray:
+        colorArray: list = [int(i) for i in str(abs(hash(color)))[:desiredLength]]
+        return np.transpose(np.array(colorArray))

cythonModules/rotateContour.pyx

+import numpy as np
+cimport numpy as np
+cimport cython
+
+DTYPE = np.float
+ctypedef np.float_t DTYPE_t
+ctypedef np.int32_t INT32_t
+
+def rotate_contour_around_point(np.ndarray[DTYPE_t, ndim=3] contour, np.ndarray[DTYPE_t, ndim=1] refPoint, np.float angleDegree):
+# def rotate_contour_around_point(contour: np.ndarray, refPoint: tuple, angleDegree: float) -> np.ndarray:
+    """
+    Rotates a point around another one...
+    :param contour: Array of points to be rotated, [:, 0, 0] = x, [:, 0, 1] = y
+    :param refPoint: The referemce point around which the first point is rotated, tuple of x and y
+    :param angleDegree: The angle in degree to rotate (counter-clockwise)
+    :return: Array of the rotated point, [:, 0, 0] = x, [:, 0, 1] = y
+    """
+    cdef int i
+    cdef double theta, sin, cos, x, y
+    cdef np.ndarray[DTYPE_t, ndim=3] newContour
+
+    theta = np.deg2rad(angleDegree)
+    sin = np.sin(theta)
+    cos = np.cos(theta)
+    newContour = np.zeros_like(contour, dtype=np.float)
+    for i in range(contour.shape[0]):
+        x: float = cos * (contour[i, 0, 0]-refPoint[0]) - sin * (contour[i, 0, 1]-refPoint[1]) + refPoint[0]
+        y: float = sin * (contour[i, 0, 0]-refPoint[0]) + cos * (contour[i, 0, 1]-refPoint[1]) + refPoint[1]
+        newContour[i, 0, 0] = x
+        newContour[i, 0, 1] = y
+
+    return newContour

cythonModules/setup_cython.py

+# try:
+from setuptools import setup
+from setuptools import Extension
+from Cython.Build import cythonize
+import numpy as np
+import sys
+
+if len(sys.argv) == 1:
+    sys.argv.append("build_ext")
+    sys.argv.append("--inplace")
+
+ext = Extension("rotateContour", ["rotateContour.pyx"], extra_compile_args=['-O3'],)
+
+setup(
+    name="rotate contour around reference point",
+    ext_modules=cythonize([ext], annotate=True),  # accepts a glob pattern
+    include_dirs=[np.get_include()]
+)
\ No newline at end of file

evaluation.py

@@ -14,6 +14,7 @@ import matplotlib.pyplot as plt
 from helpers import ParticleBinSorter
 import methods as meth
 import geometricMethods as gmeth
+import chemometricMethods as cmeth
 sys.path.append("C://Users//xbrjos//Desktop//Python")
 from gepard import dataset
 
@@ -23,9 +24,11 @@ def get_name_from_directory(dirPath: str) -> str:
 
 
 class TotalResults(object):
-    methods: list = [meth.RandomSampling, meth.SizeBinFractioning, gmeth.CrossBoxSubSampling,
-                     gmeth.SpiralBoxSubsampling]
-    measuredFreactions: list = [0.05, 0.1, 0.15, 0.2, 0.3, 0.5, 0.9]
+    # methods: list = [meth.RandomSampling, meth.SizeBinFractioning, gmeth.CrossBoxSubSampling,
+    #                  gmeth.SpiralBoxSubsampling, cmeth.ChemometricSubsampling]
+    measuredFractions: list = [0.01, 0.05, 0.1, 0.15, 0.2, 0.5, 0.75, 0.9]
+    # measuredFractions: list = [0.1, 0.15, 0.2, 0.5, 0.75, 0.9]
+    # measuredFractions: list = [0.1, 0.3, 0.5, 0.9]
 
     def __init__(self):
         super(TotalResults, self).__init__()
@@ -47,18 +50,19 @@ class TotalResults(object):
 
         return newResult
 
-    def update_all(self) -> None:
+    def update_all(self, force: bool = False) -> None:
         """
         Updates all samples with all methods and all fractions
+        :param force: Wether to force an update of an already existing method.
         :return:
         """
         for index, sample in enumerate(self.sampleResults):
             sample.load_dataset()
-            for fraction in self.measuredFreactions:
+            for fraction in self.measuredFractions:
                 possibleMethods = self._get_methods_for_fraction(sample.dataset, fraction)
                 for curMethod in possibleMethods:
-                    # print(f'updating {sample.sampleName} with {curMethod.label} at fraction {fraction}')
-                    sample.update_result_with_method(curMethod)
+                    print(f'updating {sample.sampleName} with {curMethod.label} at fraction {fraction}')
+                    sample.update_result_with_method(curMethod, force=force)
             print(f'processed {index+1} of {len(self.sampleResults)} samples')
 
     def get_error_vs_fraction_data(self, attributes: list = [], methods: list = []) -> dict:
@@ -102,10 +106,11 @@ class TotalResults(object):
         particleContainer = dataset.particleContainer
         methods: list = [meth.RandomSampling(particleContainer, fraction),
                          meth.SizeBinFractioning(particleContainer, fraction)]
-
         boxCreator: gmeth.BoxSelectionCreator = gmeth.BoxSelectionCreator(dataset)
         methods += boxCreator.get_crossBoxSubsamplers_for_fraction(fraction)
         methods += boxCreator.get_spiralBoxSubsamplers_for_fraction(fraction)
+        methods.append(cmeth.ChemometricSubsampling(particleContainer, fraction))
+        # methods = [cmeth.ChemometricSubsampling(particleContainer, fraction)]
         return methods
 
 
@@ -156,7 +161,6 @@ class SampleResult(object):
         """
         if not self.has_attribute(newAttribute):
             self.attributes.append(newAttribute)
-            print(f'sample {self.filepath} has now attribute {newAttribute}')
 
     def has_any_attribute(self, listOfAttributes: list) -> bool:
         hasAttr: bool = False
@@ -206,6 +210,8 @@ class SubsamplingResult(object):
         self.subSampledParticleCount: int = None
         self.mpCountError: float = None
         self.mpCountErrorPerBin: tuple = None
+        # TODO: UPDATE PATTERNS -> ARE THESE REASONABLE???
+        self.mpPatterns = ['poly', 'rubber', 'pb', 'pr', 'pg', 'py', 'pv']
 
     def update(self) -> None:
         """
@@ -248,15 +254,13 @@ class SubsamplingResult(object):
     
     def _get_error_from_values(self, exact: float, estimate: float) -> float:
         assert(exact != 0)
-        return abs(exact - estimate) / exact
+        return abs(exact - estimate) / exact * 100
     
     def _get_number_of_MP_particles(self, particleList: list) -> int:
-        mpPatterns = ['poly', 'rubber', 'pb', 'pr', 'pg', 'py', 'pv']
         numMPParticles = 0
-        
         for particle in particleList:
             assignment = particle.getParticleAssignment()
-            for pattern in mpPatterns:
+            for pattern in self.mpPatterns:
                 if assignment.lower().find(pattern) != -1:
                     numMPParticles += 1
                     break

gui/filterView.py

 from PyQt5 import QtGui, QtWidgets, QtCore
+import numpy as np
 import sys
 sys.path.append("C://Users//xbrjos//Desktop//Python")
 import gepard
 from gepard import dataset
 import helpers
-import numpy as np
+from cythonModules import rotateContour as rc
 
 
 class FilterView(QtWidgets.QGraphicsView):
@@ -14,6 +15,7 @@ class FilterView(QtWidgets.QGraphicsView):
         self.setWindowTitle('FilterView')
 
         self.dataset: dataset.DataSet = None
+        self.rotation: int = 0
 
         scene = QtWidgets.QGraphicsScene(self)
         scene.setItemIndexMethod(QtWidgets.QGraphicsScene.NoIndex)
@@ -47,6 +49,21 @@ class FilterView(QtWidgets.QGraphicsView):
         self._update_particle_contours()
         self._fit_to_window()
 
+    @helpers.timingDecorator
+    def update_rotation(self, newRotation: int) -> None:
+        if newRotation != self.rotation:
+            angle: float = np.float(newRotation-self.rotation)
+            center: np.ndarray = np.array([self.filter.circleOffset[0] + self.filter.diameter/2,
+                                           self.filter.circleOffset[1] + self.filter.diameter/2], dtype=np.float)
+
+            for particle in self.dataset.particleContainer.particles:
+                contour: np.ndarray = particle.contour.astype(np.float)
+                particle.contour = rc.rotate_contour_around_point(contour, center, angle)
+
+            self._update_particle_contours()
+            self.rotation = newRotation
+
+    @helpers.timingDecorator
     def _update_particle_contours(self) -> None:
         self._remove_particle_contours()
         if self.dataset is not None:

gui/mainView.py

@@ -25,14 +25,24 @@ class MainView(QtWidgets.QWidget):
         loadDsetBtn = QtWidgets.QPushButton('Load Dataset')
         loadDsetBtn.released.connect(self._load_dataset)
 
+        self.rotationSpinBox = QtWidgets.QSpinBox()
+        self.rotationSpinBox.setMinimum(0)
+        self.rotationSpinBox.setMaximum(359)
+        self.rotationSpinBox.setValue(0)
+        self.rotationSpinBox.setMaximumWidth(50)
+        self.rotationSpinBox.valueChanged.connect(self._update_fiter_rotation)
+
         self.controlGroup = QtWidgets.QGroupBox()
         self.controlGroupLayout = QtWidgets.QHBoxLayout()
         self.controlGroup.setLayout(self.controlGroupLayout)
 
         self.controlGroupLayout.addWidget(loadDsetBtn)
+        self.controlGroupLayout.addWidget(QtWidgets.QLabel('Filter Rotation'))
+        self.controlGroupLayout.addWidget(self.rotationSpinBox)
         self.controlGroupLayout.addWidget(QtWidgets.QLabel('Select Subsampling Mode:'))
         self.controlGroupLayout.addWidget(self.modeSelector)
         self.controlGroupLayout.addWidget(self.activeModeControl)
+        self.controlGroupLayout.addStretch()
 
         self.layout.addWidget(self.controlGroup)
         self.filterView = FilterView()
@@ -62,10 +72,11 @@ class MainView(QtWidgets.QWidget):
 
             self.activeMode = requestedMode
             self.activeModeControl = self.activeMode.get_control_groupBox()
-            self.controlGroupLayout.insertWidget(2, self.activeModeControl)
+            self.controlGroupLayout.insertWidget(3, self.activeModeControl)
 
             self.activeMode.update_measure_viewItems()
 
+    @helpers.timingDecorator
     def _load_dataset(self) -> None:
         fname = QtWidgets.QFileDialog.getOpenFileName(self, 'Select .pkl file', filter='pkl file (*.pkl)')
         if fname[0] != '':
@@ -91,6 +102,10 @@ class MainView(QtWidgets.QWidget):
                 self.filterView.update_from_dataset(dset)
                 self.activeMode.update_measure_viewItems()
 
+    def _update_fiter_rotation(self):
+        self.filterView.update_rotation(self.rotationSpinBox.value())
+        self.activeMode.send_measuredParticles_to_filterview()
+
 
 if __name__ == '__main__':
     import sys

gui/measureModes.py

@@ -9,6 +9,7 @@ class MeasureMode(QtCore.QObject):
         self.filterView: FilterView = relatedFilterView
         self.uiControls: QtWidgets.QGroupBox = QtWidgets.QGroupBox()
         self.boxGenerator: BoxSelectionSubsamplingMethod = None
+        self.subParticles: list = []
 
     def get_control_groupBox(self) -> QtWidgets.QGroupBox:
         return self.uiControls
@@ -16,7 +17,7 @@ class MeasureMode(QtCore.QObject):
     def update_measure_viewItems(self) -> None:
         raise NotImplementedError
 
-    def _send_measuredParticles_to_filterview(self) -> None:
+    def send_measuredParticles_to_filterview(self) -> None:
         if self.boxGenerator.particleContainer is not None:
             subParticles = self.boxGenerator.apply_subsampling_method()
             self.filterView.update_measured_particles(subParticles)
@@ -44,7 +45,7 @@ class CrossBoxMode(MeasureMode):
         topLefts: list = self.boxGenerator.get_topLeft_of_boxes()
         boxSize = self.boxGenerator.boxSize
         self.filterView.update_measure_boxes(topLefts, boxSize)
-        self._send_measuredParticles_to_filterview()
+        self.send_measuredParticles_to_filterview()
 
 
 class CrossBoxesControls(QtWidgets.QGroupBox):
@@ -103,7 +104,7 @@ class SpiralBoxMode(MeasureMode):
         topLefts: list = self.boxGenerator.get_topLeft_of_boxes()
         boxSize = self.boxGenerator.boxSize
         self.filterView.update_measure_boxes(topLefts, boxSize)
-        self._send_measuredParticles_to_filterview()
+        self.send_measuredParticles_to_filterview()
 
 
 class SpiralBoxControls(QtWidgets.QGroupBox):

helpers.py

@@ -3,24 +3,42 @@ import numpy as np
 import sys
 sys.path.append("C://Users//xbrjos//Desktop//Python")
 from gepard import dataset
+import time
+
+
+def timingDecorator(callingFunction):
+    """
+    A wrapper function for timing the duration of the given function.
+    :param callingFunction:
+    :return: wrapped function
+    """
+
+    def wrapper(*args, **kwargs):
+        t0 = time.time()
+        ret = callingFunction(*args, **kwargs)
+        print(f'{callingFunction.__name__} took {np.round(time.time()-t0, 2)} seconds')
+        return ret
+
+    return wrapper
 
 
 class ParticleBinSorter(object):
+
     def __init__(self):
         super(ParticleBinSorter, self).__init__()
         self.bins = [5, 10, 20, 50, 100, 200, 500]
-        
+
     def sort_particles_into_bins(self, particleList):
         particlesInBins = self._get_empty_bins()
-        
+
         for particle in particleList:
             binIndex = self._get_binIndex_of_particle(particle)
             particlesInBins[binIndex].append(particle)
         return particlesInBins
-    
+
     def _get_empty_bins(self):
         return [[] for _ in range(len(self.bins)+1)]
-    
+
     def _get_binIndex_of_particle(self, particle):
         size = particle.getParticleSize()
         binIndex = 0
@@ -114,7 +132,7 @@ def get_polygon_area(polygon: QtGui.QPolygonF) -> float:
     return area
 
 
-def get_filterDimensions_from_dataset(dataset) -> tuple:
+def get_filterDimensions_from_dataset(dataset: dataset.DataSet) -> tuple:
     """
     Processes the datasets boundary items to calculate diameter and offset (coord system offset of circular filter
     with respect to actual dataset). This is used to set circular filter dimensions to use in the geometric

input_output.py

@@ -4,6 +4,7 @@ from evaluation import TotalResults
 
 
 def load_results(fname: str) -> TotalResults:
+    # TODO: REMVOE DATASET FROM SAMPLERESULTS, OTHERWISE THE FILESIZE IS GOING TO BE HUGE
     res: TotalResults = None
     if os.path.exists(fname):
         with open(fname, "rb") as fp:

subsampling.py

@@ -10,33 +10,57 @@ SET GEPARD TO EVALUATION BRANCH (WITHOUT THE TILING STUFF), OTHERWISE SOME OF TH
 """
 
 
-# results: TotalResults = TotalResults()
-# pklsInFolders = get_pkls_from_directory(r'C:\Users\xbrjos\Desktop\temp MP\NewDatasets')
-#
-# for folder in pklsInFolders.keys():
-#     for samplePath in pklsInFolders[folder]:
-#         newSampleResult: SampleResult = results.add_sample(samplePath)
-#         for attr in get_attributes_from_foldername(folder):
-#             newSampleResult.set_attribute(attr)
-#
-# t0 = time.time()
-# results.update_all()
-# print('updating all took', time.time()-t0, 'seconds')
-#
+results: TotalResults = TotalResults()
+pklsInFolders = get_pkls_from_directory(r'C:\Users\xbrjos\Desktop\temp MP\NewDatasets')
+
+for folder in pklsInFolders.keys():
+    for samplePath in pklsInFolders[folder]:
+        newSampleResult: SampleResult = results.add_sample(samplePath)
+        for attr in get_attributes_from_foldername(folder):
+            newSampleResult.set_attribute(attr)
+
+t0 = time.time()
+results.update_all()
+print('updating all took', time.time()-t0, 'seconds')
+
+save_results('results1.res', results)
+# results: TotalResults = load_results('results1.res')
+# results.update_all(force=True)
 # save_results('results1.res', results)
-results: TotalResults = load_results('results1.res')
 
-errorPerFraction: dict = results.get_error_vs_fraction_data(methods=['spiral', 'cross'])
 plt.clf()
+errorPerFraction: dict = results.get_error_vs_fraction_data(attributes=['air', 'water'],
+                                                            methods