took dropna out of violinplot (deprecated in latest seaborn); fixed p…

…roblem with seaborn palette plotting PCA (fig 11)

nPYc/plotting/_multivariatePlotting.py

@@ -66,7 +66,7 @@ def plotScree(R2, Q2=None, title='', xlabel='', ylabel='', savePath=None, figure
 def plotScores(pcaModel, classes=None, colourType=None, colourDict=None, markerDict=None, components=None,
                hotelling_alpha=0.05,
                plotAssociation=None, title='', xlabel='', figures=None, savePath=None, figureFormat='png', dpi=72,
-               figureSize=(11, 7)):
+               figureSize=(11, 7), opacity=.4):
     """
 	Plot PCA scores for each pair of components in PCAmodel, coloured by values defined in classes, and with Hotelling's T2 ellipse (95%)
 
@@ -85,6 +85,7 @@ def plotScores(pcaModel, classes=None, colourType=None, colourDict=None, markerD
 	:param dict figures: If not ``None``, saves location of each figure for output in html report (see multivariateReport.py)
 	"""
 
+    print("Plotting scores %s" % colourType)
     # Check inputs
     if not isinstance(pcaModel, ChemometricsPCA):
         raise TypeError('PCAmodel must be an instance of ChemometricsPCA')
@@ -114,8 +115,7 @@ def plotScores(pcaModel, classes=None, colourType=None, colourDict=None, markerD
     # If colourDict check colour defined for every unique entry in class
     colourDict = checkAndSetPlotAttributes(uniqKeys=uniq, attribDict=colourDict, dictName="colourDict")
 
-    markerDict = checkAndSetPlotAttributes(uniqKeys=uniq, attribDict=markerDict,
-                                           dictName="markerDict", defaultVal="o")
+    markerDict = checkAndSetPlotAttributes(uniqKeys=uniq, attribDict=markerDict,dictName="markerDict", defaultVal="o")
 
     from matplotlib.patches import Ellipse
 
@@ -183,7 +183,7 @@ def plotScores(pcaModel, classes=None, colourType=None, colourDict=None, markerD
                     ax.scatter(values[classes.values == u, components[i]],
                                values[classes.values == u, components[j]],
                                c=colourDict[u], marker=markerDict[u],
-                               label=u, alpha=.4)
+                               label=u, alpha=opacity)
 
             else:
                 colors_sns = {}
@@ -207,7 +207,7 @@ def plotScores(pcaModel, classes=None, colourType=None, colourDict=None, markerD
                     if classIX < 20:
                         ax.scatter(values[classes.values == u, components[i]],
                                    values[classes.values == u, components[j]], c=c, label=u,
-                                   alpha=.4)  # olors[classIX], label=u)
+                                   alpha=opacity)  # olors[classIX], label=u)
                     elif classIX == len(uniqnonan) - 1:
                         ax.scatter(values[classes.values == u, components[i]],
                                    values[classes.values == u, components[j]], c='0', alpha=0, label='...')
@@ -217,11 +217,13 @@ def plotScores(pcaModel, classes=None, colourType=None, colourDict=None, markerD
                     else:
                         ax.scatter(values[classes.values == u, components[i]],
                                    values[classes.values == u, components[j]], c=c,
-                                   label='_nolegend_', alpha=.4)  # colors[classIX], label='_nolegend_')
+                                   label='_nolegend_', alpha=opacity)  # colors[classIX], label='_nolegend_')
                     classIX = classIX + 1
-                    colors_sns[u] = c
+                    colors_sns[str(u)] = c
+
 
             if plotAssociation is not None:
+
                 nonans = [i for i, x in enumerate(classes) if x in {'nan', 'NaN', 'NaT', '', 'NA'}]
                 plotClasses = classes.copy()
                 plotClasses[nonans] = 'NA'
@@ -232,14 +234,15 @@ def plotScores(pcaModel, classes=None, colourType=None, colourDict=None, markerD
                                                                'PC' + str(components[j] + 1)])
 
                 # Association for component[i]
-                ax1 = sns.stripplot(x=plotTitle, y='PC' + str(components[i] + 1), data=tempdata, ax=ax1,
-                                    palette=colors_sns)
+
+                ax1 = sns.stripplot(x=plotTitle, y='PC' + str(components[i] + 1),
+                                    data=tempdata, ax=ax1, palette=colors_sns)
                 ax1.set(xticklabels=[])
                 ax1.set(xlabel='')
 
                 # Association for component[j]
-                ax2 = sns.stripplot(x=plotTitle, y='PC' + str(components[j] + 1), data=tempdata, ax=ax2,
-                                    palette=colors_sns)
+                ax2 = sns.stripplot(x=plotTitle, y='PC' + str(components[j] + 1),
+                                    data=tempdata, ax=ax2, palette=colors_sns)
                 ax2.set(xticklabels=[])
 
             ax.legend(loc='upper left', bbox_to_anchor=(1, 1))
@@ -253,7 +256,7 @@ def plotScores(pcaModel, classes=None, colourType=None, colourDict=None, markerD
                 ax.legend()
 
             cb = ax.scatter(values[plotnans == False, components[i]], values[plotnans == False, components[j]],
-                            c=classes[plotnans == False], cmap=plt.cm.rainbow, alpha=.4)
+                            c=classes[plotnans == False], cmap=plt.cm.rainbow, alpha=opacity)
             cbar = plt.colorbar(cb, ax=ax)
             cbar.set_label(title)
 
@@ -263,14 +266,14 @@ def plotScores(pcaModel, classes=None, colourType=None, colourDict=None, markerD
 
                 # Association for component[i]
                 ax1.scatter(classes[plotnans == False], values[plotnans == False, components[i]],
-                            c=classes[plotnans == False], cmap=plt.cm.rainbow, alpha=.4)
+                            c=classes[plotnans == False], cmap=plt.cm.rainbow, alpha=opacity)
                 ax1.scatter(numpy.ones([sum(plotnans), 1]) * xvalnan, values[plotnans, components[i]], c='#D3D3D3')
                 ax1.set_ylabel('PC' + str(components[i] + 1))
                 ax1.set(xticklabels=[])
 
                 # Association for component[j]
                 ax2.scatter(classes[plotnans == False], values[plotnans == False, components[j]],
-                            c=classes[plotnans == False], cmap=plt.cm.rainbow, alpha=.4)
+                            c=classes[plotnans == False], cmap=plt.cm.rainbow, alpha=opacity)
                 ax2.scatter(numpy.ones([sum(plotnans), 1]) * xvalnan, values[plotnans, components[j]], c='#D3D3D3')
                 ax2.set_xlabel(plotTitle)
                 ax2.set_ylabel('PC' + str(components[j] + 1))
@@ -281,6 +284,7 @@ def plotScores(pcaModel, classes=None, colourType=None, colourDict=None, markerD
         xlabel = 'PC' + str(components[i] + 1) + ' (' + '{0:.2f}'.format(
             pcaModel.modelParameters['VarExpRatio'][components[i]] * 100) + '%)'
         if plotAssociation is not None:
+
             ylabel = ylabel + ' significance: ' + '{0:.2f}'.format(plotAssociation[components[j]])
             xlabel = xlabel + ' significance: ' + '{0:.2f}'.format(plotAssociation[components[i]])
         ax.set_ylabel(ylabel)

nPYc/plotting/_plotTIC.py

@@ -27,7 +27,7 @@ def plotTIC(dataset, addViolin=True, addBatchShading=False,
 			colourDict=None, markerDict=None, abbrDict=None,
 			logy=False, title='',
 			withExclusions=True, savePath=None,
-			figureFormat='png', dpi=72, figureSize=(11,7)):
+			figureFormat='png', dpi=72, figureSize=(11,7), opacity=.6):
 	"""
 	Visualise TIC for all or a subset of features coloured by either dilution value or detector voltage.
 	With the option to shade by batch.
@@ -159,7 +159,7 @@ def plotTIC(dataset, addViolin=True, addBatchShading=False,
 							marker=markerDict[u],
 							s=30,
 							c=colourDict[u],
-							alpha=.4,
+							alpha=opacity,
 							label=u)
 
 			if addViolin:
@@ -189,7 +189,8 @@ def plotTIC(dataset, addViolin=True, addBatchShading=False,
 						c=msData.sampleMetadata[colourBy],
 						cmap=cmap,
 						vmin=mincol,
-						vmax=maxcol)
+						vmax=maxcol,
+						alpha=opacity)
 
 	# Shade by automatically defined batches (if required)
 	if addBatchShading:
@@ -225,7 +226,7 @@ def plotTIC(dataset, addViolin=True, addBatchShading=False,
 				end = end.values[0]
 
 			# Plot rectangle
-			rect = Rectangle((start, ymin), end-start, abs(ymin)+abs(ymax), color=colors[colIX], alpha=0.4, zorder=0)#,label='Batch %d' % (i))
+			rect = Rectangle((start, ymin), end-start, abs(ymin)+abs(ymax), color=colors[colIX], alpha=opacity, zorder=0)#,label='Batch %d' % (i))
 			ax.add_patch(rect)
 			colIX = colIX + 1
 
@@ -272,7 +273,7 @@ def plotTIC(dataset, addViolin=True, addBatchShading=False,
 
 def plotTICinteractive(dataset, x='Run Order', y='TIC', labelBy='Run Order',
 					   colourBy='Correction Batch', withExclusions=True,
-					   destinationPath=None, autoOpen=True):
+					   destinationPath=None, autoOpen=True, opacity=.6):
 	"""
 	Interactively visualise TIC or intensity for a given feature with plotly, provides tooltips to allow identification of samples.
 
@@ -353,7 +354,7 @@ def plotTICinteractive(dataset, x='Run Order', y='TIC', labelBy='Run Order',
 			text=hovertext[plotnans == True],
 			name='NA',
 			hoverinfo='text',
-			showlegend=True
+			showlegend=True, opacity=opacity
 			)
 		data.append(NaNplot)
 
@@ -371,7 +372,8 @@ def plotTICinteractive(dataset, x='Run Order', y='TIC', labelBy='Run Order',
 				),
 			text=hovertext[plotnans == False],
 			hoverinfo='text',
-			showlegend=False
+			showlegend=False,
+			opacity=opacity
 			)
 		data.append(CLASSplot)
 
@@ -390,14 +392,16 @@ def plotTICinteractive(dataset, x='Run Order', y='TIC', labelBy='Run Order',
 				text=hovertext[classes == i],
 				name=i,
 				hoverinfo='text',
-				showlegend=True
+				showlegend=True, opacity=opacity
 				)
 			data.append(CLASSplot)
 
 	# Overlay SR and LTR if columns present
 	if ('SampleType' in msData.sampleMetadata.columns) & ('AssayRole' in msData.sampleMetadata.columns):
-		SRmask = ((msData.sampleMetadata['SampleType'].values == SampleType.StudyPool) & (msData.sampleMetadata['AssayRole'].values == AssayRole.PrecisionReference))
-		LTRmask = ((msData.sampleMetadata['SampleType'].values == SampleType.ExternalReference) & (msData.sampleMetadata['AssayRole'].values == AssayRole.PrecisionReference))
+		SRmask = ((msData.sampleMetadata['SampleType'].values == SampleType.StudyPool) &
+				  (msData.sampleMetadata['AssayRole'].values == AssayRole.PrecisionReference)) #SPmask
+		LTRmask = ((msData.sampleMetadata['SampleType'].values == SampleType.ExternalReference) &
+				   (msData.sampleMetadata['AssayRole'].values == AssayRole.PrecisionReference)) # ERmask
 
 		SRplot = go.Scatter(
 			x=msData.sampleMetadata.loc[SRmask, x],
@@ -410,7 +414,7 @@ def plotTICinteractive(dataset, x='Run Order', y='TIC', labelBy='Run Order',
 			text=hovertext[SRmask],
 			name='Study Reference',
 			hoverinfo='text',
-			showlegend=True
+			showlegend=True, opacity=opacity
 		)
 		data.append(SRplot)
 
@@ -425,7 +429,7 @@ def plotTICinteractive(dataset, x='Run Order', y='TIC', labelBy='Run Order',
 			text=hovertext[LTRmask],
 			name='Long-Term Reference',
 			hoverinfo='text',
-			showlegend=True
+			showlegend=True, opacity=opacity
 		)
 		data.append(LTRplot)
 

nPYc/plotting/_plotting.py

@@ -12,7 +12,7 @@
 
 
 def histogram(values, inclusionVector=None, quantiles=None, title='', xlabel='', histBins=100, color=None, logy=False,
-              logx=False, xlim=None, savePath=None, figureFormat='png', dpi=72, figureSize=(11, 7)):
+              logx=False, xlim=None, savePath=None, figureFormat='png', dpi=72, figureSize=(11, 7), opacity=.5):
     """
 	histogram(values, inclusionVector=None, quantiles=None, histBins=100, color=None, logy=False, logx=False, **kwargs)
 
@@ -123,7 +123,7 @@ def histogram(values, inclusionVector=None, quantiles=None, title='', xlabel='',
                 localValues[localValues == 0] = numpy.finfo(numpy.float64).epsneg
 
             ax.hist(localValues,
-                    alpha=.4,
+                    alpha=opacity,
                     range=(minVal, maxVal),
                     label=key,
                     bins=nbins)
@@ -141,7 +141,7 @@ def histogram(values, inclusionVector=None, quantiles=None, title='', xlabel='',
                      label=label)
         else:
             ax.hist(values[mask],
-                    alpha=.4,
+                    alpha=opacity,
                     label=label,
                     bins=nbins)
 
@@ -153,7 +153,7 @@ def histogram(values, inclusionVector=None, quantiles=None, title='', xlabel='',
                          label=label)
             else:
                 ax.hist(values[mask],
-                        alpha=.4,
+                        alpha=opacity,
                         label=label,
                         bins=nbins)
 
@@ -164,7 +164,7 @@ def histogram(values, inclusionVector=None, quantiles=None, title='', xlabel='',
                      label=label)
         else:
             ax.hist(values[mask],
-                    alpha=.4,
+                    alpha=opacity,
                     label=label,
                     bins=nbins)
     else:
@@ -194,7 +194,7 @@ def histogram(values, inclusionVector=None, quantiles=None, title='', xlabel='',
 
 
 def plotLRTIC(msData, sampleMask=None, colourByDetectorVoltage=False, title='', label=False, savePath=None,
-              figureFormat='png', dpi=72, figureSize=(11, 7)):
+              figureFormat='png', dpi=72, figureSize=(11, 7), opacity=.4):
     """
 	Visualise TIC for linearity reference (LR) samples (either all or a subset) coloured by either dilution value or detector voltage.
 
@@ -237,12 +237,12 @@ def plotLRTIC(msData, sampleMask=None, colourByDetectorVoltage=False, title='',
                         cmap=plt.cm.get_cmap('bwr'),
                         vmin=cMin,
                         vmax=cMax,
-                        edgecolors='grey')
+                        edgecolors='grey', alpha=opacity)
     else:
         ax.scatter(runIX, tic,
                    c=msData.sampleMetadata['Dilution'][LRmask],
                    cmap=plt.cm.jet,
-                   edgecolors='grey')
+                   edgecolors='grey',alpha=opacity)
 
     # Add sample labels
     if label == True:
@@ -276,7 +276,7 @@ def plotLRTIC(msData, sampleMask=None, colourByDetectorVoltage=False, title='',
 
 
 def plotCorrelationToLRbyFeature(msData, featureMask=None, title='', maxNo=5, savePath=None, figureFormat='png', dpi=72,
-                                 figureSize=(11, 7)):
+                                 figureSize=(11, 7), opacity=.4):
     """
 	Summary plots of correlation to dilution for a subset of features, separated by sample batch. Each figure includes a scatter plot of feature intensity vs dilution, TIC of LR and surrounding SP samples, and a heatmap of correlation to dilution for each LR batch subset, overall, and mean.
 
@@ -344,7 +344,7 @@ def plotCorrelationToLRbyFeature(msData, featureMask=None, title='', maxNo=5, sa
         # Plot scatter of LR intensity coloured by dilution
         ax1.scatter(runIX, msData.intensityData[LRmask, feature],
                     c=msData.sampleMetadata['Dilution'][LRmask],
-                    cmap=plt.cm.jet)
+                    cmap=plt.cm.jet, alpha=opacity)
 
         # Add a line where samples are not adjacent
         sampletime = [x - runIX[i - 1] for i, x in enumerate(runIX)]
@@ -387,12 +387,15 @@ def plotCorrelationToLRbyFeature(msData, featureMask=None, title='', maxNo=5, sa
 
 def checkAndSetPlotAttributes(uniqKeys, attribDict, dictName, defaultVal=None):
     # check all the keys of attribDict are in uniqKeys
+    # putting this here to see if it's a useful refactor. It may not be.
     if attribDict:
         if not all(k in attribDict.keys() for k in uniqKeys):
+            print(dictName + " keys are " + attribDict.keys())
+            print("Category keys are " + uniqKeys)
             raise ValueError(
                 'Check keys in ' + dictName + "; some aren't present in the categories list.")
     else:
-        # only do this if a default has been specified
+        # only set all the vals if a default has been specified
         if defaultVal:
             attribDict = {}
             for u in uniqKeys:

nPYc/plotting/_violinPlot.py

@@ -31,9 +31,9 @@ def _violinPlotHelper(ax, values, sampleMasks, xlabel, ylabel, palette=None, yli
 	sns.set_color_codes(palette='deep')
 
 	if palette is not None:
-		sns.violinplot(data=localDFpre, scale='width', bw=.2, cut=0, ax=ax, palette=palette, dropna=True)
+		sns.violinplot(data=localDFpre, scale='width', bw=.2, cut=0, ax=ax, palette=palette)
 	else:
-		sns.violinplot(data=localDFpre, scale='width', bw=.2, cut=0, ax=ax, dropna=True)
+		sns.violinplot(data=localDFpre, scale='width', bw=.2, cut=0, ax=ax)
 
 	# ax formatting
 	if ylimits:

nPYc/reports/multivariateReport.py

@@ -326,6 +326,7 @@ def multivariateReport(dataTrue, pcaModel, reportType='analytical', withExclusio
                                  classes=data.sampleMetadata['SampleClass'],
                                  colourType='categorical',
                                  colourDict=data.Attributes['sampleTypeColours'],
+                                 markerDict=data.Attributes['sampleTypeMarkers'],
                                  title='SampleClass',
                                  figures=figuresQCscores,
                                  hotelling_alpha=hotellings_alpha,