Merge pull request #5 from lennepkade/beta

Merge from beta

dzetsaka.py

@@ -432,6 +432,13 @@ def loadMenu(self):
         self.menu.filterMedian = QAction(QIcon(":/plugins/dzetsaka/img/filter.png"), "Median", self.iface.mainWindow())
         QObject.connect(self.menu.filterMedian, SIGNAL("triggered()"), self.loadFilters)
         filterMenu.addAction(self.menu.filterMedian)
+
+        ## Separator
+        filterMenu.addSeparator()
+
+        self.menu.filterClass = QAction(QIcon(":/plugins/dzetsaka/img/historicalmap.png"), "Classification to Vector (single class)", self.iface.mainWindow())
+        QObject.connect(self.menu.filterClass, SIGNAL("triggered()"), self.loadHistoricalMap)
+        filterMenu.addAction(self.menu.filterClass)
 
         ## Separator
         filterMenu.addSeparator()
@@ -774,9 +781,10 @@ def loadHistoricalMap(self):
         """!@brief Load and init historical map dock"""
         self.historicalmap = historical_dock()
 
-        self.historicalmap.show()
-
+        if self.sender()==self.menu.filterClass:
+           self.historicalmap.tabWidget.setCurrentIndex(1)
 
+        self.historicalmap.show()
 
         # save raster 
         self.historicalmap.outRasterButton.clicked.connect(self.select_output_file)

metadata.txt

@@ -1,4 +1,4 @@
-# This file contains metadata for your plugin. Since 
+# This file contains metadata for your plugin. Since 
 # version 2.0 of QGIS this is the proper way to supply 
 # information about a plugin. The old method of 
 # embedding metadata in __init__.py will 
@@ -8,7 +8,7 @@
 
 [general]
 name=dzetsaka : Classification tool
-qgisMinimumVersion=2.0
+qgisMinimumVersion=2.0.1
 description=Fast and Easy Classification plugin for Qgis
 version=2.0
 author=Nicolaï Van Lennepkade
@@ -23,7 +23,7 @@ repository=http://www.github.com/lennepkade/dzetsaka
 # Recommended items:
 
 # Uncomment the following line and add your changelog:
-changelog= Now support Random Forest, SVM and KNN classifiers. Correct some bugs and add settings management.
+changelog= Now support Random Forest, SVM and KNN classifiers (v2.0). Correct some bugs (split classification) and add classification to vector in filters menu.
 # Tags are comma separated with spaces allowed
 tags=classification,semi-automatic,gaussian,mixture,model,random forest,svm,knn,forest
 

scripts/mainfunction.py

@@ -103,7 +103,7 @@ def __init__(self,inRaster,inVector,inField='Class',outModel=None,inSplit=1,inSe
             learningProgress.addStep() # Add Step to ProgressBar
 
             # Learning process take split of groundthruth pixels for training and the remaining for testing
-            """
+
 
             try:
                 if SPLIT < 1:
@@ -128,7 +128,7 @@ def __init__(self,inRaster,inVector,inField='Class',outModel=None,inSplit=1,inSe
                         #Add Pb
             except:
                 QgsMessageLog.logMessage("Problem while learning if SPLIT <1")
-            """        
+
 
             x,y=X,Y
 
@@ -150,28 +150,36 @@ def __init__(self,inRaster,inVector,inField='Class',outModel=None,inSplit=1,inSe
                     from sklearn.ensemble import RandomForestClassifier
                     from sklearn.cross_validation import StratifiedKFold
                     from sklearn.grid_search import GridSearchCV
-                    try:    
+                    try:   
+
+                        # AS Qgis in Windows doensn't manage multiprocessing, force to use 1 thread for not linux system
+                        if os.name == 'posix':
+                            n_jobs=-1
+                        else:
+                            n_jobs=1
+
+                        # 
                         if inClassifier == 'RF':
                             param_grid_rf = dict(n_estimators=3**sp.arange(1,5),max_features=sp.arange(1,4))
                             y.shape=(y.size,)    
                             cv = StratifiedKFold(y, n_folds=3)
-                            grid = GridSearchCV(RandomForestClassifier(), param_grid=param_grid_rf, cv=cv,n_jobs=1)
+                            grid = GridSearchCV(RandomForestClassifier(), param_grid=param_grid_rf, cv=cv,n_jobs=n_jobs)
                             grid.fit(x, y)
                             model = grid.best_estimator_
                             model.fit(x,y)        
                         elif inClassifier == 'SVM':
                             param_grid_svm = dict(gamma=2.0**sp.arange(-4,4), C=10.0**sp.arange(-2,5))
                             y.shape=(y.size,)    
                             cv = StratifiedKFold(y, n_folds=5)
-                            grid = GridSearchCV(SVC(), param_grid=param_grid_svm, cv=cv,n_jobs=1)
+                            grid = GridSearchCV(SVC(), param_grid=param_grid_svm, cv=cv,n_jobs=n_jobs)
                             grid.fit(x, y)
                             model = grid.best_estimator_
                             model.fit(x,y)
                         elif inClassifier == 'KNN':
                             param_grid_knn = dict(n_neighbors = sp.arange(1,20,4))
                             y.shape=(y.size,)    
                             cv = StratifiedKFold(y, n_folds=3)
-                            grid = GridSearchCV(neighbors.KNeighborsClassifier(), param_grid=param_grid_knn, cv=cv,n_jobs=1)
+                            grid = GridSearchCV(neighbors.KNeighborsClassifier(), param_grid=param_grid_knn, cv=cv,n_jobs=n_jobs)
                             grid.fit(x, y)
                             model = grid.best_estimator_
                             model.fit(x,y)