diff --git a/classificationWorkflow.py b/classificationWorkflow.py index b2898aa2d68acf90ee83951dade9d5e34926eae0..d0b298e29ea696f5ace7f5cc79dcb6e79b0964b5 100644 --- a/classificationWorkflow.py +++ b/classificationWorkflow.py @@ -143,7 +143,7 @@ def baseDeepTraining(shp,code,flds, params, model_file, out_scaler, csv_classes, for s in shp[1:]: ds = ds.append(geopandas.read_file(s)) #Extract feats and - feats = ds.truncate(before=flds[0],axis="columns").truncate(after=flds[-1],axis="columns") + feats = ds.filter(flds,axis=1) targets = ds[code] nb_class = len(targets.unique()) classes = np.array(sorted(targets.unique())) @@ -188,7 +188,7 @@ def baseDeepClassify(shp, model_file, code,flds, out_file, compute_confidence=Fa csv_classes = os.path.join(os.path.dirname(model_file),os.path.basename(model_file).replace(code,code + '_class').replace('.h5','.csv')) ds = geopandas.read_file(shp) - feats = ds.truncate(before=flds[0],axis='columns').truncate(after=flds[-1],axis='columns') + feats = ds.filter(flds,axis=1) scaler = joblib.load(scaler_file) cfeats = scaler.transform(feats) @@ -227,7 +227,7 @@ def deepTraining(shp,code,model_fld,params,feat,feat_mode = 'list', epochs=20): #Read training shp with geopandas ds = geopandas.read_file(shp) #Extract feats and - feats = ds.truncate(before=feat[0],axis="columns").truncate(after=feat[-1],axis="columns") + feats = ds.filter(feat,axis=1) targets = ds[code] nb_class = len(targets.unique()) classes = np.array(sorted(targets.unique())) @@ -235,7 +235,6 @@ def deepTraining(shp,code,model_fld,params,feat,feat_mode = 'list', epochs=20): ctargets = np.array([np.where(classes==i)[0][0] for i in targets]) scaler = StandardScaler() - print (feats) scaler.fit(feats) cfeats = scaler.transform(feats) @@ -282,7 +281,7 @@ def deepClassify(shp_list,code,scaler,model_file, csv_classes,out_fld,out_ext,fe for shp in shp_list: out_file = os.path.join(out_fld, os.path.basename(shp).replace('.shp', out_ext + '.shp')) ds = geopandas.read_file(shp) - feats = ds.truncate(before=feat[0],axis='columns').truncate(after=feat[-1],axis='columns') + feats = ds.filter(feat,axis=1) cfeats = scaler.transform(feats) predict = model.predict(cfeats)