Legacy Supervisor

.gitignore

@@ -1,7 +1,9 @@
 [Rr]es/
 [Ll]ogs/
 [Dd]ata/
+Enrichment/
 *.pyc
 *.log
 .ipynb_checkpoints/
 triskele
+Untitled.ipynb

GroundTruth/jurse_meta_idx.csv

@@ -0,0 +1,22 @@
+index,metaclass_index
+0,0
+1,1
+2,1
+3,0
+4,2
+5,2
+6,0
+7,0
+8,3
+9,4
+10,5
+11,0
+12,0
+13,5
+14,5
+15,0
+16,0
+17,0
+18,6
+19,7
+20,0

GroundTruth/jurse_meta_lbl.csv

@@ -0,0 +1,9 @@
+metaclass_index,metaclass_label
+0,Unclassified
+1,Grass
+2,Trees
+3,Residential buildings
+4,Non-residential buildings
+5,Roads
+6,Cars
+7,Trains

GroundTruth/labels.csv

@@ -0,0 +1,22 @@
+index,label
+0,Unclassified
+1,Healthy grass
+2,Stressed grass
+3,Artificial turf
+4,Evergreen trees
+5,Deciduous trees
+6,Bare earth
+7,Water
+8,Residential buildings
+9,Non-residential buildings
+10,Roads
+11,Sidewalks
+12,Crosswalks
+13,Major thoroughfares
+14,Highways
+15,Railways
+16,Paved parking lots
+17,Unpaved parking lots
+18,Cars
+19,Trains
+20,Stadium seats

GroundTruth/metaclass_indexes-Copy1.csv

@@ -0,0 +1,22 @@
+index,metaclass_index
+0,0
+1,1
+2,1
+3,1
+4,2
+5,2
+6,3
+7,0
+8,4
+9,4
+10,5
+11,5
+12,5
+13,5
+14,5
+15,6
+16,5
+17,0
+18,7
+19,8
+20,9

GroundTruth/metaclass_labels.csv

@@ -0,0 +1,11 @@
+metaclass_index,metaclass_label
+0,Unclassified
+1,Grass
+2,Trees
+3,Bare earth
+4,Buildings
+5,Roads
+6,Railways
+7,Cars
+8,Trains
+9,Stadium

Notebooks/CrossVal spatial.ipynb

@@ -0,0 +1,277 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "sys.path.append('../triskele/python/')\n",
+    "import triskele\n",
+    "\n",
+    "figsize = np.array((16, 3)) * 2"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Spatial Cross Validation Generator\n",
+    "\n",
+    "Due to the operating of attribute profiles, we need a spatial cross validation generator to ensure we do not train and test samples with the same root in the hierarchical representation used during the description process."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Load ground truth & metadata"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gt = triskele.read('../Data/ground_truth/2018_IEEE_GRSS_DFC_GT_TR.tif')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.figure(figsize=figsize)\n",
+    "plt.imshow(gt, cmap=plt.get_cmap('GnBu'))\n",
+    "plt.colorbar()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dfc_lbl  = pd.read_csv('../GroundTruth/labels.csv')\n",
+    "meta_idx = pd.read_csv('../GroundTruth/jurse_meta_idx.csv')\n",
+    "meta_lbl = pd.read_csv('../GroundTruth/jurse_meta_lbl.csv')\n",
+    "\n",
+    "imap = np.array(meta_idx['metaclass_index'])\n",
+    "\n",
+    "all_meta_view = dfc_lbl.merge(meta_idx).merge(meta_lbl)\n",
+    "all_meta_view"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.figure(figsize=figsize)\n",
+    "plt.imshow(imap[gt], cmap=plt.get_cmap('GnBu'))\n",
+    "plt.colorbar()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Labels map"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig, axs = plt.subplots(dfc_lbl['label'].size, figsize=figsize * dfc_lbl['label'].size)\n",
+    "\n",
+    "for i, lbl in enumerate(dfc_lbl['label']):\n",
+    "    omap = gt == np.array(dfc_lbl[dfc_lbl['label'] == lbl ]['index'])\n",
+    "    axs[i].set_title(lbl)\n",
+    "    axs[i].imshow(1. * omap, cmap=plt.get_cmap('GnBu'))\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Meta labels map"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig, axs = plt.subplots(meta_lbl['metaclass_label'].size, figsize=figsize * meta_lbl['metaclass_label'].size)\n",
+    "\n",
+    "for i, lbl in enumerate(meta_lbl['metaclass_label']):\n",
+    "    omap = np.isin(gt, np.array(all_meta_view[all_meta_view['metaclass_label'] == lbl]['index']))\n",
+    "    axs[i].set_title(lbl)\n",
+    "    axs[i].imshow(1. * omap, cmap=plt.get_cmap('GnBu'))\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Split data "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "count"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "col, count = np.unique(cut, return_counts=True)\n",
+    "df = pd.DataFrame(count[np.newaxis,:], columns=col)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "count = 5\n",
+    "\n",
+    "step = int(gt.shape[0] / count)\n",
+    "\n",
+    "fig, axs = plt.subplots(count, figsize=figsize * count)\n",
+    "\n",
+    "col, count_all = np.unique(imap[gt], return_counts=True)\n",
+    "\n",
+    "metrics = pd.DataFrame(columns=col)\n",
+    "counts = list()\n",
+    "for i in range(count):\n",
+    "    cut = imap[gt][i*step:(i+1)*step+1]\n",
+    "    axs[i].imshow(cut, cmap=plt.get_cmap('GnBu'))\n",
+    "    axs[i].set_title('Cut {}'.format(i))\n",
+    "    \n",
+    "    col, count = np.unique(cut, return_counts=True)\n",
+    "    df = pd.DataFrame(count[np.newaxis,:], columns=col, index=[i])\n",
+    "    counts.append(df)\n",
+    "\n",
+    "plt.savefig('../Res/meta.png',bbox_inches='tight', transparent=\"True\", pad_inches=0)\n",
+    "plt.show()\n",
+    "\n",
+    "metrics = pd.concat(counts)\n",
+    "metrics / count_all * 100"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Try to remove filtered object"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sys.path.append('..')\n",
+    "import ld2dap"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tif = ld2dap.LoadTIFF('../Data/phase1_rasters/DSM_C12/UH17c_GEF051_TR.tif')\n",
+    "trh = ld2dap.Treshold(70)\n",
+    "dsp = ld2dap.ShowFig(symb=True)\n",
+    "\n",
+    "aps = ld2dap.SelfDualAttributeProfiles(area=[100, 1000, 1e4, 1e5, 1e6, 1e7])\n",
+    "dif = ld2dap.Differential()\n",
+    "\n",
+    "dif.input = aps\n",
+    "aps.input = trh\n",
+    "dsp.input = dif\n",
+    "trh.input = tif\n",
+    "\n",
+    "dsp.run()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tif = ld2dap.LoadTIFF('../Data/phase1_rasters/DSM_C12/UH17c_GEF051_TR.tif')\n",
+    "trh = ld2dap.Treshold(1e4)\n",
+    "aps = ld2dap.SelfDualAttributeProfiles(area=[100, 1e3, 1e4])\n",
+    "dsp = ld2dap.ShowFig(symb=True)\n",
+    "dif = ld2dap.Differential()\n",
+    "ddsp = ld2dap.ShowFig(symb=True)\n",
+    "\n",
+    "ddsp.input = dif\n",
+    "dif.input = aps\n",
+    "dsp.input = aps\n",
+    "aps.input = trh\n",
+    "trh.input = tif\n",
+    "\n",
+    "tif.run()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

Notebooks/Raster combination.ipynb

@@ -56,6 +56,22 @@
     "dtm = ra.rasterize_cache('z', C12, .5, 'nearest', True, '../Res/enrichment_rasters/')"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print('Hello world')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Ici nous avons lancé un print en Python."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -122,8 +138,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "C1_raster = ra.rasterize_cache('intensity', C1, .5, 'linear', False, '../Res/enrichment_rasters/')\n",
-    "C2_raster = ra.rasterize_cache('intensity', C2, .5, 'linear', False, '../Res/enrichment_rasters/')"
+    "C1_raster = ra.rasterize_cache('intensity', C1, 1., 'linear', False, '../Res/enrichment_rasters/')\n",
+    "C2_raster = ra.rasterize_cache('intensity', C2, 1., 'linear', False, '../Res/enrichment_rasters/')"
    ]
   },
   {

Notebooks/YAML Serialization.ipynb

@@ -16,9 +16,12 @@
     "- [X] Write/move results\n",
     "- [X] Watch folder\n",
     "- [X] Main loop\n",
-    "- [ ] Logs\n",
-    "- [ ] Catch errors\n",
-    "- [ ] Custom CVG\n",
+    "- [X] Logs\n",
+    "- [X] Catch errors\n",
+    "- [X] Custom CVG\n",
+    "- [ ] Use meta labelling\n",
+    "- [ ] Create new workflow\n",
+    "- [ ] Workflow selection in recipe\n",
     "\n",
     "\n",
     "## Init"
@@ -41,12 +44,7 @@
     "import datetime\n",
     "from sklearn import metrics\n",
     "from pathlib import Path\n",
-    "\n",
-    "from sklearn.ensemble import RandomForestClassifier\n",
-    "\n",
-    "sys.path.append('..')\n",
-    "import Descriptors\n",
-    "from CrossValidationGenerator import APsCVG\n",
+    "import pandas as pd\n",
     "\n",
     "sys.path.append('../triskele/python')\n",
     "import triskele"
@@ -205,6 +203,36 @@
     "att.shape"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Meta labeling"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_ground_truth(expe):\n",
+    "    gt = triskele.read(expe['ground_truth'])\n",
+    "    \n",
+    "    # Meta labeling\n",
+    "    idx_map = np.arange(gt.max() + 1)\n",
+    "\n",
+    "    if 'meta_labels' in expe:\n",
+    "        meta_idx = pd.read_csv(expe['meta_labels'])\n",
+    "        idx = np.array(meta_idx['index'])\n",
+    "        midx = np.array(meta_idx['metaclass_index'])\n",
+    "        idx_map[idx] = midx\n",
+    "    \n",
+    "    return idx_map[gt]\n",
+    "\n",
+    "expe_ground_truth(expe)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -221,8 +249,7 @@
     "def compute_classification(expe, att):\n",
     "    \"\"\"Read a standard expe recipe and attributes, return the result classification\"\"\"\n",
     "    # Ground truth\n",
-    "    gt = triskele.read(expe['ground_truth'])\n",
-    "\n",
+    "    gt = get_ground_truth(expe)\n",
     "\n",
     "    # CrossVal and ML\n",
     "    cv = expe['cross_validation']\n",
@@ -304,6 +331,14 @@
     "    \n",
     "    ### Extensible: meta-classes\n",
     "    gt = triskele.read(expe['ground_truth'])\n",
+    "    idx_map = np.arange(gt.max() + 1)\n",
+    "\n",
+    "    if 'meta_labels' in expe:\n",
+    "        meta_idx = pd.read_csv(expe['meta_labels'])\n",
+    "        idx = np.array(meta_idx['index'])\n",
+    "        midx = np.array(meta_idx['metaclass_index'])\n",
+    "        idx_map[idx] = midx\n",
+    "\n",
     "    return compute_metrics(gt, classification)\n",
     "\n",
     "expe_results = run_metrics(expe, classification)\n",

supervisor.py

@@ -190,11 +190,25 @@ def compute_descriptors(expe):
     return att
 
 
+def get_ground_truth(expe):
+    gt = triskele.read(expe['ground_truth'])
+    
+    # Meta labeling
+    idx_map = np.arange(gt.max() + 1)
+
+    if 'meta_labels' in expe:
+        meta_idx = pd.read_csv(expe['meta_labels'])
+        idx = np.array(meta_idx['index'])
+        midx = np.array(meta_idx['metaclass_index'])
+        idx_map[idx] = midx
+    
+    return idx_map[gt]
+
+
 def compute_classification(expe, descriptors):
     """Read a standard expe recipe and descriptors, return the result classification"""
     # Ground truth
-    gt = triskele.read(expe['ground_truth'])
-
+    gt = get_ground_truth(expe)
 
     # CrossVal and ML
     cv = expe['cross_validation']
@@ -234,7 +248,7 @@ def run_metrics(expe, classification, descriptors):
     """Compute the metrics from a standard expe recipe and an given classification"""
     
     ### Extensible: meta-classes
-    gt = triskele.read(expe['ground_truth'])
+    gt = get_ground_truth(expe)
     return compute_metrics(gt, classification, descriptors)
 
 

test.py

@@ -8,30 +8,47 @@
 #
 # TODO details
 
-#from core import Input, Output, Filter
-from ld2dap import LoadTIFF, SaveFig, Treshold, ShowFig, Differential
-from ld2dap import AttributeProfiles as APs
-from ld2dap import SelfDualAttributeProfiles as SDAPs
-from ld2dap.core import logger
-
 import numpy as np
+import ld2dap
+import logger
+
+def diff_test():
+    layers_files = [
+        '../Data/phase1_rasters/DEM+B_C123/UH17_GEM051_TR.tif',
+        '../Data/phase1_rasters/DEM_C123_3msr/UH17_GEG051_TR.tif',
+        '../Data/phase1_rasters/DEM_C123_TLI/UH17_GEG05_TR.tif',
+        '../Data/phase1_rasters/DSM_C12/UH17c_GEF051_TR.tif',
+        '../Data/phase1_rasters/Intensity_C1/UH17_GI1F051_TR.tif',
+        '../Data/phase1_rasters/Intensity_C2/UH17_GI2F051_TR.tif',
+        '../Data/phase1_rasters/Intensity_C3/UH17_GI3F051_TR.tif'
+    ]
+
+    l = ld2dap.LoadTIFF(layers_files[0:3])
+    t = ld2dap.Treshold(1e4)
+    p = ld2dap.SelfDualAttributeProfiles(area=[100,1e4])
+    f = ld2dap.Differential()
+    #p = ld2dap.AttributeProfiles(area=[100,1e4,1e6])
+    m = ld2dap.Merger()
+    a = ld2dap.LocalFeatures([np.std], 7)#, sd=[.4,.6,.8], moi=[.5,.9])
+    d = ld2dap.ShowFig(stack_id='all', symb=True)
+    o = ld2dap.RawOutput()
+
+    d.input = m
+    m.input = f
+    m.second.input = a
+    a.input = f
+    f.input = p
+    p.input = t
+    t.input = l
+
+    d.run()
+
+
+#from core import Input, Output, Filter
 
 def main():
     logger.setup_logging()
-    i = LoadTIFF(['Data/test.tiff', 'Data/test2.tiff'])
-    t = Treshold(1e4)
-    ap = SDAPs([100,1e3], [.5,.7,.9], [.1,.3])
-    o = SaveFig('Res/test.png')
-    s = ShowFig(0, False)
-    d = Differential()
-
-    t.input = i
-    ap.input = t
-    o.input = ap
-    d.input = ap
-    s.input = d
-
-    i.run()
+    diff_test()
 
 if __name__ == '__main__':
     main()

test.yml

@@ -0,0 +1,38 @@
+expe:
+  name: Première expérience
+  date: 9 juillet 2018
+  priority: 1
+  workflow: split-first # desc-first (default), split-first
+  ground_truth: ../Data/ground_truth/2018_IEEE_GRSS_DFC_GT_TR.tif
+  meta_labels: ../GroundTruth/jurse_meta_idx.csv
+  descriptors_script:
+    name: Descriptors.dfc_sdaps
+    parameters:
+      areas:
+      - 100
+      - 1000
+      - 1e5 
+      moi:
+      - 0.5
+      - 0.9
+      rasters:
+      - ./Data/phase1_rasters/DEM+B_C123/UH17_GEM051_TR.tif
+      - ./Data/phase1_rasters/DEM_C123_3msr/UH17_GEG051_TR.tif
+      treshold: 1e4
+#      features:
+#      - std
+#      - mean
+#      patch_size: 3
+  cross_validation:
+    package: CVGenerators
+    name: APsCVG
+    parameters:
+      n_test: 2
+  classifier:
+    package: sklearn.ensemble
+    name: RandomForestClassifier
+    parameters:
+      min_samples_leaf: 10
+      n_estimators: 50
+      n_jobs: -1
+      random_state: 0