Update notebooks

Notebooks/Classification Scores-Copy1.ipynb

@@ -17,12 +17,6 @@
     "from sklearn import metrics\n",
     "import matplotlib.pyplot as plt\n",
     "import pandas as pd\n",
-    "\n",
-    "# Triskele\n",
-    "import sys\n",
-    "from pathlib import Path\n",
-    "triskele_path = Path('../triskele/python')\n",
-    "sys.path.append(str(triskele_path.resolve()))\n",
     "import triskele\n",
     "\n",
     "figsize = np.array((16, 9))"
@@ -41,9 +35,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df_dfc_lbl  = pd.read_csv('../labels.csv')\n",
+    "df_dfc_lbl  = pd.read_csv('../../minigrida/Data/ground_truth/labels.csv')\n",
-    "df_meta_idx = pd.read_csv('../metaclass_indexes.csv')\n",
+    "df_meta_idx = pd.read_csv('../../minigrida/Data/ground_truth/jurse_meta_idx.csv')\n",
-    "df_meta_lbl = pd.read_csv('../metaclass_labels.csv')\n",
+    "df_meta_lbl = pd.read_csv('../../minigrida/Data/ground_truth/jurse_meta_lbl.csv')\n",
     "\n",
     "df_dfc_lbl.merge(df_meta_idx).merge(df_meta_lbl)"
    ]
@@ -71,7 +65,7 @@
    "outputs": [],
    "source": [
     "gt = triskele.read('../Data/ground_truth/2018_IEEE_GRSS_DFC_GT_TR.tif')\n",
-    "pred = triskele.read('../Res/tmppred_8_10pleaf_3cv.tif')"
+    "pred = triskele.read('../../minigrida/Enrichment/Results/tellus_fourhth_95bfcf.tif')"
    ]
   },
   {
@@ -111,7 +105,7 @@
     "fig, (ax_gt, ax_pred) = plt.subplots(2, figsize=figsize * 2)\n",
     "ax_gt.imshow(meta_idx[gt])\n",
     "ax_gt.set_title('Ground Truth')\n",
-    "ax_pred.imshow(meta_idx[pred])\n",
+    "ax_pred.imshow(pred)\n",
     "ax_pred.set_title('Prediction')\n",
     "plt.show()"
    ]
@@ -212,17 +206,32 @@
    "outputs": [],
    "source": [
     "f = np.nonzero(pred)\n",
-    "m_pred_s = meta_idx[pred_s]\n",
+    "m_pred_s = pred_s\n",
     "m_gt_s = meta_idx[gt_s]\n",
     "\n",
     "ct = pd.crosstab(m_gt_s, m_pred_s,\n",
     "        rownames=['Prediction'], colnames=['Reference'],\n",
     "        margins=True, margins_name='Total',\n",
-    "        normalize=False # all, index, columns\n",
+    "        normalize=False # all, index, columns, False\n",
     "        )\n",
     "ct"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lbl = df_meta_lbl['metaclass_label'][ct.columns[:-1]].tolist()\n",
+    "lbl.append('Total')\n",
+    "ct.columns = lbl\n",
+    "ct.columns.name = 'Reference'\n",
+    "ct.index = lbl\n",
+    "ct.index.name = 'Reference'\n",
+    "ct"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -273,6 +282,13 @@
     "metrics.precision_recall_fscore_support(m_gt_s, m_pred_s)\n",
     "print(metrics.classification_report(m_gt_s, m_pred_s))"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

Notebooks/CrossVal spatial.ipynb

@@ -160,7 +160,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "count = 5\n",
+    "count = 4\n",
     "\n",
     "step = int(gt.shape[0] / count)\n",
     "\n",

Notebooks/Raster Factory.ipynb

@@ -53,7 +53,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "raster = ra.rasterize_cache('intensity', C1, 1., 'nearest', False, cache_dir='../Res/enrichment_rasters')"
+    "raster = ra.rasterize_cache('num_returns', C1, .5, 'nearest', False, cache_dir='../Res/enrichment_rasters')\n",
+    "\n",
+    "plt.figure(figsize=figsize)\n",
+    "plt.imshow(raster, origin='upper')\n",
+    "plt.show()\n",
+    "plt.imsave('../Res/raster_validation.png', raster)"
    ]
   },
   {

Notebooks/Split First.ipynb

@@ -29,7 +29,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "n = 5; d = 0"
+    "n = 1; d = 0"
    ]
   },
   {
@@ -173,6 +173,82 @@
     "\n",
     "t_dsp.run()"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Split cross val"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "d = 0\n",
+    "s = 2\n",
+    "n = 3\n",
+    "\n",
+    "\n",
+    "step = int(descriptors.shape[d] / n)\n",
+    "size = descriptors.shape[d]\n",
+    "cfilter = (np.arange(size) - step * s) % size < step\n",
+    "\n",
+    "test_filter = np.zeros_like(descriptors[:,:,0], dtype=np.bool)\n",
+    "view = np.moveaxis(test_filter, d, 0)\n",
+    "view[cfilter] = True\n",
+    "\n",
+    "plt.imshow(test_filter)\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "descriptors[test_filter].shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "descriptors.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "f = np.zeros_like(test_filter, dtype=np.bool)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_filter |= f\n",
+    "test_filter"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_filter"
+   ]
   }
  ],
  "metadata": {