pipeline/sparse_matrix.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from scipy.sparse import csr_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Driver: GTiff/GeoTIFF\n",
      "Files: aso_vegabove2_test.tif\n",
      "Size is 32768, 26547\n",
      "Coordinate System is:\n",
      "GEOGCS[\"WGS 84\",\n",
      "    DATUM[\"WGS_1984\",\n",
      "        SPHEROID[\"WGS 84\",6378137,298.257223563,\n",
      "            AUTHORITY[\"EPSG\",\"7030\"]],\n",
      "        AUTHORITY[\"EPSG\",\"6326\"]],\n",
      "    PRIMEM[\"Greenwich\",0],\n",
      "    UNIT[\"degree\",0.0174532925199433],\n",
      "    AUTHORITY[\"EPSG\",\"4326\"]]\n",
      "Origin = (-119.893798828000001,38.229546134000003)\n",
      "Pixel Size = (0.000021457671875,-0.000016956626474)\n",
      "Metadata:\n",
      "  AREA_OR_POINT=Area\n",
      "Image Structure Metadata:\n",
      "  COMPRESSION=LZW\n",
      "  INTERLEAVE=BAND\n",
      "Corner Coordinates:\n",
      "Upper Left  (-119.8937988,  38.2295461) (119d53'37.68\"W, 38d13'46.37\"N)\n",
      "Lower Left  (-119.8937988,  37.7793986) (119d53'37.68\"W, 37d46'45.83\"N)\n",
      "Upper Right (-119.1906738,  38.2295461) (119d11'26.43\"W, 38d13'46.37\"N)\n",
      "Lower Right (-119.1906738,  37.7793986) (119d11'26.43\"W, 37d46'45.83\"N)\n",
      "Center      (-119.5422363,  38.0044724) (119d32'32.05\"W, 38d 0'16.10\"N)\n",
      "Band 1 Block=32768x1 Type=Float32, ColorInterp=Gray\n",
      "  Min=0.000 Max=1.000 \n",
      "  Minimum=0.000, Maximum=1.000, Mean=nan, StdDev=nan\n",
      "  NoData Value=-3.39999999999999996e+38\n",
      "  Metadata:\n",
      "    STATISTICS_MAXIMUM=1\n",
      "    STATISTICS_MEAN=nan\n",
      "    STATISTICS_MINIMUM=0\n",
      "    STATISTICS_STDDEV=nan\n"
     ]
    }
   ],
   "source": [
    "!gdalinfo aso_vegabove2_test.tif"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Driver: GTiff/GeoTIFF\n",
      "Files: pred_vegabove2_test.tif\n",
      "Size is 32768, 26547\n",
      "Coordinate System is:\n",
      "GEOGCS[\"WGS 84\",\n",
      "    DATUM[\"WGS_1984\",\n",
      "        SPHEROID[\"WGS 84\",6378137,298.257223563,\n",
      "            AUTHORITY[\"EPSG\",\"7030\"]],\n",
      "        AUTHORITY[\"EPSG\",\"6326\"]],\n",
      "    PRIMEM[\"Greenwich\",0],\n",
      "    UNIT[\"degree\",0.0174532925199433],\n",
      "    AUTHORITY[\"EPSG\",\"4326\"]]\n",
      "Origin = (-119.893798828000001,38.229546134000003)\n",
      "Pixel Size = (0.000021457671875,-0.000016956626474)\n",
      "Metadata:\n",
      "  AREA_OR_POINT=Area\n",
      "Image Structure Metadata:\n",
      "  COMPRESSION=LZW\n",
      "  INTERLEAVE=BAND\n",
      "Corner Coordinates:\n",
      "Upper Left  (-119.8937988,  38.2295461) (119d53'37.68\"W, 38d13'46.37\"N)\n",
      "Lower Left  (-119.8937988,  37.7793986) (119d53'37.68\"W, 37d46'45.83\"N)\n",
      "Upper Right (-119.1906738,  38.2295461) (119d11'26.43\"W, 38d13'46.37\"N)\n",
      "Lower Right (-119.1906738,  37.7793986) (119d11'26.43\"W, 37d46'45.83\"N)\n",
      "Center      (-119.5422363,  38.0044724) (119d32'32.05\"W, 38d 0'16.10\"N)\n",
      "Band 1 Block=32768x1 Type=Float32, ColorInterp=Gray\n",
      "  Min=0.000 Max=1.000 \n",
      "  Minimum=0.000, Maximum=1.000, Mean=nan, StdDev=nan\n",
      "  NoData Value=-3.39999999999999996e+38\n",
      "  Metadata:\n",
      "    STATISTICS_MAXIMUM=1\n",
      "    STATISTICS_MEAN=nan\n",
      "    STATISTICS_MINIMUM=0\n",
      "    STATISTICS_STDDEV=nan\n"
     ]
    }
   ],
   "source": [
    "!gdalinfo pred_vegabove2_test.tif"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ubuntu/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/matplotlib/__init__.py:1067: UserWarning: Duplicate key in file \"/home/ubuntu/.config/matplotlib/matplotlibrc\", line #2\n",
      "  (fname, cnt))\n",
      "/home/ubuntu/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/matplotlib/__init__.py:1067: UserWarning: Duplicate key in file \"/home/ubuntu/.config/matplotlib/matplotlibrc\", line #3\n",
      "  (fname, cnt))\n"
     ]
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "import rasterio as rio\n",
    "import numpy as np\n",
    "from matplotlib import pyplot as plt\n",
    "import rasterio.plot\n",
    "import os\n",
    "from datetime import datetime as dt\n",
    "# aso_vegabove2_test.tif\n",
    "#pred_vegabove2_test.tif\n",
    "# Load the veg aso\n",
    "veg_aso_2 = rio.open(r'aso_vegabove2_test.tif')\n",
    "veg_aso_2_mask = veg_aso_2.read(1)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "veg_mask_2 = rio.open(r'pred_vegabove2_test.tif')\n",
    "veg_pred_2_mask = veg_mask_2.read(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([-3.4e+38,  0.0e+00,  1.0e+00], dtype=float32)"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.unique(veg_pred_2_mask)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "true = veg_pred_2_mask[~(veg_pred_2_mask == -3.4e+38)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([-3.4e+38,  0.0e+00,  1.0e+00], dtype=float32)"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.unique(true)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x864 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import earthpy.spatial as es\n",
    "import earthpy.plot as ep\n",
    "ep.hist(veg_pred_2_mask, colors=['purple'],\n",
    "        title=\"Distribution of ndvi\",\n",
    "        xlabel='ndvi',\n",
    "        ylabel='Frequency')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "def compute_performance(true, pred, nodata = -9999):\n",
    "\n",
    "    true = true.flatten()\n",
    "    true = true[~(true == nodata)]\n",
    "\n",
    "    pred = pred.flatten()\n",
    "    pred = pred[~(pred == nodata)]\n",
    "\n",
    "    assert(pred.shape == true.shape)\n",
    "\n",
    "    performance = metrics.precision_recall_fscore_support(true, pred, average = 'binary')\n",
    "\n",
    "    accuracy = metrics.balanced_accuracy_score(true, pred)\n",
    "\n",
    "    kappa = metrics.cohen_kappa_score(true, pred)\n",
    "\n",
    "    result = {\n",
    "        \"Precision\": performance[0],\n",
    "        \"Recall\" : performance[1],\n",
    "        \"F-Score\": performance[2],\n",
    "        \"Balanced Accuracy\": accuracy,\n",
    "        \"Kappa\" : kappa\n",
    "    }\n",
    "\n",
    "    return result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "continuous is not supported",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-22-0bd2a72cfa55>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mmetrics\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mok\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcompute_performance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mveg_aso_2_mask\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mveg_pred_2_mask\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mnodata\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m3.39999999999999996e+38\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m<ipython-input-20-7e1e7d4745ba>\u001b[0m in \u001b[0;36mcompute_performance\u001b[0;34m(true, pred, nodata)\u001b[0m\n\u001b[1;32m      9\u001b[0m     \u001b[0;32massert\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpred\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0mtrue\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     10\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 11\u001b[0;31m     \u001b[0mperformance\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmetrics\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprecision_recall_fscore_support\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpred\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maverage\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m'binary'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     12\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     13\u001b[0m     \u001b[0maccuracy\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmetrics\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbalanced_accuracy_score\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpred\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/sklearn/metrics/classification.py\u001b[0m in \u001b[0;36mprecision_recall_fscore_support\u001b[0;34m(y_true, y_pred, beta, labels, pos_label, average, warn_for, sample_weight)\u001b[0m\n\u001b[1;32m   1029\u001b[0m         \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"beta should be >0 in the F-beta score\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1030\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1031\u001b[0;31m     \u001b[0my_type\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_true\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_pred\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_check_targets\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_true\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_pred\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1032\u001b[0m     \u001b[0mcheck_consistent_length\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_true\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_pred\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1033\u001b[0m     \u001b[0mpresent_labels\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0munique_labels\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_true\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_pred\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/sklearn/metrics/classification.py\u001b[0m in \u001b[0;36m_check_targets\u001b[0;34m(y_true, y_pred)\u001b[0m\n\u001b[1;32m     86\u001b[0m     \u001b[0;31m# No metrics support \"multiclass-multioutput\" format\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     87\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0my_type\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m\"binary\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"multiclass\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"multilabel-indicator\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 88\u001b[0;31m         \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"{0} is not supported\"\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_type\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     89\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     90\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0my_type\u001b[0m \u001b[0;32min\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m\"binary\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"multiclass\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mValueError\u001b[0m: continuous is not supported"
     ]
    }
   ],
   "source": [
    "from sklearn import metrics\n",
    "ok = compute_performance(veg_aso_2_mask,veg_pred_2_mask,nodata=-3.39999999999999996e+38)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "veg_pred_2_mask_bo = veg_pred_2_mask>0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "veg_aso_2_mask_bo = veg_aso_2_mask>0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.038196406373601534"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "accuracy_score(veg_pred_2_mask_bo, veg_aso_2_mask_bo)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ubuntu/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/sklearn/metrics/classification.py:1143: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 in labels with no predicted samples.\n",
      "  'precision', 'predicted', average, warn_for)\n",
      "/home/ubuntu/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/sklearn/metrics/classification.py:1145: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 in labels with no true samples.\n",
      "  'recall', 'true', average, warn_for)\n"
     ]
    }
   ],
   "source": [
    "mets = sklearn.metrics.f1_score(veg_pred_2_mask_bo, veg_aso_2_mask_bo, , average='weighted',labels=np.unique(y_pred))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.        , 0.        , 0.        , ..., 0.35587189, 0.35591358,\n",
       "       0.36816327])"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7f23eec6a780>"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from rasterio.plot import show\n",
    "show(veg_pred_2_mask)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sklearn.metrics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "S = csr_matrix(veg_aso_2_mask.flatten())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "ename": "MemoryError",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mMemoryError\u001b[0m                               Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-17-552908594e6c>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mP\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcsr_matrix\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mveg_pred_2_mask\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mflatten\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/scipy/sparse/compressed.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, arg1, shape, dtype, copy)\u001b[0m\n\u001b[1;32m     81\u001b[0m                                  \"\".format(self.format))\n\u001b[1;32m     82\u001b[0m             \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0mcoo\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mcoo_matrix\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 83\u001b[0;31m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_set_self\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__class__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcoo_matrix\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0marg1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     84\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     85\u001b[0m         \u001b[0;31m# Read matrix dimensions given, if any\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/scipy/sparse/coo.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, arg1, shape, dtype, copy)\u001b[0m\n\u001b[1;32m    190\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mastype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdtype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcopy\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    191\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 192\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_check\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    193\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    194\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mreshape\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/scipy/sparse/coo.py\u001b[0m in \u001b[0;36m_check\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    271\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    272\u001b[0m         \u001b[0midx_dtype\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mget_index_dtype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmaxval\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmax\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 273\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrow\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0masarray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrow\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0midx_dtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    274\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcol\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0masarray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcol\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0midx_dtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    275\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mto_native\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/numpy/core/numeric.py\u001b[0m in \u001b[0;36masarray\u001b[0;34m(a, dtype, order)\u001b[0m\n\u001b[1;32m    499\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    500\u001b[0m     \"\"\"\n\u001b[0;32m--> 501\u001b[0;31m     \u001b[0;32mreturn\u001b[0m \u001b[0marray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0ma\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcopy\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0morder\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0morder\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    502\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    503\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mMemoryError\u001b[0m: "
     ]
    }
   ],
   "source": [
    "P = csr_matrix(veg_pred_2_mask.flatten())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "Classification metrics can't handle a mix of continuous and binary targets",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-15-dd0ece61f9b5>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m mets = sklearn.metrics.precision_recall_fscore_support(np.round(veg_aso_2_mask.flatten()), \n\u001b[0;32m----> 2\u001b[0;31m                                                           (veg_pred_2_mask > 0).flatten().astype(int))\n\u001b[0m",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/sklearn/metrics/classification.py\u001b[0m in \u001b[0;36mprecision_recall_fscore_support\u001b[0;34m(y_true, y_pred, beta, labels, pos_label, average, warn_for, sample_weight)\u001b[0m\n\u001b[1;32m   1029\u001b[0m         \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"beta should be >0 in the F-beta score\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1030\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1031\u001b[0;31m     \u001b[0my_type\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_true\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_pred\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_check_targets\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_true\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_pred\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1032\u001b[0m     \u001b[0mcheck_consistent_length\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_true\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_pred\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1033\u001b[0m     \u001b[0mpresent_labels\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0munique_labels\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_true\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_pred\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/sklearn/metrics/classification.py\u001b[0m in \u001b[0;36m_check_targets\u001b[0;34m(y_true, y_pred)\u001b[0m\n\u001b[1;32m     79\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_type\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     80\u001b[0m         raise ValueError(\"Classification metrics can't handle a mix of {0} \"\n\u001b[0;32m---> 81\u001b[0;31m                          \"and {1} targets\".format(type_true, type_pred))\n\u001b[0m\u001b[1;32m     82\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     83\u001b[0m     \u001b[0;31m# We can't have more than one value on y_type => The set is no more needed\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mValueError\u001b[0m: Classification metrics can't handle a mix of continuous and binary targets"
     ]
    }
   ],
   "source": [
    "mets = sklearn.metrics.f1_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Environment (conda_pytorch_p36)",
   "language": "python",
   "name": "conda_pytorch_p36"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}