FYS-STK4155/doc/Programs/ProjectsData/data_exploration.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_data = np.load(\"../data/images/pr_train_simulated_50.0.npy\")\n",
    "test_data = np.load(\"../data/images/pr_test_simulated_50.0.npy\")\n",
    "all_data = np.concatenate([train_data, test_data])\n",
    "np.save(\"../data/images/project_data.npy\", all_data)\n",
    "\n",
    "train_targets = np.load(\"../data/targets/train_targets.npy\")\n",
    "test_targets = np.load(\"../data/targets/test_targets.npy\")\n",
    "all_targets = np.concatenate([train_targets, test_targets])\n",
    "np.save(\"../data/targets/project_targets.npy\", all_targets)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5600, 64, 64, 1)"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2400, 128, 128, 1)"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x11c83b898>"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.imshow(train[4].reshape((128, 128)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "other_maxs = np.zeros(train.shape[0])\n",
    "\n",
    "for i, e in enumerate(train):\n",
    "    other_maxs[i] = e.max()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2400,)"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "other_maxs.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "maxs = np.amax(train, axis=(1,2, 3))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2400,)"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "maxs.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([916., 920., 204.,  69.,  27.,  18.,  37.,  21.,  25.,  19.,  15.,\n",
       "         38.,  41.,  12.,   6.,   6.,   7.,  10.,   4.,   5.]),\n",
       " array([  1.759  ,  13.81965,  25.8803 ,  37.94095,  50.0016 ,  62.06225,\n",
       "         74.1229 ,  86.18355,  98.2442 , 110.30485, 122.3655 , 134.42615,\n",
       "        146.4868 , 158.54745, 170.6081 , 182.66875, 194.7294 , 206.79005,\n",
       "        218.8507 , 230.91135, 242.972  ]),\n",
       " <a list of 20 Patch objects>)"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.hist(other_maxs, bins=20)"
   ]
  },
  {
   "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",
   "version": "3.7.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}