{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "import csv\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from tqdm import tqdm\n",
    "import utils.samplefiles\n",
    "import h5py"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = utils.samplefiles.SampleFile()\n",
    "data.read_hdf('./output/train.hdf')\n",
    "\n",
    "wave, noise = data.as_dataframe(injection_parameters=True, \n",
    "                  static_arguments=False, \n",
    "                  command_line_arguments=False, \n",
    "                  split_injections_noise=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "4096"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wave['h1_strain'][0].size"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Turn strain into multi-dimension array"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "h1w = wave['h1_strain'].tolist()\n",
    "h1n = noise['h1_strain'].tolist()\n",
    "wary = np.array(h1w)\n",
    "nary = np.array(h1n)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "4096"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "h1w[0].size"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Split train and test set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_wnum = 50\n",
    "train_nnum = 50\n",
    "test_wnum = 50\n",
    "test_nnum = 50\n",
    "\n",
    "wtrain = wary[:train_wnum,:]\n",
    "ntrain = nary[:train_nnum,:]\n",
    "wtest = wary[train_wnum:,:]\n",
    "ntest = nary[train_nnum:,:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(50, 4096)"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "wtrain.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Insert label"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "wtrain = np.insert(wtrain, 0, values=1, axis=1)\n",
    "ntrain = np.insert(ntrain, 0, values=0, axis=1)\n",
    "wtest = np.insert(wtest, 0, values=1, axis=1)\n",
    "ntest = np.insert(ntest, 0, values=0, axis=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Training set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 4096/4096 [00:00<00:00, 774600.71it/s]\n"
     ]
    }
   ],
   "source": [
    "train_name = []\n",
    "num = wtrain.shape[1]-1 # 4096\n",
    "train_name.append('label')\n",
    "for i in tqdm(range(0,num)):\n",
    "    train_name.append('point{s1}'.format(s1=i))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 50/50 [00:00<00:00, 120.83it/s]\n"
     ]
    }
   ],
   "source": [
    "with open(\"output/train.csv\",\"w\") as csvfile: \n",
    "    writer = csv.writer(csvfile)\n",
    "    #columns_name\n",
    "    writer.writerow(train_name)\n",
    "    #use writerows to write lines\n",
    "    for i in tqdm(range(0,train_wnum)):\n",
    "        writer.writerow(wtrain[i])\n",
    "        writer.writerow(ntrain[i])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_set = pd.read_csv(\"./output/train.csv\", dtype=np.float32)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(100, 4097)"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_set.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Testing set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 4096/4096 [00:00<00:00, 457568.56it/s]\n"
     ]
    }
   ],
   "source": [
    "test_name = []\n",
    "num = wtrain.shape[1]-1 # 4096\n",
    "test_name.append('label')\n",
    "for i in tqdm(range(0,num)):\n",
    "    test_name.append('point{s1}'.format(s1=i))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 50/50 [00:00<00:00, 120.86it/s]\n"
     ]
    }
   ],
   "source": [
    "with open(\"output/test.csv\",\"w\") as csvfile: \n",
    "    writer = csv.writer(csvfile)\n",
    "    #columns_name\n",
    "    writer.writerow(test_name)\n",
    "    #use writerows to write lines\n",
    "    for i in tqdm(range(0,test_wnum)):\n",
    "        writer.writerow(wtest[i])\n",
    "        writer.writerow(ntest[i])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_set = pd.read_csv(\"./output/test.csv\", dtype=np.float32)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(100, 4097)"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_set.shape"
   ]
  },
  {
   "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": "3.8.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}