461 lines
65 KiB
Plaintext
461 lines
65 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "b5fd075a",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Needed Imports\n",
|
|
"import pandas as pd\n",
|
|
"import numpy as np\n",
|
|
"import tensorflow as tf\n",
|
|
"import os\n",
|
|
"import pickle\n",
|
|
"import matplotlib.pyplot as plt\n",
|
|
"from math import isqrt"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "805e21e0",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"os.environ['TF_FORCE_GPU_ALLOW_GROWTH'] = 'true' # this is required\n",
|
|
"os.environ['CUDA_VISIBLE_DEVICES'] = '2' # set to '0' for GPU0, '1' for GPU1 or '2' for GPU2. Check \"gpustat\" in a terminal."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "52b164a4",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"delim = ';'\n",
|
|
"user_count = 100\n",
|
|
"base_path = '/opt/iui-datarelease1-sose2021/'\n",
|
|
"Xpickle_file = './X.pickle'\n",
|
|
"ypickle_file = './y.pickle'\n",
|
|
"\n",
|
|
"# Function that opens and reads pickle Data from FS and returns the read data as NumpyArray\n",
|
|
"def load_pickles():\n",
|
|
" _p = open(Xpickle_file, 'rb')\n",
|
|
" X = pickle.load(_p)\n",
|
|
" _p.close()\n",
|
|
" \n",
|
|
" _p = open(ypickle_file, 'rb')\n",
|
|
" y = pickle.load(_p)\n",
|
|
" _p.close()\n",
|
|
" \n",
|
|
" return (np.asarray(X, dtype = pd.DataFrame), np.asarray(y, dtype = str))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"id": "2b75bbc1",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Function used to save data as a pickle file\n",
|
|
"def save_pickle():\n",
|
|
"# _p = open(np.asarray(data, dtype=pd.DataFrame), 'wb')\n",
|
|
" _p = open(Xpickle_file, 'wb')\n",
|
|
" pickle.dump(X, _p)\n",
|
|
" _p.close()\n",
|
|
"\n",
|
|
"# _p = open(np.asarray(label, dtype=str), 'wb')\n",
|
|
" _p = open(ypickle_file, 'wb')\n",
|
|
" pickle.dump(y, _p)\n",
|
|
" _p.close()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"id": "03037493",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Function that loads data from the picklefiles and prints them into NumpyArrays (one for Data and one for Lables)\n",
|
|
"def load_data():\n",
|
|
" if os.path.isfile(Xpickle_file) and os.path.isfile(ypickle_file):\n",
|
|
" return load_pickles()\n",
|
|
" data = []\n",
|
|
" label = []\n",
|
|
" for user in range(0, user_count):\n",
|
|
" user_path = base_path + str(user) + '/split_letters_csv/'\n",
|
|
" for file in os.listdir(user_path):\n",
|
|
" file_name = user_path + file\n",
|
|
" letter = ''.join(filter(lambda x: x.isalpha(), file))[0]\n",
|
|
" data.append(pd.read_csv(file_name, delim))\n",
|
|
" label.append(letter)\n",
|
|
" return (np.asarray(data, dtype = pd.DataFrame), np.asarray(label, dtype = str))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"id": "b91b4622",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"(13102, 13102)"
|
|
]
|
|
},
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# Load Data\n",
|
|
"X, y = load_data()\n",
|
|
"len(X), len(y)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"id": "817f4cef",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"(13102,)\n",
|
|
"(13102,)\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# Show Data Shape\n",
|
|
"print(X.shape)\n",
|
|
"print(y.shape) "
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "3c11cf82",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Show how many datasets are make how many percent \n",
|
|
"X_len = np.asarray(list(map(len, X)))\n",
|
|
"l = []\n",
|
|
"sq_xlen = pd.Series(X_len)\n",
|
|
"ptiles = [x*0.01 for x in range(100)]\n",
|
|
"for i in ptiles:\n",
|
|
" l.append(sq_xlen.quantile(i))\n",
|
|
"plt.plot(l, ptiles)\n",
|
|
"sq_xlen.describe(percentiles=[x*0.01 for x in range(90,100)])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 17,
|
|
"id": "c34dd9d0",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Remove outliner data from the dataset\n",
|
|
"threshold_p = 0.99\n",
|
|
"threshold = int(sq_xlen.quantile(threshold_p))\n",
|
|
"len_mask = np.where(X_len <= threshold)\n",
|
|
"\n",
|
|
"X_filter = X[len_mask]\n",
|
|
"y_filter = y[len_mask]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 98,
|
|
"id": "eb03d293",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Sliding Window Function\n",
|
|
"def sliding_window(data):\n",
|
|
" input_data = data\n",
|
|
" _window_sz = 10\n",
|
|
" sum_windows_passed = 0\n",
|
|
" \n",
|
|
" \n",
|
|
" data_above_thresh = []\n",
|
|
" thresh = 70\n",
|
|
" \n",
|
|
" values_sum = 0\n",
|
|
" \n",
|
|
" for i in range(0, len(input_data), _window_sz):\n",
|
|
" for j in range(i, min(i + _window_sz, len(input_data))):\n",
|
|
" values_sum += input_data[j]\n",
|
|
" data_above_thresh.append(values_sum / _window_sz)\n",
|
|
" \n",
|
|
" return data_above_thresh"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 75,
|
|
"id": "1581a370",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"[<matplotlib.lines.Line2D at 0x7f08c64055e0>]"
|
|
]
|
|
},
|
|
"execution_count": 75,
|
|
"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": [
|
|
"input_data = X[5]['Force']\n",
|
|
"window_sz = 10\n",
|
|
"sum_windows_passed = 0\n",
|
|
" \n",
|
|
" \n",
|
|
"win_above_thresh = []\n",
|
|
"thresh = 70\n",
|
|
" \n",
|
|
" \n",
|
|
"for i in range(0, len(input_data), window_sz):\n",
|
|
" values_sum = 0\n",
|
|
" for j in range(i, min(i + window_sz, len(input_data))): \n",
|
|
" values_sum += input_data[j]\n",
|
|
"\n",
|
|
" win_above_thresh.append(values_sum / window_sz)\n",
|
|
" \n",
|
|
"plt.plot(win_above_thresh)\n",
|
|
"plt.plot(X[5]['Force'])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 111,
|
|
"id": "f26eca93",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"(array([140, 150, 160, 170, 190, 200, 210]),)\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"_blep = np.where(np.asarray(win_above_thresh) > thresh)\n",
|
|
"\n",
|
|
"for i in range(len(_blep[0])):\n",
|
|
" _blep[0][i] = _blep[0][i] * window_sz\n",
|
|
" \n",
|
|
"print(_blep) # s.u. Range der Daten über threshold ist von 140 bis 180 und von 190 bis 220; \n",
|
|
" # Alles vor 140 und nach 220 ist 0 und kann gecutted werden"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 120,
|
|
"id": "407f8efe",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"X_new = X[_blep]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 121,
|
|
"id": "1c886109",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"(13102,)\n",
|
|
"(124,)\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"print(X.shape)\n",
|
|
"print(X_new[5]['Force'].shape)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 134,
|
|
"id": "cfa4732e",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"((13102,), (257, 15), (257, 15))"
|
|
]
|
|
},
|
|
"execution_count": 134,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"X.shape, X[140].shape, X_new[0].shape\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 141,
|
|
"id": "4a15e2ac",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"[<matplotlib.lines.Line2D at 0x7f08c2e739a0>]"
|
|
]
|
|
},
|
|
"execution_count": 141,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
},
|
|
{
|
|
"data": {
|
|
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAX0AAAD4CAYAAAAAczaOAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/Z1A+gAAAACXBIWXMAAAsTAAALEwEAmpwYAAAnyUlEQVR4nO3deZRcZ33m8e+vtt6kVqullixLsiXbso2NCRYaY0IgBBu8kInNhDBwOMFhnPjMHJiEkCExk5kDs3AGmAwknknIcbCJySEsITD2cMxiGxKHgI1lbORFXrRYllpLt1qt3qq61nf+qFvdJbmWW0t39b31fM7R6apbt2/f6yo//fbvfe/7mnMOERHpDpFOn4CIiCwfhb6ISBdR6IuIdBGFvohIF1Hoi4h0kVinT6CW9evXu23btnX6NEREAuXxxx8/6ZwbqfTaig79bdu2sXv37k6fhohIoJjZoWqvqbwjItJFFPoiIl1EoS8i0kUU+iIiXUShLyLSRRT6IiJdRKEvItJFFPoiXShfcHz1py8zm851+lRkmSn0RbrQ/U8d4/ZvPsU3dh/u9KnIMlPoi3Shu350EIDHDk12+ExkuSn0RbrMEy9P8uTh0wwkojz+0iRaPa+7KPRFuszXHjtMfyLKB996Ecen5xk9ner0KckyUuiLdJFkJse39xzjxis28csXFydhfOylUx0+K1lOCn2RLvK9Z44zm87xrtdt4dJzBtk42MMn7nuWH+8/2elTk2Wi0BfpIt94/AjnDfdz1bZhohHja7e9gcG+GJ/+7vOdPjVZJgp9kS5xZDLJj/dP8Os7txCJGADb1g9ww6s3sffYNJlcocNnKMtBoS/SJb75s1Gcg3+1c/MZ26/YvIZMrsALJ2Y6dGaynBT6Il3i+88e519sW8vW4f4ztr9myxoAnhqd6sRpyTJT6It0gdl0jmePTvOGC9a94rXzhvsZ7I2x54hCvxso9EW6wBMvT1Jw8Lptw694zcx4zZYh9hw5zVw6x2cfeIFjU9XH7v/2PY/xps/8gD978MWlPGVZIgp9kS6w+6VJIgY7zxuq+PrVFwzzzNFpPvWd57jjoRf5rbsf47MPvMBnvvscP963OJxz9HSKB/eOcWIqzd88srj2dqHguP5PH+avHj6w1JciLVLoi3SB3YdOcck5g6zujVd8/d27thKLGH/zyCG2Dvdx4OQs/+cHL3Lnwwd4312P8q0njgDwj8+PA3DzledycjbN5FwGgGePTfPc8Rm+vefo8lyQNE2hLxJyzjn2HJ6q2soH2DDYy/WvPgeAP3jbJfzDR3+Fn3/87Tz1iet4wwXr+Ojf7WF8Js0/vjDG5qE+brhiE8DCiJ8feX8N7BmdYiqZXdoLkpbUDX0zu9vMxszs6bJt/9PMnjOzPWb2LTMbKnvtY2a2z8yeN7PryrZf723bZ2a3t/1KRKSik7MZZtI5LtqwquZ+H752B+97/XnccMU5bB7qY3VvnL5ElP/0jsvIFRz3P3WMf943wZsvHuHijasBeGFsFoB/enGc3ngE54q/AMZm5vnh82O88y/+mWeOqoN4JfHT0v9r4Pqztj0AvNo59xrgBeBjAGZ2GfAe4HLve/7CzKJmFgX+HLgBuAx4r7eviCyxA+PFYL5gpHboX7RhNZ985xX0xKJnbH/VptVsHe7jU995jtl0jn/5C5s4d00vq3pivHhihlQmz2MHJ/nXu7bSn4jyu199gqs++RAf+OJjPPHyaT6zRHf7Hj6V5FPfeY58QbOENiJWbwfn3MNmtu2sbd8ve/oI8C7v8U3AV51zaeCgme0DrvJe2+ecOwBgZl/19n22tdMXkXoOnpwD4IL1A019v5lx3WXn8IUfHeQXL1zHL164HoCLNqzihRMzPHpwgky+wFtftRFHcbz/O67YRDRiTCaz3PHQizx5+DSv3TrUpisq+vaeY/zlP+7nXa/bzEUbVrf12GFWN/R9+DfA17zHmyn+Eig54m0DOHzW9tdXOpiZ3QbcBnDeeee14fREutvBk3MkohHOHepr+hjv3LmZbz4xyu03XLqw7eKNq3hw7xgPv3CSRCzCVduGF2buLJlN5/jijw7yt48eanvoj55OAnBoIqnQb0BLHblm9sdADvhye04HnHN3Oud2Oed2jYyM1P8GEanpwMk5zl/XT9Sbb6cZl5+7hp/957fxmi1DC9veeNF6Ts1l+NufHuKqbcP0JaKv+L5VPTF+5dINPLh3jFy+vXP7HD09D8BLE8m2Hjfsmg59M/st4FeB97nFpXdGga1lu23xtlXbLiJL7ODJOS4Yaa60U8s7rtjE9vUDzGcLvGnH+qr7XXf5OZyay/DtPccWSk3tcNRb/OXlifYdsxs0Ffpmdj3wh8CvOefKf83eB7zHzHrMbDuwA/gp8Biww8y2m1mCYmfvfa2duojUky84Dk3MsX197U7cZsSiET587Q4iBm+9dEPV/d5yyQiJWIQPf+1Jfv3zPybbphZ/acUvtfQbU7emb2ZfAd4CrDezI8DHKY7W6QEeMDOAR5xz/9Y594yZfZ1iB20O+KBzLu8d50PA94AocLdz7pkluB4RKfPk4dNk845Lz1mamvdNr93Mm3aMMDyQqLrPQE+M37/2Yh576RQ/eG6Mn+wvDvtsxfR8lpn5HAAvn1LoN8LP6J33Vth8V439Pwl8ssL2+4H7Gzo7EWnJ3//sCH3xKNdetnHJfkatwC/5d2+5kA9kt7Hrvz/I/U8dazn0S6Wd89f1c/hUkly+QCyqe0390H8lkZCaz+b5fz8/yg2vPodVPe0YqNea3niUa161ge89c7zlsfWl0P/FC9eRKziOTc234xS7gkJfJKR+vP8kM/M53nnWoimd9Lrz1zKZzDKZzLR0nFFv5M7V3lTRKvH4p9AXCakXTxTvxC0fZtlpvfHisM75bL6l44xOpohHjQu9u4xL9X2pT6EvElL7x2dZv6qHNX2VZ9bshL42hf7J2TQjq3roT7TneN1EoS8SUgfG57hwCcbnt2Kxpd/asM3pVJbBvvjCDWHJjELfL4W+SEjtH5+tO8naciu19FMttsyn54uh3x+PteV43UShLxJCp+YyTCazK66l35coRk6qxZb5dCrHYG+cXu94Ku/4p9AXCaH93nTKF9aZQ3+5laZtbjWkiy39GIlohIhBMqOOXL8U+iIhtN9b3OTCJZh+oRWlGnzL5Z1UlsHeOGZGfyJGKtPeydzCTKEvEkKPH5pksDfG5rXNT6e8FEoduekWOnILBcdMOsegNyqpNx5VTb8BCn2RkCkUHD98fpw3XzzS0nTKS6EdHbmzmRzOwWBvsRO3LxEhpfKObwp9kZB5+ugUJ2fTNWe+7JTeuNeR20LoT6eKC6+XWvr98Zha+g1Q6IuEzEN7xzDjFatYrQS9bejInU4VW/WDvV55JxEl1eK4/26i0BcJmccPTXL5uYOsW9XT6VN5hUjE6IlFWmvpz5da+l55J67yTiMU+iIh89zxaV51zmCnT6Oq3niU+RbG6S+Ud7yWfn9C5Z1GKPRFQuTkbJqTsxkuWaJFU9qhLx5taRqGaW9ytdKcQn3xaMs3e3UThb5IiDx/fAaAS1d0S7/F8s5ZLf3eFn+JdBuFvkiIPOeF/kpu6RdDuvWa/ipvyGZ/Iqo7chug0BcJkeePT7NuIMHI6pXXiVvSl2jtZqrpVI7VPbGFexBaPV63UeiLhMjzx2dWdCsfisM2W23pD5atEVAq7xRaXIKxWyj0RUJk9PQ85w33d/o0aupLtNiRm8qyundxzd+FhVRyau37UTf0zexuMxszs6fLtg2b2QNm9qL3da233czsDjPbZ2Z7zGxn2ffc4u3/opndsjSXI9K9CgXHZDLD+hU4Pr9cyx25Z7X0F6Z20AgeX/y09P8auP6sbbcDDznndgAPec8BbgB2eP9uAz4PxV8SwMeB1wNXAR8v/aIQkfaYSmXJFxzDA4lOn0pNvS0OsZxNF2v6Je1amKVb1A1959zDwKmzNt8E3OM9vge4uWz7l1zRI8CQmW0CrgMecM6dcs5NAg/wyl8kItKCibkMAOtWrezQ74tHSbdQikmm8wyUh35CLf1GNFvT3+icO+Y9Pg5s9B5vBg6X7XfE21Zt+yuY2W1mttvMdo+Pjzd5eiLdZ2I2DcC6gZVe3mmtpT+XyS3U8UEt/Ua13JHrnHNA27rNnXN3Oud2Oed2jYysvAmjRFaqILX053MFitHRuGQ6T39CLf1mNRv6J7yyDd7XMW/7KLC1bL8t3rZq20WkTRZCf8XX9CPkC45svvHQd84xl8kx0FPW0vdCP6mWvi/Nhv59QGkEzi3AvWXb3++N4rkamPLKQN8D3m5ma70O3Ld720SkTUrlnbUrPvSbL8ekcwUKjjNb+t7xWpnErZvE6u1gZl8B3gKsN7MjFEfhfAr4upndChwC3u3tfj9wI7APSAIfAHDOnTKz/wY85u33X51zZ3cOi0gLTs1lGOqPE4+u7NtvSi3zdDYPZUMv/ZhLF6dbKG/p97dp3d1uUTf0nXPvrfLSNRX2dcAHqxznbuDuhs5ORHybmM2s+OGasLiQSjMhnfRa85Va+km19H1Z2U0CEfFtYi7N+hU+cgfKOl6bCP05b2K1gbLRO72J1lfj6iYKfZGQCExL31snt5mpGObSXku/bJx+O5Zg7CYKfZGQODWXWfHDNaGsI7eJckyyQks/Hi3OttnMaKBupNAXCYF8wXEqmVnxwzUBemLF2MnmW2jpl9X0zYx41Jo6XjdS6IuEwKm5DM7B+hU8j35JaXRRMyG90NIvG71TOmYmp9D3Q6EvEgJjM/MAbAh56M9VGL1TOqZa+v4o9EVCYGy6eGPWyOreDp9JfaXQzzRRg09WGKdfOmYzx+tGCn2REAhSSz9Rauk3UY6Zy+QxWxyxs3hM1fT9UuiLhMBiS3/lh348Vhpt00RNP52jPx4l4q2PW5KIqbzjl0JfJATGZtKs6YsvDIdcyVqt6ZeP0S8/pkLfH4W+SAiMzcwHorQDLdb0M7kzxuiXHzOTU03fD4W+SAiMzaTZMBiM0E+00tI/ay79krjKO74p9EVCYGw6zYYAjNyBsjtom+jITZ41l36JOnL9U+iLBJxzjvGZdGDKO9GIYdZCTb9SS181fd8U+iIBN5XKkskXAjFyB0rTJjQ3rj6ZrtzS1zh9/xT6IgE3NlMcrrlhMBjlHSjW9ZubhqF6S1/TMPij0BcJuHEv9EdWBaOlDzQ9QdpcldE7iZhq+n4p9EUC7qS3Nu76AEyrXNJMDd45x1w6R59q+i1R6IsE3Km5DADrAtXSb3xcfTpXIJt3DPZVCX2Vd3xR6IsE3MRshojBUIOLjHdSM9MmTKeyAKypcJ2JmDpy/VLoiwTcxFya4YGeV8xHs5LFIo3X4Kfni6E/2Fsh9FXe8a2l0Dez3zezZ8zsaTP7ipn1mtl2M3vUzPaZ2dfMLOHt2+M93+e9vq0tVyDS5U7OZgJVz4fmavBTXkt/sEJLXytn+dd06JvZZuB3gV3OuVcDUeA9wKeBzznnLgImgVu9b7kVmPS2f87bT0RaNDGbDsSC6OXiTZRjplPFufQHe9WR24pWyzsxoM/MYkA/cAx4K/AN7/V7gJu9xzd5z/Fev8bMgvP3qMgKVVwQPTiduOBNm9Bgx2upvFOppl8MfYdzquvX03ToO+dGgT8BXqYY9lPA48Bp51zO2+0IsNl7vBk47H1vztt/3dnHNbPbzGy3me0eHx9v9vREusbEbDAWRC/XTMt8ukZ5J7Gw2LpCv55WyjtrKbbetwPnAgPA9a2ekHPuTufcLufcrpGRkVYPJxJq89k8M+lcV9X0V1cs7zS/MEu3aaW8cy1w0Dk37pzLAt8E3ggMeeUegC3AqPd4FNgK4L2+Bpho4eeLdL0gjtGH5ubKmZ7P0RuP0BOrPPcOKPT9aCX0XwauNrN+rzZ/DfAs8EPgXd4+twD3eo/v857jvf4DpwKcSEtKoR+0jtxmpk2YTmUrDteEsoVZdINWXa3U9B+l2CH7M+Ap71h3An8EfMTM9lGs2d/lfctdwDpv+0eA21s4bxEhmFMwQJM1/flsxU5cWFyYJaOWfl2vLI41wDn3ceDjZ20+AFxVYd954Dda+XkicqaJWa+8MxC88k7Do3dSuYqduFC+2LqKB/XojlyRAJuqMTXBShaPRsgWGgvoqVS24hj90vFANX0/FPoiAZb2Wsu98Vd2bq5kzSxvOD2frdrST6im75tCXyTASiFXGqceFM2Vd6rX9OMxtfT9CtYnRUTOkM7liUWMaIAmW4NiSDdSf3fOMT2fqzp6JxHVzVl+KfRFAiydK9ATsFY+lMbpF3xPm5DM5MkXKs+lXzoeqKXvR/A+LSKyIJMrBK60A8WaPkDOZ2fuwgybVcfpF4+nIZv1Be/TIiIL0rl8xTtUV7pGW+alm9CG+mvfnKXVs+pT6IsEWFBb+osh7a+lf2QyBcCWtf0VX9eEa/4F79MiIgsCW9OPNXYH7ZHJJABbq4T+wjQM+Xwbzi7cgvdpEZEF6VyBnnjw/jdONDgr5uFTSVb3xGp05HrHa3Cx9W4UvE+LiCzI5AoLwxWDpNGa/pHJFFuG+6m27pLm3vEveJ8WEVnQLR25hyeTbF3b17bjdTOFvkiABbW8szgVcv1yjHOOw6dSVTtxobwjV6FfT/A+LSKyIKjlnUTMf01/Yi5DKptn67Cflr5q+vUE79MiIguKLf1wl3fqDdcsHs+7OUvj9OtS6IsEWFBb+vEGOl5HF0K/ekvfzIg3MXNnNwrep0VEFqRz+UDX9P2UY6bn/a0Z0MxqXN0oeJ8WEVmQzgbz5qxEA9MmpDLFG676E7XLWMXQV02/nuB9WkRkQTof0GkYGujITWWLod/nI/Q1Tr++4H1aRAQoDmXM5AqBHqfvJ6STmRzRiNXtu0hETROu+aDQFwmoUmAGurzjoxyTzOTpj0er3o1bEo+ppe9HS58WMxsys2+Y2XNmttfM3mBmw2b2gJm96H1d6+1rZnaHme0zsz1mtrM9lyDSnUrr4wYx9BsZspnK5OuWdkrHVEdufa1+Wv4M+K5z7lLgF4C9wO3AQ865HcBD3nOAG4Ad3r/bgM+3+LNFulo6G+TQ91/TT2bydTtxi8eM+LrDt9s1/WkxszXAm4G7AJxzGefcaeAm4B5vt3uAm73HNwFfckWPAENmtqnZny/S7UqljGB25JamYfAX+n2JyrNrlkvE1NL3o5VPy3ZgHPiimT1hZl8wswFgo3PumLfPcWCj93gzcLjs+494285gZreZ2W4z2z0+Pt7C6YmEW9ob1RLEjtxGZsVMZXP0+bgXIaGbs3xpJfRjwE7g8865K4E5Fks5ALjiqscN/b3lnLvTObfLObdrZGSkhdMTCbdAt/QbWDmrWN6p39JXTd+fVj4tR4AjzrlHveffoPhL4ESpbON9HfNeHwW2ln3/Fm+biDQhyDX9aMSIRszXSleNdORmdHNWXU1/Wpxzx4HDZnaJt+ka4FngPuAWb9stwL3e4/uA93ujeK4GpsrKQCLSoMXRO8Er70CxxOO3pu+3I1fj9Our/zdTbf8e+LKZJYADwAco/iL5upndChwC3u3tez9wI7APSHr7ikiTSoEZxPIO4E2QVr9lnsr6C/1ETDV9P1oKfefck8CuCi9dU2FfB3ywlZ8nIovSuVJHbjBDPxGLLvy1Uksqk6cvrpp+uwTz0yIigW/p9/gYYumcI5nJ+S/vqKZfVzA/LSIS6DtyoVjeqVfTT+cKFFz9ydaKx4v4+suh2wXz0yIii+WdAK6cBcW/UOqFvt9plUHj9P1S6IsE1EJ5J4ArZ4G/GnyyNK2yj19squn7E8xPi4gslncCuHIWeC39OiGdyuQAn+UdTcPgSzA/LSIS+Jp+wkcNPrlQ3vEx947XkVscKCjVBPPTIiILgRnU8o6fCdKSjdT0Y/7n6O9mwfy0iAjpXJ5ELFJ3cZGVys8duaWOXH+jd/xP19zNFPoiAZXJFegJaCsffI7eyfpv6TeyMEs3C+4nRqTLpXOFwHbigs/RO6Xyjs87csHfdM3dLLifGJEul8rk6Q3oGH3wO07f/+idRtbd7WYKfZGAmkplWdMX7/RpNK04ZLN2QDfSkRuPeTV93ZVbk0JfJKACH/rRCJlc7fn0S6Hv5y8alXf8UeiLBFTgQ9/PzVnZPD2xCNFI/RFKC6Gvln5NCn2RgAp66PuZT38unWNVj78Z4BMaveOLQl8koIIe+ololHzBkS9UD/65dI4Bn6EfV0euLwp9kQCaz+bJ5AoMBjn0Y/XLMbNpf6tmlR9PLf3aFPoiATSVygIEuqVfuoO2Vl0/mfFf3vFzPFHoiwRSGEK/x0dLv6nyjjpya1LoiwRQGEJ/obxTo2U+m84x0NNoeUc1/VoU+iIBNJUMfuj7aZknM3kGfEyrfMbxVN6pqeXQN7OomT1hZt/2nm83s0fNbJ+Zfc3MEt72Hu/5Pu/1ba3+bJFu1V0tfdX026kdLf3fA/aWPf808Dnn3EXAJHCrt/1WYNLb/jlvPxFpQihCv87NVM45r6bvs7yjlr4vLYW+mW0B3gF8wXtuwFuBb3i73APc7D2+yXuO9/o1FtSJwEU6rBT6QR6yGa/T0k/nChQc6shts1Zb+n8K/CFQ+q+8DjjtnMt5z48Am73Hm4HDAN7rU97+ZzCz28xst5ntHh8fb/H0RMJpKpVldU/M1/QEK1VPnZb+bLoYI76HbPooF0kLoW9mvwqMOeceb+P54Jy70zm3yzm3a2RkpJ2HFgmN6VQ20K18WAzpauWYOS/0/ayPC+UrZ2n0Ti3+/mtW9kbg18zsRqAXGAT+DBgys5jXmt8CjHr7jwJbgSNmFgPWABMt/HyRrhX0KRigfk1/Ll2cYXOVz5p+PKIJ1/xouqXvnPuYc26Lc24b8B7gB8659wE/BN7l7XYLcK/3+D7vOd7rP3Batl6kKdPzIQj9OjdnzXkLqPit6Uci5k3iptCvZSnG6f8R8BEz20exZn+Xt/0uYJ23/SPA7Uvws0W6Qhha+vXmv59tsLxTOqZCv7ZWyjsLnHP/APyD9/gAcFWFfeaB32jHzxPpdmEI/XrTMCQXyjuNhr4KCLXojlyRAJpKZVnTH+zQr3dzVqkj1+84fSiGvkbv1KbQFwmYdC7PfLYQ+JZ+vXH1pfKO32kYABJR0zj9OhT6IgEThhuzoH5LP9lgRy4Uh4Gqpl+bQl8kYKZDMAUDlE+bULkGP5vOk4hGFn45+KGafn0KfZGACcO8O7B4M1W66jh9//PuLB5TNf16FPoiAROW0DczEtFIzXH6jQzXhGJNXzdn1abQFwmYhZp+b1tGXHdUrZup5tL+l0pcPJ5q+vUo9EUCJgwLqJQkYjVa+ul8U+UdhX5tCn2RgJlKFUe1BH30DtQO/VNzGdb2Jxo6XjwWIaOO3JoU+iIBM5XKMpCILoxzD7JaHa+n5jIMDzQW+oloROP06wj+p0aky4RhCoaS3niUdC7/iu3OOSbm0qxb1dPQ8RIxTbhWj0JfJGCmQjCXfklPLEI6+8qQnknnyOYd6xps6WvIZn0KfZGAmQ5ZS3++Qkv/1GwGoKnyjoZs1qbQFwmYMJV3qrX0J+aKob9uVYOhX6NjWIoU+iIBE6bQr9bSn5hNA7BuoNGavkK/HoW+SMCEKfSrtfRPeS394SZa+mnV9GtS6IsEyGw6Ryqbb3hUy0pVtaVfKu80WNPv8Wr6Wom1OoW+SICMTqYA2LK2r8Nn0h5Va/qzGQYSUXrjjd2RW5qRUzNtVqfQFwmQ0dNJADaHJPR741HmsxVG78ylGy7twGLoVxr7L0UKfZEAWWjpD4Uj9HviEeYrdLxOzGUa7sQF6IkV/zJQZ251Cn2RADlyOkUiGmF9SGr6PbFoxRr8xGym4Xo+1F+NS1oIfTPbamY/NLNnzewZM/s9b/uwmT1gZi96X9d6283M7jCzfWa2x8x2tusiRLrFkckU5w71EolYp0+lLXrjpXLMmSHdzLw7sLgal1r61bXS0s8Bf+Ccuwy4GvigmV0G3A485JzbATzkPQe4Adjh/bsN+HwLP1ukK41OpkJTz4fFcszZnbkz881NNbHQ0lfoV9V06DvnjjnnfuY9ngH2ApuBm4B7vN3uAW72Ht8EfMkVPQIMmdmmZn++SDcaPZ1ic0jq+bDY0i8ftumcI5nN059obOQOlHfkKvSraUtN38y2AVcCjwIbnXPHvJeOAxu9x5uBw2XfdsTbdvaxbjOz3Wa2e3x8vB2nJxIK89k84zNpNg/1d/pU2qZSSz+dK+AcDQ/XBNX0/Wg59M1sFfD3wIedc9Plr7li70xDA2adc3c653Y553aNjIy0enoioXFsah4Iz3BNqNzST2WKj5tp6feopl9XS6FvZnGKgf9l59w3vc0nSmUb7+uYt30U2Fr27Vu8bSLiw4npYuhvWtPb4TNpn0ot/WS2+dBXTb++VkbvGHAXsNc599myl+4DbvEe3wLcW7b9/d4onquBqbIykIjUMTZTnIRsZHU4hmtCtZZ+cTnIvkTjC7+rpl9f4/9VF70R+E3gKTN70tv2H4FPAV83s1uBQ8C7vdfuB24E9gFJ4AMt/GyRrjPuhf6GEIV+qaVfflduslTeaaWmr9CvqunQd879CKg2WPiaCvs74IPN/jyRbjc2M08iGgnNDJtQNk6/vLzTSk2/dEduXtMwVKM7ckUCYnwmzcjqHoqV1XBYaOlX6MjtVU1/SSj0RQJifCbN+hCVdqBySz/VSkeuRu/UpdAXCYjxmXSo6vmwOBa/vKW/WNNXR+5SUOiLBESpvBMmPbEKLf2F0TvN1PR1c1Y9Cn2RAMjmC0zMZRgJyeyaJTVb+irvLAmFvkgATMwWlw/cMBiu0C+FdKXRO31NDNmMRIxYxBT6NSj0RQJgbKZ4N27YWvqRiJGIRc4cvZPN0xOLND19dCIWUU2/BoW+SAAs3Jg1GJ4pGErOXic3mck1VdopScQiaunXoNAXCYAT0+G7G7ekNx49Y03bVKZAfxNTMJQkogr9WhT6IgFw9HSKiIUz9HtiEebPGKefa2rkzsLx4hGN3qlBoS8SAEenUmwc7CUWDd//sme39JOZ5hZQKVFLv7bwfYJEQujY6XnODdGKWeXObuknM/mmRu6UJGJRdeTWoNAXCYCjU6lQzaNf7pU1/XxL5Z1ETOWdWhT6Iiucc45jU93U0m9t9E5PNEImp1k2q1Hoi6xwE3MZMrkC53ZTS7+JeXdKNGSzNoW+yAp39HQKgE0hbekP9saYnMsuPE9lW+zIVXmnJoW+yAp39HTxbtxz14Qz9M9fN8DRqdTC6lntGL1TfrOXnEmhL7LCHZsqtvTPHQpneWf7+gGcg8OnkuQLjnSuoI7cJaTQF1nhDk0k6YlFGB5IdPpUlsT56/oBeGkiubCASmtDNlXTr0WhL7LCPfzCOFdtHw7VMonltq8fAOClk3Mkvbn0Wxq9o9CvSaEvsoLtH5/lwMk53nbZxk6fypIZ6k8w1B/n4MQcTx2ZAop1/mappV/bsoe+mV1vZs+b2T4zu325f740byqV5cf7T5INWL20UHDc++Qop5MZvvv0cb6952inT8m37z9zAoBrXhXe0AfYtm6Al07O8eDeMVb1xHj9BcNNHysRi5AO2Gd0OTU/GLYJZhYF/hx4G3AEeMzM7nPOPbuc59EJ6VyeZ49O86pNgwurBQXJgfFZfudLu9k/PseG1T3c8d4rufqCdZ0+LV/+6p8O8D++8xy/sHWIvUenKTjH9vUDXH7umk6fWlVj0/N86G+f4KcvneI1W9awOaTDNUu2rx/gkQMT7Bub5ZcvHqEn1urNWQWcc8tSEhubnucP/u7nvHbrEL9/7cVNrwOwXJY19IGrgH3OuQMAZvZV4CagraF/OpnhN/7yJ+08ZMvGZtJMpbKs7olxTsBusskXHAdOzjHYG+O//NrlfOknL/Gbdz3Kthb+BG/1fE5Mz7OqN8Zgb7zu/gdPzrFtXT8/P3ya4YEE0Yjxvi88uqIXJBmbSZPLF/jodZfw6zu3dPp0ltwVm9fwrSdGAbj2sg0tHau0OPrbPvcwyxG/YzNp5tI5/unFk/zfJ0fpbeEXVrlLNw3yv997ZVuOVW65Q38zcLjs+RHg9eU7mNltwG0A5513XlM/JBIxdmxc1eQpLo0rzxvi6gvW8dhLp5hKZet/wwpz85WbefeurZyzppebX7uZP/n+80zMpTtyLmbGL18ywux8jjmv46+Wq7YP89HrLuErPz3MzvOGiEUjfPGfD1JwbhnOtjmXnTvI77zpAl69eeX+NdJO73/D+QwPJHjy8Gmuu/yclo719svP4fkTs+QLy1PiKb1XTxw+zU/2n2zbcbeuXZq/7swt4wffzN4FXO+c+23v+W8Cr3fOfajS/rt27XK7d+9etvMTEQkDM3vcOber0mvL3ZE7Cmwte77F2yYiIstguUP/MWCHmW03swTwHuC+ZT4HEZGutaw1fedczsw+BHwPiAJ3O+eeWc5zEBHpZsvdkYtz7n7g/uX+uSIiojtyRUS6ikJfRKSLKPRFRLqIQl9EpIss681ZjTKzceBQC4dYD7TvFrmVrZuuFbrrenWt4bVU13u+c26k0gsrOvRbZWa7q92VFjbddK3QXderaw2vTlyvyjsiIl1EoS8i0kXCHvp3dvoEllE3XSt01/XqWsNr2a831DV9ERE5U9hb+iIiUkahLyLSRUIZ+t2w+LqZvWRmT5nZk2a229s2bGYPmNmL3te1nT7PZpjZ3WY2ZmZPl22reG1WdIf3Xu8xs52dO/PmVLneT5jZqPf+PmlmN5a99jHvep83s+s6c9bNMbOtZvZDM3vWzJ4xs9/ztofu/a1xrZ19b51zofpHccrm/cAFQAL4OXBZp89rCa7zJWD9Wds+A9zuPb4d+HSnz7PJa3szsBN4ut61ATcC3wEMuBp4tNPn36br/QTwHyrse5n3me4Btnuf9Winr6GBa90E7PQerwZe8K4pdO9vjWvt6Hsbxpb+wuLrzrkMUFp8vRvcBNzjPb4HuLlzp9I859zDwKmzNle7tpuAL7miR4AhM9u0LCfaJlWut5qbgK8659LOuYPAPoqf+UBwzh1zzv3MezwD7KW4dnbo3t8a11rNsry3YQz9Souv1/oPHVQO+L6ZPe4tJg+w0Tl3zHt8HNjYmVNbEtWuLczv94e8ksbdZaW60FyvmW0DrgQeJeTv71nXCh18b8MY+t3il5xzO4EbgA+a2ZvLX3TFvxdDOR43zNdW5vPAhcBrgWPA/+ro2bSZma0C/h74sHNuuvy1sL2/Fa61o+9tGEO/KxZfd86Nel/HgG9R/DPwROlPX+/rWOfOsO2qXVso32/n3AnnXN45VwD+isU/8wN/vWYWpxiCX3bOfdPbHMr3t9K1dvq9DWPoh37xdTMbMLPVpcfA24GnKV7nLd5utwD3duYMl0S1a7sPeL83yuNqYKqsTBBYZ9Wt30nx/YXi9b7HzHrMbDuwA/jpcp9fs8zMgLuAvc65z5a9FLr3t9q1dvy97XQP9xL1mt9Isad8P/DHnT6fJbi+Cyj28v8ceKZ0jcA64CHgReBBYLjT59rk9X2F4p+9WYp1zVurXRvFUR1/7r3XTwG7On3+bbrev/GuZ48XBpvK9v9j73qfB27o9Pk3eK2/RLF0swd40vt3Yxjf3xrX2tH3VtMwiIh0kTCWd0REpAqFvohIF1Hoi4h0EYW+iEgXUeiLiHQRhb6ISBdR6IuIdJH/DzFAHuL/Ch+IAAAAAElFTkSuQmCC\n",
|
|
"text/plain": [
|
|
"<Figure size 432x288 with 1 Axes>"
|
|
]
|
|
},
|
|
"metadata": {
|
|
"needs_background": "light"
|
|
},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": [
|
|
"plt.plot(X[140]['Force'])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 142,
|
|
"id": "4128a3cd",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"[<matplotlib.lines.Line2D at 0x7f08c2dcca90>]"
|
|
]
|
|
},
|
|
"execution_count": 142,
|
|
"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.plot(X_new[0]['Force'])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 144,
|
|
"id": "9af3f711",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"[<matplotlib.lines.Line2D at 0x7f08c2c16f40>]"
|
|
]
|
|
},
|
|
"execution_count": 144,
|
|
"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.plot(X_new[1]['Force'])\n",
|
|
"plt.plot(X[150]['Force'])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "775983d4",
|
|
"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": "3.8.5"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|