309 lines
14 KiB
Plaintext
309 lines
14 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "6be7788e",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import pandas as pd\n",
|
|
"import numpy as np\n",
|
|
"import tensorflow as tf\n",
|
|
"import matplotlib.pyplot as plt\n",
|
|
"from math import isqrt\n",
|
|
"import pickle\n",
|
|
"from tqdm import tqdm\n",
|
|
"import os\n",
|
|
"from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
|
|
"from sklearn.model_selection import train_test_split\n",
|
|
"from sklearn.preprocessing import LabelEncoder, LabelBinarizer\n",
|
|
"from tensorflow.keras.models import Sequential\n",
|
|
"from tensorflow.keras.layers import Dense, Flatten, BatchNormalization\n",
|
|
"\n",
|
|
"os.environ['TF_FORCE_GPU_ALLOW_GROWTH'] = 'true'\n",
|
|
"os.environ['CUDA_VISIBLE_DEVICES'] = '2'\n",
|
|
"\n",
|
|
"delim = ';'\n",
|
|
"user_count = 100\n",
|
|
"base_path = '/opt/iui-datarelease2-sose2021/'\n",
|
|
"Xpickle_file = './X2.pickle'\n",
|
|
"ypickle_file = './y2.pickle'\n",
|
|
"xshorted_pickle_file = './X2_shorted.pickle'\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "9af358ae",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"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": 3,
|
|
"id": "12a870d7",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"\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))\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "610ab5e0",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def shorten_pickle(l):\n",
|
|
" \n",
|
|
" temp = l\n",
|
|
" thresh = 80\n",
|
|
" temp_over_T = 0\n",
|
|
" isOver = False\n",
|
|
" temp_short = [] ##Daten nachdem vorne abgeschnitten wird\n",
|
|
" temp_final = [] ##Daten nachdem auch hinten abgeschnitten wurde\n",
|
|
" \n",
|
|
" temp_X = [] ## Zweite Dimension von Temp, beinhaltet force \n",
|
|
" temp_short_X = []\n",
|
|
" \n",
|
|
" for a in tqdm(range (0, len(temp))): \n",
|
|
" temp_X = temp[a] \n",
|
|
" \n",
|
|
" temp_X = l['Force']\n",
|
|
" thresh = 80\n",
|
|
" temp_over_T = 0\n",
|
|
" \n",
|
|
" temp_short = [] ##Daten nachdem vorne abgeschnitten wird\n",
|
|
" temp_final = [] ##Daten nachdem auch hinten abgeschnitten wurde\n",
|
|
" temp_short_X = []\n",
|
|
" \n",
|
|
" \n",
|
|
" \n",
|
|
" for b in range (0, len(temp_X)): \n",
|
|
" if(temp_X[b]>thresh):\n",
|
|
" temp_over_T = b\n",
|
|
" break\n",
|
|
" \n",
|
|
" for x in range (temp_over_T,len(temp_X)):\n",
|
|
" temp_short_X.append(temp_X[x]) ##hier werden die Daten von y appended in eine liste ( Von form data[x][y])\n",
|
|
" \n",
|
|
" \n",
|
|
" for y in range ((len(temp_short_X)-1),0, -1): \n",
|
|
" if(temp_short_X[y] > thresh):\n",
|
|
" temp_over_T = y\n",
|
|
" break\n",
|
|
" \n",
|
|
" for z in range(0, temp_over_T+1):\n",
|
|
" temp_short.append(temp_short_X[z]) ##hier wird [y] als einzelne Datei gespeichert\n",
|
|
" \n",
|
|
" temp_short.append(0) # Damit beim Plot die linie bis nach unten geht\n",
|
|
" \n",
|
|
" \n",
|
|
" temp_final.append(temp_short)\n",
|
|
" \n",
|
|
" return temp_final\n",
|
|
" \n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "7f232eeb",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def shorten_v2(npList):\n",
|
|
" temp = npList['Force']\n",
|
|
" \n",
|
|
" print (\"I was here\")\n",
|
|
" \n",
|
|
" thresh = 80\n",
|
|
" leeway = 1\n",
|
|
" \n",
|
|
" temps_over_T = np.where(temp > thresh)[0]\n",
|
|
" print(\"I Was here too\")\n",
|
|
" return npList[max(temps_over_T[0],0):temps_over_T[-1]]\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"id": "429f89ae",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"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": "5bb89103",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"## save_pickle() pickles sind erstellt"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"id": "78b21c1c",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"x,y = load_pickles()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"id": "ce783824",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"26179\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"print (len(x))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 10,
|
|
"id": "f1c165b1",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
" 0%| | 0/185 [00:00<?, ?it/s]\n"
|
|
]
|
|
},
|
|
{
|
|
"ename": "KeyError",
|
|
"evalue": "0",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
|
"\u001b[0;31mKeyError\u001b[0m Traceback (most recent call last)",
|
|
"\u001b[0;32m/opt/jupyterhub/lib/python3.8/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_loc\u001b[0;34m(self, key, method, tolerance)\u001b[0m\n\u001b[1;32m 3079\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3080\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcasted_key\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 3081\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
|
"\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
|
|
"\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
|
|
"\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
|
|
"\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
|
|
"\u001b[0;31mKeyError\u001b[0m: 0",
|
|
"\nThe above exception was the direct cause of the following exception:\n",
|
|
"\u001b[0;31mKeyError\u001b[0m Traceback (most recent call last)",
|
|
"\u001b[0;32m<timed exec>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n",
|
|
"\u001b[0;32m<ipython-input-4-9fb2e4a993ea>\u001b[0m in \u001b[0;36mshorten_pickle\u001b[0;34m(l)\u001b[0m\n\u001b[1;32m 12\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 13\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0ma\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mtqdm\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrange\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtemp\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[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 14\u001b[0;31m \u001b[0mtemp_X\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtemp\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0ma\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 15\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 16\u001b[0m \u001b[0mtemp_X\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0ml\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Force'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
|
"\u001b[0;32m/opt/jupyterhub/lib/python3.8/site-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m 3022\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnlevels\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 3023\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_getitem_multilevel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3024\u001b[0;31m \u001b[0mindexer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\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 3025\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mis_integer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mindexer\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[1;32m 3026\u001b[0m \u001b[0mindexer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mindexer\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
|
"\u001b[0;32m/opt/jupyterhub/lib/python3.8/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_loc\u001b[0;34m(self, key, method, tolerance)\u001b[0m\n\u001b[1;32m 3080\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcasted_key\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3081\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3082\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3083\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3084\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mtolerance\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
|
"\u001b[0;31mKeyError\u001b[0m: 0"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"%%time\n",
|
|
"f_data = np.array(list(map(shorten_pickle, x)))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 11,
|
|
"id": "7540198d",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "NameError",
|
|
"evalue": "name 'f_data' is not defined",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
|
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
|
|
"\u001b[0;32m<ipython-input-11-5fc433f33b3d>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mplot\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mf_data\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
|
|
"\u001b[0;31mNameError\u001b[0m: name 'f_data' is not defined"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"plt.plot(f_data)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "7f003da0",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"exit()"
|
|
]
|
|
}
|
|
],
|
|
"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
|
|
}
|