Datasets
Models
Downloads: 1
[d8f241]:
/
Acceleration Features, Train = 10 users Test = 5 users, Random Analysis.ipynb
638 lines (637 with data), 13.9 kB
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# train 1(14=0.01) test 14 (.99)"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 1.18 s, sys: 577 ms, total: 1.76 s\n",
"Wall time: 9.18 s\n"
]
}
],
"source": [
"%%time\n",
"import pandas as pd\n",
"import numpy as np\n",
"from sklearn.ensemble import ExtraTreesClassifier\n",
"from sklearn.metrics import classification_report\n",
"from sklearn.model_selection import train_test_split"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 1min 25s, sys: 13.7 s, total: 1min 38s\n",
"Wall time: 2min 26s\n"
]
}
],
"source": [
"%%time\n",
"df = pd.read_csv(\"master_data.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['target', 'subject', 'chest_ACC_x', 'chest_ACC_y', 'chest_ACC_z',\n",
" 'chest_ECG', 'chest_EMG', 'chest_EDA', 'chest_Temp', 'chest_Resp'],\n",
" dtype='object')"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.columns"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 533 ms, sys: 124 ms, total: 657 ms\n",
"Wall time: 698 ms\n"
]
}
],
"source": [
"%%time\n",
"df=df[['chest_ACC_x','chest_ACC_y','chest_ACC_z','target','subject']]"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 510 ms, sys: 43 µs, total: 510 ms\n",
"Wall time: 508 ms\n"
]
},
{
"data": {
"text/plain": [
"[2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17]"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%time\n",
"df['subject'].unique()\n",
"list_of_subjects=list(df['subject'].unique())\n",
"list_of_subjects.sort()\n",
"list_of_subjects"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 107 µs, sys: 18 µs, total: 125 µs\n",
"Wall time: 129 µs\n"
]
},
{
"data": {
"text/plain": [
"['chest_ACC_x', 'chest_ACC_y', 'chest_ACC_z']"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%%time\n",
"features=df.columns.tolist()\n",
"to_remove = [fea for fea in features if \"target\" in fea or \"subject\" in fea]\n",
"feature = [x for x in features if x not in to_remove]\n",
"feature"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2\n",
"subject_2\n",
"3\n",
"subject_3\n",
"4\n",
"subject_4\n",
"5\n",
"subject_5\n",
"6\n",
"subject_6\n",
"7\n",
"subject_7\n",
"8\n",
"subject_8\n",
"9\n",
"subject_9\n",
"10\n",
"subject_10\n",
"11\n",
"subject_11\n",
"13\n",
"subject_13\n",
"14\n",
"subject_14\n",
"15\n",
"subject_15\n",
"16\n",
"subject_16\n",
"17\n",
"subject_17\n",
"CPU times: user 16.3 s, sys: 2.31 s, total: 18.6 s\n",
"Wall time: 18.7 s\n"
]
}
],
"source": [
"%%time\n",
"for i in list_of_subjects:\n",
" print(i)\n",
" globals()['subject_%s' % i]=df[df['subject'] == i]\n",
" globals()['subject_%s_train' % i],globals()['subject_%s_test' % i]=train_test_split(globals()['subject_%s' % i], test_size=0.3)\n",
" print('subject_'+str(i))"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(4165000, 5)\n",
"(2915500, 5)\n",
"(1249500, 5)\n"
]
}
],
"source": [
"print(subject_2.shape)\n",
"print(subject_2_train.shape)\n",
"print(subject_2_test.shape)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 614 ms, sys: 1.47 s, total: 2.08 s\n",
"Wall time: 2.08 s\n"
]
}
],
"source": [
"%%time\n",
"train=pd.concat([subject_2,subject_3,subject_4,subject_5,subject_6,subject_7,subject_8,subject_9,subject_10,subject_11])\n",
"test=pd.concat([subject_13,subject_14,subject_15,subject_16,subject_17])"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(40143599, 5)\n",
"(18981901, 5)\n"
]
}
],
"source": [
"print(train.shape)\n",
"print(test.shape)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Index 321148792\n",
"chest_ACC_x 321148792\n",
"chest_ACC_y 321148792\n",
"chest_ACC_z 321148792\n",
"target 321148792\n",
"subject 321148792\n",
"dtype: int64\n",
"Index 151855208\n",
"chest_ACC_x 151855208\n",
"chest_ACC_y 151855208\n",
"chest_ACC_z 151855208\n",
"target 151855208\n",
"subject 151855208\n",
"dtype: int64\n"
]
}
],
"source": [
"print(train.memory_usage(index=True, deep=False))\n",
"print(test.memory_usage(index=True, deep=False))"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"Int64Index: 40143599 entries, 26710599 to 8382499\n",
"Data columns (total 5 columns):\n",
"chest_ACC_x float64\n",
"chest_ACC_y float64\n",
"chest_ACC_z float64\n",
"target int64\n",
"subject int64\n",
"dtypes: float64(3), int64(2)\n",
"memory usage: 1.8 GB\n",
"None\n",
"<class 'pandas.core.frame.DataFrame'>\n",
"Int64Index: 18981901 entries, 39094999 to 51311399\n",
"Data columns (total 5 columns):\n",
"chest_ACC_x float64\n",
"chest_ACC_y float64\n",
"chest_ACC_z float64\n",
"target int64\n",
"subject int64\n",
"dtypes: float64(3), int64(2)\n",
"memory usage: 868.9 MB\n",
"None\n"
]
}
],
"source": [
"print(train.info(memory_usage='deep'))\n",
"print(test.info(memory_usage='deep'))"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['chest_ACC_x', 'chest_ACC_y', 'chest_ACC_z']"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"feature"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"features=['chest_ACC_x','chest_ACC_y','chest_ACC_z']\n",
"target=['target']"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['chest_ACC_x', 'chest_ACC_y', 'chest_ACC_z']\n",
"CPU times: user 98 µs, sys: 17 µs, total: 115 µs\n",
"Wall time: 120 µs\n"
]
}
],
"source": [
"%%time\n",
"features=feature\n",
"print(features)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['target']\n",
"CPU times: user 99 µs, sys: 0 ns, total: 99 µs\n",
"Wall time: 103 µs\n"
]
}
],
"source": [
"%%time\n",
"target=['target']\n",
"print(target)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"2\n",
"3\n",
"4\n",
"5\n",
"6\n",
"7\n",
"8\n",
"9\n",
"10\n",
"11\n",
"13\n",
"14\n",
"15\n",
"16\n",
"17\n",
"CPU times: user 870 µs, sys: 127 ms, total: 127 ms\n",
"Wall time: 122 ms\n"
]
}
],
"source": [
"%%time\n",
"for i in list_of_subjects[0:]:\n",
" print(i)\n",
" del(globals()['subject_%s' % i])\n",
" del(globals()['subject_%s_train' % i])\n",
" del(globals()['subject_%s_test' % i])\n",
"del df"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ExtraTreesClassifier\t classification_report\t feature\t features\t i\t list_of_subjects\t np\t pd\t target\t \n",
"test\t to_remove\t train\t train_test_split\t \n"
]
}
],
"source": [
"who"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17]"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"list_of_subjects"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/sf/.local/lib/python3.6/site-packages/ipykernel_launcher.py:2: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().\n",
" \n",
"[Parallel(n_jobs=10)]: Using backend ThreadingBackend with 10 concurrent workers.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"building tree 1 of 50\n",
"building tree 2 of 50\n",
"building tree 3 of 50building tree 4 of 50\n",
"building tree 5 of 50\n",
"building tree 6 of 50\n",
"\n",
"building tree 7 of 50\n",
"building tree 8 of 50\n",
"building tree 9 of 50\n",
"building tree 10 of 50\n"
]
}
],
"source": [
"%%time\n",
"et = ExtraTreesClassifier(n_estimators=50, n_jobs=10, verbose=2)\n",
"et.fit(train[features],train[target])\n",
"y_pred=et.predict(test[features])"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" precision recall f1-score support\n",
"\n",
" 0 0.86 0.87 0.87 8295722\n",
" 1 0.85 0.83 0.84 3698748\n",
" 2 0.74 0.73 0.74 2092335\n",
" 3 0.82 0.80 0.81 1170648\n",
" 4 0.88 0.88 0.88 2480199\n",
"\n",
" accuracy 0.84 17737652\n",
" macro avg 0.83 0.82 0.83 17737652\n",
"weighted avg 0.84 0.84 0.84 17737652\n",
"\n",
"CPU times: user 34.9 s, sys: 6.72 s, total: 41.6 s\n",
"Wall time: 41.6 s\n"
]
}
],
"source": [
"%%time\n",
"print(classification_report(test[target],y_pred ))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"del train\n",
"del test"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"collapsed": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"11\n",
"14\n",
"8\n",
"15\n",
"9\n",
"10\n",
"16\n",
"4\n",
"13\n",
"3\n",
"17\n",
"5\n",
"7\n",
"CPU times: user 19.1 ms, sys: 306 ms, total: 325 ms\n",
"Wall time: 318 ms\n"
]
}
],
"source": []
},
{
"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": "3.6.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}