public-projects
/
knuckletouch
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
knuckletouch/python/Step_01_UserData.ipynb

341 lines
7.8 KiB
Plaintext
Raw Permalink Blame History

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"%matplotlib inline\n",
"\n",
"from scipy.odr import *\n",
"from scipy.stats import *\n",
"import numpy as np\n",
"import pandas as pd\n",
"import os\n",
"import time\n",
"import matplotlib.pyplot as plt\n",
"from multiprocessing import Pool"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"def cast_to_int(row):\n",
" try:\n",
" return np.array([a if float(a) >= 0 else 0 for a in row[2:-1]], dtype=np.uint8)\n",
" except Exception as e:\n",
" return None\n",
" \n",
"def load_csv(file):\n",
" temp_df = pd.read_csv(file, header=None, names = [\"UserID\", \"Age\", \"Gender\"], delimiter=\";\")\n",
" return temp_df"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 298 ms, sys: 443 ms, total: 741 ms\n",
"Wall time: 937 ms\n"
]
}
],
"source": [
"%%time\n",
"pool = Pool(os.cpu_count() - 2)\n",
"data_files = [\"DataStudyCollection/%s\" % file for file in os.listdir(\"DataStudyCollection\") if file.endswith(\".csv\") and \"userData\" in file]\n",
"df_lst = pool.map(load_csv, data_files)\n",
"dfAll = pd.concat(df_lst)\n",
"dfAll = dfAll.sort_values(\"UserID\")\n",
"dfAll = dfAll.reset_index(drop=True)\n",
"pool.close()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"24.166666666666668"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dfAll.Age.mean()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"1.4245742398014511"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dfAll.Age.std()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"21"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dfAll.Age.min()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"26"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dfAll.Age.max()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>UserID</th>\n",
" <th>Age</th>\n",
" <th>Gender</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>23</td>\n",
" <td>male</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>24</td>\n",
" <td>male</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>25</td>\n",
" <td>male</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>25</td>\n",
" <td>male</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>26</td>\n",
" <td>male</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>6</td>\n",
" <td>23</td>\n",
" <td>male</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>7</td>\n",
" <td>21</td>\n",
" <td>female</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>8</td>\n",
" <td>24</td>\n",
" <td>male</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>9</td>\n",
" <td>24</td>\n",
" <td>male</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>10</td>\n",
" <td>24</td>\n",
" <td>male</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>11</td>\n",
" <td>25</td>\n",
" <td>female</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>12</td>\n",
" <td>26</td>\n",
" <td>male</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>13</td>\n",
" <td>22</td>\n",
" <td>female</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>14</td>\n",
" <td>24</td>\n",
" <td>male</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>15</td>\n",
" <td>24</td>\n",
" <td>male</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>16</td>\n",
" <td>26</td>\n",
" <td>female</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>17</td>\n",
" <td>26</td>\n",
" <td>male</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>18</td>\n",
" <td>23</td>\n",
" <td>male</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" UserID Age Gender\n",
"0 1 23 male\n",
"1 2 24 male\n",
"2 3 25 male\n",
"3 4 25 male\n",
"4 5 26 male\n",
"5 6 23 male\n",
"6 7 21 female\n",
"7 8 24 male\n",
"8 9 24 male\n",
"9 10 24 male\n",
"10 11 25 female\n",
"11 12 26 male\n",
"12 13 22 female\n",
"13 14 24 male\n",
"14 15 24 male\n",
"15 16 26 female\n",
"16 17 26 male\n",
"17 18 23 male"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dfAll"
]
}
],
"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": "3.7.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Reference in New Issue View Git Blame Copy Permalink