{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# Work, Men, Women"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Data sources:\n",
"\n",
"1. https://stats.oecd.org/index.aspx?queryid=54757\n",
"2. https://stats.oecd.org/Index.aspx?DatasetCode=AVE_HRS"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"\n",
"import matplotlib.pyplot as plt\n",
"from matplotlib.ticker import MaxNLocator"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"GENDER_EMP_12112018223032946.csv\n",
"men_working_time_AVE_HRS_12112018221342527.csv\n",
"women_working_time_AVE_HRS_12112018221357215.csv\n"
]
}
],
"source": [
"%%bash\n",
"ls datasets/work"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"working_time_df = pd.read_csv( 'datasets/work/men_working_time_AVE_HRS_12112018221342527.csv' )\n",
"gender_working_df = pd.read_csv('datasets/work/GENDER_EMP_12112018223032946.csv')"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"men_df = working_time_df[ working_time_df['Sex'] == 'Men' ]\n",
"women_df = working_time_df[ working_time_df['Sex'] == 'Women' ]\n",
"both_df = working_time_df[ working_time_df['Sex'] == 'All persons' ]"
]
},
{
"cell_type": "code",
"execution_count": 136,
"metadata": {},
"outputs": [],
"source": [
"men_time = men_df[ ['Time', 'Value'] ].groupby('Time').mean()\n",
"women_time = women_df[ ['Time', 'Value'] ].groupby('Time').mean()"
]
},
{
"cell_type": "code",
"execution_count": 137,
"metadata": {},
"outputs": [],
"source": [
"men_gender_working_df = gender_working_df[ gender_working_df['Sex'] == 'Men' ][ ['Indicator', 'Time','Value'] ]\n",
"women_gender_working_df = gender_working_df[ gender_working_df['Sex'] == 'Women' ][ ['Indicator', 'Time','Value'] ]"
]
},
{
"cell_type": "code",
"execution_count": 138,
"metadata": {},
"outputs": [],
"source": [
"women_reported = women_gender_working_df.groupby('Indicator').mean()/60"
]
},
{
"cell_type": "code",
"execution_count": 139,
"metadata": {},
"outputs": [],
"source": [
"men_reported = men_gender_working_df.groupby('Indicator').mean()/60"
]
},
{
"cell_type": "code",
"execution_count": 140,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Value | \n",
"
\n",
" \n",
" | Indicator | \n",
" | \n",
"
\n",
" \n",
" \n",
" \n",
" | Time spent in paid work, by sex | \n",
" 3.542957 | \n",
"
\n",
" \n",
" | Time spent in total work, by sex | \n",
" 7.979086 | \n",
"
\n",
" \n",
" | Time spent in unpaid work, by sex | \n",
" 4.436452 | \n",
"
\n",
" \n",
"
\n",
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Value | \n",
"
\n",
" \n",
" | Indicator | \n",
" | \n",
"
\n",
" \n",
" \n",
" \n",
" | Time spent in paid work, by sex | \n",
" 5.30172 | \n",
"
\n",
" \n",
" | Time spent in total work, by sex | \n",
" 7.47672 | \n",
"
\n",
" \n",
" | Time spent in unpaid work, by sex | \n",
" 2.17500 | \n",
"
\n",
" \n",
"
\n",
"