diff --git a/.gitignore b/.gitignore index ad47670..5a34a36 100644 --- a/.gitignore +++ b/.gitignore @@ -112,3 +112,4 @@ crashlytics-build.properties atusdata/ .direnv/ +categories_to_consider.txt diff --git a/Init_Notebook.ipynb b/Init_Notebook.ipynb new file mode 100644 index 0000000..e456bb8 --- /dev/null +++ b/Init_Notebook.ipynb @@ -0,0 +1,373 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "import re\n", + "import math\n", + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "import matplotlib.pyplot as plt" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "%matplotlib inline" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "summary = pd.read_csv(\"atusdata/atussum_2013.dat\")\n", + "# = pd.read_csv(\"atusdata/atusact_2013.dat\")\n", + "# = pd.read_csv(\"atusdata/atuscps_2013.dat\")\n", + "#respondant = pd.read_csv(\"atusdata/atusresp_2013.dat\")\n", + "# = pd.read_csv(\"atusdata/atusrost_2013.dat\")\n", + "# = pd.read_csv(\"atusdata/atusrostec_2013.dat\")\n", + "# = pd.read_csv(\"atusdata/atussum_2013.dat\")\n", + "# = pd.read_csv(\"atusdata/atuswho_2013.dat\")" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "basic_selection = [\"tucaseid\", \"TUFINLWGT\", \"TRCHILDNUM\", \"TEAGE\", \"TESEX\"]" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "def average_minutes(data, activity_code):\n", + " activity_col = \"t{}\".format(activity_code)\n", + " data = data.rename(columns={\"TUFINLWGT\": \"weight\", activity_col: \"minutes\"})\n", + " data = data[['weight', \"minutes\"]]\n", + " data['weighted_minutes'] = data.weight * data.minutes\n", + " return data.weighted_minutes.sum() / data.weight.sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "def stdev_minutes(data, activity_code):\n", + " data_mean = average_minutes(data, activity_code)\n", + " num_non0_obs = summary[summary.TUFINLWGT != 0].TUFINLWGT.count()\n", + " activity_col = \"t{}\".format(activity_code)\n", + " data = data.rename(columns={\"TUFINLWGT\": \"weight\", activity_col: \"minutes\"})\n", + " data = data[[\"weight\", \"minutes\"]]\n", + " data['weighted_ss'] = data.weight * (data.minutes - data_mean)**2\n", + " return math.sqrt(data.weighted_ss.sum()/(((num_non0_obs-1)/num_non0_obs)*data.weight.sum()))" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "def activity_columns(data, activity_code):\n", + " \"\"\"For the activity code given, return all columns that fall under that activity.\"\"\"\n", + " col_prefix = \"t{}\".format(activity_code)\n", + " return [column for column in data.columns if re.match(col_prefix, column)]" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "def hypothesis_test_plot(data, group_var, test_var):\n", + " data = data[[group_var, test_var, \"TUFINLWGT\"]]\n", + " data_grouped = data.groupby(group_var)\n", + " frame = pd.DataFrame()\n", + " for group in data_grouped:\n", + " count = group[1].TUFINLWGT.count()\n", + " mean = average_minutes(group[1], test_var[1:])\n", + " stdev = stdev_minutes(group[1], test_var[1:])\n", + " frame = frame.append({group_var: group[0], \"mean\": mean, \"error\": (stdev*1.96/math.sqrt(count))}, ignore_index=True)\n", + " frame.index = frame.pop(group_var)\n", + " plot = frame.plot(kind=\"bar\", yerr=\"error\", figsize=(12, 8))\n", + " return (frame, plot)\n", + " " + ] + }, + { + "cell_type": "markdown", + "metadata": { + "collapsed": true + }, + "source": [ + "###Household & personal organization and planning (020302) vs Television and movies (not religious) (120303)" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "current = summary[basic_selection + [\"t020302\", \"t120303\"]]" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "pandas.core.groupby.DataFrameGroupBy" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "current_grouped = current.groupby(\"TESEX\")\n", + "type(current_grouped)" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
meanstdev
TESEX
1178.9327085.079676
2153.8442243.905072
\n", + "
" + ], + "text/plain": [ + " mean stdev\n", + "TESEX \n", + "1 178.932708 5.079676\n", + "2 153.844224 3.905072" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "newframe = pd.DataFrame()\n", + "\n", + "for group in current_grouped:\n", + " count = group[1].TUFINLWGT.count()\n", + " mean = average_minutes(group[1], \"120303\")\n", + " stdev = stdev_minutes(group[1], \"120303\")\n", + " newframe = newframe.append({\"TESEX\": group[0], \"mean\": mean, \"stdev\": (stdev*1.96/math.sqrt(count))}, ignore_index=True)\n", + "newframe.index = newframe.pop(\"TESEX\")\n", + "newframe" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAsEAAAHzCAYAAADB68BPAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "newframe.plot(kind=\"bar\", yerr=\"stdev\", figsize=(12, 8))" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAsEAAAHzCAYAAADB68BPAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "hypothesis_test_plot(summary, \"TESEX\", \"t120303\")[1]" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "collapsed": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAsYAAAH6CAYAAAAEOIr+AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAQCgEowBAKASjAEAoKr/HwoW/tGIEOCLAAAAAElFTkSuQmCC\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "temp_data = summary\n", + "temp_data[\"Decade_Age\"] = temp_data.TEAGE //10 * 10\n", + "hypothesis_test_plot(summary, \"Decade_Age\", \"t120302\")[1]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "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": "3.4.3" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} diff --git a/Starting Point.ipynb b/Starting Point.ipynb deleted file mode 100644 index 2e6fffc..0000000 --- a/Starting Point.ipynb +++ /dev/null @@ -1,1559 +0,0 @@ -{ - "cells": [ - { - "cell_type": "code", - "execution_count": 27, - "metadata": { - "collapsed": false - }, - "outputs": [], - "source": [ - "import pandas as pd\n", - "import re" - ] - }, - { - "cell_type": "code", - "execution_count": 28, - "metadata": { - "collapsed": false - }, - "outputs": [], - "source": [ - "import matplotlib.pyplot as plt" - ] - }, - { - "cell_type": "code", - "execution_count": 29, - "metadata": { - "collapsed": false - }, - "outputs": [], - "source": [ - "%matplotlib inline" - ] - }, - { - "cell_type": "code", - "execution_count": 30, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\n", - "Int64Index: 11385 entries, 0 to 11384\n", - "Columns: 413 entries, tucaseid to t500107\n", - "dtypes: float64(1), int64(412)\n", - "memory usage: 36.0 MB\n" - ] - } - ], - "source": [ - "summary = pd.read_csv(\"atusdata/atussum_2013.dat\")\n", - "summary.info()" - ] - }, - { - "cell_type": "code", - "execution_count": 31, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "data": { - "text/plain": [ - "Index(['tucaseid', 'TUFINLWGT', 'TRYHHCHILD', 'TEAGE', 'TESEX', 'PEEDUCA',\n", - " 'PTDTRACE', 'PEHSPNON', 'GTMETSTA', 'TELFS', \n", - " ...\n", - " 't181501', 't181599', 't181601', 't181801', 't189999', 't500101',\n", - " 't500103', 't500105', 't500106', 't500107'],\n", - " dtype='object', length=413)" - ] - }, - "execution_count": 31, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "summary.columns" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Pertinent columns:\n", - "\n", - "* TUFINLWGT - statistical weight of respondent\n", - "* TRYHHCHILD - age of youngest child in household\n", - "* TEAGE - age of respondent\n", - "* TESEX - sex of respondent\n", - "* TELFS - working status of respondent\n", - "* TRCHILDNUM - number of children in household" - ] - }, - { - "cell_type": "code", - "execution_count": 32, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
tucaseidTUFINLWGTTRYHHCHILDTEAGETESEXPEEDUCAPTDTRACEPEHSPNONGTMETSTATELFS...t181501t181599t181601t181801t189999t500101t500103t500105t500106t500107
02013010113000411899905.66203412222408215...0000000000
1201301011301124447638.0095131391431211...0000000000
22013010113012310377056.507734-1472401214...25000000000
3201301011306117731257.992805-1502401111...0000000000
4201301011306164725269.227067-1452402211...0000000000
\n", - "

5 rows × 413 columns

\n", - "
" - ], - "text/plain": [ - " tucaseid TUFINLWGT TRYHHCHILD TEAGE TESEX PEEDUCA \\\n", - "0 20130101130004 11899905.662034 12 22 2 40 \n", - "1 20130101130112 4447638.009513 1 39 1 43 \n", - "2 20130101130123 10377056.507734 -1 47 2 40 \n", - "3 20130101130611 7731257.992805 -1 50 2 40 \n", - "4 20130101130616 4725269.227067 -1 45 2 40 \n", - "\n", - " PTDTRACE PEHSPNON GTMETSTA TELFS ... t181501 t181599 t181601 \\\n", - "0 8 2 1 5 ... 0 0 0 \n", - "1 1 2 1 1 ... 0 0 0 \n", - "2 1 2 1 4 ... 25 0 0 \n", - "3 1 1 1 1 ... 0 0 0 \n", - "4 2 2 1 1 ... 0 0 0 \n", - "\n", - " t181801 t189999 t500101 t500103 t500105 t500106 t500107 \n", - "0 0 0 0 0 0 0 0 \n", - "1 0 0 0 0 0 0 0 \n", - "2 0 0 0 0 0 0 0 \n", - "3 0 0 0 0 0 0 0 \n", - "4 0 0 0 0 0 0 0 \n", - "\n", - "[5 rows x 413 columns]" - ] - }, - "execution_count": 32, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "summary.head()" - ] - }, - { - "cell_type": "code", - "execution_count": 33, - "metadata": { - "collapsed": false - }, - "outputs": [], - "source": [ - "adults_crit = summary.TEAGE >= 18\n", - "no_children_crit = summary.TRCHILDNUM == 0" - ] - }, - { - "cell_type": "code", - "execution_count": 34, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\n", - "Int64Index: 10953 entries, 0 to 11384\n", - "Columns: 413 entries, tucaseid to t500107\n", - "dtypes: float64(1), int64(412)\n", - "memory usage: 34.6 MB\n" - ] - } - ], - "source": [ - "adults = summary[adults_crit]\n", - "adults.info()" - ] - }, - { - "cell_type": "code", - "execution_count": 35, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\n", - "Int64Index: 6481 entries, 2 to 11381\n", - "Columns: 413 entries, tucaseid to t500107\n", - "dtypes: float64(1), int64(412)\n", - "memory usage: 20.5 MB\n" - ] - } - ], - "source": [ - "people_with_no_children = summary[no_children_crit]\n", - "people_with_no_children.info()" - ] - }, - { - "cell_type": "code", - "execution_count": 36, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\n", - "Int64Index: 6481 entries, 2 to 11381\n", - "Columns: 413 entries, tucaseid to t500107\n", - "dtypes: float64(1), int64(412)\n", - "memory usage: 20.5 MB\n" - ] - } - ], - "source": [ - "adults_with_no_children = summary[adults_crit & no_children_crit]\n", - "adults_with_no_children.info()" - ] - }, - { - "cell_type": "code", - "execution_count": 37, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
weightminutes
210377056.50773460
37731257.99280565
44725269.22706790
52372791.046351270
65671341.270490244
\n", - "
" - ], - "text/plain": [ - " weight minutes\n", - "2 10377056.507734 60\n", - "3 7731257.992805 65\n", - "4 4725269.227067 90\n", - "5 2372791.046351 270\n", - "6 5671341.270490 244" - ] - }, - "execution_count": 37, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "data = adults_with_no_children[['TUFINLWGT', 't120303']]\n", - "data = data.rename(columns={\"TUFINLWGT\": \"weight\", \"t120303\": \"minutes\"})\n", - "data.head()" - ] - }, - { - "cell_type": "code", - "execution_count": 38, - "metadata": { - "collapsed": false - }, - "outputs": [], - "source": [ - "data['weighted_minutes'] = data.weight * data.minutes" - ] - }, - { - "cell_type": "code", - "execution_count": 39, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
weightminutesweighted_minutes
210377056.507734606.226234e+08
37731257.992805655.025318e+08
44725269.227067904.252742e+08
52372791.0463512706.406536e+08
65671341.2704902441.383807e+09
\n", - "
" - ], - "text/plain": [ - " weight minutes weighted_minutes\n", - "2 10377056.507734 60 6.226234e+08\n", - "3 7731257.992805 65 5.025318e+08\n", - "4 4725269.227067 90 4.252742e+08\n", - "5 2372791.046351 270 6.406536e+08\n", - "6 5671341.270490 244 1.383807e+09" - ] - }, - "execution_count": 39, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "data.head()" - ] - }, - { - "cell_type": "code", - "execution_count": 40, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "data": { - "text/plain": [ - "211.67427866070051" - ] - }, - "execution_count": 40, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# Minutes on average spent watching TV (unweighted) - DO NOT USE\n", - "data.minutes.sum() / len(data)" - ] - }, - { - "cell_type": "code", - "execution_count": 41, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "data": { - "text/plain": [ - "190.25402840855642" - ] - }, - "execution_count": 41, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# Minutes on average spent watching TV (weighted)\n", - "data.weighted_minutes.sum() / data.weight.sum()" - ] - }, - { - "cell_type": "code", - "execution_count": 42, - "metadata": { - "collapsed": false - }, - "outputs": [], - "source": [ - "def average_minutes(data, activity_code):\n", - " activity_col = \"t{}\".format(activity_code)\n", - " data = data[['TUFINLWGT', activity_col]]\n", - " data = data.rename(columns={\"TUFINLWGT\": \"weight\", activity_col: \"minutes\"})\n", - " data['weighted_minutes'] = data.weight * data.minutes\n", - " return data.weighted_minutes.sum() / data.weight.sum()" - ] - }, - { - "cell_type": "code", - "execution_count": 43, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "data": { - "text/plain": [ - "8.7508537061809992" - ] - }, - "execution_count": 43, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "sleeping = average_minutes(adults_with_no_children, \"010101\")\n", - "sleepless = average_minutes(adults_with_no_children, \"010102\")\n", - "(sleeping + sleepless) / 60 # hours" - ] - }, - { - "cell_type": "code", - "execution_count": 44, - "metadata": { - "collapsed": false - }, - "outputs": [], - "source": [ - "def activity_columns(data, activity_code):\n", - " \"\"\"For the activity code given, return all columns that fall under that activity.\"\"\"\n", - " col_prefix = \"t{}\".format(activity_code)\n", - " return [column for column in data.columns if re.match(col_prefix, column)]" - ] - }, - { - "cell_type": "code", - "execution_count": 45, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "data": { - "text/plain": [ - "['t010101', 't010102']" - ] - }, - "execution_count": 45, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "activity_columns(summary, \"0101\")" - ] - }, - { - "cell_type": "code", - "execution_count": 46, - "metadata": { - "collapsed": false - }, - "outputs": [], - "source": [ - "def average_minutes2(data, activity_code):\n", - " cols = activity_columns(data, activity_code)\n", - " activity_data = data[cols]\n", - " activity_sums = activity_data.sum(axis=1)\n", - " data = data[['TUFINLWGT']]\n", - " data['minutes'] = activity_sums\n", - " data = data.rename(columns={\"TUFINLWGT\": \"weight\"})\n", - " data['weighted_minutes'] = data.weight * data.minutes\n", - " return data.weighted_minutes.sum() / data.weight.sum()" - ] - }, - { - "cell_type": "code", - "execution_count": 47, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/Users/clinton/src/github.com/tiyd-python-2015-05/atus-analysis/.direnv/python-3.4.3/lib/python3.4/site-packages/IPython/kernel/__main__.py:6: SettingWithCopyWarning: \n", - "A value is trying to be set on a copy of a slice from a DataFrame.\n", - "Try using .loc[row_indexer,col_indexer] = value instead\n", - "\n", - "See the the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n" - ] - }, - { - "data": { - "text/plain": [ - "8.750853706181001" - ] - }, - "execution_count": 47, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "average_minutes2(adults_with_no_children, \"0101\") / 60" - ] - }, - { - "cell_type": "code", - "execution_count": 48, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/Users/clinton/src/github.com/tiyd-python-2015-05/atus-analysis/.direnv/python-3.4.3/lib/python3.4/site-packages/IPython/kernel/__main__.py:6: SettingWithCopyWarning: \n", - "A value is trying to be set on a copy of a slice from a DataFrame.\n", - "Try using .loc[row_indexer,col_indexer] = value instead\n", - "\n", - "See the the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n" - ] - }, - { - "data": { - "text/plain": [ - "9.5541911543273592" - ] - }, - "execution_count": 48, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "average_minutes2(adults_with_no_children, \"01\") / 60" - ] - }, - { - "cell_type": "code", - "execution_count": 49, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Help on method groupby in module pandas.core.generic:\n", - "\n", - "groupby(by=None, axis=0, level=None, as_index=True, sort=True, group_keys=True, squeeze=False) method of pandas.core.frame.DataFrame instance\n", - " Group series using mapper (dict or key function, apply given function\n", - " to group, return result as series) or by a series of columns\n", - " \n", - " Parameters\n", - " ----------\n", - " by : mapping function / list of functions, dict, Series, or tuple /\n", - " list of column names.\n", - " Called on each element of the object index to determine the groups.\n", - " If a dict or Series is passed, the Series or dict VALUES will be\n", - " used to determine the groups\n", - " axis : int, default 0\n", - " level : int, level name, or sequence of such, default None\n", - " If the axis is a MultiIndex (hierarchical), group by a particular\n", - " level or levels\n", - " as_index : boolean, default True\n", - " For aggregated output, return object with group labels as the\n", - " index. Only relevant for DataFrame input. as_index=False is\n", - " effectively \"SQL-style\" grouped output\n", - " sort : boolean, default True\n", - " Sort group keys. Get better performance by turning this off\n", - " group_keys : boolean, default True\n", - " When calling apply, add group keys to index to identify pieces\n", - " squeeze : boolean, default False\n", - " reduce the dimensionaility of the return type if possible,\n", - " otherwise return a consistent type\n", - " \n", - " Examples\n", - " --------\n", - " DataFrame results\n", - " \n", - " >>> data.groupby(func, axis=0).mean()\n", - " >>> data.groupby(['col1', 'col2'])['col3'].mean()\n", - " \n", - " DataFrame with hierarchical index\n", - " \n", - " >>> data.groupby(['col1', 'col2']).mean()\n", - " \n", - " Returns\n", - " -------\n", - " GroupBy object\n", - "\n" - ] - } - ], - "source": [ - "# grouping\n", - "help(adults_with_no_children.groupby)" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Joining files" - ] - }, - { - "cell_type": "code", - "execution_count": 53, - "metadata": { - "collapsed": false - }, - "outputs": [], - "source": [ - "respondents = pd.read_csv(\"atusdata/atusresp_2013/atusresp_2013.dat\")\n", - "activities = pd.read_csv(\"atusdata/atusact_2013/atusact_2013.dat\")" - ] - }, - { - "cell_type": "code", - "execution_count": 54, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\n", - "Int64Index: 11385 entries, 0 to 11384\n", - "Columns: 175 entries, TUCASEID to TXTONHH\n", - "dtypes: float64(1), int64(172), object(2)\n", - "memory usage: 15.3+ MB\n" - ] - } - ], - "source": [ - "respondents.info()" - ] - }, - { - "cell_type": "code", - "execution_count": 55, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\n", - "Int64Index: 215576 entries, 0 to 215575\n", - "Data columns (total 31 columns):\n", - "TUCASEID 215576 non-null int64\n", - "TUACTIVITY_N 215576 non-null int64\n", - "TEWHERE 215576 non-null int64\n", - "TRTCCTOT_LN 215576 non-null int64\n", - "TRTCC_LN 215576 non-null int64\n", - "TRTCOC_LN 215576 non-null int64\n", - "TRTEC_LN 215576 non-null int64\n", - "TRTHH_LN 215576 non-null int64\n", - "TRTNOHH_LN 215576 non-null int64\n", - "TRTOHH_LN 215576 non-null int64\n", - "TRTONHH_LN 215576 non-null int64\n", - "TRTO_LN 215576 non-null int64\n", - "TRWBELIG 215576 non-null int64\n", - "TUACTDUR 215576 non-null int64\n", - "TUACTDUR24 215576 non-null int64\n", - "TUCC5 215576 non-null int64\n", - "TUCC5B 215576 non-null int64\n", - "TUCC7 215576 non-null int64\n", - "TUCC8 215576 non-null int64\n", - "TUCUMDUR 215576 non-null int64\n", - "TUCUMDUR24 215576 non-null int64\n", - "TUDURSTOP 215576 non-null int64\n", - "TUEC24 215576 non-null int64\n", - "TUSTARTTIM 215576 non-null object\n", - "TUSTOPTIME 215576 non-null object\n", - "TUTIER1CODE 215576 non-null int64\n", - "TUTIER2CODE 215576 non-null int64\n", - "TUTIER3CODE 215576 non-null int64\n", - "TRCODE 215576 non-null int64\n", - "TRTIER2 215576 non-null int64\n", - "TXWHERE 215576 non-null int64\n", - "dtypes: int64(29), object(2)\n", - "memory usage: 52.6+ MB\n" - ] - } - ], - "source": [ - "activities.info()" - ] - }, - { - "cell_type": "code", - "execution_count": 56, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
TUCASEIDTULINENOTUYEARTUMONTHTEABSRSNTEERNTEERNH1OTEERNH2TEERNHROTEERNHRY...TXSPEMPNOTTXSPUHRSTXTCCTXTCCTOTTXTCOCTXTHHTXTNOHHTXTOTXTOHHTXTONHH
020130101130004120131-1-1-1-1-1-1...-1-100000-1-1-1
120130101130112120131-1-1-1-1-12...000000-100-1
220130101130123120131-1-1-1-1-1-1...00-100-1-1-1-1-1
320130101130611120131-1-1-1-1-12...-1-1-100-1-1-1-1-1
420130101130616120131-1-1-1-1-12...-1-1-100-1-1-1-1-1
\n", - "

5 rows × 175 columns

\n", - "
" - ], - "text/plain": [ - " TUCASEID TULINENO TUYEAR TUMONTH TEABSRSN TEERN TEERNH1O \\\n", - "0 20130101130004 1 2013 1 -1 -1 -1 \n", - "1 20130101130112 1 2013 1 -1 -1 -1 \n", - "2 20130101130123 1 2013 1 -1 -1 -1 \n", - "3 20130101130611 1 2013 1 -1 -1 -1 \n", - "4 20130101130616 1 2013 1 -1 -1 -1 \n", - "\n", - " TEERNH2 TEERNHRO TEERNHRY ... TXSPEMPNOT TXSPUHRS TXTCC \\\n", - "0 -1 -1 -1 ... -1 -1 0 \n", - "1 -1 -1 2 ... 0 0 0 \n", - "2 -1 -1 -1 ... 0 0 -1 \n", - "3 -1 -1 2 ... -1 -1 -1 \n", - "4 -1 -1 2 ... -1 -1 -1 \n", - "\n", - " TXTCCTOT TXTCOC TXTHH TXTNOHH TXTO TXTOHH TXTONHH \n", - "0 0 0 0 0 -1 -1 -1 \n", - "1 0 0 0 -1 0 0 -1 \n", - "2 0 0 -1 -1 -1 -1 -1 \n", - "3 0 0 -1 -1 -1 -1 -1 \n", - "4 0 0 -1 -1 -1 -1 -1 \n", - "\n", - "[5 rows x 175 columns]" - ] - }, - "execution_count": 56, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "respondents.head()" - ] - }, - { - "cell_type": "code", - "execution_count": 57, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
TUCASEIDTUACTIVITY_NTEWHERETRTCCTOT_LNTRTCC_LNTRTCOC_LNTRTEC_LNTRTHH_LNTRTNOHH_LNTRTOHH_LN...TUDURSTOPTUEC24TUSTARTTIMTUSTOPTIMETUTIER1CODETUTIER2CODETUTIER3CODETRCODETRTIER2TXWHERE
0201301011300041-1000-100-1...2-104:00:0012:00:00111101011010
12013010113000421550-155-1...1-112:00:0012:05:00111111010111010
220130101130004311201200-1120120-1...1-112:05:0014:05:00123312030312030
32013010113000441000-100-1...2-114:05:0019:00:00631603016030
4201301011300045130300-13030-1...1-119:00:0019:30:00111111010111010
\n", - "

5 rows × 31 columns

\n", - "
" - ], - "text/plain": [ - " TUCASEID TUACTIVITY_N TEWHERE TRTCCTOT_LN TRTCC_LN TRTCOC_LN \\\n", - "0 20130101130004 1 -1 0 0 0 \n", - "1 20130101130004 2 1 5 5 0 \n", - "2 20130101130004 3 1 120 120 0 \n", - "3 20130101130004 4 1 0 0 0 \n", - "4 20130101130004 5 1 30 30 0 \n", - "\n", - " TRTEC_LN TRTHH_LN TRTNOHH_LN TRTOHH_LN ... TUDURSTOP TUEC24 \\\n", - "0 -1 0 0 -1 ... 2 -1 \n", - "1 -1 5 5 -1 ... 1 -1 \n", - "2 -1 120 120 -1 ... 1 -1 \n", - "3 -1 0 0 -1 ... 2 -1 \n", - "4 -1 30 30 -1 ... 1 -1 \n", - "\n", - " TUSTARTTIM TUSTOPTIME TUTIER1CODE TUTIER2CODE TUTIER3CODE TRCODE \\\n", - "0 04:00:00 12:00:00 1 1 1 10101 \n", - "1 12:00:00 12:05:00 11 1 1 110101 \n", - "2 12:05:00 14:05:00 12 3 3 120303 \n", - "3 14:05:00 19:00:00 6 3 1 60301 \n", - "4 19:00:00 19:30:00 11 1 1 110101 \n", - "\n", - " TRTIER2 TXWHERE \n", - "0 101 0 \n", - "1 1101 0 \n", - "2 1203 0 \n", - "3 603 0 \n", - "4 1101 0 \n", - "\n", - "[5 rows x 31 columns]" - ] - }, - "execution_count": 57, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "activities.head()" - ] - }, - { - "cell_type": "code", - "execution_count": 58, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\n", - "Int64Index: 215576 entries, 0 to 215575\n", - "Columns: 205 entries, TUCASEID to TXWHERE\n", - "dtypes: float64(1), int64(200), object(4)\n", - "memory usage: 338.8+ MB\n" - ] - } - ], - "source": [ - "merged = pd.merge(respondents, activities, left_on=\"TUCASEID\", right_on=\"TUCASEID\")\n", - "merged.info()" - ] - }, - { - "cell_type": "code", - "execution_count": 59, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
TUCASEIDTUACTIVITY_NTXTCOC
02013010113000410
12013010113000420
22013010113000430
32013010113000440
42013010113000450
\n", - "
" - ], - "text/plain": [ - " TUCASEID TUACTIVITY_N TXTCOC\n", - "0 20130101130004 1 0\n", - "1 20130101130004 2 0\n", - "2 20130101130004 3 0\n", - "3 20130101130004 4 0\n", - "4 20130101130004 5 0" - ] - }, - "execution_count": 59, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "merged[[\"TUCASEID\", \"TUACTIVITY_N\", \"TXTCOC\"]].head()" - ] - }, - { - "cell_type": "code", - "execution_count": 60, - "metadata": { - "collapsed": false - }, - "outputs": [], - "source": [ - "telfs = pd.Series({1: \"Employed - at work\",\n", - " 2: \"Employed - absent\",\n", - " 3: \"Unemployed - laid off\",\n", - " 4: \"Unemployed - looking\",\n", - " 5: \"Not in labor force\"})" - ] - }, - { - "cell_type": "code", - "execution_count": 61, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "data": { - "text/plain": [ - "1 Employed - at work\n", - "2 Employed - absent\n", - "3 Unemployed - laid off\n", - "4 Unemployed - looking\n", - "5 Not in labor force\n", - "dtype: object" - ] - }, - "execution_count": 61, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "telfs" - ] - }, - { - "cell_type": "code", - "execution_count": 63, - "metadata": { - "collapsed": false - }, - "outputs": [ - { - "data": { - "text/plain": [ - "0 Not in labor force\n", - "1 Employed - at work\n", - "2 Unemployed - looking\n", - "3 Employed - at work\n", - "4 Employed - at work\n", - "5 Not in labor force\n", - "6 Not in labor force\n", - "7 Employed - at work\n", - "8 Employed - at work\n", - "9 Employed - at work\n", - "10 Employed - at work\n", - "11 Employed - at work\n", - "12 Employed - at work\n", - "13 Employed - at work\n", - "14 Not in labor force\n", - "15 Not in labor force\n", - "16 Employed - at work\n", - "17 Employed - absent\n", - "18 Employed - at work\n", - "19 Unemployed - looking\n", - "20 Unemployed - looking\n", - "21 Employed - at work\n", - "22 Employed - at work\n", - "23 Not in labor force\n", - "24 Employed - at work\n", - "25 Employed - at work\n", - "26 Not in labor force\n", - "27 Not in labor force\n", - "28 Unemployed - looking\n", - "29 Employed - at work\n", - " ... \n", - "11355 Employed - absent\n", - "11356 Employed - at work\n", - "11357 Not in labor force\n", - "11358 Employed - at work\n", - "11359 Employed - at work\n", - "11360 Employed - at work\n", - "11361 Employed - at work\n", - "11362 Employed - at work\n", - "11363 Not in labor force\n", - "11364 Not in labor force\n", - "11365 Employed - at work\n", - "11366 Not in labor force\n", - "11367 Employed - at work\n", - "11368 Employed - at work\n", - "11369 Not in labor force\n", - "11370 Employed - at work\n", - "11371 Employed - at work\n", - "11372 Employed - at work\n", - "11373 Not in labor force\n", - "11374 Employed - at work\n", - "11375 Employed - at work\n", - "11376 Employed - at work\n", - "11377 Employed - at work\n", - "11378 Not in labor force\n", - "11379 Employed - at work\n", - "11380 Not in labor force\n", - "11381 Employed - at work\n", - "11382 Employed - at work\n", - "11383 Employed - at work\n", - "11384 Not in labor force\n", - "Name: TELFS, dtype: object" - ] - }, - "execution_count": 63, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "summary.TELFS.map(telfs)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "collapsed": true - }, - "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": "3.4.3" - } - }, - "nbformat": 4, - "nbformat_minor": 0 -}