API tools faq
paste
Advertisement
Guest User

Untitled

a guest
Jun 24th, 2019
88
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 11.30 KB | None | 0 0
raw download clone embed print report
  1. {
  2. "cells": [
  3. {
  4. "metadata": {},
  5. "cell_type": "markdown",
  6. "source": "## Structure WB data to HuruMap"
  7. },
  8. {
  9. "metadata": {
  10. "trusted": true
  11. },
  12. "cell_type": "code",
  13. "source": "import pandas as pd",
  14. "execution_count": 1,
  15. "outputs": []
  16. },
  17. {
  18. "metadata": {
  19. "scrolled": true
  20. },
  21. "cell_type": "markdown",
  22. "source": "# Load the WB data and takwimu indicators "
  23. },
  24. {
  25. "metadata": {
  26. "trusted": true
  27. },
  28. "cell_type": "code",
  29. "source": "# generate a dict from the indicators file\ntakwimu_indicators = pd.read_csv('../data/takwimu_indicators.csv',\n index_col=0, squeeze=True).to_dict()\n# Gather indicator data on the selected country\n\n# # Kenya\n# data = pd.read_csv('../data/Kenya/WB_KEN.csv')\n# structured = '../huru/ke/ke_'\n# country_code = 'KE'\n\n# Ethiopia\ndata = pd.read_csv('../data/Ethiopia/WB_ET.csv')\nstructured = '../huru/et/et_'\ncountry_code = 'ET'\n\n",
  30. "execution_count": 48,
  31. "outputs": []
  32. },
  33. {
  34. "metadata": {},
  35. "cell_type": "markdown",
  36. "source": "### Wrangle by Indicator"
  37. },
  38. {
  39. "metadata": {
  40. "trusted": true
  41. },
  42. "cell_type": "code",
  43. "source": "# population total\ndef population_total():\n \n i_code = ['SP.POP.TOTL.FE.IN','SP.POP.TOTL.MA.IN']\n\n df = data.loc[data['I_code'].isin(i_code)].drop(['I_code'],axis=1).T.reset_index()\n df.columns = df.iloc[0]\n df = df[1:]\n df = df.rename(columns={\"Indicator\": 'geo_version' , \"Population, male\": 'male',\"Population, female\":'female' })\n df['geo_code'] = country_code\n\n df = df.melt(id_vars=['geo_code','geo_version'], value_vars=['female','male'],\n var_name='sex', value_name='total')\n population = df.set_index(['geo_code','geo_version']).sort_index() \n \n return population\n\n# Prevalence of HIV,(% ages 15-24)\n\ndef hiv_prevalence():\n i_code = ['SH.HIV.1524.MA.ZS','SH.HIV.1524.FE.ZS']\n \n df = data.loc[data['I_code'].isin(i_code)].drop(['I_code'],axis=1).T.reset_index()\n df.columns = df.iloc[0]\n df = df[1:]\n df = df.rename(columns={\"Indicator\": 'geo_version' , \"Prevalence of HIV, male (% ages 15-24)\": 'male',\n \"Prevalence of HIV, female (% ages 15-24)\":'female' })\n df['geo_code'] = country_code\n\n df = df.melt(id_vars=['geo_code','geo_version'], value_vars=['female','male'],\n var_name='sex', value_name='total')\n prevalence = df.set_index(['geo_code','geo_version']).sort_index() \n \n return prevalence\n \n# Infant and Under 5 Mortality Rate \n\ndef infant_under_5_mortality():\n \n i_code = ['SP.DYN.IMRT.IN','SH.DYN.MORT']\n \n df = data.loc[data['I_code'].isin(i_code)].drop(['I_code'],axis=1).T.reset_index()\n df.columns = df.iloc[0]\n df = df[1:]\n df = df.rename(columns={\"Indicator\": 'geo_version' , \"Mortality rate, infant (per 1,000 live births)\": 'infant',\n \"Mortality rate, under-5 (per 1,000 live births)\":'under_5' })\n df['geo_code'] = country_code\n\n df = df.melt(id_vars=['geo_code','geo_version'], value_vars=['infant','under_5'],\n var_name='mortality', value_name='total')\n infant_under_5 = df.set_index(['geo_code','geo_version']).sort_index() \n \n return infant_under_5\n\n# Adult Literacy rate\n\ndef adult_literacy_rate():\n \n i_code = ['SE.ADT.LITR.FE.ZS','SE.ADT.LITR.MA.ZS']\n \n df = data.loc[data['I_code'].isin(i_code)].drop(['I_code'],axis=1).T.reset_index()\n df.columns = df.iloc[0]\n df = df[1:]\n df = df.rename(columns={\"Indicator\": 'geo_version' , \"Literacy rate, adult male (% of males ages 15 and above)\": 'male',\n \"Literacy rate, adult female (% of females ages 15 and above)\":'female' })\n df['geo_code'] = country_code\n\n df = df.melt(id_vars=['geo_code','geo_version'], value_vars=['female','male'],\n var_name='sex', value_name='total')\n literacy_rate = df.set_index(['geo_code','geo_version']).sort_index() \n \n return literacy_rate\n\n# Employment in agriculture, (% of employment) (modeled ILO estimate)\n\ndef agr_employment():\n \n i_code = ['SL.AGR.EMPL.FE.ZS','SL.AGR.EMPL.MA.ZS']\n\n df = data.loc[data['I_code'].isin(i_code)].drop(['I_code'],axis=1).T.reset_index()\n df.columns = df.iloc[0]\n df = df[1:]\n df = df.rename(columns={\"Indicator\": 'geo_version' , \"Employment in agriculture, female (% of female employment) (modeled ILO estimate)\": 'female',\n \"Employment in agriculture, male (% of male employment) (modeled ILO estimate)\":'male' })\n df['geo_code'] = country_code\n\n df = df.melt(id_vars=['geo_code','geo_version'], value_vars=['female','male'],\n var_name='sex', value_name='total')\n agr_employment = df.set_index(['geo_code','geo_version']).sort_index() \n \n return agr_employment\n\n\n# School enrollment, primary,\n\n\ndef primary_ed_enrollment():\n \n i_code = ['SE.PRM.ENRR.MA','SE.PRM.ENRR.FE']\n \n df = data.loc[data['I_code'].isin(i_code)].drop(['I_code'],axis=1).T.reset_index()\n df.columns = df.iloc[0]\n df = df[1:]\n df = df.rename(columns={\"Indicator\": 'geo_version' , \"School enrollment, primary, male (% gross)\": 'male',\n \"School enrollment, primary, female (% gross)\":'female' })\n df['geo_code'] = country_code\n\n df = df.melt(id_vars=['geo_code','geo_version'], value_vars=['female','male'],\n var_name='sex', value_name='total')\n primary_enrollment = df.set_index(['geo_code','geo_version']).sort_index() \n \n return primary_enrollment\n\n# School enrollment, Secondary,\n\n\ndef secondary_ed_enrollment():\n \n i_code = ['SE.SEC.ENRR.FE','SE.SEC.ENRR.MA']\n \n df = data.loc[data['I_code'].isin(i_code)].drop(['I_code'],axis=1).T.reset_index()\n df.columns = df.iloc[0]\n df = df[1:]\n df = df.rename(columns={\"Indicator\": 'geo_version' , \"School enrollment, secondary, male (% gross)\": 'male',\n \"School enrollment, secondary, female (% gross)\":'female' })\n df['geo_code'] = country_code\n\n df = df.melt(id_vars=['geo_code','geo_version'], value_vars=['female','male'],\n var_name='sex', value_name='total')\n secondary_enrollment = df.set_index(['geo_code','geo_version']).sort_index() \n \n return secondary_enrollment\n\n# Mobile cellular subscriptions (per 100 people),\n\n\ndef cellular_subcription():\n \n i_code = ['IT.CEL.SETS.P2']\n df = data.loc[data['I_code'].isin(i_code)].drop(['I_code'],axis=1).T.reset_index()\n df.columns = df.iloc[0]\n df = df[1:]\n df = df.rename(columns={\"Indicator\": 'geo_version' , \"Mobile cellular subscriptions (per 100 people)\": 'total'})\n df['geo_code'] = country_code\n cellular_subcription = df.set_index(['geo_code','geo_version']).sort_index() \n \n return cellular_subcription\n\n# Life expectancy at birth,(years)\n\ndef life_expectancy():\n \n i_code = ['SP.DYN.LE00.FE.IN','SP.DYN.LE00.MA.IN']\n \n df = data.loc[data['I_code'].isin(i_code)].drop(['I_code'],axis=1).T.reset_index()\n df.columns = df.iloc[0]\n df = df[1:]\n df = df.rename(columns={\"Indicator\": 'geo_version' , \"Life expectancy at birth, male (years)\": 'male',\n \"Life expectancy at birth, female (years)\":'female' })\n df['geo_code'] = country_code\n\n df = df.melt(id_vars=['geo_code','geo_version'], value_vars=['female','male'],\n var_name='sex', value_name='total')\n life_expectancy = df.set_index(['geo_code','geo_version']).sort_index() \n \n return life_expectancy\n\n# Women in national parliaments (%)\n\ndef women_in_parliament():\n \n i_code = ['SG.GEN.PARL.ZS']\n df = data.loc[data['I_code'].isin(i_code)].drop(['I_code'],axis=1).T.reset_index()\n df.columns = df.iloc[0]\n df = df[1:]\n df = df.rename(columns={\"Indicator\": 'geo_version' , \"Proportion of seats held by women in national parliaments (%)\": 'total'})\n df['geo_code'] = country_code\n\n women_in_parliament = df.set_index(['geo_code','geo_version']).sort_index() \n \n return women_in_parliament\n\n# Maternal mortality ratio (modeled estimate, per 100,000 live births)\n\ndef maternal_mortality():\n \n i_code = ['SH.STA.MMRT']\n df = data.loc[data['I_code'].isin(i_code)].drop(['I_code'],axis=1).T.reset_index()\n df.columns = df.iloc[0]\n df = df[1:]\n df = df.rename(columns={\"Indicator\": 'geo_version' , \"Maternal mortality ratio (modeled estimate, per 100,000 live births)\": 'total'})\n df['geo_code'] = country_code\n\n maternal_mortality = df.set_index(['geo_code','geo_version']).sort_index() \n \n return maternal_mortality\n\n# Medical Staff - Physicians, Nurses and Midwives (per 1,000 people)\n\ndef physicians_nurses():\n \n i_code = ['SH.MED.PHYS.ZS','SH.MED.NUMW.P3']\n\n df = data.loc[data['I_code'].isin(i_code)].drop(['I_code'],axis=1).T.reset_index()\n df.columns = df.iloc[0]\n df = df[1:]\n df = df.rename(columns={\"Indicator\": 'geo_version' , \"Physicians (per 1,000 people)\": 'physicians',\n \"Nurses and midwives (per 1,000 people)\":'nurses_midwives' })\n df['geo_code'] = country_code\n\n df = df.melt(id_vars=['geo_code','geo_version'], value_vars=['nurses_midwives','physicians'],\n var_name='medical_staff', value_name='total')\n physicians_nurses = df.set_index(['geo_code','geo_version']).sort_index()\n \n return physicians_nurses\n\n\n\n",
  44. "execution_count": 49,
  45. "outputs": []
  46. },
  47. {
  48. "metadata": {
  49. "trusted": true
  50. },
  51. "cell_type": "code",
  52. "source": "# Save to location\n\ndef save_to_location():\n population_total().to_csv(structured +'population.csv')\n hiv_prevalence().to_csv(structured +'hiv_prevalence.csv')\n infant_under_5_mortality().to_csv(structured +'infant_under_5_mortality.csv')\n adult_literacy_rate().to_csv(structured +'adult_literacy_rate.csv')\n agr_employment().to_csv(structured +'agr_employment.csv')\n primary_ed_enrollment().to_csv(structured +'primary_enrollment.csv')\n secondary_ed_enrollment().to_csv(structured +'secondary_enrollment.csv')\n cellular_subcription().to_csv(structured + 'cellular subscriptions_per_100.csv')\n life_expectancy().to_csv(structured + 'life_expectancy.csv')\n women_in_parliament().to_csv(structured + 'women_in_parliament.csv')\n maternal_mortality().to_csv(structured + 'maternal_mortality.csv')\n physicians_nurses().to_csv(structured + 'physicians_nurses.csv')\n \n return ",
  53. "execution_count": 50,
  54. "outputs": []
  55. },
  56. {
  57. "metadata": {
  58. "trusted": true
  59. },
  60. "cell_type": "code",
  61. "source": "save_to_location()",
  62. "execution_count": 51,
  63. "outputs": []
  64. },
  65. {
  66. "metadata": {
  67. "trusted": true
  68. },
  69. "cell_type": "code",
  70. "source": "",
  71. "execution_count": null,
  72. "outputs": []
  73. }
  74. ],
  75. "metadata": {
  76. "kernelspec": {
  77. "name": "python3",
  78. "display_name": "Python 3",
  79. "language": "python"
  80. },
  81. "language_info": {
  82. "codemirror_mode": {
  83. "name": "ipython",
  84. "version": 3
  85. },
  86. "file_extension": ".py",
  87. "mimetype": "text/x-python",
  88. "name": "python",
  89. "nbconvert_exporter": "python",
  90. "pygments_lexer": "ipython3",
  91. "version": "3.6.8"
  92. }
  93. },
  94. "nbformat": 4,
  95. "nbformat_minor": 2
  96. }
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!