[INIT] Hello World!

.gitignore

@@ -0,0 +1,119 @@
+########################################################################
+#
+# .gitignore DIME template
+# https://github.com/worldbank/DIMEwiki/tree/master/Topics/GitHub
+#
+# We recommend that you create a .gitignore file using GitHub's tools and
+# replace the content of that file with the content of this file. Otherwise
+# you have to rename this file .gitignore. But if you rename the fine in a
+# regular folder window PCs and Macs are likely to keep the file extension
+# so that the file ends up being names .gitignore.txt. Code editors like, Atom,
+# can edit the file extension, but if you are not familiar with how to do that,
+# we recommend that you generate an ignore file using GitHub and simply replace
+# the content of that file.
+#
+# Note that if you are using GitKraken you need to use version 5.x or more
+# recent for this template to work properly
+#
+########################################################################
+
+#######################
+# Start by ignoring everything, and below we are explicitly saying
+# what to not ignore
+*
+
+#######################
+# List of files with GitHub functionality anywhere in the repo
+# that we do not want to ignore
+
+# These files include GitHub settings
+!.gitignore
+!.gitattributes
+
+# Keep markdown files used for documentation on GitHub
+!README.md
+!CONTRIBUTING.md
+!LICENSE.md
+
+#######################
+# For performance reasons, if a folder is already ignored, then
+# GitHub does not check the content for that folder for matches
+# with additional rules. The line below includes folder in the
+# top folder (but not their content), so that anything matching
+# the rules below will still not be ignored.
+!*/
+
+#######################
+# The following file types are code that should always be
+# included no matter where in the repository folder they are
+# located unless you explicitly ignore that folder
+
+# Stata
+!/**/*.do
+!/**/*.ado
+!/**/*.sthlp
+
+# R-scrips and Rmarkdown-scripts
+!/**/*.R
+!/**/*.Rmd
+
+# LaTeX
+!/**/*.tex
+
+# Python
+!/**/*.py
+!/**/*.ipynb
+
+# Matlab
+!/**/*.m
+
+# Markdown
+!/**/*.md
+
+# Dyntext script
+!00_documentation/002_repo_structure/0022_dataset_tables/dyntext*.txt
+
+# csv files in input folders
+!/**/*_rawdata/*.csv
+!/**/*_rawdata/*/*.csv
+
+# csv files in selected input folders
+!08_2pager/081_data/cleaned_*.csv
+!08_2pager/081_data/hosted_in_repo/*.csv
+
+
+##################
+#Include images used in the 2pager template
+!08_2pager/082_program/Rmd_template/Rmd_template_images/*.png
+
+#Include the Excel input file
+#!08_2pager/081_data/twopager_input.xls
+
+#Include the Excel input file with Name of TTLs
+!08_2pager/081_data/hosted_in_repo/20190903_TTL List.xlsx
+
+#Do not commit the intermediate tex files generated by the Rmd
+08_2pager/083_interm_output/raw_output_2pagers/*.tex
+
+#Do not commit the aggregation tex files
+08_2pager/084_2pagers/*/*.tex
+08_2pager/084_2pagers/*/*/*.tex
+
+# image files in documentation folders
+!/00_documentation/*/*/*.png
+!/00_documentation/*/*/*.jpg
+!/00_documentation/*/*.png
+!/00_documentation/*/*.jpg
+!/00_documentation/*.png
+!/00_documentation/*.jpg
+
+#######################
+# Include all the files with passwords or tokens here. All files named
+# password or passwords are with this template ignored no matter which
+# format you are using. Additionally, all content in any folder called
+password or passwords are also ignored. NOTE that your project might be
+using different names and then you must edit the lines below accordingly.
+password.*
+passwords.*
+password/
+passwords/

00_documentation/002_repo_structure/0022_dataset_tables/dyntext_LP.txt

@@ -0,0 +1,89 @@
+<<dd_version: 1>>
+<<dd_do:quietly>>
+
+* This is the documentation generator companion from edukit_save.
+* It's a do file section that create locals to display dynamically
+* Author: Diana Goldemberg
+
+* Dataset observations and variables
+describe
+local nobs  = r(N)
+local nvars = r(k)
+
+/*  Metadata automatically generated by edukit_save is stored in metadata_chars
+    the idea is to read through them all and index them, so they are all displayed
+    with their correct names and values. */
+
+    local i = 1
+    local metadata_chars:   char _dta[metadata_chars]
+    while "`metadata_chars'" != "" {
+      gettoken thischar metadata_chars : metadata_chars, parse(" ")
+      local char_i`i' = 	    "`thischar'"
+      local char_value_i`i':  char _dta[`thischar']
+      local ++i
+    }
+
+/*  The loop above was generic, so it could be reused in other dyndocs.
+    but for all Learning Poverty files, we know the exact order or metadata.
+    As in any file saved by edukit_save, metadata_chars starts with:
+      i1.  lastsave
+      i2.  varclasses_used
+    Moreover, in Learning Poverty do files, we save metadatada also into:
+      i3.  description
+      i4.  sources
+      i5.  filename
+*/
+
+/*  We also want to read varclasses_used to read each of the chars it defines.
+    By reading each of those chars, we find which variables are in those classes. */
+
+    local j = 1
+    local varclasses_used:	char _dta[varclasses_used]
+    while "`varclasses_used'" != "" {
+      gettoken thischar varclasses_used : varclasses_used, parse(" ")
+      local char_j`j' = 	    "`thischar'"
+      local char_value_j`j':  char _dta[`thischar']
+      local ++j
+    }
+
+/*  As in any file saved by edukit_save, varclasses_used starts with:
+      j1.  idvars
+    Moreover, in Learning Poverty do files, it's always:
+      j2.  valuevars
+      j3.  traitvars
+    Some do files (or future edits) may entail having more varclasses_used. */
+
+/*  NOTE: we purposefully use individual spaces instead of tabs in the
+    dd_display section below, to get consistency in spacing across platforms. */
+
+<</dd_do>>
+
+Documentation of <<dd_display:"`char_value_i5'">>
+=====================================================================
+
+<sup>back to the [Repo Structure](https://github.com/worldbank/LearningPoverty/blob/master/00_documentation/002_repo_structure/Repo_Structure.md) :leftwards_arrow_with_hook:</sup>
+
+<<dd_display:"`char_value_i3'">>
+
+**Metadata** stored in this dataset:
+
+~~~~
+<<dd_display:"`char_i4'">>:     <<dd_display:"`char_value_i4'">>
+<<dd_display:"`char_i1'">>:    <<dd_display:"`char_value_i1'">>
+~~~~
+
+
+About the **<<dd_display:`nvars'>> variables** in this dataset:
+
+~~~~
+The variables belong to the following variable classifications:
+<<dd_display:"`char_value_i2'">>
+
+<<dd_display:"`char_j1'">>:    <<dd_display:"`char_value_j1'">>
+<<dd_display:"`char_j2'">>: <<dd_display:"`char_value_j2'">>
+<<dd_display:"`char_j3'">>: <<dd_display:"`char_value_j3'">>
+
+<<dd_do>>
+codebook, compact
+<</dd_do>>
+~~~~

00_documentation/002_repo_structure/0022_dataset_tables/enrollment.md

@@ -0,0 +1,46 @@
+
+Documentation of Enrollment
+=====================================================================
+
+<sup>back to the [Repo Structure](https://github.com/worldbank/LearningPoverty/blob/master/00_documentation/002_repo_structure/Repo_Structure.md) :leftwards_arrow_with_hook:</sup>
+
+Dataset of enrollment. Long in countrycode and year, wide in enrollment definitions (ie: interpolated, validated) and subgroups (all, male, female).
+
+**Metadata** stored in this dataset:
+
+~~~~
+sources:     Multiple enrollment definitions were combined according to a ranking. Original data from World Bank (country team validation, ANER) and UIS (TNER, NET, GER)
+lastsave:    16 Oct 2019 20:42:20 by wb255520
+~~~~
+
+
+About the **13 variables** in this dataset:
+
+~~~~
+The variables belong to the following variable classifications:
+idvars valuevars traitvars
+
+idvars:    countrycode year
+valuevars: enrollment_validated_all enrollment_validated_fe enrollment_validated_ma enrollment_validated_flag enrollment_interpolated_all enrollment_interpolated_fe enrollment_interpolated_ma enrollment_interpolated_flag
+traitvars: enrollment_source enrollment_definition year_enrollment
+
+. codebook, compact
+
+Variable       Obs Unique      Mean       Min       Max  Label
+----------------------------------------------------------------------------------------------------------------------------------------
+countrycode   6293    217         .         .         .  WB country code (3 letters)
+year          6293     29      2004      1990      2018  Year
+en~dated_all  5771   2908  87.21567  19.10539       100  Validated % of children enrolled in school (using closest year, both genders)
+enr~dated_fe  5348   2742  86.29536  15.50506       100  Validated % of children enrolled in school (using closest year, female only)
+enr~dated_ma  5348   2743  87.94001     22.14  100.4548  Validated % of children enrolled in school (using closest year, male only)
+e~dated_flag  6293      2   .194184         0         1  Flag for enrollment by gender filled up from aggregate (>=98.5%)
+en~lated_all  5771   3755  87.24924  19.10539       100  Validated % of children enrolled in school (using interpolation, both genders)
+enr~lated_fe  4739   2857  87.20877  15.50506       100  Validated % of children enrolled in school (using interpolation, female only)
+enr~lated_ma  4739   2858  88.61073     22.14  100.4548  Validated % of children enrolled in school (using interpolation, male only)
+e~lated_flag  6293      2  .1978389         0         1  Flag for enrollment by gender filled up from aggregate (>=98.5%)
+enrollmen~ce  6293      5         .         .         .  The source used for this enrollment value
+enrollment~n  6293      5         .         .         .  The definition used for this enrollment value
+year_enrol~t  5771     29  2005.041      1990      2018  The year that the enrollment value is from
+----------------------------------------------------------------------------------------------------------------------------------------
+
+~~~~

00_documentation/002_repo_structure/0022_dataset_tables/population.md

@@ -0,0 +1,48 @@
+
+Documentation of Population
+=====================================================================
+
+<sup>back to the [Repo Structure](https://github.com/worldbank/LearningPoverty/blob/master/00_documentation/002_repo_structure/Repo_Structure.md) :leftwards_arrow_with_hook:</sup>
+
+Dataset of late primary aged population. Long in countrycode and year, wide in population definitions (ie: 10-14y, primary-aged, etc) and subgroups (all, male, female). In units, not thousands nor millions.
+
+**Metadata** stored in this dataset:
+
+~~~~
+sources:     World Bank staff estimates using the World Bank's total population and age distributions of the United Nations Population Division's World Population Prospects.
+lastsave:    16 Oct 2019 20:42:18 by wb255520
+~~~~
+
+
+About the **15 variables** in this dataset:
+
+~~~~
+The variables belong to the following variable classifications:
+idvars valuevars traitvars
+
+idvars:    countrycode year_population
+valuevars: population_fe_10 population_fe_primary population_fe_9plus population_ma_10 population_ma_primary population_ma_9plus population_all_10 population_all_primary population_all_9plus population_fe_1014 population_ma_1014 population_all_1014 population_source
+traitvars: population_source
+
+. codebook, compact
+
+Variable        Obs Unique      Mean   Min       Max  Label
+----------------------------------------------------------------------------------------------------------------------------------------
+countrycode   13237    217         .     .         .  WB country code (3 letters)
+year_popul~n  13237     61      2020  1990      2050  Year of population
+populat~e_10  11795   6667  320676.7   479  1.33e+07  Female population aged 10 (WB API)
+po~e_primary  10514   7901   2282059  3477  7.53e+07  Female population primary age, country specific (WB API)
+popu~e_9plus  11722   8056   1192931   967  5.14e+07  Female population aged 9 to end of primary, country specific (WB API)
+populat~a_10  11795   6671    339959   492  1.42e+07  Male population aged 10 (WB API)
+po~a_primary  10514   7939   2419477  3858  8.08e+07  Male population primary age, country specific (WB API)
+popu~a_9plus  11722   8043   1259789  1007  5.52e+07  Male population aged 9 to end of primary, country specific (WB API)
+populat~l_10  11795   7305  660635.7   971  2.75e+07  Total population aged 10 (WB API)
+po~l_primary  10514   8655   4701535  7335  1.56e+08  Total population primary age, country specific (WB API)
+popu~l_9plus  11722   8815   2452720  1974  1.07e+08  Total population aged 9 to end of primary, country specific (WB API)
+popul~e_1014  11792   8026   1582075  2300  6.21e+07  Female population between ages 10 to 14 (WB API)
+popul~a_1014  11792   8055   1676621  2300  6.72e+07  Male population between ages 10 to 14 (WB API)
+popul~l_1014  11792   8758   3258696  4600  1.29e+08  Total population between ages 10 to 14 (WB API)
+population~e  13237      1         .     .         .  The source used for population variables
+----------------------------------------------------------------------------------------------------------------------------------------
+
+~~~~

00_documentation/002_repo_structure/0022_dataset_tables/proficiency.md

@@ -0,0 +1,48 @@
+
+Documentation of Proficiency
+=====================================================================
+
+<sup>back to the [Repo Structure](https://github.com/worldbank/LearningPoverty/blob/master/00_documentation/002_repo_structure/Repo_Structure.md) :leftwards_arrow_with_hook:</sup>
+
+Dataset of proficiency. One country may have multiple or no observations at all. Long on specific measures in time (that is, assessment year grade subject country) and wide in subgroups (all, male, female).
+
+**Metadata** stored in this dataset:
+
+~~~~
+sources:     Compilation of proficiency measures from 3 sources: CLO (Country Level Outcomes from GLAD), National Learning Assessment (from UIS), HAD (Harmonized Assessment Database)
+lastsave:    16 Oct 2019 20:42:18 by wb255520
+~~~~
+
+
+About the **15 variables** in this dataset:
+
+~~~~
+The variables belong to the following variable classifications:
+idvars valuevars traitvars
+
+idvars:    countrycode year idgrade test nla_code subject
+valuevars: nonprof_all se_nonprof_all nonprof_ma se_nonprof_ma nonprof_fe se_nonprof_fe
+traitvars: min_proficiency_threshold source_assessment surveyid
+
+. codebook, compact
+
+Variable      Obs Unique      Mean       Min       Max  Label
+----------------------------------------------------------------------------------------------------------------------------------------
+countrycode   697    146         .         .         .  WB country code (3 letters)
+year          697     20  2009.898      1996      2017  Year of assessment
+idgrade       697      4  4.308465         3         6  Grade ID
+test          697      7         .         .         .  Assessment
+nla_code      697     22         .         .         .  Reference code for NLA in markdown documentation
+subject       697      3         .         .         .  Subject
+nonprof_all   697    697  30.44718  .2252221  99.89659  % pupils below minimum proficiency (all)
+se_nonprof~l  559    559  .9498702  .1218972  3.419903  SE of pupils below minimum proficiency (all)
+nonprof_ma    559    559  24.92177  .1586974  97.96137  % pupils below minimum proficiency (ma)
+se_nonprof~a  559    559  1.199997  .1287481  3.848194  SE of pupils below minimum proficiency (ma)
+nonprof_fe    559    559  22.02045  .1284599  97.83222  % pupils below minimum proficiency (fe)
+se_nonprof~e  559    559  1.142743  .1141958  3.566816  SE of pupils below minimum proficiency (fe)
+min_profic~d  694     18         .         .         .  Minimum Proficiency Threshold (assessment-specific)
+source_ass~t  697      3         .         .         .  Source of assessment data
+surveyid      697    503         .         .         .  SurveyID (countrycode_year_assessment)
+----------------------------------------------------------------------------------------------------------------------------------------
+
+~~~~