LSMS_Library 0.2.1__py3-none-any.whl

Uganda/2013-14/Data/GSEC15BB.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: 1a3f3742b46844423a75045e4e949144
+  path: GSEC15BB.dta

Uganda/2013-14/Data/GSEC15BB_2.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: 9b4c14966c57f4fd7148d409e61bcb8d
+  path: GSEC15BB_2.dta

Uganda/2013-14/Data/GSEC15BB_3.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: 0e2752b9834caeaf9ac3921dc3ac28ef
+  path: GSEC15BB_3.dta

Uganda/2013-14/Data/GSEC15C.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: 7b0eb1e13ac5c10bb1af7309412442a2
+  path: GSEC15C.dta

Uganda/2013-14/Data/GSEC15D.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: d4c574ed3c5e797453920d8558828d25
+  path: GSEC15D.dta

Uganda/2013-14/Data/GSEC15E.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: a96999136ea971d7e99678140c906881
+  path: GSEC15E.dta

Uganda/2013-14/Data/GSEC16.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: 1f2be3edefd6ea40fe46bdde832be97e
+  path: GSEC16.dta

Uganda/2013-14/Data/GSEC17_1.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: 233aa6431cd5ac6f5045c2aba444b40f
+  path: GSEC17_1.dta

Uganda/2013-14/Data/GSEC17_2.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: c8af0ce6de9e464d7e1c799438910377
+  path: GSEC17_2.dta

Uganda/2013-14/Data/GSEC17_3.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: 5dcbffbca0318330919782f6e0d0ba20
+  path: GSEC17_3.dta

Uganda/2013-14/Data/GSEC17_4.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: ae5ab5e225958e1df5f582ace7518478
+  path: GSEC17_4.dta

Uganda/2013-14/Data/GSEC19.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: ecfbb7fe6b41e2a852b005b0459b60e1
+  path: GSEC19.dta

Uganda/2013-14/Data/GSEC2.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: b0174f77c9cf3012a06458f7b3c239e7
+  path: GSEC2.dta

Uganda/2013-14/Data/GSEC3.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: 87ecae47feafde59d2977851d197d0ac
+  path: GSEC3.dta

Uganda/2013-14/Data/GSEC4.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: aa6c4eab5962b0fe22198bb16e982b17
+  path: GSEC4.dta

Uganda/2013-14/Data/GSEC5.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: b024b0c53fd561b452168646933e1585
+  path: GSEC5.dta

Uganda/2013-14/Data/GSEC6_1.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: 845735389b692ee12409866761651f91
+  path: GSEC6_1.dta

Uganda/2013-14/Data/GSEC6_2.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: 1126f5732ad12a1d4ddd01c77300ba84
+  path: GSEC6_2.dta

Uganda/2013-14/Data/GSEC6_3.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: 5ccfea88eef985339d7f34b4a8743771
+  path: GSEC6_3.dta

Uganda/2013-14/Data/GSEC8_1.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: 219c43c5eb6a30d61846efb97b75daac
+  path: GSEC8_1.dta

Uganda/2013-14/Data/GSEC9_1.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: 39ed952a1cbd64adf59dc8830a9f5cfa
+  path: GSEC9_1.dta

Uganda/2013-14/Data/GSEC9_2.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: bf30c4417326b5ba8222004c9cf3eb44
+  path: GSEC9_2.dta

Uganda/2013-14/Data/UNPS 2013-14 Consumption Aggregate.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: f17476f72dcd63af4429129eb602855e
+  path: UNPS 2013-14 Consumption Aggregate.dta

Uganda/2013-14/Data/WSEC1A.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: 4a64cb25f2412a8c906bf15452643445
+  path: WSEC1A.dta

Uganda/2013-14/Data/WSEC2.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: 0376953c2f27f9582f3c365374b0a143
+  path: WSEC2.dta

Uganda/2013-14/Data/WSEC3.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: db57827c38945f6e23d56514f0608e47
+  path: WSEC3.dta

Uganda/2013-14/Data/WSEC4.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: 6fe097cc33f1f6f436feda9165a88ea9
+  path: WSEC4.dta

Uganda/2013-14/Data/WSEC5.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: 1b2c56df08764848be50178361feaa0f
+  path: WSEC5.dta

Uganda/2013-14/Data/gsec12.dta.dvc

@@ -0,0 +1,3 @@
+outs:
+- md5: 940bedafb5fb2254b572cb14c2c4e83c
+  path: gsec12.dta

Uganda/2013-14/Documentation/.gitignore

@@ -0,0 +1,5 @@
+/Basic Information Document.pdf
+/unps_2013_14_agriculture_qx.pdf
+/unps_2013_14_community_qx.pdf
+/unps_2013_14_household_qx.pdf
+/unps_2013_14_woman_qx.pdf

Uganda/2013-14/Documentation/Basic Information Document.pdf.dvc

@@ -0,0 +1,5 @@
+outs:
+- md5: d6ec178ddfcd27d4691d23117a184503
+  size: 775454
+  hash: md5
+  path: Basic Information Document.pdf

Uganda/2013-14/Documentation/LICENSE

@@ -0,0 +1,23 @@
+LICENSE
+
+https://microdata.worldbank.org/index.php/catalog/2663#metadata-data_access
+
+1.Access policy
+CONTACTS
+Name	Email	URL
+Uganda Bureau of Statistics	ubos@ubos.org	www.ubos.org
+
+CITATION REQUIREMENTS
+Use of the dataset must be acknowledged using a citation which would include:
+- the Identification of the Primary Investigator
+- the title of the survey (including country, acronym and year of implementation)
+- the survey reference number
+- the source and date of download
+
+Example:
+Uganda Bureau of Statistics. Uganda- National Panel Survey (UNPS) 2013-2014, Ref. UGA_2013_UNPS_v02_M. Dataset downloaded from [url] on [date].
+
+
+2.Disclaimer and copyrights
+DISCLAIMER
+The user of the data acknowledges that the original collector of the data, the authorized distributor of the data, and the relevant funding agency bear no responsibility for use of the data or for interpretations or inferences based upon such uses.

Uganda/2013-14/Documentation/SOURCE

@@ -0,0 +1,3 @@
+SOURCE 
+
+https://microdata.worldbank.org/index.php/catalog/2663

Uganda/2013-14/Documentation/unps_2013_14_agriculture_qx.pdf.dvc

@@ -0,0 +1,5 @@
+outs:
+- md5: 880268f1b293ee54e29baeaa5a8041bc
+  size: 1241468
+  hash: md5
+  path: unps_2013_14_agriculture_qx.pdf

Uganda/2013-14/Documentation/unps_2013_14_community_qx.pdf.dvc

@@ -0,0 +1,5 @@
+outs:
+- md5: 46eb0a5bfce1cf39953f12e564bb3cbc
+  size: 1519121
+  hash: md5
+  path: unps_2013_14_community_qx.pdf

Uganda/2013-14/Documentation/unps_2013_14_household_qx.pdf.dvc

@@ -0,0 +1,5 @@
+outs:
+- md5: ed762d54b3e077fca73ad42b935c05eb
+  size: 1620239
+  hash: md5
+  path: unps_2013_14_household_qx.pdf

Uganda/2013-14/Documentation/unps_2013_14_woman_qx.pdf.dvc

@@ -0,0 +1,5 @@
+outs:
+- md5: f16f4b4642db62da7c46c358381cb8ed
+  size: 424257
+  hash: md5
+  path: unps_2013_14_woman_qx.pdf

Uganda/2013-14/_/assets.py

@@ -0,0 +1,18 @@
+from lsms_library.local_tools import to_parquet
+#!/usr/bin/env python3
+import numpy as np
+import pandas as pd
+import dvc.api
+from lsms import from_dta
+
+fn = '../Data/GSEC14A.dta'
+
+with dvc.api.open(fn,mode='rb') as dta:
+    df = from_dta(dta)
+
+assets = df.groupby('HHID')['h14q5'].sum().replace(0,np.nan)
+
+assets.index.name = 'j'
+assets.name = 'assets'
+
+to_parquet(pd.DataFrame({"Assets":assets}), 'assets.parquet')

Uganda/2013-14/_/data_info.yml

@@ -0,0 +1,22 @@
+Country: Uganda
+Wave: 2013-14
+
+people_last7days:
+    file: GSEC15.dta
+    idxvars:
+        i: HHID
+    myvars:
+        Men : T6FQ01a
+        Women : T6FQ01b
+        Boys : T6FQ01c
+        Girls : T6FQ01d
+
+cluster_features:
+    file: ../Data/GSEC1.dta
+    idxvars:
+        i: HHID
+        v: h1aq4a # Docs identify this as "Parish"?
+    myvars:
+        Region: region
+        Rural: urban
+        District: h1aq1a  # TODO: 3 digit numeric code; map to string?

Uganda/2013-14/_/earnings.py

@@ -0,0 +1,20 @@
+from lsms_library.local_tools import to_parquet
+#!/usr/bin/env python3
+
+import pandas as pd
+import dvc.api
+from lsms import from_dta
+
+# NB: Earnings here are for last seven days.
+fn = '../Data/GSEC8_1.dta'
+earnings1 = ['h8q31a','h8q31b']  # Earnings from first job (cash, inkind)
+earnings2 = ['h8q45a','h8q45b']  # Earnings from second job (cash, inkind)
+
+with dvc.api.open(fn,mode='rb') as dta:
+    df = from_dta(dta)
+
+earnings = df.groupby('HHID')[earnings1+earnings2].sum().sum(axis=1)
+
+earnings.index.name = 'j'
+
+to_parquet(pd.DataFrame({"Earnings":earnings}), 'earnings.parquet')

Uganda/2013-14/_/education_expenses.py

@@ -0,0 +1,55 @@
+#!/usr/bin/env python
+from lsms_library.local_tools import to_parquet
+
+import sys
+import pandas as pd
+import numpy as np
+import dvc.api
+from lsms import from_dta
+sys.path.append('../../_')
+
+
+with dvc.api.open('../Data/GSEC4.dta',mode='rb') as dta:
+    df = from_dta(dta)
+
+labels = {'HHID': 'j',
+          'PID': 'pid',
+          'h4q4': 'Read and Write?',
+          'h4q5': 'Ever attended any formal school?',
+          'h4q6': 'Why has not attended school?',
+          'h4q7': 'Highest Grade/Class Completed',
+          'h4q8': 'Main Reason for Leaving School', 
+          'h4q9': 'Grade/Class Attending Last Year',
+          'h4q10': 'Grade/Class Attending Currently',
+          'h4q10b': 'Name of School Attending Currently',
+          'h4q11': 'School Management Authority',
+          'h4q12': 'Type of School',
+          'h4q12b': 'Boarding or Day Section of School',
+          'h4q13': 'Distance to School in km',
+          'h4q14': 'Time in min',
+          'h4q14b': 'Transportation',
+          'h4q15a': 'School and Registration Fees',
+          'h4q15b': 'Uniform Fee',
+          'h4q15c': 'Book Fee',
+          'h4q15d': 'Transportation Fee',
+          'h4q15e': 'Boarding Fee',
+          'h4q15f': 'Other Fee',
+          'h4q15g': 'Total Education Expenditure',
+          'h4q16': 'Scholarship or Subsidy',
+          'h4q17': 'Source of funding',
+          'h4q18': 'Meals at School'}
+
+ed = df[labels.keys()].rename(columns = labels).dropna(how = 'all')
+
+ed = ed.set_index(['j','pid'])
+
+ed_expense = ed[['School and Registration Fees','Uniform Fee',
+                 'Book Fee','Transportation Fee', 
+                 'Boarding Fee','Other Fee',
+                 'Total Education Expenditure']]
+
+ed_expense = ed_expense.replace({0: np.nan}).dropna(how='all')
+
+#ed_expense = ed_expense.groupby('j').sum()
+
+to_parquet(ed_expense, 'education_expenses.parquet')

Uganda/2013-14/_/enterprise_income.py

@@ -0,0 +1,26 @@
+from lsms_library.local_tools import to_parquet
+#!/usr/bin/env python3
+import numpy as np
+import pandas as pd
+import dvc.api
+from lsms import from_dta
+
+fn = '../Data/gsec12.dta'
+hhid = 'hhid'
+d = dict(revenue = 'h12q13',
+         wagebill = 'h12q15',
+         materials = 'h12q16',
+         otherexpense = 'h12q17')
+
+with dvc.api.open(fn,mode='rb') as dta:
+    df = from_dta(dta)
+
+enterprise_income = df.groupby(hhid)[list(d.values())].sum() # Sum over enterprises
+enterprise_income.index.name = 'j'
+
+enterprise_income = enterprise_income.rename(columns={v:k for k,v in d.items()})
+
+enterprise_income['profits'] = np.maximum(enterprise_income['revenue'] - enterprise_income[['wagebill','materials','otherexpense']].sum(axis=1),0)
+enterprise_income['losses'] = -np.minimum(enterprise_income['revenue'] - enterprise_income[['wagebill','materials','otherexpense']].sum(axis=1),0)
+
+to_parquet(enterprise_income, 'enterprise_income.parquet')

Uganda/2013-14/_/food_acquired.py

@@ -0,0 +1,25 @@
+#!/usr/bin/env python
+from lsms_library.local_tools import to_parquet
+import sys
+sys.path.append('../../_/')
+from uganda import food_acquired
+
+fn='../Data/GSEC15B.dta'
+
+myvars = dict(item='itmcd',
+              HHID='HHID',
+              market='h15bq12',
+              farmgate='h15bq13',
+              value_home='h15bq5',
+              value_away='h15bq7',
+              value_own='h15bq9',
+              value_inkind='h15bq11',
+              quantity_home='h15bq4',
+              quantity_away='h15bq6',
+              quantity_own='h15bq8',
+              quantity_inkind='h15bq10',
+              units='untcd')
+
+df = food_acquired(fn,myvars)
+
+to_parquet(df, 'food_acquired.parquet')

Uganda/2013-14/_/household_characteristics.py

@@ -0,0 +1,22 @@
+#!/usr/bin/env python
+from lsms_library.local_tools import to_parquet
+
+import sys
+sys.path.append('../../_/')
+import pandas as pd
+import numpy as np
+from uganda import age_sex_composition
+
+myvars = dict(fn='../Data/GSEC2.dta',
+              HHID='HHID',
+              sex='h2q3',
+              age='h2q8',
+              months_spent='h2q5')
+
+df = age_sex_composition(**myvars)
+
+df = df.filter(regex='ales ')
+
+df['log HSize'] = np.log(df.sum(axis=1))
+
+to_parquet(df, 'household_characteristics.parquet')

Uganda/2013-14/_/housing.py

@@ -0,0 +1,31 @@
+from lsms_library.local_tools import to_parquet
+#!/usr/bin/env python3
+import numpy as np
+import pandas as pd
+import dvc.api
+from lsms import from_dta
+
+fn = '../Data/GSEC9_1.dta'
+d = {"hhid":['HHID'],
+    "Thatched roof" : ['h9q4',lambda x: 0 + ('Thatch' in x)],
+     "Earthen floor" : ['h9q6',lambda x: 0 + ('earth' in x)]}
+
+with dvc.api.open(fn,mode='rb') as dta:
+    df = from_dta(dta)
+
+housing = df[[v[0] for v in d.values()]]
+housing.columns.name = 'k'
+housing = housing.fillna('0')
+
+housing = housing.rename(columns={v[0]:k for k,v in d.items()})
+
+for k,v in d.items():
+    try:
+        housing[k] = housing[k].apply(v[1])
+    except IndexError:
+        pass
+
+housing.set_index('hhid', inplace=True)
+housing.index.name = 'j'
+
+to_parquet(housing, 'housing.parquet')

Uganda/2013-14/_/interview_date.py

@@ -0,0 +1,17 @@
+import pandas as pd
+import sys
+sys.path.append('../../../_/')
+from lsms_library.local_tools import df_data_grabber, to_parquet
+
+idxvars = dict(j='HHID',
+                t=('rotate', lambda x: "2013-14"))
+myvars = dict(year='year',
+                month='month',
+                day='day')
+
+df = df_data_grabber('../Data/GSEC1.dta',idxvars,**myvars)
+df['date'] = pd.to_datetime(df[['year', 'month', 'day']])
+df = df.drop(columns=['year','month','day'])
+
+to_parquet(df,'interview_date.parquet')
+

Uganda/2013-14/_/nonfood_expenditures.py

@@ -0,0 +1,16 @@
+#!/usr/bin/env python
+from lsms_library.local_tools import to_parquet
+import sys
+sys.path.append('../../_')
+from uganda import nonfood_expenditures
+
+myvars = dict(fn='../Data/GSEC15C.dta',
+              item='itmcd',
+              HHID='HHID',
+              purchased='h15cq5',
+              away=None,
+              produced='h15cq7',
+              given='h15cq9')
+
+x = nonfood_expenditures(**myvars) 
+to_parquet(x, 'nonfood_expenditures.parquet')

Uganda/2013-14/_/other_features.py

@@ -0,0 +1,37 @@
+#!/usr/bin/env python
+from lsms_library.local_tools import to_parquet
+
+import sys
+sys.path.append('../../_/')
+import pandas as pd
+import numpy as np
+from uganda import other_features
+from pathlib import Path
+
+pwd = Path.cwd()
+round = str(pwd.parent).split('/')[-1]
+
+
+myvars = dict(fn='../Data/GSEC1.dta',
+              HHID='HHID',
+              urban='urban',
+              region='region',
+              urban_converter = lambda s: s.lower() == 'urban')
+
+
+df = other_features(**myvars)
+
+# Some "Central" households have region coded as 0?  These seem to be households in one of the 34
+# Enumeration Areas (comm) of Kampala.
+# See https://microdata.worldbank.org/index.php/catalog/1001/data-dictionary/F41?file_name=2005_GSEC1
+df = df.replace({'region':{'0':'Kampala'}})
+
+df['Rural'] = 1 - df.urban.astype(int)
+
+df = df.rename(columns={'region':'m'})
+
+df['t'] = round
+
+df = df.reset_index().set_index(['j','t','m'])[['Rural']]
+
+to_parquet(df, 'other_features.parquet')

Uganda/2013-14/_/plots.py

@@ -0,0 +1,26 @@
+import numpy as np
+import pandas as pd
+import sys
+sys.path.append('../../../_/')
+from lsms_library.local_tools import df_data_grabber, to_parquet
+    
+def intercrop_area(row):
+    if not np.isnan(row['area_percentage']):
+        return row['acres'] * row['area_percentage']/100
+    else:
+        return row['acres']
+
+idxvars = dict(j='HHID',
+               t=('HHID', lambda x: "2013-14"),
+               plt=(['parcelID','plotID'],lambda x: "{parcelID}-{plotID}".format_map(x)),
+               crop="cropID"
+               )
+
+myvars = dict(acres='a4aq7',
+              area_units = ('a4aq7', lambda x: 'ACRES'),
+              intercrop = 'a4aq8',
+              area_percentage = 'a4aq9')
+df = df_data_grabber('../Data/AGSEC4A.dta',idxvars,**myvars)
+
+df = df.assign(acres = df.apply(intercrop_area,axis=1)).drop(columns=['area_percentage'])
+to_parquet(df,'plots.parquet')

Uganda/2013-14/_/shocks.py

@@ -0,0 +1,61 @@
+#!/usr/bin/env python
+from lsms_library.local_tools import to_parquet
+
+from calendar import month
+import sys
+sys.path.append('../../_/')
+import pandas as pd
+import dvc.api
+from datetime import datetime
+from lsms import from_dta
+
+#shock dataset
+with dvc.api.open('../Data/GSEC16.dta',mode='rb') as dta:
+    df = from_dta(dta)
+df = df[df['h16q2y'].notna()] #filter for valid entry 
+
+#general hh dataset 
+with dvc.api.open('../Data/GSEC1.dta',mode='rb') as dta:
+    date = from_dta(dta)
+
+#filter for hhs who have taken the shock questionnaire 
+date = date[date.set_index('HHID').index.isin(df.set_index('HHID').index)]
+
+#calculate shock onset 
+df['h16q02a'] = pd.to_datetime(df.h16q02a, format='%B').dt.month
+df['start_date'] = pd.to_datetime(df.rename(columns={'h16q2y': 'year', 'h16q02a': 'month'})[['year', 'month']].assign(DAY=1)) #no day reported; assume 1st of the month 
+date['end_date'] = pd.to_datetime(date[['year', 'month']].assign(DAY=1)) #round the interview date to 1st of the month to match shock date
+date = date[["HHID", "end_date"]]
+df = pd.merge(df, date, on='HHID')
+df['Onset'] = (df.end_date.dt.to_period('M') - df.start_date.dt.to_period('M')).dropna().apply(lambda x: x.n)
+
+shocks = pd.DataFrame({"j": df.HHID.values.tolist(),
+                    "Shock":df.h16q00.values.tolist(), 
+                    "Year": df.h16q2y.values.tolist(),
+                    "Onset":df.Onset.values.tolist(), 
+                    "Duration":df.h16q02b.values.tolist(),
+                    "EffectedIncome":df.h16q3a.values.tolist(), 
+                    "EffectedAssets":df.h16q3b.values.tolist(), 
+                    "EffectedProduction":df.h16q3c.values.tolist(), 
+                    "EffectedConsumption":df.h16q3d.values.tolist(), 
+                    "HowCoped0":df.h16q4a.values.tolist(),
+                    "HowCoped1":df.h16q4b.values.tolist(),
+                    "HowCoped2":df.h16q4c.values.tolist()})
+
+#converting data types 
+for col in ["EffectedIncome",  "EffectedAssets",  "EffectedProduction", "EffectedConsumption"]:
+    shocks[col] = shocks[col].map({"Yes": True,"No": False})
+    shocks[col] = shocks[col].astype('boolean')
+shocks = shocks.astype({'Shock': 'category',
+                        'Year': 'Int64',
+                        'Onset': 'Int64',
+                        'Duration': 'float',
+                        "HowCoped0": 'category',
+                        "HowCoped1": 'category',
+                        "HowCoped2": 'category'
+                        }) 
+
+shocks.insert(1, 't', '2013-14')
+shocks.set_index(['j','t','Shock'], inplace = True)
+
+to_parquet(shocks, 'shocks.parquet')