diff --git a/Makefile b/Makefile index a321987..ac1d836 100644 --- a/Makefile +++ b/Makefile @@ -13,7 +13,7 @@ test: ## Run tests with pytest and coverage @rm -rf temp make clean-dta # Git checkout census.dta - git checkout datasets/census.dta + git checkout assets/datasets/census.dta .PHONY: lint MYPY_OPTS := --ignore-missing-imports diff --git a/datasets/Makefile b/assets/datasets/Makefile similarity index 100% rename from datasets/Makefile rename to assets/datasets/Makefile diff --git a/datasets/README.md b/assets/datasets/README.md similarity index 100% rename from datasets/README.md rename to assets/datasets/README.md diff --git a/datasets/auto.dta b/assets/datasets/auto.dta similarity index 100% rename from datasets/auto.dta rename to assets/datasets/auto.dta diff --git a/datasets/auto2.dta b/assets/datasets/auto2.dta similarity index 100% rename from datasets/auto2.dta rename to assets/datasets/auto2.dta diff --git a/datasets/autornd.dta b/assets/datasets/autornd.dta similarity index 100% rename from datasets/autornd.dta rename to assets/datasets/autornd.dta diff --git a/datasets/bplong.dta b/assets/datasets/bplong.dta similarity index 100% rename from datasets/bplong.dta rename to assets/datasets/bplong.dta diff --git a/datasets/cancer.dta b/assets/datasets/cancer.dta similarity index 100% rename from datasets/cancer.dta rename to assets/datasets/cancer.dta diff --git a/assets/datasets/census.dta b/assets/datasets/census.dta new file mode 100644 index 0000000..a938a14 Binary files /dev/null and b/assets/datasets/census.dta differ diff --git a/datasets/citytemp.dta b/assets/datasets/citytemp.dta similarity index 100% rename from datasets/citytemp.dta rename to assets/datasets/citytemp.dta diff --git a/datasets/educ99gdp.dta b/assets/datasets/educ99gdp.dta similarity index 100% rename from datasets/educ99gdp.dta rename to assets/datasets/educ99gdp.dta diff --git a/datasets/getdata.do b/assets/datasets/getdata.do similarity index 100% rename from datasets/getdata.do rename to assets/datasets/getdata.do diff --git a/datasets/gnp96.dta b/assets/datasets/gnp96.dta similarity index 100% rename from datasets/gnp96.dta rename to assets/datasets/gnp96.dta diff --git a/datasets/lifeexp.dta b/assets/datasets/lifeexp.dta similarity index 100% rename from datasets/lifeexp.dta rename to assets/datasets/lifeexp.dta diff --git a/datasets/manifest.txt b/assets/datasets/manifest.txt similarity index 100% rename from datasets/manifest.txt rename to assets/datasets/manifest.txt diff --git a/datasets/nickchk-causaldata/Mroz.dta b/assets/datasets/nickchk-causaldata/Mroz.dta similarity index 100% rename from datasets/nickchk-causaldata/Mroz.dta rename to assets/datasets/nickchk-causaldata/Mroz.dta diff --git a/datasets/nickchk-causaldata/abortion.dta b/assets/datasets/nickchk-causaldata/abortion.dta similarity index 100% rename from datasets/nickchk-causaldata/abortion.dta rename to assets/datasets/nickchk-causaldata/abortion.dta diff --git a/datasets/nickchk-causaldata/adult_services.dta b/assets/datasets/nickchk-causaldata/adult_services.dta similarity index 100% rename from datasets/nickchk-causaldata/adult_services.dta rename to assets/datasets/nickchk-causaldata/adult_services.dta diff --git a/datasets/nickchk-causaldata/avocado.dta b/assets/datasets/nickchk-causaldata/avocado.dta similarity index 100% rename from datasets/nickchk-causaldata/avocado.dta rename to assets/datasets/nickchk-causaldata/avocado.dta diff --git a/datasets/nickchk-causaldata/black_politicians.dta b/assets/datasets/nickchk-causaldata/black_politicians.dta similarity index 100% rename from datasets/nickchk-causaldata/black_politicians.dta rename to assets/datasets/nickchk-causaldata/black_politicians.dta diff --git a/datasets/nickchk-causaldata/castle.dta b/assets/datasets/nickchk-causaldata/castle.dta similarity index 100% rename from datasets/nickchk-causaldata/castle.dta rename to assets/datasets/nickchk-causaldata/castle.dta diff --git a/datasets/nickchk-causaldata/close_college.dta b/assets/datasets/nickchk-causaldata/close_college.dta similarity index 100% rename from datasets/nickchk-causaldata/close_college.dta rename to assets/datasets/nickchk-causaldata/close_college.dta diff --git a/datasets/nickchk-causaldata/close_elections_lmb.dta b/assets/datasets/nickchk-causaldata/close_elections_lmb.dta similarity index 100% rename from datasets/nickchk-causaldata/close_elections_lmb.dta rename to assets/datasets/nickchk-causaldata/close_elections_lmb.dta diff --git a/datasets/nickchk-causaldata/cps_mixtape.dta b/assets/datasets/nickchk-causaldata/cps_mixtape.dta similarity index 100% rename from datasets/nickchk-causaldata/cps_mixtape.dta rename to assets/datasets/nickchk-causaldata/cps_mixtape.dta diff --git a/datasets/nickchk-causaldata/credit_cards.dta b/assets/datasets/nickchk-causaldata/credit_cards.dta similarity index 100% rename from datasets/nickchk-causaldata/credit_cards.dta rename to assets/datasets/nickchk-causaldata/credit_cards.dta diff --git a/datasets/nickchk-causaldata/gapminder.dta b/assets/datasets/nickchk-causaldata/gapminder.dta similarity index 100% rename from datasets/nickchk-causaldata/gapminder.dta rename to assets/datasets/nickchk-causaldata/gapminder.dta diff --git a/datasets/nickchk-causaldata/google_stock.dta b/assets/datasets/nickchk-causaldata/google_stock.dta similarity index 100% rename from datasets/nickchk-causaldata/google_stock.dta rename to assets/datasets/nickchk-causaldata/google_stock.dta diff --git a/datasets/nickchk-causaldata/gov_transfers.dta b/assets/datasets/nickchk-causaldata/gov_transfers.dta similarity index 100% rename from datasets/nickchk-causaldata/gov_transfers.dta rename to assets/datasets/nickchk-causaldata/gov_transfers.dta diff --git a/datasets/nickchk-causaldata/gov_transfers_density.dta b/assets/datasets/nickchk-causaldata/gov_transfers_density.dta similarity index 100% rename from datasets/nickchk-causaldata/gov_transfers_density.dta rename to assets/datasets/nickchk-causaldata/gov_transfers_density.dta diff --git a/datasets/nickchk-causaldata/greek_data.dta b/assets/datasets/nickchk-causaldata/greek_data.dta similarity index 100% rename from datasets/nickchk-causaldata/greek_data.dta rename to assets/datasets/nickchk-causaldata/greek_data.dta diff --git a/datasets/nickchk-causaldata/mortgages.dta b/assets/datasets/nickchk-causaldata/mortgages.dta similarity index 100% rename from datasets/nickchk-causaldata/mortgages.dta rename to assets/datasets/nickchk-causaldata/mortgages.dta diff --git a/datasets/nickchk-causaldata/nhefs.dta b/assets/datasets/nickchk-causaldata/nhefs.dta similarity index 100% rename from datasets/nickchk-causaldata/nhefs.dta rename to assets/datasets/nickchk-causaldata/nhefs.dta diff --git a/datasets/nickchk-causaldata/nhefs_complete.dta b/assets/datasets/nickchk-causaldata/nhefs_complete.dta similarity index 100% rename from datasets/nickchk-causaldata/nhefs_complete.dta rename to assets/datasets/nickchk-causaldata/nhefs_complete.dta diff --git a/datasets/nickchk-causaldata/nsw_mixtape.dta b/assets/datasets/nickchk-causaldata/nsw_mixtape.dta similarity index 100% rename from datasets/nickchk-causaldata/nsw_mixtape.dta rename to assets/datasets/nickchk-causaldata/nsw_mixtape.dta diff --git a/datasets/nickchk-causaldata/organ_donations.dta b/assets/datasets/nickchk-causaldata/organ_donations.dta similarity index 100% rename from datasets/nickchk-causaldata/organ_donations.dta rename to assets/datasets/nickchk-causaldata/organ_donations.dta diff --git a/datasets/nickchk-causaldata/restaurant_inspections.dta b/assets/datasets/nickchk-causaldata/restaurant_inspections.dta similarity index 100% rename from datasets/nickchk-causaldata/restaurant_inspections.dta rename to assets/datasets/nickchk-causaldata/restaurant_inspections.dta diff --git a/datasets/nickchk-causaldata/ri.dta b/assets/datasets/nickchk-causaldata/ri.dta similarity index 100% rename from datasets/nickchk-causaldata/ri.dta rename to assets/datasets/nickchk-causaldata/ri.dta diff --git a/datasets/nickchk-causaldata/scorecard.dta b/assets/datasets/nickchk-causaldata/scorecard.dta similarity index 100% rename from datasets/nickchk-causaldata/scorecard.dta rename to assets/datasets/nickchk-causaldata/scorecard.dta diff --git a/datasets/nickchk-causaldata/snow.dta b/assets/datasets/nickchk-causaldata/snow.dta similarity index 100% rename from datasets/nickchk-causaldata/snow.dta rename to assets/datasets/nickchk-causaldata/snow.dta diff --git a/datasets/nickchk-causaldata/social_insure.dta b/assets/datasets/nickchk-causaldata/social_insure.dta similarity index 100% rename from datasets/nickchk-causaldata/social_insure.dta rename to assets/datasets/nickchk-causaldata/social_insure.dta diff --git a/datasets/nickchk-causaldata/texas.dta b/assets/datasets/nickchk-causaldata/texas.dta similarity index 100% rename from datasets/nickchk-causaldata/texas.dta rename to assets/datasets/nickchk-causaldata/texas.dta diff --git a/datasets/nickchk-causaldata/thornton_hiv.dta b/assets/datasets/nickchk-causaldata/thornton_hiv.dta similarity index 100% rename from datasets/nickchk-causaldata/thornton_hiv.dta rename to assets/datasets/nickchk-causaldata/thornton_hiv.dta diff --git a/datasets/nickchk-causaldata/titanic.dta b/assets/datasets/nickchk-causaldata/titanic.dta similarity index 100% rename from datasets/nickchk-causaldata/titanic.dta rename to assets/datasets/nickchk-causaldata/titanic.dta diff --git a/datasets/nickchk-causaldata/training_bias_reduction.dta b/assets/datasets/nickchk-causaldata/training_bias_reduction.dta similarity index 100% rename from datasets/nickchk-causaldata/training_bias_reduction.dta rename to assets/datasets/nickchk-causaldata/training_bias_reduction.dta diff --git a/datasets/nickchk-causaldata/training_example.dta b/assets/datasets/nickchk-causaldata/training_example.dta similarity index 100% rename from datasets/nickchk-causaldata/training_example.dta rename to assets/datasets/nickchk-causaldata/training_example.dta diff --git a/datasets/nickchk-causaldata/yule.dta b/assets/datasets/nickchk-causaldata/yule.dta similarity index 100% rename from datasets/nickchk-causaldata/yule.dta rename to assets/datasets/nickchk-causaldata/yule.dta diff --git a/datasets/nlsw88.dta b/assets/datasets/nlsw88.dta similarity index 100% rename from datasets/nlsw88.dta rename to assets/datasets/nlsw88.dta diff --git a/datasets/pop2000.dta b/assets/datasets/pop2000.dta similarity index 100% rename from datasets/pop2000.dta rename to assets/datasets/pop2000.dta diff --git a/datasets/sp500.dta b/assets/datasets/sp500.dta similarity index 100% rename from datasets/sp500.dta rename to assets/datasets/sp500.dta diff --git a/datasets/testopen-converted-log.txt b/assets/datasets/testopen-converted-log.txt similarity index 100% rename from datasets/testopen-converted-log.txt rename to assets/datasets/testopen-converted-log.txt diff --git a/datasets/testopen-converted.do b/assets/datasets/testopen-converted.do similarity index 100% rename from datasets/testopen-converted.do rename to assets/datasets/testopen-converted.do diff --git a/datasets/testopen-log.txt b/assets/datasets/testopen-log.txt similarity index 100% rename from datasets/testopen-log.txt rename to assets/datasets/testopen-log.txt diff --git a/datasets/testopen.do b/assets/datasets/testopen.do similarity index 100% rename from datasets/testopen.do rename to assets/datasets/testopen.do diff --git a/datasets/txt2macro.ado b/assets/datasets/txt2macro.ado similarity index 100% rename from datasets/txt2macro.ado rename to assets/datasets/txt2macro.ado diff --git a/datasets/uslifeexp.dta b/assets/datasets/uslifeexp.dta similarity index 100% rename from datasets/uslifeexp.dta rename to assets/datasets/uslifeexp.dta diff --git a/datasets/uslifeexp2.dta b/assets/datasets/uslifeexp2.dta similarity index 100% rename from datasets/uslifeexp2.dta rename to assets/datasets/uslifeexp2.dta diff --git a/datasets/voter.dta b/assets/datasets/voter.dta similarity index 100% rename from datasets/voter.dta rename to assets/datasets/voter.dta diff --git a/datasets/census.dta b/datasets/census.dta deleted file mode 100644 index 0d1406f..0000000 Binary files a/datasets/census.dta and /dev/null differ diff --git a/tests/test_wbstata.py b/tests/test_wbstata.py index f990548..642ed80 100644 --- a/tests/test_wbstata.py +++ b/tests/test_wbstata.py @@ -14,6 +14,8 @@ ) +DATAPATH = "assets/datasets" + def test_normalize_dta_filename(): expected = "census.dta" @@ -25,13 +27,13 @@ def test_normalize_dta_filename(): result = normalize_dta_filename(filename) assert result == expected - expected = "datasets/census.dta" + expected = f"{DATAPATH}/census.dta" - filename = "datasets/census" + filename = f"{DATAPATH}/census" result = normalize_dta_filename(filename) assert result == expected - filename = "datasets/census.dta" + filename = f"{DATAPATH}/census.dta" result = normalize_dta_filename(filename) assert result == expected @@ -56,7 +58,7 @@ def test_add_suffix(): def test_get_output_name(): - file = "census.dta" + file = f"{DATAPATH}/census.dta" # Overwriting expected = file @@ -83,7 +85,7 @@ def test_get_output_name(): def test_is_dta_file(): - valid_file = "datasets/census.dta" + valid_file = f"{DATAPATH}/census.dta" is_dta_file(valid_file) invalid_file = "wrongfile.dta" @@ -108,8 +110,8 @@ def test_glob_dta_files(): def test_convert_dta(): for version in range(10, 17 + 1): convert_dta( - "datasets/census.dta", - "datasets/test-output.dta", + f"{DATAPATH}/census.dta", + f"{DATAPATH}/test-output.dta", target_version=version, ) @@ -135,13 +137,13 @@ def test_wbstata(): ) # Check that prompt works with just file (prompt for version) - result = runner.invoke(wbstata, ["datasets/census.dta"]) + result = runner.invoke(wbstata, [f"{DATAPATH}/census.dta"]) assert result.exit_code == 0 assert "> Target version" in result.output # Check minimal command - dta = "datasets/census.dta" - expected_output = f"{dta} to datasets/census-wbstata.dta in version 13.\n" + dta = f"{DATAPATH}/census.dta" + expected_output = f"{dta} to {DATAPATH}/census-wbstata.dta in version 13.\n" result = runner.invoke( wbstata, [f"{dta}", "--target-version", "13", "--verbose"] ) @@ -150,9 +152,9 @@ def test_wbstata(): assert COMPLETION_MSG in result.output # Check multiple - dta1 = "datasets/census.dta" - dta2 = "datasets/auto.dta" - dta3 = "datasets/lifeexp.dta" + dta1 = f"{DATAPATH}/census.dta" + dta2 = f"{DATAPATH}/auto.dta" + dta3 = f"{DATAPATH}/lifeexp.dta" result = runner.invoke( wbstata, [