Changed private GitHub repository links to relative paths.

.gitignore

@@ -102,3 +102,6 @@ venv.bak/
 
 # mypy
 .mypy_cache/
+
+# Jetbrains IDEs
+.idea/

Dataframes/adult.data

@@ -1,3 +1,4 @@
+age, workclass, fnlwgt, education, education-num, marital-status, occupation, relationship, race, sex, capital-gain, capital-loss, hours-per-week, native-country, target
 39, State-gov, 77516, Bachelors, 13, Never-married, Adm-clerical, Not-in-family, White, Male, 2174, 0, 40, United-States, <=50K
 50, Self-emp-not-inc, 83311, Bachelors, 13, Married-civ-spouse, Exec-managerial, Husband, White, Male, 0, 0, 13, United-States, <=50K
 38, Private, 215646, HS-grad, 9, Divorced, Handlers-cleaners, Not-in-family, White, Male, 0, 0, 40, United-States, <=50K

Dataframes/adult.test

@@ -1,4 +1,5 @@
 |1x3 Cross validator
+age, workclass, fnlwgt, education, education-num, marital-status, occupation, relationship, race, sex, capital-gain, capital-loss, hours-per-week, native-country, target
 25, Private, 226802, 11th, 7, Never-married, Machine-op-inspct, Own-child, Black, Male, 0, 0, 40, United-States, <=50K.
 38, Private, 89814, HS-grad, 9, Married-civ-spouse, Farming-fishing, Husband, White, Male, 0, 0, 50, United-States, <=50K.
 28, Local-gov, 336951, Assoc-acdm, 12, Married-civ-spouse, Protective-serv, Husband, White, Male, 0, 0, 40, United-States, >50K.

Execution/adult_50k/adult_50k.sql

@@ -0,0 +1,59 @@
+select count(*) from banking_aws.t_50k_adult_data;
+
+
+
+select b.job, count(b.job) from banking_aws.banking_aws b group by b.job;
+
+
+select b.marital, count(b.marital) from banking_aws.banking_aws b group by b.marital;
+
+
+select * from adult_50k.adult_data;
+
+update adult_50k.adult_test
+set "workclass" = trim("workclass"),
+    "education" = trim("education"),
+    "marital-status" = trim("marital-status"),
+    "occupation" = trim("occupation"),
+    "relationship" = trim("relationship"),
+    "race" = trim("race"),
+    "sex" = trim("sex"),
+    "native-country" = trim("native-country"),
+    "target" = trim("target");
+
+alter table adult_50k.adult_test rename column "education-num" to education_num;
+
+alter table adult_50k.adult_test rename column "marital-status" to marital_status;
+
+alter table adult_50k.adult_test rename column "capital-gain" to capital_gain;
+
+alter table adult_50k.adult_test rename column "capital-loss" to capital_loss;
+
+alter table adult_50k.adult_test rename column "hours-per-week" to hours_per_week;
+
+alter table adult_50k.adult_test rename column "native-country" to native_country;
+
+
+
+
+select count(*) from adult_50k.adult_data;
+
+select a.workclass, count(a.workclass) from adult_50k.adult_data a group by a.workclass;
+
+select a.education, count(a.education) from adult_50k.adult_data a group by a.education;
+
+select a."marital_status", count(a."marital_status") from adult_50k.adult_data a group by a."marital_status";
+
+select a.occupation, count(a.occupation) from adult_50k.adult_data a group by a.occupation;
+
+select a.relationship, count(a.relationship) from adult_50k.adult_data a group by a.relationship;
+
+select a.race, count(a.race) from adult_50k.adult_data a group by a.race;
+
+select a.sex, count(a.sex) from adult_50k.adult_data a group by a.sex;
+
+select a."native_country", count(a."native_country") from adult_50k.adult_data a group by a."native_country";
+
+ALTER TABLE adult_50k.adult_data ADD COLUMN id SERIAL PRIMARY KEY;
+ALTER TABLE adult_50k.adult_test ADD COLUMN id SERIAL PRIMARY KEY;
+

Execution/adult_50k/t1_views.sql

@@ -0,0 +1,55 @@
+
+drop view if exists adult_50k.v_t1_adult_data_target;
+
+create view adult_50k.v_t1_adult_data_target as
+    select id,
+           case when target = '>50K' then 1 else 0 end as target
+    from adult_50k.adult_data;
+
+drop view if exists adult_50k.v_t1_adult_data_dataset;
+
+create view adult_50k.v_t1_adult_data_dataset as
+    select id,
+           age,
+           workclass,
+           fnlwgt,
+           education,
+           education_num,
+           marital_status,
+           occupation,
+           relationship,
+           race,
+           sex,
+           capital_gain,
+           capital_loss,
+           hours_per_week,
+           native_country
+    from adult_50k.adult_data;
+
+
+drop view if exists adult_50k.v_t1_adult_test_target;
+
+create view adult_50k.v_t1_adult_test_target as
+    select id,
+           case when target = '>50K' then 1 else 0 end as target
+    from adult_50k.adult_test;
+
+drop view if exists adult_50k.v_t1_adult_test_dataset;
+
+create view adult_50k.v_t1_adult_test_dataset as
+    select id,
+           age,
+           workclass,
+           fnlwgt,
+           education,
+           education_num,
+           marital_status,
+           occupation,
+           relationship,
+           race,
+           sex,
+           capital_gain,
+           capital_loss,
+           hours_per_week,
+           native_country
+    from adult_50k.adult_test;