Add tidying-a-file.rst to tutorial section to walk users

through an example of test driven data-wrangling.

docs/_static/test_users.py

@@ -0,0 +1,26 @@
+import pytest
+from datatest import working_directory
+from datatest import Selector
+from datatest import validate
+
+
+@pytest.fixture(scope='module')
+@working_directory(__file__)
+def users():
+    return Selector('users.csv')
+
+
+def test_columns(users):
+    validate(users.fieldnames, {'user_id', 'active'})
+
+
+def test_user_id(users):
+
+    def is_wellformed(x):  # <- Helper function.
+        return x[:-1].isdigit() and x[-1:].isupper()
+
+    validate(users('user_id'), is_wellformed)
+
+
+def test_active(users):
+    validate(users({'active'}), {'Y', 'N'})

docs/_static/test_users_unit.py

@@ -0,0 +1,25 @@
+from datatest import working_directory
+from datatest import Selector
+from datatest import DataTestCase
+
+
+def setUpModule():
+    global users
+    with working_directory(__file__):
+        users = Selector('users.csv')
+
+
+class TestUserData(DataTestCase):
+
+    def test_columns(self):
+        self.assertValid(users.fieldnames, {'user_id', 'active'})
+
+    def test_user_id(self):
+
+        def is_wellformed(x):  # <- Helper function.
+            return x[:-1].isdigit() and x[-1:].isupper()
+
+        self.assertValid(users('user_id'), is_wellformed)
+
+    def test_active(self):
+        self.assertValid(users({'active'}), {'Y', 'N'})

docs/_static/users.csv

@@ -0,0 +1,121 @@
+USER_ID,ACTIVE
+0999F,Y
+1000C,Y
+1001C,n
+1002A,n
+1003C,Y
+1004E,Y
+1005H,Y
+1006E,n
+1007H,Y
+1008A,Y
+1009F,n
+1010D,n
+1011H,Y
+1012H,Y
+1013E,Y
+1014D,Y
+1015C,Y
+1016H,Y
+1017G,Y
+1018A,Y
+1019H,Y
+1020E,Y
+1021H,n
+1022A,n
+1023B,Y
+1024D,n
+1025C,Y
+1026B,Y
+1027H,Y
+1028B,n
+1029A,n
+1030H,n
+1031A,n
+1032G,y
+1033H,y
+1034F,y
+1035F,n
+1036E,y
+1037E,y
+1038G,y
+1039G,y
+1040A,n
+1041A,Y
+1042H,Y
+1043B,Y
+1044G,n
+1045A,n
+1046A,Y
+1047H,Y
+1048D,n
+1049A,n
+1050H,n
+1051A,n
+1052E,Y
+1053A,Y
+1054G,Y
+1055C,Y
+1056a,Y
+1057F,Y
+1058D,Y
+1059H,Y
+1060A,YES
+1061D,YES
+1062E,NO
+1063C,NO
+1064H,YES
+1065A,YES
+1066F,YES
+1067A,YES
+1068F,YES
+1069D,YES
+1070H,YES
+1071E,YES
+1072G,YES
+1073B,YES
+1074B,NO
+1075B,Y
+1076A,Y
+1077A,n
+1078H,Y
+1079C,Y
+1080F,Y
+1081B,n
+1082F,Y
+1083F,Y
+1084F,n
+1085H,n
+1086G,Y
+1087C,Y
+1088A,Y
+1089A,Y
+1090E,Y
+1091B,n
+1092C,Y
+1093G,n
+1094B,n
+1095C,Y
+1096A,n
+1097E,Y
+1098C,Y
+1099b,n
+1100G,n
+1101B,Y
+1102C,Y
+1103A,Y
+1104H,Y
+1105H,Y
+1106A,n
+1107E,n
+1108E,Y
+1109G,Y
+1110B,Y
+1111F,n
+1112D,n
+1113B,Y
+1114H,Y
+1115A,Y
+1116B,Y
+1117B,Y
+1118D,n

docs/tutorial/index.rst

@@ -19,3 +19,5 @@ Tutorials
 
     introduction
     querying-data
+    Tidying a File <tidying-a-file.rst>
+