dataset_example.py

# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the BSD-style license found in the
# LICENSE file in the root directory of this source tree.

"""
Dataset for the Constraint Environment.

Three difficulty tiers (easy / medium / hard) with increasing structural
complexity for translating natural-language scheduling constraints into a
JSON-based AST DSL.

day_names = ["Mon", "Tue", "Wed", "Thr", "Fri", "Sat"]


slot_names = [
    "9:00", "10:00", "11:00", "12:00",
    "BREAK",
    "2:00", "3:00", "4:00", "5:00"
]

"""
dataset = {
    # ------------------------------------------------------------------
    # EASY
    # ------------------------------------------------------------------
    "easy": [
        {
            "prompt": "The branch CS must not have classes on Wednesday and on 12:00. ",
            "target_ast":
            {
                "type": "hard",
                "name": "cs_department_meeting",
                "forall": [
                    {"b": "branches"},
                    {"sub": {"subjects": "b"}},
                    {"d": "days"},
                    {"s": "slots"}
                ],
                "where": {
                    "operator": "AND",
                    "left": {
                        "operator": "==",
                        "left": {"name":"b"},
                        "right": "CS"
                    },
                    "right": {
                        "operator": "AND",
                        "left": {
                            "operator": "==",
                            "left": "d",
                            "right": 2
                        },
                        "right": {
                            "operator": "==",
                            "left": "s",
                            "right": 3
                        }
                    }
                },
                "assert": {
                    "operator": "==",
                    "left": {
                        "target": "schedule",
                        "args": [{"name": "b"}, {"name":"sub" }, "d", "s"]
                    },
                    "right": 0
                }
            }
        },

        {
            "prompt": "'Dr. smith' must not have any class on fridays",
            "target_ast":{
                "type": "hard",
                "name": "dr_smith_friday_off",
                "forall": [
                    {"b": "branches"},
                    {"sub": {"subjects": "b"}},
                    {"s": "slots"}
                ],
                "where": {
                    "operator": "in",
                    "left": "Dr. smith",
                    "right": {"teachers": "sub"}
                },
                "assert": {
                    "operator": "==",
                    "left": {
                        "target": "schedule",
                        "args": [{"name": "b"}, {"name":"sub" }, 4, "s"]
                    },
                    "right": 0
                }
            }

    }
        
    ],

    # ------------------------------------------------------------------
    # MEDIUM 
    # ------------------------------------------------------------------
    "medium": [
        {
            "prompt": (
                "Subjects must be equal to their defined frequency"
            ),
            "target_ast": {
                    "type": "hard",
                    "name": "subject_weekly_frequency",
                    "forall": [
                        {"b": "branches"},
                        {"sub": {"subjects": "b"}}
                    ],
                    "assert": {
                        "operator": "==",
                        "left": {
                            "operator": "sum",
                            "over": [
                                {"d": "days"}, 
                                {"s": "slots"}
                            ],
                            "expression": {
                                "target": "schedule",
                                "args": [{"name": "b"}, {"name":"sub" }, "d", "s"]
                            }
                        },
                        "right": {"frequency": "sub"}
                    }
                }
        },
        {
            "prompt": (
                "Each subject must occur at most 1 time per day. "
            ),
            "target_ast": {
                "type": "hard",
                "name": "max_one_occurrence_per_day",
                "forall": [
                    {"b": "branches"},
                    {"sub": {"subjects": "b"}},
                    {"d": "days"}
                ],
                "assert": {
                    "operator": "<=",
                    "left": {
                        "operator": "sum",
                        "over": [
                            {"s": "slots"}
                        ],
                        "expression": {
                            "target": "schedule",
                            "args": [{"name": "b"}, {"name":"sub" }, "d", "s"]
                        }
                    },
                    "right": 1
                }
            }
        },
    ],

    # ------------------------------------------------------------------
    # HARD 
    # ------------------------------------------------------------------
    "hard": [
                {
            "prompt": (
                "No classes should be scheduled on Saturday, except for online classes."
            ),
            "target_ast":{
                "type": "hard",
                "name": "no_classes_on_saturday",
                "forall": [
                    {"b": "branches"},
                    {"sub": {"subjects": "b"}},
                    {"d": "days"},
                    {"s": "slots"}
                ],
                "where": {
                    "operator": "AND",
                    "left":
                        {
                            "operator": "==",
                            "left": "d",
                            "right": 5
                        },
                    "right":
                        {
                            "operator": "!=",
                            "left": {"type": "sub"},
                            "right": "online"
                        }
                    
                },
                "assert": {
                    "operator": "==",
                    "left": {
                        "target": "schedule",
                        "args": [{"name": "b"}, {"name":"sub" }, "d", "s"]
                    },
                    "right": 0
                }
            }
        },
        {
            "prompt": (
                "Every teacher must teach one class at a time."
            ),
            "target_ast": {
                    "type": "hard",
                    "name": "teacher_no_double_booking",
                    "forall": [
                        {"teacher": "teachers"},
                        {"d": "days"},
                        {"t": "slots"}
                    ],
                    "assert": {
                        "operator": "<=",
                        "left": {
                            "operator": "sum",
                            "over": [
                                {"b": "branches"},
                                {"sub": {"subjects": "b"}}
                            ],
                            "expression": {
                                "target": "occupies_teacher",
                                "args": ["b", "sub", "teacher", "d", "t"]
                            }
                        },
                        "right": 1
                    }
            },
        },

       
    ],
}


















# dataset = {
#     # ------------------------------------------------------------------
#     # EASY – single quantifier, no WHERE clause, direct assert
#     # ------------------------------------------------------------------
#     "easy": [
#         {
#             "prompt": (
#                 "No classes should be scheduled on Saturday."
#             ),
#             "target_ast": {
#                 "type": "hard",
#                 "name": "no_saturday_classes",
#                 "forall": [
#                     {"var": "b", "domain": "branches"},
#                     {"var": "sub", "domain": "subjects"},
#                     {"var": "d", "domain": "days"},
#                     {"var": "s", "domain": "slots"},
#                 ],
#                 "where": "d == 5",
#                 "assert": "schedule(b, sub, d, s) == 0",
#             },
#         },
#         {
#             "prompt": (
#                 "Every teacher must teach at least one subject."
#             ),
#             "target_ast": {
#                 "type": "soft",
#                 "name": "teacher_teaches_one",
#                 "forall": [
#                     {"var": "t", "domain": "teachers"},
#                 ],
#                 "assert": "SUM(teaches(t, sub)) >= 1",
#             },
#         },
#     ],

#     # ------------------------------------------------------------------
#     # MEDIUM – two quantifiers, WHERE clause, combined assert
#     # ------------------------------------------------------------------
#     "medium": [
#         {
#             "prompt": (
#                 "No non-online classes should be scheduled on Saturday."
#             ),
#             "target_ast": {
#                 "type": "hard",
#                 "name": "no_non_online_saturday",
#                 "forall": [
#                     {"var": "b", "domain": "branches"},
#                     {"var": "sub", "domain": "subjects"},
#                     {"var": "d", "domain": "days"},
#                     {"var": "s", "domain": "slots"},
#                 ],
#                 "where": "subject_type(b, sub) != 'online' AND d == 5",
#                 "assert": "schedule(b, sub, d, s) == 0",
#             },
#         },
#         {
#             "prompt": (
#                 "A teacher cannot be assigned to two different slots at the same time."
#             ),
#             "target_ast": {
#                 "type": "hard",
#                 "name": "no_teacher_time_conflict",
#                 "forall": [
#                     {"var": "t", "domain": "teachers"},
#                     {"var": "d", "domain": "days"},
#                     {"var": "s", "domain": "slots"},
#                 ],
#                 "assert": "COUNT(occupies_teacher(t, d, s)) <= 1",
#             },
#         },
#     ],

#     # ------------------------------------------------------------------
#     # HARD – multiple quantifiers, nested WHERE + AND/OR, minimize
#     # ------------------------------------------------------------------
#     "hard": [
#         {
#             "prompt": (
#                 "Minimize the number of occupied slots for each branch on any given day, "
#                 "but only for subjects that are labelled as practical."
#             ),
#             "target_ast": {
#                 "type": "soft",
#                 "name": "minimize_practical_slots",
#                 "forall": [
#                     {"var": "b", "domain": "branches"},
#                     {"var": "sub", "domain": "subjects"},
#                     {"var": "d", "domain": "days"},
#                     {"var": "s", "domain": "slots"},
#                 ],
#                 "where": "subject_type(b, sub) == 'practical'",
#                 "minimize": "SUM(occupies(b, sub, d, s))",
#             },
#         },
#         {
#             "prompt": (
#                 "No branch may have more than four scheduled slots in a single day, "
#                 "unless a subject is online, in which case it may occupy one extra slot."
#             ),
#             "target_ast": {
#                 "type": "hard",
#                 "name": "daily_slot_cap",
#                 "forall": [
#                     {"var": "b", "domain": "branches"},
#                     {"var": "d", "domain": "days"},
#                     {"var": "sub", "domain": "subjects"},
#                     {"var": "s", "domain": "slots"},
#                 ],
#                 "assert": (
#                     "SUM(schedule(b, sub, d, s)) <= 4 OR "
#                     "(subject_type(b, sub) == 'online' AND SUM(schedule(b, sub, d, s)) <= 5)"
#                 ),
#             },
#         },
#     ],
# }