edsl 0.1.39__py3-none-any.whl → 0.1.39.dev1__py3-none-any.whl

edsl/scenarios/ScenarioListExportMixin.py

@@ -27,6 +27,13 @@ def decorate_methods_from_mixin(cls, mixin_cls):
     return cls
 
 
+# def decorate_all_methods(cls):
+#     for attr_name, attr_value in cls.__dict__.items():
+#         if callable(attr_value):
+#             setattr(cls, attr_name, to_dataset(attr_value))
+#     return cls
+
+
 # @decorate_all_methods
 class ScenarioListExportMixin(DatasetExportMixin):
     """Mixin class for exporting Results objects."""

edsl/scenarios/ScenarioListPdfMixin.py

@@ -1,9 +1,22 @@
+import fitz  # PyMuPDF
 import os
-import re
 import copy
-import atexit
-import tempfile
 import subprocess
+import requests
+import tempfile
+import os
+
+# import urllib.parse as urlparse
+from urllib.parse import urlparse
+
+# from edsl import Scenario
+
+import requests
+import re
+import tempfile
+import os
+import atexit
+from urllib.parse import urlparse, parse_qs
 
 
 class GoogleDriveDownloader:
@@ -12,8 +25,6 @@ class GoogleDriveDownloader:
 
     @classmethod
     def fetch_from_drive(cls, url, filename=None):
-        import requests
-
         # Extract file ID from the URL
         file_id = cls._extract_file_id(url)
         if not file_id:
@@ -56,8 +67,6 @@ class GoogleDriveDownloader:
 
     @staticmethod
     def _extract_file_id(url):
-        from urllib.parse import urlparse, parse_qs
-
         # Try to extract file ID from '/file/d/' format
         file_id_match = re.search(r"/d/([a-zA-Z0-9-_]+)", url)
         if file_id_match:
@@ -83,8 +92,6 @@ class GoogleDriveDownloader:
 
 def fetch_and_save_pdf(url, filename):
     # Send a GET request to the URL
-    import requests
-
     response = requests.get(url)
 
     # Check if the request was successful
@@ -107,6 +114,11 @@ def fetch_and_save_pdf(url, filename):
     return temp_file_path
 
 
+# Example usage:
+# url = "https://example.com/sample.pdf"
+# fetch_and_save_pdf(url, "sample.pdf")
+
+
 class ScenarioListPdfMixin:
     @classmethod
     def from_pdf(cls, filename_or_url, collapse_pages=False):
@@ -139,8 +151,6 @@ class ScenarioListPdfMixin:
 
     @staticmethod
     def is_url(string):
-        from urllib.parse import urlparse
-
         try:
             result = urlparse(string)
             return all([result.scheme, result.netloc])
@@ -179,8 +189,7 @@ class ScenarioListPdfMixin:
 
     @staticmethod
     def extract_text_from_pdf(pdf_path):
-        from edsl.scenarios.Scenario import Scenario
-        import fitz  # PyMuPDF
+        from edsl import Scenario
 
         # TODO: Add test case
         # Ensure the file exists
@@ -234,6 +243,19 @@ class ScenarioListPdfMixin:
 
 
 if __name__ == "__main__":
-    import doctest
+    pass
+
+    # from edsl import ScenarioList
+
+    # class ScenarioListNew(ScenarioList, ScenaroListPdfMixin):
+    #     pass
+
+    # #ScenarioListNew.create_hello_world_pdf('hello_world')
+    # #scenarios = ScenarioListNew.from_pdf('hello_world.pdf')
+    # #print(scenarios)
 
-    doctest.testmod()
+    # from edsl import ScenarioList, QuestionFreeText
+    # homo_silicus = ScenarioList.from_pdf('w31122.pdf')
+    # q = QuestionFreeText(question_text = "What is the key point of the text in {{ text }}?", question_name = "key_point")
+    # results = q.by(homo_silicus).run(progress_bar = True)
+    # results.select('scenario.page', 'answer.key_point').order_by('page').print()

edsl/scenarios/__init__.py

@@ -1,3 +1,4 @@
 from edsl.scenarios.Scenario import Scenario
 from edsl.scenarios.ScenarioList import ScenarioList
-from edsl.scenarios.FileStore import FileStore
+
+# from edsl.scenarios.FileStore import FileStore

edsl/study/ObjectEntry.py

@@ -1,7 +1,7 @@
 import time
 import webbrowser
 from typing import Any, Dict, Optional, Type
-from edsl.questions.QuestionBase import QuestionBase
+from edsl import QuestionBase
 from edsl.Base import RegisterSubclassesMeta
 
 

edsl/study/SnapShot.py

@@ -32,7 +32,7 @@ class SnapShot:
         {'Cache': <class 'edsl.data.Cache.Cache'>}
         """
         from edsl.Base import RegisterSubclassesMeta
-        from edsl.questions.QuestionBase import QuestionBase
+        from edsl import QuestionBase
 
         all_edsl_objects = RegisterSubclassesMeta.get_registry()
 

edsl/study/Study.py

@@ -7,9 +7,7 @@ import socket
 from datetime import datetime
 from typing import Dict, Optional, Union
 from uuid import UUID, uuid4
-
-from edsl.data.Cache import Cache
-from edsl import set_session_cache, unset_session_cache
+from edsl import Cache, set_session_cache, unset_session_cache
 from edsl.utilities.utilities import dict_hash
 from edsl.study.ObjectEntry import ObjectEntry
 from edsl.study.ProofOfWork import ProofOfWork
@@ -407,7 +405,7 @@ class Study:
 
         study_file = tempfile.NamedTemporaryFile()
         with cls(filename=study_file.name, verbose=verbose) as study:
-            from edsl.questions.QuestionFreeText import QuestionFreeText
+            from edsl import QuestionFreeText
 
             q = QuestionFreeText.example(randomize=randomize)
         return study
@@ -466,7 +464,7 @@ class Study:
     def push(self) -> dict:
         """Push the objects to coop."""
 
-        from edsl.coop.coop import Coop
+        from edsl import Coop
 
         coop = Coop()
         return coop.create(self, description=self.description)
@@ -519,3 +517,12 @@ if __name__ == "__main__":
     import doctest
 
     doctest.testmod(optionflags=doctest.ELLIPSIS)
+
+    # with Study(name = "cool_study") as study:
+    #      from edsl import QuestionFreeText
+    #      q = QuestionFreeText.example()
+
+    # assert len(study.objects) == 1
+
+    # print(study.versions())
+    # {'q': [ObjectEntry(variable_name='q', object=Question('free_text', question_name = """how_are_you""", question_text = """How are you?"""), description='Question name: how_are_you', coop_info=None, created_at=1720276402.561273, edsl_class_name='QuestionFreeText')]}

edsl/surveys/Rule.py

@@ -21,13 +21,13 @@ import ast
 import random
 from typing import Any, Union, List
 
-
-# from rich import print
+from jinja2 import Template
+from rich import print
 from simpleeval import EvalWithCompoundTypes
 
 from edsl.exceptions.surveys import SurveyError
 
-from edsl.exceptions.surveys import (
+from edsl.exceptions import (
     SurveyRuleCannotEvaluateError,
     SurveyRuleCollectionHasNoRulesAtNodeError,
     SurveyRuleRefersToFutureStateError,
@@ -37,7 +37,7 @@ from edsl.exceptions.surveys import (
 )
 from edsl.surveys.base import EndOfSurvey
 from edsl.utilities.ast_utilities import extract_variable_names
-from edsl.utilities.remove_edsl_version import remove_edsl_version
+from edsl.utilities.decorators import add_edsl_version, remove_edsl_version
 
 
 class QuestionIndex:
@@ -253,7 +253,6 @@ class Rule:
         ...
         edsl.exceptions.surveys.SurveyRuleCannotEvaluateError...
         """
-        from jinja2 import Template
 
         def substitute_in_answers(expression, current_info_env):
             """Take the dictionary of answers and substitute them into the expression."""

edsl/surveys/RuleCollection.py

@@ -1,17 +1,20 @@
 """A collection of rules for a survey."""
 
 from typing import List, Union, Any, Optional
-from collections import defaultdict, UserList, namedtuple
+from collections import defaultdict, UserList
 
-from edsl.exceptions.surveys import (
+from edsl.exceptions import (
     SurveyRuleCannotEvaluateError,
     SurveyRuleCollectionHasNoRulesAtNodeError,
 )
-
+from edsl.utilities.interface import print_table_with_rich
 from edsl.surveys.Rule import Rule
 from edsl.surveys.base import EndOfSurvey
 from edsl.surveys.DAG import DAG
 
+# from graphlib import TopologicalSorter
+
+from collections import namedtuple
 
 NextQuestion = namedtuple(
     "NextQuestion", "next_q, num_rules_found, expressions_evaluating_to_true, priority"
@@ -43,24 +46,6 @@ class RuleCollection(UserList):
         """
         return f"RuleCollection(rules={self.data}, num_questions={self.num_questions})"
 
-    def to_dataset(self):
-        """Return a Dataset object representation of the RuleCollection object."""
-        from edsl.results.Dataset import Dataset
-
-        keys = ["current_q", "expression", "next_q", "priority", "before_rule"]
-        rule_list = {}
-        for rule in sorted(self, key=lambda r: r.current_q):
-            for k in keys:
-                rule_list.setdefault(k, []).append(getattr(rule, k))
-
-        return Dataset([{k: v} for k, v in rule_list.items()])
-
-    def _repr_html_(self):
-        """Return an HTML representation of the RuleCollection object."""
-        from edsl.results.Dataset import Dataset
-
-        return self.to_dataset()._repr_html_()
-
     def to_dict(self, add_edsl_version=True):
         """Create a dictionary representation of the RuleCollection object."""
         return {
@@ -121,7 +106,12 @@ class RuleCollection(UserList):
         │ 1         │ q1 == 'no'  │ 2      │ 1        │ False       │
         └───────────┴─────────────┴────────┴──────────┴─────────────┘
         """
-        return self.to_dataset()
+        keys = ["current_q", "expression", "next_q", "priority", "before_rule"]
+        rule_list = []
+        for rule in sorted(self, key=lambda r: r.current_q):
+            rule_list.append({k: getattr(rule, k) for k in keys})
+
+        print_table_with_rich(rule_list)
 
     def skip_question_before_running(self, q_now: int, answers: dict[str, Any]) -> bool:
         """Determine if a question should be skipped before running the question.
@@ -193,6 +183,17 @@ class RuleCollection(UserList):
         NextQuestion(next_q=3, num_rules_found=2, expressions_evaluating_to_true=1, priority=1)
 
         """
+        # # is this the first question? If it is, we need to check if it should be skipped.
+        # if q_now == 0:
+        #     if self.skip_question_before_running(q_now, answers):
+        #         return NextQuestion(
+        #             next_q=q_now + 1,
+        #             num_rules_found=0,
+        #             expressions_evaluating_to_true=0,
+        #             priority=-1,
+        #         )
+
+        # breakpoint()
         expressions_evaluating_to_true = 0
         next_q = None
         highest_priority = -2  # start with -2 to 'pick up' the default rule added
@@ -214,6 +215,7 @@ class RuleCollection(UserList):
                 f"No rules found for question {q_now}"
             )
 
+        # breakpoint()
         ## Now we need to check if the *next question* has any 'before; rules that we should follow
         for rule in self.applicable_rules(next_q, before_rule=True):
             if rule.evaluate(answers):  # rule evaluates to True
@@ -258,7 +260,8 @@ class RuleCollection(UserList):
             [2, 3]
 
         """
-        # If it's the end of the survey, all questions between the start_q and the end of the survey now depend on the start_q
+        # If it's the end of the survey, all questions between the start_q and the end of the survey
+        # now depend on the start_q
         if end_q == EndOfSurvey:
             if self.num_questions is None:
                 raise ValueError(
@@ -378,8 +381,7 @@ class RuleCollection(UserList):
 
 
 if __name__ == "__main__":
+    # pass
     import doctest
 
     doctest.testmod(optionflags=doctest.ELLIPSIS)
-
-    print(RuleCollection.example()._repr_html_())