edsl 0.1.29.dev6__py3-none-any.whl → 0.1.30.dev1__py3-none-any.whl

edsl/scenarios/FileStore.py

@@ -0,0 +1,140 @@
+from edsl import Scenario
+import base64
+import io
+import tempfile
+from typing import Optional
+
+
+class FileStore(Scenario):
+    def __init__(
+        self,
+        filename: str,
+        binary: Optional[bool] = None,
+        suffix: Optional[str] = None,
+        base64_string: Optional[str] = None,
+    ):
+        self.filename = filename
+        self.suffix = suffix or "." + filename.split(".")[-1]
+        self.binary = binary or False
+        self.base64_string = base64_string or self.encode_file_to_base64_string(
+            filename
+        )
+        super().__init__(
+            {
+                "filename": self.filename,
+                "base64_string": self.base64_string,
+                "binary": self.binary,
+                "suffix": self.suffix,
+            }
+        )
+
+    @classmethod
+    def from_dict(cls, d):
+        return cls(d["filename"], d["binary"], d["suffix"], d["base64_string"])
+
+    def encode_file_to_base64_string(self, file_path):
+        try:
+            # Attempt to open the file in text mode
+            with open(file_path, "r") as text_file:
+                # Read the text data
+                text_data = text_file.read()
+                # Encode the text data to a base64 string
+                base64_encoded_data = base64.b64encode(text_data.encode("utf-8"))
+        except UnicodeDecodeError:
+            # If reading as text fails, open the file in binary mode
+            with open(file_path, "rb") as binary_file:
+                # Read the binary data
+                binary_data = binary_file.read()
+                # Encode the binary data to a base64 string
+                base64_encoded_data = base64.b64encode(binary_data)
+                self.binary = True
+        # Convert the base64 bytes to a string
+        base64_string = base64_encoded_data.decode("utf-8")
+
+        return base64_string
+
+    def open(self):
+        if self.binary:
+            return self.base64_to_file(self["base64_string"], is_binary=True)
+        else:
+            return self.base64_to_text_file(self["base64_string"])
+
+    @staticmethod
+    def base64_to_text_file(base64_string):
+        # Decode the base64 string to bytes
+        text_data_bytes = base64.b64decode(base64_string)
+
+        # Convert bytes to string
+        text_data = text_data_bytes.decode("utf-8")
+
+        # Create a StringIO object from the text data
+        text_file = io.StringIO(text_data)
+
+        return text_file
+
+    @staticmethod
+    def base64_to_file(base64_string, is_binary=True):
+        # Decode the base64 string to bytes
+        file_data = base64.b64decode(base64_string)
+
+        if is_binary:
+            # Create a BytesIO object for binary data
+            return io.BytesIO(file_data)
+        else:
+            # Convert bytes to string for text data
+            text_data = file_data.decode("utf-8")
+            # Create a StringIO object for text data
+            return io.StringIO(text_data)
+
+    def to_tempfile(self, suffix=None):
+        if suffix is None:
+            suffix = self.suffix
+        if self.binary:
+            file_like_object = self.base64_to_file(
+                self["base64_string"], is_binary=True
+            )
+        else:
+            file_like_object = self.base64_to_text_file(self["base64_string"])
+
+        # Create a named temporary file
+        temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=suffix)
+        temp_file.write(file_like_object.read())
+        temp_file.close()
+
+        return temp_file.name
+
+    def push(self, description=None):
+        scenario_version = Scenario.from_dict(self.to_dict())
+        if description is None:
+            description = "File: " + self["filename"]
+        info = scenario_version.push(description=description)
+        return info
+
+    @classmethod
+    def pull(cls, uuid):
+        scenario_version = Scenario.pull(uuid)
+        return cls.from_dict(scenario_version.to_dict())
+
+
+class CSVFileStore(FileStore):
+    def __init__(self, filename):
+        super().__init__(filename, suffix=".csv")
+
+
+class PDFFileStore(FileStore):
+    def __init__(self, filename):
+        super().__init__(filename, suffix=".pdf")
+
+
+if __name__ == "__main__":
+    # file_path = "../conjure/examples/Ex11-2.sav"
+    # fs = FileStore(file_path)
+    # info = fs.push()
+    # print(info)
+
+    # from edsl import Conjure
+
+    # c = Conjure(datafile_name=fs.to_tempfile())
+    f = PDFFileStore("paper.pdf")
+    # print(f.to_tempfile())
+    f.push()

edsl/scenarios/Scenario.py

@@ -1,17 +1,12 @@
 """A Scenario is a dictionary with a key/value to parameterize a question."""
 
+import time
 import copy
 from collections import UserDict
 from typing import Union, List, Optional, Generator
 import base64
 import hashlib
-import json
-
-import fitz  # PyMuPDF
 import os
-import subprocess
-
-from rich.table import Table
 
 from edsl.Base import Base
 from edsl.scenarios.ScenarioImageMixin import ScenarioImageMixin
@@ -217,6 +212,8 @@ class Scenario(Base, UserDict, ScenarioImageMixin, ScenarioHtmlMixin):
 
     @classmethod
     def from_pdf(cls, pdf_path):
+        import fitz  # PyMuPDF
+
         # Ensure the file exists
         if not os.path.exists(pdf_path):
             raise FileNotFoundError(f"The file {pdf_path} does not exist.")
@@ -404,6 +401,8 @@ class Scenario(Base, UserDict, ScenarioImageMixin, ScenarioHtmlMixin):
 
     def rich_print(self) -> "Table":
         """Display an object as a rich table."""
+        from rich.table import Table
+
         table_data, column_names = self._table()
         table = Table(title=f"{self.__class__.__name__} Attributes")
         for column in column_names:

edsl/scenarios/ScenarioList.py

@@ -5,25 +5,22 @@ import csv
 import random
 from collections import UserList, Counter
 from collections.abc import Iterable
-
 from typing import Any, Optional, Union, List
 
-from rich.table import Table
 from simpleeval import EvalWithCompoundTypes
 
-from edsl.scenarios.Scenario import Scenario
 from edsl.Base import Base
 from edsl.utilities.decorators import add_edsl_version, remove_edsl_version
+from edsl.scenarios.Scenario import Scenario
 from edsl.scenarios.ScenarioListPdfMixin import ScenarioListPdfMixin
+from edsl.scenarios.ScenarioListExportMixin import ScenarioListExportMixin
 
-from edsl.utilities.interface import print_scenario_list
 
-from edsl.utilities import is_valid_variable_name
+class ScenarioListMixin(ScenarioListPdfMixin, ScenarioListExportMixin):
+    pass
 
-from edsl.results.ResultsExportMixin import ResultsExportMixin
 
-
-class ScenarioList(Base, UserList, ScenarioListPdfMixin, ResultsExportMixin):
+class ScenarioList(Base, UserList, ScenarioListMixin):
     """Class for creating a list of scenarios to be used in a survey."""
 
     def __init__(self, data: Optional[list] = None):
@@ -157,6 +154,8 @@ class ScenarioList(Base, UserList, ScenarioListPdfMixin, ResultsExportMixin):
             )
         raw_var_name, expression = new_var_string.split("=", 1)
         var_name = raw_var_name.strip()
+        from edsl.utilities.utilities import is_valid_variable_name
+
         if not is_valid_variable_name(var_name):
             raise Exception(f"{var_name} is not a valid variable name.")
 
@@ -376,6 +375,8 @@ class ScenarioList(Base, UserList, ScenarioListPdfMixin, ResultsExportMixin):
         >>> scenario_list[1]['age']
         '25'
         """
+        from edsl.scenarios.Scenario import Scenario
+
         observations = []
         with open(filename, "r") as f:
             reader = csv.reader(f)
@@ -413,12 +414,16 @@ class ScenarioList(Base, UserList, ScenarioListPdfMixin, ResultsExportMixin):
         ScenarioList([Scenario({'name': 'Alice'}), Scenario({'name': 'Bob'})])
 
         """
+        from edsl.scenarios.Scenario import Scenario
+
         return cls([Scenario(s) for s in scenario_dicts_list])
 
     @classmethod
     @remove_edsl_version
     def from_dict(cls, data) -> ScenarioList:
         """Create a `ScenarioList` from a dictionary."""
+        from edsl.scenarios.Scenario import Scenario
+
         return cls([Scenario.from_dict(s) for s in data["scenarios"]])
 
     def code(self) -> str:
@@ -443,6 +448,8 @@ class ScenarioList(Base, UserList, ScenarioListPdfMixin, ResultsExportMixin):
 
     def rich_print(self) -> None:
         """Display an object as a table."""
+        from rich.table import Table
+
         table = Table(title="ScenarioList")
         table.add_column("Index", style="bold")
         table.add_column("Scenario")
@@ -457,6 +464,8 @@ class ScenarioList(Base, UserList, ScenarioListPdfMixin, ResultsExportMixin):
         pretty_labels: Optional[dict] = None,
         filename: str = None,
     ):
+        from edsl.utilities.interface import print_scenario_list
+
         print_scenario_list(self[:max_rows])
 
     def __getitem__(self, key: Union[int, slice]) -> Any:

edsl/scenarios/ScenarioListExportMixin.py

@@ -0,0 +1,32 @@
+"""Mixin class for exporting results."""
+
+from functools import wraps
+from edsl.results.DatasetExportMixin import DatasetExportMixin
+
+
+def to_dataset(func):
+    """Convert the Results object to a Dataset object before calling the function."""
+
+    @wraps(func)
+    def wrapper(self, *args, **kwargs):
+        """Return the function with the Results object converted to a Dataset object."""
+        if self.__class__.__name__ == "ScenarioList":
+            return func(self.to_dataset(), *args, **kwargs)
+        else:
+            raise Exception(
+                f"Class {self.__class__.__name__} not recognized as a Results or Dataset object."
+            )
+
+    return wrapper
+
+
+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

@@ -2,7 +2,7 @@ import fitz  # PyMuPDF
 import os
 import subprocess
 
-from edsl import Scenario
+# from edsl import Scenario
 
 
 class ScenarioListPdfMixin:
@@ -22,6 +22,7 @@ class ScenarioListPdfMixin:
         """
         import tempfile
         from pdf2image import convert_from_path
+        from edsl.scenarios import Scenario
 
         with tempfile.TemporaryDirectory() as output_folder:
             # Convert PDF to images

edsl/scenarios/__init__.py

@@ -1 +1,2 @@
 from edsl.scenarios.Scenario import Scenario
+from edsl.scenarios.ScenarioList import ScenarioList

edsl/surveys/MemoryPlan.py

@@ -3,9 +3,9 @@
 from collections import UserDict, defaultdict
 from typing import Optional
 
-from edsl.surveys.Memory import Memory
-from edsl.prompts.Prompt import Prompt
-from edsl.surveys.DAG import DAG
+# from edsl.surveys.Memory import Memory
+# from edsl.prompts.Prompt import Prompt
+# from edsl.surveys.DAG import DAG
 
 
 class MemoryPlan(UserDict):
@@ -61,6 +61,8 @@ class MemoryPlan(UserDict):
         :param answers: A dictionary of question names to answers.
 
         """
+        from edsl.prompts.Prompt import Prompt
+
         self._check_valid_question_name(focal_question)
 
         if focal_question not in self:
@@ -121,6 +123,7 @@ class MemoryPlan(UserDict):
         self._check_valid_question_name(focal_question)
         self._check_valid_question_name(prior_question)
         self._check_order(focal_question, prior_question)
+        from edsl.surveys.Memory import Memory
 
         if focal_question not in self:
             memory = Memory()
@@ -160,6 +163,8 @@ class MemoryPlan(UserDict):
     @classmethod
     def from_dict(cls, data) -> "MemoryPlan":
         """Deserialize a memory plan from a dictionary."""
+        from edsl.surveys.Memory import Memory
+
         newdata = {}
         for question_name, memory in data["data"].items():
             newdata[question_name] = Memory.from_dict(memory)
@@ -182,13 +187,15 @@ class MemoryPlan(UserDict):
         return new_d
 
     @property
-    def dag(self) -> DAG:
+    def dag(self) -> "DAG":
         """Return a directed acyclic graph of the memory plan.
 
         >>> mp = MemoryPlan.example()
         >>> mp.dag
         {1: {0}}
         """
+        from edsl.surveys.DAG import DAG
+
         d = defaultdict(set)
         for focal_question, memory in self.items():
             for prior_question in memory:

edsl/surveys/Survey.py

@@ -5,9 +5,6 @@ import re
 
 from typing import Any, Generator, Optional, Union, List, Literal, Callable
 
-from rich import print
-from rich.table import Table
-
 from edsl.exceptions import SurveyCreationError, SurveyHasNoRulesError
 from edsl.questions.QuestionBase import QuestionBase
 from edsl.surveys.base import RulePriority, EndOfSurvey
@@ -18,8 +15,8 @@ from edsl.Base import Base
 from edsl.surveys.SurveyExportMixin import SurveyExportMixin
 from edsl.surveys.descriptors import QuestionsDescriptor
 from edsl.surveys.MemoryPlan import MemoryPlan
+
 from edsl.surveys.DAG import DAG
-from edsl.utilities import is_notebook
 from edsl.utilities.decorators import add_edsl_version, remove_edsl_version
 from edsl.surveys.SurveyFlowVisualizationMixin import SurveyFlowVisualizationMixin
 
@@ -563,6 +560,12 @@ class Survey(SurveyExportMixin, SurveyFlowVisualizationMixin, Base):
         job = Jobs(survey=self)
         return job.by(*args)
 
+    def to_jobs(self):
+        """Convert the survey to a Jobs object."""
+        from edsl.jobs.Jobs import Jobs
+
+        return Jobs(survey=self)
+
     def run(self, *args, **kwargs) -> "Results":
         """Turn the survey into a Job and runs it.
 
@@ -957,6 +960,8 @@ class Survey(SurveyExportMixin, SurveyFlowVisualizationMixin, Base):
         │ └───────────────┴─────────────────┴───────────────┴──────────────────────────────────────────────┘ │
         └────────────────────────────────────────────────────────────────────────────────────────────────────┘
         """
+        from rich.table import Table
+
         table = Table(show_header=True, header_style="bold magenta")
         table.add_column("Questions", style="dim")
 

edsl/surveys/SurveyExportMixin.py

@@ -1,8 +1,6 @@
 """A mixin class for exporting surveys to different formats."""
 
-from docx import Document
 from typing import Union, Optional
-import black
 
 
 class SurveyExportMixin:
@@ -29,6 +27,8 @@ class SurveyExportMixin:
 
     def docx(self, filename=None) -> Union["Document", None]:
         """Generate a docx document for the survey."""
+        from docx import Document
+
         doc = Document()
         doc.add_heading("EDSL Survey")
         doc.add_paragraph(f"\n")
@@ -83,6 +83,8 @@ class SurveyExportMixin:
         survey = Survey(questions=[q0, q1, q2])
         ...
         """
+        import black
+
         header_lines = ["from edsl.surveys.Survey import Survey"]
         header_lines.append("from edsl import Question")
         lines = ["\n".join(header_lines)]

edsl/surveys/SurveyFlowVisualizationMixin.py

@@ -1,10 +1,7 @@
 """A mixin for visualizing the flow of a survey."""
 
-import pydot
-import tempfile
-from IPython.display import Image
-from edsl.utilities import is_notebook
 from edsl.surveys.base import RulePriority, EndOfSurvey
+import tempfile
 
 
 class SurveyFlowVisualizationMixin:
@@ -13,6 +10,8 @@ class SurveyFlowVisualizationMixin:
     def show_flow(self, filename: str = None):
         """Create an image showing the flow of users through the survey."""
         # Create a graph object
+        import pydot
+
         graph = pydot.Dot(graph_type="digraph")
 
         # Add nodes for each question
@@ -101,8 +100,11 @@ class SurveyFlowVisualizationMixin:
                         on Ubuntu.
                     """
                 )
+            from edsl.utilities.utilities import is_notebook
 
             if is_notebook():
+                from IPython.display import Image
+
                 display(Image(tmp_file.name))
             else:
                 import os

edsl/utilities/__init__.py

@@ -1,22 +1,22 @@
-from edsl.utilities.interface import (
-    print_dict_as_html_table,
-    print_dict_with_rich,
-    print_list_of_dicts_as_html_table,
-    print_table_with_rich,
-    print_public_methods_with_doc,
-    print_list_of_dicts_as_markdown_table,
-)
+# from edsl.utilities.interface import (
+#     print_dict_as_html_table,
+#     print_dict_with_rich,
+#     print_list_of_dicts_as_html_table,
+#     print_table_with_rich,
+#     print_public_methods_with_doc,
+#     print_list_of_dicts_as_markdown_table,
+# )
 
-from edsl.utilities.utilities import (
-    create_valid_var_name,
-    dict_to_html,
-    hash_value,
-    HTMLSnippet,
-    is_notebook,
-    is_gzipped,
-    is_valid_variable_name,
-    random_string,
-    repair_json,
-    shorten_string,
-    time_all_functions,
-)
+# from edsl.utilities.utilities import (
+#     create_valid_var_name,
+#     dict_to_html,
+#     hash_value,
+#     HTMLSnippet,
+#     is_notebook,
+#     is_gzipped,
+#     is_valid_variable_name,
+#     random_string,
+#     repair_json,
+#     shorten_string,
+#     time_all_functions,
+# )