~

.vscode/extensions.json

@@ -3,8 +3,8 @@
         "usernamehw.errorlens",
         "njqdev.vscode-python-typehint",
         "ms-python.python",
-        "matangover.mypy",
         "ms-toolsai.jupyter",
-        "charliermarsh.ruff"
+        "charliermarsh.ruff",
+        "matangover.mypy"
     ]
 }

.vscode/settings.json

@@ -12,5 +12,5 @@
     ],
     "python.testing.unittestEnabled": false,
     "python.testing.pytestEnabled": true,
-    "python.analysis.typeCheckingMode": "strict"
+    "mypy.runUsingActiveInterpreter": true
 }

cli.py

@@ -5,19 +5,15 @@
 from shutil import rmtree
 from typing import Any
 
-from controllers.configuration import (
-    get_user_configs,
-    set_model_configs,
-    update_config_file,
-)
+from controllers.configuration import get_user_configs, save_configs, set_model_configs
 from controllers.file_system import (
     conversation_set_from_json,
     conversation_set_from_zip,
     create_n_save_all_weekwise_graphs,
     generate_n_save_all_wordclouds,
     get_bookmarklet_json_filepath,
     save_conversation_set,
-    save_custom_instructions_to_file,
+    save_custom_instructions,
 )
 from models.conversation_set import ConversationSet
 
@@ -113,7 +109,7 @@ def main() -> None:
 
     custom_instructions_filepath: Path = output_folder / "custom_instructions.json"
 
-    save_custom_instructions_to_file(
+    save_custom_instructions(
         conv_set=all_conversations_set,
         filepath=custom_instructions_filepath,
     )
@@ -122,7 +118,7 @@ def main() -> None:
         f"\nDone ✅ ! Check the output 📝 here : {custom_instructions_filepath.as_uri()} 🔗\n",
     )
 
-    update_config_file(user_configs=configs_dict)
+    save_configs(user_configs=configs_dict)
     print("(Settings ⚙️ have been updated and saved to 'config.json')\n")
 
     print(

config.json

@@ -1,6 +1,6 @@
 {
-  "zip_file": null,
-  "output_folder": null,
+  "zip_file": "C:\\Users\\Mohamed.CheikhSidiya\\Downloads\\be0445bfde7aa6cc7beb67a750a167631e75b9fc9a3723eead4d20900dd7c73e-2023-09-29-02-21-47.zip",
+  "output_folder": "C:\\Users\\Mohamed.CheikhSidiya\\Documents\\ChatGPT Data",
   "message": {
     "author_headers": {
       "system": "### System",

controllers/configuration.py

@@ -10,7 +10,7 @@
 from models.node import Node
 from views.prompt_user import prompt_user
 
-from .file_system import default_output_folder, most_recently_downloaded_zip
+from .file_system import default_output_folder, get_most_recently_downloaded_zip
 
 
 def get_user_configs() -> dict[str, Any]:
@@ -21,15 +21,15 @@ def get_user_configs() -> dict[str, Any]:
         default_configs = json_load(fp=file)
 
     if not default_configs["zip_file"]:
-        default_configs["zip_file"] = most_recently_downloaded_zip()
+        default_configs["zip_file"] = get_most_recently_downloaded_zip()
 
     if not default_configs["output_folder"]:
         default_configs["output_folder"] = default_output_folder()
 
     return prompt_user(default_configs=default_configs)
 
 
-def update_config_file(user_configs: dict[str, Any]) -> None:
+def save_configs(user_configs: dict[str, Any]) -> None:
     """Update the config file with the new configuration options."""
     with open(file="config.json", mode="w", encoding="utf-8") as file:
         json_dump(obj=user_configs, fp=file, indent=2)

controllers/data_analysis.py

@@ -3,7 +3,6 @@
 Should ideally only return matplotlib objects, and not deal with the filesystem.
 """
 
-# pyright: reportUnknownMemberType=false
 
 from collections import defaultdict
 from datetime import datetime
@@ -52,7 +51,7 @@ def weekwise_graph_from_timestamps(
     if month_name:
         ax.set_title(label=f"Prompt Count for {month_name}")
 
-    year: str | int = kwargs.get("year", "")
+    year: str = kwargs.get("year", "")
     if year:
         ax.set_title(label=f"Prompt Count for {year}")
 

controllers/file_system.py

@@ -7,15 +7,13 @@
 may be replaced later, with a GUI or something)
 """
 
-# pyright: reportUnknownMemberType=false
-
 
 from datetime import datetime
 from json import dump as json_dump
 from json import load as json_load
 from os import utime
 from pathlib import Path
-from typing import Any
+from typing import Any, Literal
 from zipfile import ZipFile
 
 from tqdm import tqdm
@@ -30,7 +28,7 @@
 
 
 def conversation_set_from_zip(zip_filepath: Path) -> ConversationSet:
-    """Load the conversations from the OpenAI zip export file."""
+    """Load the conversations from a zip file, containing a 'conversations.json' file."""
     with ZipFile(file=zip_filepath, mode="r") as file:
         file.extractall(path=zip_filepath.with_suffix(suffix=""))
 
@@ -45,7 +43,7 @@ def conversation_set_from_zip(zip_filepath: Path) -> ConversationSet:
 
 
 def conversation_set_from_json(json_filepath: Path) -> ConversationSet:
-    """Load the conversations from the bookmarklet json export file."""
+    """Load the conversations from a JSON file, containing an array of conversations."""
     with open(file=json_filepath, encoding="utf-8") as file:
         conversations = json_load(fp=file)
 
@@ -81,7 +79,7 @@ def save_conversation_set(conv_set: ConversationSet, dir_path: Path) -> None:
 def save_weekwise_graph_from_conversation_set(
     conv_set: ConversationSet,
     dir_path: Path,
-    time_period: tuple[datetime, str],
+    time_period: tuple[datetime, Literal["month", "year"]],
     **kwargs: Any,
 ) -> None:
     """Create a weekwise graph and saves it to the folder."""
@@ -140,7 +138,7 @@ def create_n_save_all_weekwise_graphs(
 def save_wordcloud_from_conversation_set(
     conv_set: ConversationSet,
     dir_path: Path,
-    time_period: tuple[datetime, str],
+    time_period: tuple[datetime, Literal["week", "month", "year"]],
     **kwargs: Any,
 ) -> None:
     """Create a wordcloud and saves it to the folder."""
@@ -151,10 +149,8 @@ def save_wordcloud_from_conversation_set(
             file_name = f"{time_period[0].strftime('%Y %B')}.png"
         case "year":
             file_name = f"{time_period[0].strftime('%Y')}.png"
-        case _:
-            raise ValueError("Invalid time period for wordcloud")
 
-    wordcloud_from_conversation_set(conv_set=conv_set, **kwargs).to_file(  # type: ignore
+    wordcloud_from_conversation_set(conv_set=conv_set, **kwargs).to_file(
         filename=dir_path / file_name,
     )
 
@@ -203,7 +199,7 @@ def generate_n_save_all_wordclouds(
         )
 
 
-def save_custom_instructions_to_file(conv_set: ConversationSet, filepath: Path) -> None:
+def save_custom_instructions(conv_set: ConversationSet, filepath: Path) -> None:
     """Create JSON file for custom instructions in the conversation set."""
     with open(file=filepath, mode="w", encoding="utf-8") as file:
         json_dump(obj=conv_set.all_custom_instructions(), fp=file, indent=2)
@@ -215,7 +211,7 @@ def default_output_folder() -> str:
     return str(object=Path.home() / "Documents" / "ChatGPT Data")
 
 
-def most_recently_downloaded_zip() -> str:
+def get_most_recently_downloaded_zip() -> str:
     """Path to the most recently created zip file in the Downloads folder."""
     downloads_folder: Path = Path.home() / "Downloads"
 
@@ -233,15 +229,13 @@ def get_bookmarklet_json_filepath() -> Path | None:
     """Path to the most recently downloaded JSON file, with "bookmarklet" in the name."""
     downloads_folder: Path = Path.home() / "Downloads"
 
-    # Filter out json files with names that do not contain "bookmarklet"
     bookmarklet_json_files: list[Path] = [
         x for x in downloads_folder.glob(pattern="*.json") if "bookmarklet" in x.name
     ]
 
     if not bookmarklet_json_files:
         return None
 
-    # Most recent json file in downloads folder, containing "bookmarklet"
     bookmarklet_json_filepath: Path = max(
         bookmarklet_json_files,
         key=lambda x: x.stat().st_ctime,

models/conversation.py

@@ -8,7 +8,7 @@
 from re import Pattern
 from re import compile as re_compile
 from time import ctime
-from typing import Any
+from typing import Any, Literal
 
 from utils.utils import ensure_closed_code_blocks, replace_latex_delimiters
 
@@ -69,7 +69,9 @@ def _all_message_nodes(self) -> list[Node]:
 
         return nodes
 
-    def _author_nodes(self, author: str) -> list[Node]:
+    def _author_nodes(
+        self, author: Literal["user", "assistant", "system", "tool"]
+    ) -> list[Node]:
         """List of all nodes with the given author role in the conversation. (all branches)"""
         return [
             node
@@ -121,7 +123,9 @@ def message_count(self) -> int:
             if node.message and node.message.author_role() in ("user", "assistant")
         )
 
-    def entire_author_text(self, author: str) -> str:
+    def entire_author_text(
+        self, author: Literal["user", "assistant", "system", "tool"]
+    ) -> str:
         """Entire raw text from the given author role in the conversation. (all branches)
 
         Useful for generating word clouds.
@@ -132,7 +136,9 @@ def entire_author_text(self, author: str) -> str:
             if node.message
         )
 
-    def author_message_timestamps(self, author: str) -> list[float]:
+    def author_message_timestamps(
+        self, author: Literal["user", "assistant", "system", "tool"]
+    ) -> list[float]:
         """List of all message timestamps from the given author role in the conversation.
         (all branches) Useful for generating time series plots.
         """

models/conversation_set.py

@@ -9,7 +9,7 @@
 
 from datetime import datetime
 from time import ctime
-from typing import Any
+from typing import Any, Literal
 
 from .conversation import Conversation
 
@@ -94,7 +94,9 @@ def all_custom_instructions(self) -> list[dict[str, Any]]:
 
         return custom_instructions
 
-    def all_author_message_timestamps(self, author: str) -> list[float]:
+    def all_author_message_timestamps(
+        self, author: Literal["user", "assistant", "system", "tool"]
+    ) -> list[float]:
         """Get a list of all message timestamps, in all conversations in the list."""
         timestamps: list[float] = []
 
@@ -103,7 +105,9 @@ def all_author_message_timestamps(self, author: str) -> list[float]:
 
         return timestamps
 
-    def all_author_text(self, author: str) -> str:
+    def all_author_text(
+        self, author: Literal["user", "assistant", "system", "tool"]
+    ) -> str:
         """Get a string of all text, in all conversations in the list."""
         return "\n".join(
             conversation.entire_author_text(author=author)

views/prompt_user.py

@@ -103,22 +103,18 @@ def prompt_user(default_configs: dict[str, Any]) -> dict[str, Any]:
 
     user_configs["wordcloud"] = {}
 
-    font_names: list[str] = get_font_names()
-
     user_configs["wordcloud"]["font"] = select(
         message="Select the font you want to use for the word clouds :",
-        choices=font_names,
+        choices=get_font_names(),
         default=default_configs["wordcloud"]["font"]
         if default_configs["wordcloud"]["font"]
         else None,
         style=custom_style,
     ).ask()
 
-    colormaps_list: list[str] = get_colormap_names()
-
     user_configs["wordcloud"]["colormap"] = select(
         message="Select the color theme you want to use for the word clouds :",
-        choices=colormaps_list,
+        choices=get_colormap_names(),
         default=default_configs["wordcloud"]["colormap"]
         if default_configs["wordcloud"]["colormap"]
         else None,