convoviz 0.2.11__tar.gz → 0.2.13__tar.gz

{convoviz-0.2.11 → convoviz-0.2.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: convoviz
-Version: 0.2.11
+Version: 0.2.13
 Summary: Get analytics and visualizations on your ChatGPT data!
 Keywords: markdown,chatgpt,openai,visualization,analytics,json,export,data-analysis,obsidian
 Author: Mohamed Cheikh Sidiya
@@ -49,7 +49,7 @@ See examples [here](demo).
 
 ### 2. Install the tool 🛠
 
-Try it without installing using uv ([astral-sh/uv](https://github.com/astral-sh/uv)):
+Try it without installing using uv ([astral-sh/uv](https://github.com/astral-sh/uv?tab=readme-ov-file#highlights)):
 
 ```bash
 uvx convoviz
@@ -108,6 +108,8 @@ The main outputs are:
 - **`Word-Clouds/`**: weekly/monthly/yearly word clouds
 - **`custom_instructions.json`**: extracted custom instructions
 
+![wordcloud example](demo/wordcloud-example.png)
+
 ## Share Your Feedback! 💌
 
 I hope you find this tool useful. I'm continuously looking to improve on this, but I need your help for that.

{convoviz-0.2.11 → convoviz-0.2.13}/README.md

@@ -23,7 +23,7 @@ See examples [here](demo).
 
 ### 2. Install the tool 🛠
 
-Try it without installing using uv ([astral-sh/uv](https://github.com/astral-sh/uv)):
+Try it without installing using uv ([astral-sh/uv](https://github.com/astral-sh/uv?tab=readme-ov-file#highlights)):
 
 ```bash
 uvx convoviz
@@ -82,6 +82,8 @@ The main outputs are:
 - **`Word-Clouds/`**: weekly/monthly/yearly word clouds
 - **`custom_instructions.json`**: extracted custom instructions
 
+![wordcloud example](demo/wordcloud-example.png)
+
 ## Share Your Feedback! 💌
 
 I hope you find this tool useful. I'm continuously looking to improve on this, but I need your help for that.

{convoviz-0.2.11 → convoviz-0.2.13}/convoviz/analysis/graphs.py

@@ -347,7 +347,9 @@ def generate_length_histogram(
         color="#cf222e",
     )
 
-    ax.set_title("Conversation length (user prompts)", fontproperties=font_prop, fontsize=14, pad=14)
+    ax.set_title(
+        "Conversation length (user prompts)", fontproperties=font_prop, fontsize=14, pad=14
+    )
     ax.set_xlabel("User prompts per conversation", fontproperties=font_prop)
     ax.set_ylabel("Conversations", fontproperties=font_prop)
     ax.set_xlim(left=0, right=cap)
@@ -619,7 +621,9 @@ def generate_summary_dashboard(
         locator = mdates.AutoDateLocator(minticks=4, maxticks=10)
         ax_ts.xaxis.set_major_locator(locator)
         ax_ts.xaxis.set_major_formatter(mdates.ConciseDateFormatter(locator))
-        ax_ts.set_title("Monthly activity (user prompts)", fontproperties=font_prop, fontsize=13, pad=10)
+        ax_ts.set_title(
+            "Monthly activity (user prompts)", fontproperties=font_prop, fontsize=13, pad=10
+        )
         ax_ts.set_ylabel("User prompts", fontproperties=font_prop)
         ax_ts.set_xlabel(f"Month ({_tz_label(cfg)})", fontproperties=font_prop)
         _apply_tick_font(ax_ts, font_prop)
@@ -741,11 +745,27 @@ def generate_summary_graphs(
 
     tasks: list[tuple[str, str, Callable[[], Figure]]] = [
         ("Overview", "overview.png", lambda: generate_summary_dashboard(collection, cfg)),
-        ("Activity heatmap", "activity_heatmap.png", lambda: generate_activity_heatmap(collection, cfg)),
-        ("Daily activity", "daily_activity.png", lambda: generate_daily_activity_lineplot(collection, cfg)),
-        ("Monthly activity", "monthly_activity.png", lambda: generate_monthly_activity_barplot(collection, cfg)),
+        (
+            "Activity heatmap",
+            "activity_heatmap.png",
+            lambda: generate_activity_heatmap(collection, cfg),
+        ),
+        (
+            "Daily activity",
+            "daily_activity.png",
+            lambda: generate_daily_activity_lineplot(collection, cfg),
+        ),
+        (
+            "Monthly activity",
+            "monthly_activity.png",
+            lambda: generate_monthly_activity_barplot(collection, cfg),
+        ),
         ("Model usage", "model_usage.png", lambda: generate_model_piechart(collection, cfg)),
-        ("Conversation lengths", "conversation_lengths.png", lambda: generate_length_histogram(collection, cfg)),
+        (
+            "Conversation lengths",
+            "conversation_lengths.png",
+            lambda: generate_length_histogram(collection, cfg),
+        ),
         (
             "Conversation lifetimes",
             "conversation_lifetimes.png",

{convoviz-0.2.11 → convoviz-0.2.13}/convoviz/analysis/wordcloud.py

@@ -1,5 +1,7 @@
 """Word cloud generation for conversation text."""
 
+import os
+from concurrent.futures import ProcessPoolExecutor
 from functools import lru_cache
 from pathlib import Path
 
@@ -110,6 +112,25 @@ def generate_wordcloud(text: str, config: WordCloudConfig) -> Image:
     return result
 
 
+def _generate_and_save_wordcloud(args: tuple[str, str, Path, WordCloudConfig]) -> bool:
+    """Worker function for parallel wordcloud generation.
+
+    Must be at module level for pickling by ProcessPoolExecutor.
+
+    Args:
+        args: Tuple of (text, filename, output_dir, config)
+
+    Returns:
+        True if wordcloud was generated, False if skipped (empty text)
+    """
+    text, filename, output_dir, config = args
+    if not text.strip():
+        return False
+    img = generate_wordcloud(text, config)
+    img.save(output_dir / filename, optimize=True)
+    return True
+
+
 def generate_wordclouds(
     collection: ConversationCollection,
     output_dir: Path,
@@ -119,6 +140,8 @@ def generate_wordclouds(
 ) -> None:
     """Generate word clouds for weekly, monthly, and yearly groupings.
 
+    Uses parallel processing to speed up generation on multi-core systems.
+
     Args:
         collection: Collection of conversations
         output_dir: Directory to save the word clouds
@@ -131,35 +154,43 @@ def generate_wordclouds(
     month_groups = collection.group_by_month()
     year_groups = collection.group_by_year()
 
-    for week, group in tqdm(
-        week_groups.items(),
-        desc="Creating weekly wordclouds 🔡☁️",
-        disable=not progress_bar,
-    ):
+    # Build list of all tasks: (text, filename, output_dir, config)
+    tasks: list[tuple[str, str, Path, WordCloudConfig]] = []
+
+    for week, group in week_groups.items():
         text = group.plaintext("user", "assistant")
-        if text.strip():
-            img = generate_wordcloud(text, config)
-            # Format: 2024-W15.png (ISO week format)
-            img.save(output_dir / f"{week.strftime('%Y-W%W')}.png", optimize=True)
-
-    for month, group in tqdm(
-        month_groups.items(),
-        desc="Creating monthly wordclouds 🔡☁️",
-        disable=not progress_bar,
-    ):
+        # Format: 2024-W15.png (ISO week format)
+        filename = f"{week.strftime('%Y-W%W')}.png"
+        tasks.append((text, filename, output_dir, config))
+
+    for month, group in month_groups.items():
         text = group.plaintext("user", "assistant")
-        if text.strip():
-            img = generate_wordcloud(text, config)
-            # Format: 2024-03-March.png (consistent with folder naming)
-            img.save(output_dir / f"{month.strftime('%Y-%m-%B')}.png", optimize=True)
-
-    for year, group in tqdm(
-        year_groups.items(),
-        desc="Creating yearly wordclouds 🔡☁️",
-        disable=not progress_bar,
-    ):
+        # Format: 2024-03-March.png (consistent with folder naming)
+        filename = f"{month.strftime('%Y-%m-%B')}.png"
+        tasks.append((text, filename, output_dir, config))
+
+    for year, group in year_groups.items():
         text = group.plaintext("user", "assistant")
-        if text.strip():
-            img = generate_wordcloud(text, config)
-            # Format: 2024.png
-            img.save(output_dir / f"{year.strftime('%Y')}.png", optimize=True)
+        # Format: 2024.png
+        filename = f"{year.strftime('%Y')}.png"
+        tasks.append((text, filename, output_dir, config))
+
+    if not tasks:
+        return
+
+    # Determine worker count: use config if set, otherwise half CPU count (min 1)
+    max_workers = config.max_workers
+    if max_workers is None:
+        cpu_count = os.cpu_count() or 2
+        max_workers = max(1, cpu_count // 2)
+
+    # Use parallel processing for speedup on multi-core systems
+    with ProcessPoolExecutor(max_workers=max_workers) as executor:
+        list(
+            tqdm(
+                executor.map(_generate_and_save_wordcloud, tasks),
+                total=len(tasks),
+                desc="Creating wordclouds 🔡☁️",
+                disable=not progress_bar,
+            )
+        )

convoviz-0.2.13/convoviz/assets/stopwords.txt

@@ -0,0 +1 @@
+

{convoviz-0.2.11 → convoviz-0.2.13}/convoviz/config.py

@@ -70,6 +70,7 @@ class WordCloudConfig(BaseModel):
     include_numbers: bool = False
     width: int = 600
     height: int = 600
+    max_workers: int | None = None  # None = use half CPU count
 
 
 class GraphConfig(BaseModel):

{convoviz-0.2.11 → convoviz-0.2.13}/convoviz/interactive.py

@@ -26,6 +26,7 @@ CUSTOM_STYLE = Style(
     ]
 )
 
+
 class _QuestionaryPrompt[T](Protocol):
     def ask(self) -> T | None: ...
 

{convoviz-0.2.11 → convoviz-0.2.13}/convoviz/io/writers.py

@@ -146,9 +146,7 @@ def _generate_month_index(month_dir: Path, year: str, month: str) -> None:
         month: The month folder name (e.g., "03-March")
     """
     month_name = month.split("-", 1)[1] if "-" in month else month
-    files = sorted(
-        [f.name for f in month_dir.glob("*.md") if f.name != "_index.md"]
-    )
+    files = sorted([f.name for f in month_dir.glob("*.md") if f.name != "_index.md"])
 
     lines = [
         f"# {month_name} {year}",

{convoviz-0.2.11 → convoviz-0.2.13}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "convoviz"
-version = "0.2.11"
+version = "0.2.13"
 description = "Get analytics and visualizations on your ChatGPT data!"
 license = "MIT"
 keywords = [
@@ -62,9 +62,9 @@ convoviz = "convoviz.cli:main_entry"
 
 [dependency-groups]
 dev = [
-    "mypy>=1.19.1",
     "pytest>=8.4.2",
     "ruff>=0.14.10",
+    "ty>=0.0.11",
     "types-tqdm>=4.67.0.20250809",
 ]
 
@@ -92,11 +92,8 @@ ignore = [
 [tool.ruff.lint.isort]
 known-first-party = ["convoviz"]
 
-[tool.mypy]
-python_version = "3.12"
-warn_return_any = true
-warn_unused_configs = true
-ignore_missing_imports = true
+[tool.ty.environment]
+python-version = "3.12"
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]

convoviz-0.2.11/convoviz/assets/stopwords.txt

@@ -1,75 +0,0 @@
-# Python
-def
-class
-import
-from
-as
-elif
-finally
-yield
-pass
-lambda
-async
-await
-nonlocal
-assert
-self
-cls
-# JavaScript / TypeScript
-const
-let
-var
-function
-export
-default
-extends
-implements
-static
-# Java / C#
-final
-abstract
-new
-super
-package
-throws
-synchronized
-volatile
-transient
-native
-strictfp
-override
-# C / C++
-unsigned
-signed
-typedef
-sizeof
-extern
-register
-restrict
-inline
-template
-typename
-virtual
-friend
-mutable
-explicit
-operator
-typeid
-# Rust
-mut
-fn
-pub
-mod
-trait
-impl
-where
-loop
-unsafe
-crate
-dyn
-# Go
-func
-chan
-defer
-fallthrough
-goto