hdsp-jupyter-extension 2.0.10__py3-none-any.whl → 2.0.11__py3-none-any.whl

hdsp_agent_core/knowledge/loader.py

@@ -5,19 +5,19 @@ Keyword matching + regex based library detection for loading appropriate API gui
 (No LLM calls - saves tokens and improves reliability)
 """
 
-from pathlib import Path
-from typing import List, Dict, Optional, Set
 import re
+from pathlib import Path
+from typing import Dict, List, Optional, Set
 
 # Library descriptions (reference)
 LIBRARY_DESCRIPTIONS: Dict[str, str] = {
-    'matplotlib': 'Visualization, graphs, charts, plot, histogram, scatter plot, EDA, data visualization, used with seaborn',
-    'dask': 'Large-scale data processing, pandas replacement, distributed processing, lazy evaluation, dd.read_csv',
-    'polars': 'High-performance DataFrame, pandas replacement, Rust-based, pl.read_csv',
-    'pyspark': 'Spark-based distributed processing, big data, SparkSession',
-    'vaex': 'Large-scale data exploration, out-of-core processing',
-    'modin': 'pandas acceleration, parallel processing',
-    'ray': 'Distributed computing, parallel processing framework',
+    "matplotlib": "Visualization, graphs, charts, plot, histogram, scatter plot, EDA, data visualization, used with seaborn",
+    "dask": "Large-scale data processing, pandas replacement, distributed processing, lazy evaluation, dd.read_csv",
+    "polars": "High-performance DataFrame, pandas replacement, Rust-based, pl.read_csv",
+    "pyspark": "Spark-based distributed processing, big data, SparkSession",
+    "vaex": "Large-scale data exploration, out-of-core processing",
+    "modin": "pandas acceleration, parallel processing",
+    "ray": "Distributed computing, parallel processing framework",
 }
 
 
@@ -29,90 +29,90 @@ class LibraryDetector:
 
     # Explicit library mention patterns (highest priority)
     EXPLICIT_PATTERNS: Dict[str, str] = {
-        r'\bdask\b': 'dask',
-        r'\bpolars\b': 'polars',
-        r'\bpyspark\b': 'pyspark',
-        r'\bvaex\b': 'vaex',
-        r'\bmodin\b': 'modin',
-        r'\bray\b': 'ray',
-        r'\bmatplotlib\b': 'matplotlib',
-        r'\bseaborn\b': 'matplotlib',  # seaborn -> matplotlib guide
-        r'\bplt\.': 'matplotlib',
-        r'\bdd\.read': 'dask',
-        r'\bpl\.read': 'polars',
-        r'\bpl\.DataFrame': 'polars',
+        r"\bdask\b": "dask",
+        r"\bpolars\b": "polars",
+        r"\bpyspark\b": "pyspark",
+        r"\bvaex\b": "vaex",
+        r"\bmodin\b": "modin",
+        r"\bray\b": "ray",
+        r"\bmatplotlib\b": "matplotlib",
+        r"\bseaborn\b": "matplotlib",  # seaborn -> matplotlib guide
+        r"\bplt\.": "matplotlib",
+        r"\bdd\.read": "dask",
+        r"\bpl\.read": "polars",
+        r"\bpl\.DataFrame": "polars",
     }
 
     # Keyword scores per library (0.0 ~ 1.0)
     KEYWORD_SCORES: Dict[str, Dict[str, float]] = {
-        'dask': {
-            '대용량': 0.7,
-            'big data': 0.7,
-            'bigdata': 0.7,
-            '빅데이터': 0.7,
-            'lazy': 0.8,
-            'lazy evaluation': 0.9,
-            'out-of-core': 0.9,
-            'out of core': 0.9,
-            '분산 처리': 0.6,
-            'distributed': 0.6,
-            'parallel dataframe': 0.8,
-            '병렬 데이터프레임': 0.8,
+        "dask": {
+            "대용량": 0.7,
+            "big data": 0.7,
+            "bigdata": 0.7,
+            "빅데이터": 0.7,
+            "lazy": 0.8,
+            "lazy evaluation": 0.9,
+            "out-of-core": 0.9,
+            "out of core": 0.9,
+            "분산 처리": 0.6,
+            "distributed": 0.6,
+            "parallel dataframe": 0.8,
+            "병렬 데이터프레임": 0.8,
         },
-        'polars': {
-            'rust 기반': 0.9,
-            'rust-based': 0.9,
-            'fast dataframe': 0.7,
-            '고성능 dataframe': 0.7,
-            '빠른 데이터프레임': 0.7,
+        "polars": {
+            "rust 기반": 0.9,
+            "rust-based": 0.9,
+            "fast dataframe": 0.7,
+            "고성능 dataframe": 0.7,
+            "빠른 데이터프레임": 0.7,
         },
-        'matplotlib': {
-            '시각화': 0.7,
-            'visualization': 0.7,
-            'visualize': 0.7,
-            'plot': 0.7,
-            'chart': 0.7,
-            'graph': 0.6,
-            '그래프': 0.6,
-            '차트': 0.7,
-            'histogram': 0.8,
-            '히스토그램': 0.8,
-            'scatter': 0.8,
-            '산점도': 0.8,
-            'line plot': 0.8,
-            '라인 플롯': 0.8,
-            'bar chart': 0.8,
-            '막대 그래프': 0.8,
-            'eda': 0.5,
-            '탐색적 데이터 분석': 0.6,
-            'figure': 0.5,
-            'subplot': 0.8,
-            'heatmap': 0.7,
-            '히트맵': 0.7,
+        "matplotlib": {
+            "시각화": 0.7,
+            "visualization": 0.7,
+            "visualize": 0.7,
+            "plot": 0.7,
+            "chart": 0.7,
+            "graph": 0.6,
+            "그래프": 0.6,
+            "차트": 0.7,
+            "histogram": 0.8,
+            "히스토그램": 0.8,
+            "scatter": 0.8,
+            "산점도": 0.8,
+            "line plot": 0.8,
+            "라인 플롯": 0.8,
+            "bar chart": 0.8,
+            "막대 그래프": 0.8,
+            "eda": 0.5,
+            "탐색적 데이터 분석": 0.6,
+            "figure": 0.5,
+            "subplot": 0.8,
+            "heatmap": 0.7,
+            "히트맵": 0.7,
         },
-        'pyspark': {
-            'spark': 0.9,
-            'sparksession': 0.95,
-            'spark session': 0.95,
-            'rdd': 0.9,
-            'hadoop': 0.7,
-            '클러스터': 0.6,
-            'cluster': 0.6,
+        "pyspark": {
+            "spark": 0.9,
+            "sparksession": 0.95,
+            "spark session": 0.95,
+            "rdd": 0.9,
+            "hadoop": 0.7,
+            "클러스터": 0.6,
+            "cluster": 0.6,
         },
-        'vaex': {
-            'vaex': 1.0,
-            'memory mapping': 0.8,
-            '메모리 매핑': 0.8,
+        "vaex": {
+            "vaex": 1.0,
+            "memory mapping": 0.8,
+            "메모리 매핑": 0.8,
         },
-        'modin': {
-            'modin': 1.0,
-            'pandas 가속': 0.8,
-            'pandas acceleration': 0.8,
+        "modin": {
+            "modin": 1.0,
+            "pandas 가속": 0.8,
+            "pandas acceleration": 0.8,
         },
-        'ray': {
-            'ray': 0.9,
-            '분산 컴퓨팅': 0.7,
-            'distributed computing': 0.7,
+        "ray": {
+            "ray": 0.9,
+            "분산 컴퓨팅": 0.7,
+            "distributed computing": 0.7,
         },
     }
 
@@ -123,7 +123,7 @@ class LibraryDetector:
         self,
         request: str,
         available_libraries: List[str],
-        imported_libraries: List[str] = None
+        imported_libraries: List[str] = None,
     ) -> List[str]:
         """
         Detect required libraries from user request.
@@ -141,7 +141,9 @@ class LibraryDetector:
 
         # Step 1: Explicit pattern matching (highest priority)
         for pattern, lib in self.EXPLICIT_PATTERNS.items():
-            if lib in available_libraries and re.search(pattern, request, re.IGNORECASE):
+            if lib in available_libraries and re.search(
+                pattern, request, re.IGNORECASE
+            ):
                 detected.add(lib)
 
         # Step 2: Keyword scoring
@@ -162,8 +164,8 @@ class LibraryDetector:
             for lib in imported_libraries:
                 lib_lower = lib.lower()
                 # seaborn -> matplotlib
-                if lib_lower == 'seaborn' and 'matplotlib' in available_libraries:
-                    detected.add('matplotlib')
+                if lib_lower == "seaborn" and "matplotlib" in available_libraries:
+                    detected.add("matplotlib")
                 elif lib_lower in available_libraries:
                     detected.add(lib_lower)
 
@@ -183,7 +185,7 @@ def get_library_detector() -> LibraryDetector:
 
 
 # LLM library detection prompt
-LIBRARY_DETECTION_PROMPT = '''Analyze the user's request and determine which libraries to use for code generation.
+LIBRARY_DETECTION_PROMPT = """Analyze the user's request and determine which libraries to use for code generation.
 
 ## Available Library API Guides:
 {library_list}
@@ -205,7 +207,7 @@ LIBRARY_DETECTION_PROMPT = '''Analyze the user's request and determine which lib
 {{"libraries": ["library1", "library2"]}}
 
 Empty array is also valid: {{"libraries": []}}
-'''
+"""
 
 
 class KnowledgeBase:
@@ -216,7 +218,7 @@ class KnowledgeBase:
             self.knowledge_dir = Path(knowledge_dir)
         else:
             # Default path: knowledge/libraries
-            self.knowledge_dir = Path(__file__).parent / 'libraries'
+            self.knowledge_dir = Path(__file__).parent / "libraries"
 
         self._cache: Dict[str, str] = {}
 
@@ -225,19 +227,19 @@ class KnowledgeBase:
         available = self.list_available_libraries()
         lines = []
         for lib in available:
-            desc = LIBRARY_DESCRIPTIONS.get(lib, 'Other library')
+            desc = LIBRARY_DESCRIPTIONS.get(lib, "Other library")
             lines.append(f"- **{lib}**: {desc}")
         return "\n".join(lines)
 
-    def get_detection_prompt(self, request: str, imported_libraries: List[str] = None) -> str:
+    def get_detection_prompt(
+        self, request: str, imported_libraries: List[str] = None
+    ) -> str:
         """Generate LLM library detection prompt"""
         library_list = self.get_library_list_for_prompt()
         imported = ", ".join(imported_libraries) if imported_libraries else "None"
 
         return LIBRARY_DETECTION_PROMPT.format(
-            library_list=library_list,
-            request=request,
-            imported_libraries=imported
+            library_list=library_list, request=request, imported_libraries=imported
         )
 
     def load_library_guide(self, library: str) -> Optional[str]:
@@ -255,9 +257,9 @@ class KnowledgeBase:
             return self._cache[library]
 
         # Load file
-        file_path = self.knowledge_dir / f'{library}.md'
+        file_path = self.knowledge_dir / f"{library}.md"
         if file_path.exists():
-            content = file_path.read_text(encoding='utf-8')
+            content = file_path.read_text(encoding="utf-8")
             self._cache[library] = content
             return content
 
@@ -274,7 +276,7 @@ class KnowledgeBase:
             Combined guide string
         """
         if not libraries:
-            return ''
+            return ""
 
         guides = []
         for lib in sorted(libraries):
@@ -283,7 +285,7 @@ class KnowledgeBase:
                 guides.append(f"## {lib.upper()} Library API Guide\n\n{guide}")
 
         if not guides:
-            return ''
+            return ""
 
         return "\n\n---\n\n".join(guides)
 
@@ -300,7 +302,7 @@ class KnowledgeBase:
         knowledge = self.load_libraries_knowledge(libraries)
 
         if not knowledge:
-            return ''
+            return ""
 
         return f"""
 ## 📚 Library API Reference (MUST follow!)
@@ -317,7 +319,7 @@ Follow the API usage in the guides below. Avoid ❌ incorrect code and use ✅ c
         if not self.knowledge_dir.exists():
             return []
 
-        return [f.stem for f in self.knowledge_dir.glob('*.md')]
+        return [f.stem for f in self.knowledge_dir.glob("*.md")]
 
 
 # Singleton instance