bm-preprocessing 0.2.1__tar.gz → 0.3.0__tar.gz

bm_preprocessing-0.3.0/.gitignore

@@ -0,0 +1,24 @@
+# Python
+__pycache__/
+*.py[cod]
+*.egg-info/
+dist/
+build/
+*.egg
+
+# Virtual environment
+.venv/
+
+# IDE
+.vscode/
+.idea/
+
+# Generated images
+*.png
+
+# OS files
+Thumbs.db
+.DS_Store
+
+# UV
+uv.lock

{bm_preprocessing-0.2.1 → bm_preprocessing-0.3.0}/PKG-INFO

@@ -1,9 +1,12 @@
 Metadata-Version: 2.4
 Name: bm-preprocessing
-Version: 0.2.1
+Version: 0.3.0
 Summary: A package to preprocess text data
 Requires-Python: >=3.8
 Requires-Dist: build>=1.2.2.post1
+Requires-Dist: graphviz>=0.20.3
+Requires-Dist: matplotlib>=3.7.5
+Requires-Dist: pandas>=2.0.3
 Requires-Dist: twine>=6.1.0
 Description-Content-Type: text/markdown
 

bm_preprocessing-0.3.0/USAGE.md

@@ -0,0 +1,96 @@
+# bm-preprocessing Usage Guide
+
+## Installation
+
+```bash
+pip install bm-preprocessing
+```
+
+---
+
+## Usage in Python File
+
+Create a file `example.py`:
+
+```python
+# Import modules
+from bm_preprocessing.IR import all
+from bm_preprocessing.DM import apriori, hash, hunts, hunts_test, preprocessing
+
+# Print the source code
+print("=== IR All Module ===")
+print(all)
+
+print("\n=== DM Apriori Module ===")
+print(apriori)
+
+print("\n=== DM Hash Module ===")
+print(hash)
+
+print("\n=== DM Hunts Module ===")
+print(hunts)
+
+print("\n=== DM Hunts Test Module ===")
+print(hunts_test)
+
+print("\n=== DM Preprocessing Module ===")
+print(preprocessing)
+```
+
+Run it:
+```bash
+python example.py
+```
+
+---
+
+## Usage in Terminal (Interactive Python)
+
+```bash
+python
+```
+
+Then in the Python REPL:
+
+```python
+>>> from bm_preprocessing.IR import all
+>>> print(all)
+# Prints entire IR/all.py source code
+
+>>> from bm_preprocessing.DM import apriori
+>>> print(apriori)
+# Prints entire DM/apriori.py source code
+
+>>> from bm_preprocessing.DM import hunts, hunts_test
+>>> print(hunts)
+# Prints entire DM/hunts.py source code
+>>> print(hunts_test)
+# Prints entire DM/hunts_test.py source code
+```
+
+---
+
+## One-liner in Terminal
+
+```bash
+python -c "from bm_preprocessing.IR import all; print(all)"
+python -c "from bm_preprocessing.DM import apriori; print(apriori)"
+python -c "from bm_preprocessing.DM import hash; print(hash)"
+python -c "from bm_preprocessing.DM import hunts; print(hunts)"
+python -c "from bm_preprocessing.DM import hunts_test; print(hunts_test)"
+python -c "from bm_preprocessing.DM import preprocessing; print(preprocessing)"
+```
+
+---
+
+## Available Modules
+
+| Import | Description |
+|--------|-------------|
+| `from bm_preprocessing.IR import all` | Information Retrieval (BM25, TF-IDF, Boolean) |
+| `from bm_preprocessing.DM import all` | Data Mining algorithms |
+| `from bm_preprocessing.DM import apriori` | Apriori algorithm |
+| `from bm_preprocessing.DM import hash` | Hash-based mining |
+| `from bm_preprocessing.DM import hunts` | Hunt's decision tree algorithm |
+| `from bm_preprocessing.DM import hunts_test` | Hunt's decision tree with visualization |
+| `from bm_preprocessing.DM import preprocessing` | Data preprocessing utilities |

{bm_preprocessing-0.2.1 → bm_preprocessing-0.3.0}/pyproject.toml

@@ -4,12 +4,15 @@ build-backend = "hatchling.build"
 
 [project]
 name = "bm-preprocessing"
-version = "0.2.1"
+version = "0.3.0"
 description = "A package to preprocess text data"
 readme = "README.md"
 requires-python = ">=3.8"
 dependencies = [
     "build>=1.2.2.post1",
+    "graphviz>=0.20.3",
+    "matplotlib>=3.7.5",
+    "pandas>=2.0.3",
     "twine>=6.1.0",
 ]
 

{bm_preprocessing-0.2.1 → bm_preprocessing-0.3.0}/src/bm_preprocessing/DM/__init__.py

@@ -3,6 +3,8 @@
 from .all import all
 from .apriori import apriori
 from .hash import hash
+from .hunts import hunts
+from .hunts_test import hunts_test
 from .preprocessing import preprocessing
 
-__all__ = ["all", "apriori", "hash", "preprocessing"]
+__all__ = ["all", "apriori", "hash", "hunts", "hunts_test", "preprocessing"]

{bm_preprocessing-0.2.1 → bm_preprocessing-0.3.0}/src/bm_preprocessing/DM/all.py

@@ -5,22 +5,22 @@ from pathlib import Path
 
 class SourceCodeModule:
     """A class that displays source code when printed."""
-    
+
     def __init__(self, name: str, source_path: Path):
         self.name = name
         self._source_path = source_path
         self._source_code = None
-    
+
     @property
     def source_code(self) -> str:
         """Lazily load source code."""
         if self._source_code is None:
-            self._source_code = self._source_path.read_text(encoding='utf-8')
+            self._source_code = self._source_path.read_text(encoding="utf-8")
         return self._source_code
-    
+
     def __repr__(self) -> str:
         return self.source_code
-    
+
     def __str__(self) -> str:
         return self.source_code
 

{bm_preprocessing-0.2.1 → bm_preprocessing-0.3.0}/src/bm_preprocessing/DM/apriori.py

@@ -5,22 +5,22 @@ from pathlib import Path
 
 class SourceCodeModule:
     """A class that displays source code when printed."""
-    
+
     def __init__(self, name: str, source_path: Path):
         self.name = name
         self._source_path = source_path
         self._source_code = None
-    
+
     @property
     def source_code(self) -> str:
         """Lazily load source code."""
         if self._source_code is None:
-            self._source_code = self._source_path.read_text(encoding='utf-8')
+            self._source_code = self._source_path.read_text(encoding="utf-8")
         return self._source_code
-    
+
     def __repr__(self) -> str:
         return self.source_code
-    
+
     def __str__(self) -> str:
         return self.source_code
 

{bm_preprocessing-0.2.1 → bm_preprocessing-0.3.0}/src/bm_preprocessing/DM/hash.py

@@ -5,22 +5,22 @@ from pathlib import Path
 
 class SourceCodeModule:
     """A class that displays source code when printed."""
-    
+
     def __init__(self, name: str, source_path: Path):
         self.name = name
         self._source_path = source_path
         self._source_code = None
-    
+
     @property
     def source_code(self) -> str:
         """Lazily load source code."""
         if self._source_code is None:
-            self._source_code = self._source_path.read_text(encoding='utf-8')
+            self._source_code = self._source_path.read_text(encoding="utf-8")
         return self._source_code
-    
+
     def __repr__(self) -> str:
         return self.source_code
-    
+
     def __str__(self) -> str:
         return self.source_code
 

bm_preprocessing-0.3.0/src/bm_preprocessing/DM/hunts.py

@@ -0,0 +1,30 @@
+"""Source code loader for DM/hunts.py"""
+
+from pathlib import Path
+
+
+class SourceCodeModule:
+    """A class that displays source code when printed."""
+
+    def __init__(self, name: str, source_path: Path):
+        self.name = name
+        self._source_path = source_path
+        self._source_code = None
+
+    @property
+    def source_code(self) -> str:
+        """Lazily load source code."""
+        if self._source_code is None:
+            self._source_code = self._source_path.read_text(encoding="utf-8")
+        return self._source_code
+
+    def __repr__(self) -> str:
+        return self.source_code
+
+    def __str__(self) -> str:
+        return self.source_code
+
+
+# Get the path to the source file
+_source_file = Path(__file__).parent / "sources" / "hunts.py"
+hunts = SourceCodeModule("DM.hunts", _source_file)

bm_preprocessing-0.3.0/src/bm_preprocessing/DM/hunts_test.py

@@ -0,0 +1,30 @@
+"""Source code loader for DM/hunts_test.py"""
+
+from pathlib import Path
+
+
+class SourceCodeModule:
+    """A class that displays source code when printed."""
+
+    def __init__(self, name: str, source_path: Path):
+        self.name = name
+        self._source_path = source_path
+        self._source_code = None
+
+    @property
+    def source_code(self) -> str:
+        """Lazily load source code."""
+        if self._source_code is None:
+            self._source_code = self._source_path.read_text(encoding="utf-8")
+        return self._source_code
+
+    def __repr__(self) -> str:
+        return self.source_code
+
+    def __str__(self) -> str:
+        return self.source_code
+
+
+# Get the path to the source file
+_source_file = Path(__file__).parent / "sources" / "hunts_test.py"
+hunts_test = SourceCodeModule("DM.hunts_test", _source_file)

{bm_preprocessing-0.2.1 → bm_preprocessing-0.3.0}/src/bm_preprocessing/DM/preprocessing.py

@@ -5,22 +5,22 @@ from pathlib import Path
 
 class SourceCodeModule:
     """A class that displays source code when printed."""
-    
+
     def __init__(self, name: str, source_path: Path):
         self.name = name
         self._source_path = source_path
         self._source_code = None
-    
+
     @property
     def source_code(self) -> str:
         """Lazily load source code."""
         if self._source_code is None:
-            self._source_code = self._source_path.read_text(encoding='utf-8')
+            self._source_code = self._source_path.read_text(encoding="utf-8")
         return self._source_code
-    
+
     def __repr__(self) -> str:
         return self.source_code
-    
+
     def __str__(self) -> str:
         return self.source_code
 

{bm_preprocessing-0.2.1 → bm_preprocessing-0.3.0}/src/bm_preprocessing/DM/sources/all.py

@@ -1,21 +1,21 @@
-from itertools import combinations, chain
 from collections import defaultdict
+from itertools import chain, combinations
 
 min_support = 2
 min_conf = 0.7
 
 transactions = {
-    "T1": {"I1","I2","I4","I5","I6"},
-    "T2": {"I2","I4","I6"},
-    "T3": {"I2","I3"},
-    "T4": {"I1","I2","I4"},
-    "T5": {"I1","I2","I3"},
-    "T6": {"I2","I3"},
-    "T7": {"I1","I3"},
-    "T8": {"I1","I2","I3","I5"},
-    "T9": {"I1","I2","I3"},
-    "T10": {"I1","I2","I4","I5"},
-    "T11": {"I5","I6"}
+    "T1": {"I1", "I2", "I4", "I5", "I6"},
+    "T2": {"I2", "I4", "I6"},
+    "T3": {"I2", "I3"},
+    "T4": {"I1", "I2", "I4"},
+    "T5": {"I1", "I2", "I3"},
+    "T6": {"I2", "I3"},
+    "T7": {"I1", "I3"},
+    "T8": {"I1", "I2", "I3", "I5"},
+    "T9": {"I1", "I2", "I3"},
+    "T10": {"I1", "I2", "I4", "I5"},
+    "T11": {"I5", "I6"},
 }
 
 genL = lambda C: {k: v for k, v in C.items() if v >= min_support}
@@ -85,13 +85,15 @@ for k, v in C.items():
         "Empty" if not v else "\n".join(f"{set(x)} : {y}" for x, y in v.items()),
     )
 for k, v in L.items():
-    print(f"\nL{k}:\n", "Empty" if not v else "\n".join(f"{set(x)} : {v[x]}" for x in v))
+    print(
+        f"\nL{k}:\n", "Empty" if not v else "\n".join(f"{set(x)} : {v[x]}" for x in v)
+    )
 
 print(f"\nAssociation Rules (conf >= {min_conf:.0%}):")
 for a, c, s, conf in rules:
     print(f"{set(a)} => {set(c)} | support: {s:.2f}, confidence: {conf:.2f}")
 
-from itertools import combinations, chain
+from itertools import chain, combinations
 
 transactions = {
     "10": {"A", "C", "D"},

{bm_preprocessing-0.2.1 → bm_preprocessing-0.3.0}/src/bm_preprocessing/DM/sources/apriori.py

@@ -1,11 +1,13 @@
 from collections import defaultdict
 from itertools import combinations
 
+
 def print_table(data, title):
     print(f"\n--- {title} ---")
     for itemset, count in data.items():
         print(f"{itemset}: {count}")
 
+
 C = {}
 L = {}
 
@@ -18,26 +20,26 @@ def generate_candidates(prev_frequent_itemsets, k):
         union_set = set(itemset1).union(set(itemset2))
         if len(union_set) == k:
             candidates.add(tuple(sorted(union_set)))
-            
+
     return sorted(list(candidates))
 
 
 def count_candidates(candidates, transactions):
-    
+
     candidate_count = defaultdict(int)
-    
+
     for candidate in candidates:
         for transaction in transactions.values():
             if all(item in transaction for item in candidate):
                 candidate_count[candidate] += 1
-    
+
     return candidate_count
 
 
 def prune_candidates(candidate_count, min_support, prev_freq_itemsets=None):
 
     filtered_candidates = {}
-    
+
     for itemset, count in candidate_count.items():
 
         if count >= min_support:
@@ -45,7 +47,9 @@ def prune_candidates(candidate_count, min_support, prev_freq_itemsets=None):
                 filtered_candidates[itemset] = count
             else:
                 subsets = combinations(itemset, len(itemset) - 1)
-                if all(tuple(sorted(subset)) in prev_freq_itemsets for subset in subsets):
+                if all(
+                    tuple(sorted(subset)) in prev_freq_itemsets for subset in subsets
+                ):
                     filtered_candidates[itemset] = count
 
     return filtered_candidates
@@ -53,12 +57,14 @@ def prune_candidates(candidate_count, min_support, prev_freq_itemsets=None):
 
 def apriori(transactions, min_support):
 
-    items = sorted(set(item for transaction in transactions.values() for item in transaction))
+    items = sorted(
+        set(item for transaction in transactions.values() for item in transaction)
+    )
     c1_list = [(item,) for item in items]
-    
+
     C[1] = count_candidates(c1_list, transactions)
     L[1] = prune_candidates(C[1], min_support)
-    
+
     print_table(C[1], "Candidate 1-itemsets (C1)")
     print_table(L[1], "Frequent 1-itemsets (L1)")
 
@@ -66,12 +72,12 @@ def apriori(transactions, min_support):
 
     while True:
 
-        candidates = generate_candidates(L[k-1].keys(), k)
+        candidates = generate_candidates(L[k - 1].keys(), k)
         if not candidates:
             break
 
         C[k] = count_candidates(candidates, transactions)
-        L[k] = prune_candidates(C[k], min_support, L[k-1].keys())
+        L[k] = prune_candidates(C[k], min_support, L[k - 1].keys())
 
         if not L[k]:
             print_table(C[k], f"Candidate {k}-itemsets (C{k})")
@@ -99,7 +105,7 @@ def main():
     }
 
     min_support = 2
-    
+
     apriori(transactions, min_support)
 
 

bm_preprocessing-0.3.0/src/bm_preprocessing/DM/sources/data.csv

@@ -0,0 +1,11 @@
+Tid,Home Owner,Marital Status,Annual Income,Default id
+1,Yes,Single,125K,No
+2,No,Married,100K,No
+3,No,Single,70K,No
+4,Yes,Married,120K,No
+5,No,Divorced,95K,Yes
+6,No,Married,60K,No
+7,Yes,Divorced,220K,No
+8,No,Single,85K,Yes
+9,No,Married,75K,No
+10,No,Single,90K,Yes

{bm_preprocessing-0.2.1 → bm_preprocessing-0.3.0}/src/bm_preprocessing/DM/sources/hash.py

@@ -1,14 +1,17 @@
 from collections import defaultdict
 from itertools import combinations
 
+
 def print_table(data, title):
     print(f"\n--- {title} ---")
     for itemset, count in data.items():
         print(f"{itemset}: {count}")
 
+
 C = {}
 L = {}
 
+
 class Bucket:
     def __init__(self):
         self.address: int
@@ -24,26 +27,26 @@ def generate_candidates(prev_frequent_itemsets, k):
         union_set = set(itemset1).union(set(itemset2))
         if len(union_set) == k:
             candidates.add(tuple(sorted(union_set)))
-            
+
     return sorted(list(candidates))
 
 
 def count_candidates(candidates, transactions):
-    
+
     candidate_count = defaultdict(int)
-    
+
     for candidate in candidates:
         for transaction in transactions.values():
             if all(item in transaction for item in candidate):
                 candidate_count[candidate] += 1
-    
+
     return candidate_count
 
 
 def prune_candidates(candidate_count, min_support, prev_freq_itemsets=None):
 
     filtered_candidates = {}
-    
+
     for itemset, count in candidate_count.items():
 
         if count >= min_support:
@@ -51,7 +54,9 @@ def prune_candidates(candidate_count, min_support, prev_freq_itemsets=None):
                 filtered_candidates[itemset] = count
             else:
                 subsets = combinations(itemset, len(itemset) - 1)
-                if all(tuple(sorted(subset)) in prev_freq_itemsets for subset in subsets):
+                if all(
+                    tuple(sorted(subset)) in prev_freq_itemsets for subset in subsets
+                ):
                     filtered_candidates[itemset] = count
 
     return filtered_candidates
@@ -59,12 +64,14 @@ def prune_candidates(candidate_count, min_support, prev_freq_itemsets=None):
 
 def apriori(transactions, min_support):
 
-    items = sorted(set(item for transaction in transactions.values() for item in transaction))
+    items = sorted(
+        set(item for transaction in transactions.values() for item in transaction)
+    )
     c1_list = [(item,) for item in items]
-    
+
     C[1] = count_candidates(c1_list, transactions)
     L[1] = prune_candidates(C[1], min_support)
-    
+
     print_table(C[1], "Candidate 1-itemsets (C1)")
     print_table(L[1], "Frequent 1-itemsets (L1)")
 
@@ -77,7 +84,9 @@ def apriori(transactions, min_support):
 
     buckets = [Bucket(addr) for addr in range(7)]
 
-    items_list = sorted(set(item for transaction in transactions.values() for item in transaction))
+    items_list = sorted(
+        set(item for transaction in transactions.values() for item in transaction)
+    )
     ranks = {item: idx + 1 for idx, item in enumerate(items_list)}
 
     hash_fn = lambda item1, item2: (ranks[item1] * 10 + ranks[item2]) % 7
@@ -91,25 +100,32 @@ def apriori(transactions, min_support):
 
     print("\n--- Hash Table Buckets ---")
     for bucket in buckets:
-        print(f"Address: {bucket.address}, Count: {bucket.count}, Itemsets: {bucket.itemsets}")
-    
+        print(
+            f"Address: {bucket.address}, Count: {bucket.count}, Itemsets: {bucket.itemsets}"
+        )
+
     # Filter
-    L2 = {itemset: bucket.count for bucket in buckets for itemset in bucket.itemsets if bucket.count >= min_support}
+    L2 = {
+        itemset: bucket.count
+        for bucket in buckets
+        for itemset in bucket.itemsets
+        if bucket.count >= min_support
+    }
     print_table(L2, "Frequent 2-itemsets after Hashing (L2)")
 
-    C["2"] = generate_candidates(L[k-1].keys(), k)
+    C["2"] = generate_candidates(L[k - 1].keys(), k)
     L["2"] = L2
 
     k = 3
 
     while True:
 
-        candidates = generate_candidates(L[k-1].keys(), k)
+        candidates = generate_candidates(L[k - 1].keys(), k)
         if not candidates:
             break
 
         C[k] = count_candidates(candidates, transactions)
-        L[k] = prune_candidates(C[k], min_support, L[k-1].keys())
+        L[k] = prune_candidates(C[k], min_support, L[k - 1].keys())
 
         if not L[k]:
             print_table(C[k], f"Candidate {k}-itemsets (C{k})")
@@ -137,7 +153,7 @@ def main():
     }
 
     min_support = 2
-    
+
     apriori(transactions, min_support)