bm-preprocessing 1.2.0__tar.gz → 1.3.0__tar.gz

{bm_preprocessing-1.2.0 → bm_preprocessing-1.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: bm-preprocessing
-Version: 1.2.0
+Version: 1.3.0
 Summary: A package to preprocess text data
 Requires-Python: >=3.8
 Requires-Dist: build>=1.2.2.post1

{bm_preprocessing-1.2.0 → bm_preprocessing-1.3.0}/USAGE.md

@@ -8,52 +8,33 @@ pip install bm-preprocessing
 
 ---
 
-## Usage in Python File
+## Usage in Python Scripts
 
-Create a file `example.py`:
+You can directly import and utilize the predefined Data Mining (DM) and Information Retrieval (IR) configurations. Be sure to import from either `bm_preprocessing.DM` or `bm_preprocessing.IR` depending on the subject.
 
 ```python
-# Import modules
-from bm_preprocessing.IR import all, all_vis, eval_metrics, ndd, rel
-from bm_preprocessing.DM import adaboost, apriori, bagging, hash, hunts, hunts_test, id3, id3_test, lib_doc, metrics, preprocessing
+# Import cohesive all-in-one modules
+from bm_preprocessing.IR import all, all_vis
 from bm_preprocessing.DM import all, all_vis
 
-# Print the source code
+# Import DM-specific algorithms
+from bm_preprocessing.DM import adaboost, apriori, bagging, hash, hunts, hunts_test, id3, id3_test, lib_doc, metrics, preprocessing, python_doc
+
+# Import IR-specific algorithms
+from bm_preprocessing.IR import eval_metrics, ndd, rel
+
+# Print the source code directly
 print("=== IR All Module ===")
 print(all)
 
-print("\n=== DM Apriori Module ===")
-print(apriori)
+print("\n=== IR Near Duplicate Documents ===")
+print(ndd)
 
 print("\n=== DM AdaBoost Module ===")
 print(adaboost)
-
-print("\n=== DM Bagging Module ===")
-print(bagging)
-
-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 ID3 Module ===")
-print(id3)
-
-print("\n=== DM ID3 Test Module ===")
-print(id3_test)
-
-print("\n=== DM Metrics Module ===")
-print(metrics)
-
-print("\n=== DM Preprocessing Module ===")
-print(preprocessing)
 ```
 
-Run it:
+Run it locally:
 ```bash
 python example.py
 ```
@@ -62,56 +43,45 @@ python example.py
 
 ## Usage in Terminal (Interactive Python)
 
+If you just need quick access to the source code during an exam or practical, spin up the Python REPL:
+
 ```bash
 python
 ```
 
-Then in the Python REPL:
+Then drop into the REPL to retrieve the code:
 
 ```python
+# Returns entire IR source code cohesive module
 >>> 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
 
+# Returns Data Mining AdaBoost source code
 >>> from bm_preprocessing.DM import adaboost
 >>> print(adaboost)
-# Prints entire DM/adaboost.py source code
-
->>> from bm_preprocessing.DM import bagging
->>> print(bagging)
-# Prints entire DM/bagging.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
-
->>> from bm_preprocessing.DM import id3, id3_test
->>> print(id3)
-# Prints entire DM/id3.py source code
->>> print(id3_test)
-# Prints entire DM/id3_test.py source code
-
->>> from bm_preprocessing.DM import metrics
->>> print(metrics)
-# Prints entire DM/metrics.py source code
+
+# Returns minhash and LSH source code
+>>> from bm_preprocessing.IR import ndd
+>>> print(ndd)
 ```
 
 ---
 
 ## One-liner in Terminal
 
+If you want the terminal to automatically print the file contents for you without entering the REPL, you can execute these one-liners directly in your Bash/PowerShell:
+
+### Information Retrieval (IR)
 ```bash
 python -c "from bm_preprocessing.IR import all; print(all)"
 python -c "from bm_preprocessing.IR import all_vis; print(all_vis)"
-python -c "from bm_preprocessing.IR import eval_metrics; print(eval_metrics)"
 python -c "from bm_preprocessing.IR import ndd; print(ndd)"
 python -c "from bm_preprocessing.IR import rel; print(rel)"
+python -c "from bm_preprocessing.IR import eval_metrics; print(eval_metrics)"
+```
+
+### Data Mining (DM)
+```bash
 python -c "from bm_preprocessing.DM import all; print(all)"
 python -c "from bm_preprocessing.DM import all_vis; print(all_vis)"
 python -c "from bm_preprocessing.DM import apriori; print(apriori)"
@@ -123,31 +93,35 @@ python -c "from bm_preprocessing.DM import hunts_test; print(hunts_test)"
 python -c "from bm_preprocessing.DM import id3; print(id3)"
 python -c "from bm_preprocessing.DM import id3_test; print(id3_test)"
 python -c "from bm_preprocessing.DM import metrics; print(metrics)"
-python -c "from bm_preprocessing.DM import lib_doc; print(lib_doc)"
 python -c "from bm_preprocessing.DM import preprocessing; print(preprocessing)"
+python -c "from bm_preprocessing.DM import lib_doc; print(lib_doc)"
+python -c "from bm_preprocessing.DM import python_doc; print(python_doc)"
 ```
 
 ---
 
-## Available Modules
+## Available Modules Reference
 
-| Import | Description |
-|--------|-------------|
-| `from bm_preprocessing.IR import all` | Information Retrieval (MinHash, LSH, Rocchio, Jaccard, VS) |
-| `from bm_preprocessing.IR import all_vis` | IR algorithms with Matplotlib visualizations |
-| `from bm_preprocessing.IR import eval_metrics` | Jaccard, PRF, Compression Ratio, MAP metrics & plots |
+| Import Path | Description |
+|-------------|-------------|
+| **Information Retrieval (IR)** | |
+| `from bm_preprocessing.IR import all` | Cohesive IR File: MinHash, LSH, Rocchio, Jaccard, VS |
+| `from bm_preprocessing.IR import all_vis` | Cohesive IR File + Matplotlib visualizations & Heatmaps |
 | `from bm_preprocessing.IR import ndd` | Near Duplicate Documents (MinHash & LSH) |
 | `from bm_preprocessing.IR import rel` | Relevance feedback & query expansion (Rocchio & LCA) |
-| `from bm_preprocessing.DM import all` | All DM algorithms (Hunt's, ID3, Bagging, AdaBoost, metrics) |
-| `from bm_preprocessing.DM import all_vis` | All DM algorithms + graphviz & full visualization |
+| `from bm_preprocessing.IR import eval_metrics` | Jaccard, PRF, Compression Ratios, MAP metrics & plots |
+| **Data Mining (DM)** | |
+| `from bm_preprocessing.DM import all` | Cohesive DM File: Hunt's, ID3, Bagging, AdaBoost, Metrics |
+| `from bm_preprocessing.DM import all_vis` | Cohesive DM File + Graphviz & Matplotlib visualizations |
 | `from bm_preprocessing.DM import apriori` | Apriori algorithm |
 | `from bm_preprocessing.DM import adaboost` | Bagging & AdaBoost ensemble classifiers |
 | `from bm_preprocessing.DM import bagging` | Bagging ensemble classifier |
 | `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 hunts_test` | Hunt's decision tree with dataset visualization |
 | `from bm_preprocessing.DM import id3` | ID3 decision tree algorithm |
-| `from bm_preprocessing.DM import id3_test` | ID3 decision tree with visualization |
+| `from bm_preprocessing.DM import id3_test` | ID3 decision tree with dataset visualization |
 | `from bm_preprocessing.DM import metrics` | Classification metrics & curves |
-| `from bm_preprocessing.DM import lib_doc` | Pandas/NumPy/Sklearn/DM/IR cheat sheet |
 | `from bm_preprocessing.DM import preprocessing` | Data preprocessing utilities |
+| `from bm_preprocessing.DM import lib_doc` | Pandas, NumPy, Sklearn cheat sheet (DM & IR logic) |
+| `from bm_preprocessing.DM import python_doc` | Python Basics cheat sheet (Sets, Dicts, Comprehensions, etc.) |

{bm_preprocessing-1.2.0 → bm_preprocessing-1.3.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "bm-preprocessing"
-version = "1.2.0"
+version = "1.3.0"
 description = "A package to preprocess text data"
 readme = "README.md"
 requires-python = ">=3.8"

{bm_preprocessing-1.2.0 → bm_preprocessing-1.3.0}/src/bm_preprocessing/DM/__init__.py

@@ -13,6 +13,7 @@ from .id3_test import id3_test
 from .lib_doc import lib_doc
 from .metrics import metrics
 from .preprocessing import preprocessing
+from .python_doc import python_doc
 
-__all__ = ["adaboost", "all", "all_vis", "apriori", "bagging", "hash", "hunts", "hunts_test", "id3", "id3_test", "lib_doc", "metrics", "preprocessing"]
+__all__ = ["adaboost", "all", "all_vis", "apriori", "bagging", "hash", "hunts", "hunts_test", "id3", "id3_test", "lib_doc", "metrics", "preprocessing", "python_doc"]
 

bm_preprocessing-1.3.0/src/bm_preprocessing/DM/python_doc.py

@@ -0,0 +1,30 @@
+"""Source code loader for DM/python_doc.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" / "python_doc.py"
+python_doc = SourceCodeModule("DM.python_doc", _source_file)

bm_preprocessing-1.3.0/src/bm_preprocessing/DM/sources/python_doc.py

@@ -0,0 +1,174 @@
+"""
+=============================================================================
+PYTHON BASICS CHEAT SHEET
+=============================================================================
+A quick reference guide for core Python concepts, data structures, and features.
+"""
+
+# =============================================================================
+# 1. LISTS (Mutable, Ordered)
+# =============================================================================
+my_list = [1, 2, 3, 'a', 'b']
+
+# Operations
+my_list.append(4)           # Add to end: [1, 2, 3, 'a', 'b', 4]
+my_list.insert(0, 0)        # Insert at index: [0, 1, 2, 3, 'a', 'b', 4]
+my_list.extend([5, 6])      # Append multiple: [0, 1, 2, 3, 'a', 'b', 4, 5, 6]
+my_list.pop()               # Remove & return last item (6)
+my_list.pop(1)              # Remove & return item at index 1 (1)
+my_list.remove('a')         # Remove first occurrence of 'a'
+my_list.reverse()           # Reverse in place
+# my_list.sort()            # Sort in place (requires same types)
+# sorted(my_list)           # Return new sorted list
+my_list.clear()             # Empty the list
+count = my_list.count(2)    # Count occurrences
+idx = my_list.index(3)      # Find index of first occurrence
+
+# Slicing: list[start:stop:step]
+# my_list[1:4] (index 1 to 3), my_list[::-1] (reverse)
+
+# =============================================================================
+# 2. SETS (Mutable, Unordered, Unique Elements)
+# =============================================================================
+my_set = {1, 2, 3}
+empty_set = set()           # Note: {} creates an empty dict, not a set
+
+# Operations
+my_set.add(4)               # Add element
+my_set.update([5, 6])       # Add multiple elements
+my_set.remove(6)            # Remove element (raises KeyError if not found)
+my_set.discard(10)          # Remove element (safe, no error if not found)
+my_set.pop()                # Remove & return arbitrary element
+my_set.clear()              # Empty the set
+
+set_a, set_b = {1, 2}, {2, 3}
+union = set_a | set_b               # {1, 2, 3} (or set_a.union(set_b))
+intersection = set_a & set_b        # {2} (or set_a.intersection(set_b))
+diff = set_a - set_b                # {1} (or set_a.difference(set_b))
+sym_diff = set_a ^ set_b            # {1, 3} (or set_a.symmetric_difference(set_b))
+
+# =============================================================================
+# 3. TUPLES (Immutable, Ordered)
+# =============================================================================
+my_tuple = (1, 2, 3, 2)
+single_tuple = (1,)         # Comma needed for single-element tuple
+
+# Operations (Very limited since immutable)
+count = my_tuple.count(2)   # Count occurrences (2)
+idx = my_tuple.index(3)     # Find index of first occurrence (2)
+# Tuples support unpacking: a, b, c, d = my_tuple
+
+# =============================================================================
+# 4. DICTIONARIES (Mutable, Key-Value Pairs, Unordered before Python 3.7)
+# =============================================================================
+my_dict = {'name': 'Alice', 'age': 25}
+
+# Operations
+my_dict['city'] = 'NYC'     # Add or update key
+val = my_dict.get('age')    # Safe get (returns None if not found, instead of KeyError)
+val = my_dict.get('x', 0)   # Safe get with default value
+keys = my_dict.keys()       # dict_keys(['name', 'age', 'city'])
+values = my_dict.values()   # dict_values(['Alice', 25, 'NYC'])
+items = my_dict.items()     # dict_items([('name', 'Alice'), ...])
+
+# Removal
+popped_val = my_dict.pop('age')         # Remove key 'age' and return value
+popped_item = my_dict.popitem()         # Remove & return last key-value pair as tuple
+# del my_dict['name']                   # Delete key
+my_dict.clear()                         # Empty dict
+my_dict.update({'a': 1, 'b': 2})        # Merge / Update with another dict
+
+# =============================================================================
+# 5. LIST / DICT / SET COMPREHENSIONS
+# =============================================================================
+# List Comprehension: [expression for item in iterable if condition]
+squares = [x**2 for x in range(10) if x % 2 == 0]     # [0, 4, 16, 36, 64]
+
+# Dict Comprehension: {key_expr: val_expr for item in iterable if condition}
+sq_dict = {x: x**2 for x in range(5)}                 # {0: 0, 1: 1, 2: 4, 3: 9, 4: 16}
+
+# Set Comprehension: {expression for item in iterable if condition}
+sq_set = {x**2 for x in [-1, 1, 2]}                   # {1, 4}
+
+# Generator Expression: (expression for item in iterable if condition)
+gen = (x**2 for x in range(10))                       # Lazy evaluation
+
+# =============================================================================
+# 6. LAMBDA FUNCTIONS, MAP, FILTER, REDUCE
+# =============================================================================
+# lambda arguments: expression
+add = lambda x, y: x + y
+print(add(2, 3))  # 5
+
+nums = [1, 2, 3, 4]
+# map: apply function to all items
+mapped = list(map(lambda x: x*2, nums))               # [2, 4, 6, 8]
+
+# filter: keep items where function returns True
+filtered = list(filter(lambda x: x % 2 == 0, nums))   # [2, 4]
+
+# reduce (requires functools): cumulative application
+from functools import reduce
+product = reduce(lambda x, y: x * y, nums)            # 24
+
+# Sort with lambda key
+words = ["apple", "banana", "cherry"]
+words.sort(key=lambda w: len(w))                      # Sort by length
+
+# =============================================================================
+# 7. CLASSES AND OBJECTS (OOP)
+# =============================================================================
+class Animal:
+    """Base class for animals."""
+    species_count = 0  # Class attribute
+
+    def __init__(self, name):
+        self.name = name  # Instance attribute
+        Animal.species_count += 1
+
+    def speak(self):
+        """Instance method"""
+        return "Some sound"
+
+    @classmethod
+    def get_count(cls):
+        """Class method: takes class as first arg"""
+        return cls.species_count
+
+    @staticmethod
+    def is_alive():
+        """Static method: no implicit self or cls args"""
+        return True
+
+# Inheritance
+class Dog(Animal):
+    def __init__(self, name, breed):
+        super().__init__(name)  # Call parent constructor
+        self.breed = breed
+    
+    def speak(self):            # Method Overriding
+        return "Woof!"
+
+dog = Dog("Buddy", "Golden Retriever")
+print(dog.speak())              # "Woof!"
+print(Animal.get_count())       # 1
+
+# =============================================================================
+# 8. FILE HANDLING
+# =============================================================================
+# Using 'with' is a best practice, as it automatically closes the file
+# Modes: 'r' (read), 'w' (write, truncates), 'a' (append), 'r+' (read & write), 'b' (binary)
+
+# Write to file
+with open("example.txt", "w", encoding="utf-8") as file:
+    file.write("Hello World\nLine 2")
+
+# Read from file
+with open("example.txt", "r", encoding="utf-8") as file:
+    content = file.read()       # Read entire file
+    # file.seek(0)              # Reset cursor to start
+    # lines = file.readlines()  # Read lines into a list
+    # for line in file:         # Iterate line by line (memory efficient)
+    #     print(line.strip())
+
+# Note: file is automatically closed outside the 'with' block.