bm-preprocessing 0.3.0__tar.gz → 0.4.0__tar.gz

{bm_preprocessing-0.3.0 → bm_preprocessing-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: bm-preprocessing
-Version: 0.3.0
+Version: 0.4.0
 Summary: A package to preprocess text data
 Requires-Python: >=3.8
 Requires-Dist: build>=1.2.2.post1

{bm_preprocessing-0.3.0 → bm_preprocessing-0.4.0}/USAGE.md

@@ -15,7 +15,7 @@ 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
+from bm_preprocessing.DM import apriori, hash, hunts, hunts_test, id3, id3_test, preprocessing
 
 # Print the source code
 print("=== IR All Module ===")
@@ -33,6 +33,12 @@ 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 Preprocessing Module ===")
 print(preprocessing)
 ```
@@ -66,6 +72,12 @@ Then in the Python REPL:
 # 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
 ```
 
 ---
@@ -78,6 +90,8 @@ 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 id3; print(id3)"
+python -c "from bm_preprocessing.DM import id3_test; print(id3_test)"
 python -c "from bm_preprocessing.DM import preprocessing; print(preprocessing)"
 ```
 
@@ -93,4 +107,6 @@ python -c "from bm_preprocessing.DM import preprocessing; print(preprocessing)"
 | `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 id3` | ID3 decision tree algorithm |
+| `from bm_preprocessing.DM import id3_test` | ID3 decision tree with visualization |
 | `from bm_preprocessing.DM import preprocessing` | Data preprocessing utilities |

{bm_preprocessing-0.3.0 → bm_preprocessing-0.4.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "bm-preprocessing"
-version = "0.3.0"
+version = "0.4.0"
 description = "A package to preprocess text data"
 readme = "README.md"
 requires-python = ">=3.8"

{bm_preprocessing-0.3.0 → bm_preprocessing-0.4.0}/src/bm_preprocessing/DM/__init__.py

@@ -5,6 +5,9 @@ from .apriori import apriori
 from .hash import hash
 from .hunts import hunts
 from .hunts_test import hunts_test
+from .id3 import id3
+from .id3_test import id3_test
 from .preprocessing import preprocessing
 
-__all__ = ["all", "apriori", "hash", "hunts", "hunts_test", "preprocessing"]
+__all__ = ["all", "apriori", "hash", "hunts", "hunts_test", "id3", "id3_test", "preprocessing"]
+

bm_preprocessing-0.4.0/src/bm_preprocessing/DM/id3.py

@@ -0,0 +1,30 @@
+"""Source code loader for DM/id3.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" / "id3.py"
+id3 = SourceCodeModule("DM.id3", _source_file)

bm_preprocessing-0.4.0/src/bm_preprocessing/DM/id3_test.py

@@ -0,0 +1,30 @@
+"""Source code loader for DM/id3_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" / "id3_test.py"
+id3_test = SourceCodeModule("DM.id3_test", _source_file)

bm_preprocessing-0.4.0/src/bm_preprocessing/DM/sources/id3.py

@@ -0,0 +1,134 @@
+import pandas as pd
+import numpy as np
+import os
+
+
+# Load and process data
+data_path = os.path.join(os.path.dirname(__file__), "data.csv")
+df = pd.read_csv(data_path)
+df["Annual Income"] = (
+    df["Annual Income"]
+    .astype(str)
+    .str.replace("K", "", regex=False)
+    .str.replace(" ", "", regex=False)
+    .astype(int)
+    * 1000
+)
+
+
+# Entropy calculation
+def entropy(df, target_column):
+    counts = df[target_column].value_counts()
+    probs = counts / len(df)
+    return -sum(probs * np.log2(probs))
+
+
+# Information gain calculation
+def information_gain(df, feature, target_column):
+    total_entropy = entropy(df, target_column)
+
+    values = df[feature].unique()
+
+    weighted_entropy = 0
+    for value in values:
+        subset = df[df[feature] == value]
+        weighted_entropy += (len(subset) / len(df)) * entropy(subset, target_column)
+
+    return total_entropy - weighted_entropy
+
+
+# Best feature selection
+def best_feature(df, feature_columns, target_column):
+    gains = {
+        feature: information_gain(df, feature, target_column)
+        for feature in feature_columns
+    }
+    return max(gains, key=gains.get)
+
+
+# Node class
+class ID3Node:
+    def __init__(self, feature=None, value=None, label=None):
+        self.feature = feature
+        self.value = value
+        self.children = {}
+        self.label = label
+
+    def is_leaf(self):
+        return self.label is not None
+
+
+# ID3 algorithm
+def id3(df, target_column, feature_columns):
+    # If the target column is pure, return a leaf node
+    if len(df[target_column].unique()) == 1:
+        return ID3Node(label=df[target_column].mode()[0])
+
+    # If no features left, return leaf with majority class
+    if not feature_columns:
+        return ID3Node(label=df[target_column].mode()[0])
+
+    feature = best_feature(df, feature_columns, target_column)
+    node = ID3Node(feature=feature)
+
+    if pd.api.types.is_numeric_dtype(df[feature]):
+        median_value = df[feature].median()
+        left_df = df[df[feature] <= median_value]
+        right_df = df[df[feature] > median_value]
+
+        node.value = f"{feature} <= {median_value}"
+
+        remaining_features = [col for col in feature_columns if col != feature]
+        node.children["<= " + str(median_value)] = id3(
+            left_df, target_column, remaining_features
+        )
+        node.children["> " + str(median_value)] = id3(
+            right_df, target_column, remaining_features
+        )
+    else:
+        unique_vals = df[feature].unique()
+        for val in unique_vals:
+            subset = df[df[feature] == val]
+            remaining_features = [col for col in feature_columns if col != feature]
+            node.children[val] = id3(subset, target_column, remaining_features)
+
+    return node
+
+
+# Print tree function
+def print_id3_tree(node, indent=""):
+    if node.is_leaf():
+        print(f"{indent}Leaf: {node.label}")
+        return
+
+    if node.value:
+        print(f"{indent}[Numeric Split] {node.value}")
+    else:
+        print(f"{indent}[Categorical Split] {node.feature}")
+
+    for val, child in node.children.items():
+        print(f"{indent}--> {val}:")
+        print_id3_tree(child, indent + "    ")
+
+
+def main():
+    feature_columns = [col for col in df.columns if col not in ["Default id", "Tid"]]
+
+    tree_root = id3(df, target_column="Default id", feature_columns=feature_columns)
+
+    print("=== ID3 Algorithm - Decision Tree (data.csv) ===\n")
+    print_id3_tree(tree_root)
+
+    # Tennis dataset
+    tennis_path = os.path.join(os.path.dirname(__file__), "tennis.csv")
+    tennis_df = pd.read_csv(tennis_path)
+
+    tennis_features = [col for col in tennis_df.columns if col != "Play"]
+    tennis_tree = id3(tennis_df, target_column="Play", feature_columns=tennis_features)
+
+    print("\n\n=== ID3 Algorithm - Decision Tree (tennis.csv) ===\n")
+    print_id3_tree(tennis_tree)
+
+
+if __name__ == "__main__":
+    main()

bm_preprocessing-0.4.0/src/bm_preprocessing/DM/sources/id3_test.py

@@ -0,0 +1,148 @@
+import pandas as pd
+import numpy as np
+import graphviz
+import os
+
+
+# Load and process data
+data_path = os.path.join(os.path.dirname(__file__), "data.csv")
+df = pd.read_csv(data_path)
+df["Annual Income"] = (
+    df["Annual Income"]
+    .astype(str)
+    .str.replace("K", "", regex=False)
+    .str.replace(" ", "", regex=False)
+    .astype(int)
+    * 1000
+)
+
+
+# Entropy calculation
+def entropy(df, target_column):
+    counts = df[target_column].value_counts()
+    probs = counts / len(df)
+    return -sum(probs * np.log2(probs))
+
+
+# Information gain calculation
+def information_gain(df, feature, target_column):
+    total_entropy = entropy(df, target_column)
+
+    values = df[feature].unique()
+
+    weighted_entropy = 0
+    for value in values:
+        subset = df[df[feature] == value]
+        weighted_entropy += (len(subset) / len(df)) * entropy(subset, target_column)
+
+    return total_entropy - weighted_entropy
+
+
+# Best feature selection
+def best_feature(df, feature_columns, target_column):
+    gains = {
+        feature: information_gain(df, feature, target_column)
+        for feature in feature_columns
+    }
+    return max(gains, key=gains.get)
+
+
+# Node class
+class ID3Node:
+    def __init__(self, feature=None, value=None, label=None):
+        self.feature = feature
+        self.value = value
+        self.children = {}
+        self.label = label
+
+    def is_leaf(self):
+        return self.label is not None
+
+
+# ID3 algorithm
+def id3(df, target_column, feature_columns):
+    # If the target column is pure, return a leaf node
+    if len(df[target_column].unique()) == 1:
+        return ID3Node(label=df[target_column].mode()[0])
+
+    # If no features left, return leaf with majority class
+    if not feature_columns:
+        return ID3Node(label=df[target_column].mode()[0])
+
+    feature = best_feature(df, feature_columns, target_column)
+    node = ID3Node(feature=feature)
+
+    if pd.api.types.is_numeric_dtype(df[feature]):
+        median_value = df[feature].median()
+        left_df = df[df[feature] <= median_value]
+        right_df = df[df[feature] > median_value]
+
+        node.value = f"{feature} <= {median_value}"
+
+        remaining_features = [col for col in feature_columns if col != feature]
+        node.children["<= " + str(median_value)] = id3(
+            left_df, target_column, remaining_features
+        )
+        node.children["> " + str(median_value)] = id3(
+            right_df, target_column, remaining_features
+        )
+    else:
+        unique_vals = df[feature].unique()
+        for val in unique_vals:
+            subset = df[df[feature] == val]
+            remaining_features = [col for col in feature_columns if col != feature]
+            node.children[val] = id3(subset, target_column, remaining_features)
+
+    return node
+
+
+# Tree visualization function using graphviz
+def visualize_id3_tree(node, parent_name="Root", graph=None):
+    if graph is None:
+        graph = graphviz.Digraph(format="png", engine="dot")
+
+    if node.is_leaf():
+        graph.node(parent_name, label=str(node.label), shape="ellipse")
+    else:
+        if node.value:
+            label = node.value
+        else:
+            label = str(node.feature)
+        graph.node(parent_name, label=label, shape="box")
+
+        for val, child in node.children.items():
+            child_name = f"{parent_name}_{val}"
+            graph.edge(parent_name, child_name, label=str(val))
+            visualize_id3_tree(child, child_name, graph)
+
+    return graph
+
+
+def main():
+    feature_columns = [col for col in df.columns if col not in ["Default id", "Tid"]]
+
+    tree_root = id3(df, target_column="Default id", feature_columns=feature_columns)
+
+    # Visualize the tree using graphviz
+    graph = visualize_id3_tree(tree_root)
+    output_path = os.path.join(os.path.dirname(__file__), "id3_decision_tree")
+    graph.render(output_path, view=True, cleanup=True)
+    print(f"Decision tree rendered and saved as '{output_path}.png'")
+
+    # Tennis dataset
+    tennis_path = os.path.join(os.path.dirname(__file__), "tennis.csv")
+    tennis_df = pd.read_csv(tennis_path)
+
+    tennis_features = [col for col in tennis_df.columns if col != "Play"]
+    tennis_tree = id3(tennis_df, target_column="Play", feature_columns=tennis_features)
+
+    graph_tennis = visualize_id3_tree(tennis_tree)
+    tennis_output_path = os.path.join(
+        os.path.dirname(__file__), "id3_tennis_decision_tree"
+    )
+    graph_tennis.render(tennis_output_path, view=True, cleanup=True)
+    print(f"Tennis decision tree rendered and saved as '{tennis_output_path}.png'")
+
+
+if __name__ == "__main__":
+    main()

bm_preprocessing-0.4.0/src/bm_preprocessing/DM/sources/tennis.csv

@@ -0,0 +1,15 @@
+Outlook,Temperature,Humidity,Wind,Play
+Sunny,Hot,High,Weak,No
+Sunny,Hot,High,Strong,No
+Overcast,Hot,High,Weak,Yes
+Rain,Mild,High,Weak,Yes
+Rain,Cool,Normal,Weak,Yes
+Rain,Cool,Normal,Strong,No
+Overcast,Cool,Normal,Strong,Yes
+Sunny,Mild,High,Weak,No
+Sunny,Cool,Normal,Weak,Yes
+Rain,Mild,Normal,Weak,Yes
+Sunny,Mild,Normal,Strong,Yes
+Overcast,Mild,High,Strong,Yes
+Overcast,Hot,Normal,Weak,Yes
+Rain,Mild,High,Strong,No