aek-auto-mlbuilder 0.6.1__tar.gz → 0.8.0__tar.gz

{aek_auto_mlbuilder-0.6.1 → aek_auto_mlbuilder-0.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aek-auto-mlbuilder
-Version: 0.6.1
+Version: 0.8.0
 Summary: Automatic ML model builder in Python
 Home-page: https://github.com/alpemre8/aek-auto-mlbuilder
 Author: Alp Emre Karaahmet

{aek_auto_mlbuilder-0.6.1 → aek_auto_mlbuilder-0.8.0}/aek_auto_mlbuilder/__init__.py

@@ -5,4 +5,6 @@ from .logistic_regression import LogisticClassifier
 from .decision_tree import DecisionTreeModel
 from .knn import KNNModel
 from .random_forest import RandomForestModel
-from .svm import SVMModel
+from .svm import SVMModel
+from .naive_bayes import NaiveBayesModel
+from .kmeans import KMeansModel

aek_auto_mlbuilder-0.8.0/aek_auto_mlbuilder/kmeans.py

@@ -0,0 +1,41 @@
+from sklearn.cluster import KMeans
+from .base import BaseModel
+
+
+class KMeansModel(BaseModel):
+    """
+    K-Means clustering model (unsupervised learning)
+    Brute force method has been using
+    """
+    def __init__(self, param_grid=None):
+        super().__init__()
+        self.param_grid = param_grid or {
+            "n_clusters": [2, 3, 4, 5, 6],
+            "init": ["k-means++", "random"],
+            "n_init": [10, 20],
+            "max_iter": [300, 500]
+        }
+
+    def train(self, X, y):
+        best_score = -float("inf")
+        best_model = None
+
+        for n_clusters in self.param_grid["n_clusters"]:
+            for init in self.param_grid["init"]:
+                for n_init in self.param_grid["n_init"]:
+                    for max_iter in self.param_grid["max_iter"]:
+                        model = KMeans(
+                            n_clusters=n_clusters,
+                            init=init,
+                            n_init=n_init,
+                            max_iter=max_iter,
+                            random_state=42
+                        )
+                        model.fit(X, y)
+                        score = -model.inertia_
+                        if score > best_score:
+                            best_score = score
+                            best_model = model
+        self.best_model = best_model
+        self.best_score = best_score
+        return self.best_model

{aek_auto_mlbuilder-0.6.1 → aek_auto_mlbuilder-0.8.0}/aek_auto_mlbuilder/knn.py

@@ -8,7 +8,7 @@ class KNNModel(BaseModel):
     """
     KNN model for classification for classification or regression
     Use "task" for "classification" or "regression"
-    Brute-force search is using
+    Brute-force search has been using
     """
     def __init__(self, task="classification", param_grid=None):
         super().__init__()

aek_auto_mlbuilder-0.8.0/aek_auto_mlbuilder/naive_bayes.py

@@ -0,0 +1,65 @@
+from sklearn.naive_bayes import GaussianNB, MultinomialNB, BernoulliNB
+from .base import BaseModel
+
+
+class NaiveBayesModel(BaseModel):
+    """
+    Naive bayes model supporting gaussianNB, multinomialNB, bernoulliNB
+    use 'nb_type' param to specify the variant: gaussian, multinomial, bernoulli
+    brute force hyperparameter search has been using
+    """
+    def __init__(self, nb_type="gaussian", param_grid=None):
+        super().__init__()
+        self.nb_type = nb_type.lower()
+
+        if self.nb_type == "gaussian":
+            
+            self.param_grid = param_grid or {
+                "var_smoothing": [1e-9, 1e-8, 1e-7]
+            }
+        elif self.nb_type == "multinomial":
+            
+            self.param_grid = param_grid or {
+                "alpha": [1.0, 0.5, 0.1]
+            }
+        elif self.nb_type == "bernoulli":
+            
+            self.param_grid = param_grid or {
+                "alpha": [1.0, 0.5, 0.1],
+                "binarize": [0.0, 0.5, 1.0]
+            }
+        else:
+            raise ValueError("nb_type must be 'gaussian', 'multinomial', 'bernoulli'")
+        
+    def train(self, X, y):
+        best_score = -float("inf")
+        best_model = None
+
+        if self.nb_type == "gaussian":
+            for var_smoothing in self.param_grid["var_smoothing"]:
+                model = GaussianNB(var_smoothing=var_smoothing)
+                model.fit(X, y)
+                score = model.score(X, y)
+                if score > best_score:
+                    best_score = score
+                    best_model = model
+        elif self.nb_type == "multinomial":
+            for alpha in self.param_grid["alpha"]:
+                model = MultinomialNB(alpha=alpha)
+                model.fit(X, y)
+                score = model.score(X, y)
+                if score > best_score:
+                    best_score = score
+                    best_model = model
+        elif self.nb_type == "bernoulli":
+            for alpha in self.param_grid["alpha"]:
+                for binarize in self.param_grid["binarize"]:
+                    model = BernoulliNB(alpha=alpha, binarize=binarize)
+                    model.fit(X, y)
+                    score = model.score(X, y)
+                    if score > best_score:
+                        best_score = score
+                        best_model = model
+        self.best_model = best_model
+        self.best_score = best_score
+        return self.best_model

{aek_auto_mlbuilder-0.6.1 → aek_auto_mlbuilder-0.8.0}/aek_auto_mlbuilder/random_forest.py

@@ -5,7 +5,7 @@ class RandomForestModel(BaseModel):
     """
     Random Forest model for classification or regression
     Use task either "classification" or "regression"
-    brute force method is using
+    brute force method has been using
     """
     def __init__(self, task="classification", param_grid=None):
         super().__init__()

{aek_auto_mlbuilder-0.6.1 → aek_auto_mlbuilder-0.8.0}/aek_auto_mlbuilder/svm.py

@@ -8,7 +8,7 @@ class SVMModel(BaseModel):
     """
     support vector machine for classification and regression
     use task parameter for "regression" or "classification"
-    brute force is using
+    brute force has been using
     """
     def __init__(self, task="classification", param_grid=None):
         super().__init__()

{aek_auto_mlbuilder-0.6.1 → aek_auto_mlbuilder-0.8.0}/aek_auto_mlbuilder.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aek-auto-mlbuilder
-Version: 0.6.1
+Version: 0.8.0
 Summary: Automatic ML model builder in Python
 Home-page: https://github.com/alpemre8/aek-auto-mlbuilder
 Author: Alp Emre Karaahmet

{aek_auto_mlbuilder-0.6.1 → aek_auto_mlbuilder-0.8.0}/aek_auto_mlbuilder.egg-info/SOURCES.txt

@@ -5,9 +5,11 @@ setup.py
 aek_auto_mlbuilder/__init__.py
 aek_auto_mlbuilder/base.py
 aek_auto_mlbuilder/decision_tree.py
+aek_auto_mlbuilder/kmeans.py
 aek_auto_mlbuilder/knn.py
 aek_auto_mlbuilder/linear_regression.py
 aek_auto_mlbuilder/logistic_regression.py
+aek_auto_mlbuilder/naive_bayes.py
 aek_auto_mlbuilder/random_forest.py
 aek_auto_mlbuilder/svm.py
 aek_auto_mlbuilder/utils.py

{aek_auto_mlbuilder-0.6.1 → aek_auto_mlbuilder-0.8.0}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name="aek-auto-mlbuilder",        
-    version="0.6.1",
+    version="0.8.0",
     description="Automatic ML model builder in Python",
     long_description=open("README.md", encoding="utf-8").read(),
     long_description_content_type="text/markdown",