skelearn 0.1.0__tar.gz

skelearn-0.1.0/MANIFEST.in

@@ -0,0 +1 @@
+include skelearn/*.ipynb

skelearn-0.1.0/PKG-INFO

@@ -0,0 +1,11 @@
+Metadata-Version: 2.4
+Name: skelearn
+Version: 0.1.0
+Summary: practice
+Author: kingmufaz
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Dynamic: author
+Dynamic: description-content-type
+Dynamic: requires-python
+Dynamic: summary

skelearn-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

skelearn-0.1.0/setup.py

@@ -0,0 +1,14 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="skelearn",
+    version="0.1.0",
+    author="kingmufaz",
+    description="practice",
+    long_description=open("README.md").read(),
+    long_description_content_type="text/markdown",
+    packages=find_packages(),
+    include_package_data=True,
+    package_data={"skelearn": ["*.ipynb"]},
+    python_requires=">=3.8",
+)

skelearn-0.1.0/skelearn/__init__.py

@@ -0,0 +1,10 @@
+import shutil
+from importlib.resources import files
+
+def sklearn():
+    shutil.copy(files("skelearn").joinpath("develop.pdf"), "develop.pdf")
+
+def iris():
+    shutil.copy(files("skelearn").joinpath("prac.py"), "prac.py")
+
+

skelearn-0.1.0/skelearn/prac.py

@@ -0,0 +1,74 @@
+import matplotlib.pyplot as plt
+
+from sklearn.datasets import load_iris
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from tensorflow.keras.utils import to_categorical
+
+import tensorflow as tf
+
+# Load dataset
+iris = load_iris()
+X = iris.data
+Y = iris.target
+
+# Split dataset
+x_train, x_test, y_train, y_test = train_test_split(
+    X, Y, test_size=0.2, random_state=42
+)
+
+# Normalize
+scaler = StandardScaler()
+x_train = scaler.fit_transform(x_train)
+x_test = scaler.transform(x_test)
+
+# One-hot encoding
+y_train = to_categorical(y_train, 3)
+y_test = to_categorical(y_test, 3)
+
+# Activation functions list
+activations = ['sigmoid', 'relu', 'tanh']
+
+# Train separate models
+for act in activations:
+    print(f"\n--- Using {act.upper()} Activation ---")
+
+    model = tf.keras.Sequential([
+        tf.keras.layers.Dense(128, activation=act, input_shape=(4,)),
+        tf.keras.layers.Dense(64, activation=act),
+        tf.keras.layers.Dense(3, activation='softmax')
+    ])
+
+    model.compile(
+        optimizer='adam',
+        loss='categorical_crossentropy',
+        metrics=['accuracy']
+    )
+
+    history = model.fit(
+        x_train,
+        y_train,
+        epochs=50,
+        batch_size=8,
+        verbose=0
+    )
+
+    loss, accuracy = model.evaluate(
+        x_test,
+        y_test,
+        verbose=0
+    )
+
+    print("Final Loss:", loss)
+    print("Final Accuracy:", accuracy)
+
+    # Plot loss convergence for each activation
+    plt.plot(history.history['loss'], label=act)
+
+# Final graph
+plt.title("Iris Dataset Loss Convergence Comparison")
+plt.xlabel("Epoch")
+plt.ylabel("Loss")
+plt.legend()
+
+plt.show()

skelearn-0.1.0/skelearn.egg-info/PKG-INFO

@@ -0,0 +1,11 @@
+Metadata-Version: 2.4
+Name: skelearn
+Version: 0.1.0
+Summary: practice
+Author: kingmufaz
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Dynamic: author
+Dynamic: description-content-type
+Dynamic: requires-python
+Dynamic: summary

skelearn-0.1.0/skelearn.egg-info/SOURCES.txt

@@ -0,0 +1,9 @@
+MANIFEST.in
+README.md
+setup.py
+skelearn/__init__.py
+skelearn/prac.py
+skelearn.egg-info/PKG-INFO
+skelearn.egg-info/SOURCES.txt
+skelearn.egg-info/dependency_links.txt
+skelearn.egg-info/top_level.txt

skelearn-0.1.0/skelearn.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

skelearn-0.1.0/skelearn.egg-info/top_level.txt

@@ -0,0 +1 @@
+skelearn