simpmnct 0.1.3__tar.gz

simpmnct-0.1.3/PKG-INFO

@@ -0,0 +1,83 @@
+Metadata-Version: 2.4
+Name: simpmnct
+Version: 0.1.3
+Summary: Simple Machine Learning library from scratch using NumPy
+Author: Nguyễn Chính Thanh
+License: MIT
+Project-URL: Homepage, https://github.com/thanhtaysimplo/simpmnct
+Project-URL: Bug Tracker, https://github.com/thanhtaysimplo/simpmnct/issues
+Project-URL: Source Code, https://github.com/thanhtaysimplo/simpmnct
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: numpy
+Provides-Extra: vision
+Requires-Dist: torch; extra == "vision"
+Requires-Dist: torchvision; extra == "vision"
+Requires-Dist: Pillow; extra == "vision"
+
+simpmnct
+đây là thư viện cho người mới học Machine learning , chạy hết đá số các trường hợp , có hàm có sẵn nhiều bạn sẽ phải tự xử lí bằng tay và gần như nó giúp bạn hiểu hơn về ML thay vì cứ họi hàm sẵn có.
+dựa trên nền tẳng numpy , pickle , torch , torchvision , pillow 
+
+This is a library for beginners in Machine Learning. It runs through most cases, has built-in functions, and many users will have to handle manually. It helps you understand ML better than just relying on ready-made functions.
+It's based on NumPy, Pickle, Torch, TorchVision, and Pillow.
+
+Thư viện hỗ trợ:
+Linear Regression
+Logistic Regression
+Train/Test Split
+Normalize dữ liệu (data)
+Metrics cơ bản 
+Save/Load model (.best)
+
+Example 1 — Linear Regression
+import numpy as np
+from simpmnct.models.liner import Linear
+from simpmnct.utils.train_test_split import train_test_split
+X = np.random.rand(100,1)
+y = 3*X + 2
+X_train,X_test,y_train,y_test = train_test_split(X,y)
+model = Linear(lr=0.01,epochs=1000)
+model.fit(X_train,y_train)
+pred = model.predict(X_test)
+print(pred[:5])
+
+Example 2 — Logistic Regression
+import numpy as np
+from simpmnct.models.logictic import Logistic
+X = np.random.rand(100,2)
+y = (X[:,0] + X[:,1] > 1).astype(int)
+model = Logistic(lr=0.1,epochs=1000)
+model.fit(X,y)
+print(model.predict(X[:5]))
+
+Train Test Split
+from simpmnct.utils.train_test_split import train_test_split
+X_train,X_test,y_train,y_test = train_test_split(X,y)
+Normalize
+from simpmnct.utils.normalize import normalize
+X_norm = normalize(X)
+
+Metrics
+from simpmnct.metrics.metrics import accuracy
+from simpmnct.metrics.metrics import mse
+
+Save Model
+model.save("model.best")
+File .best sẽ chứa toàn bộ model đã train.
+
+Load Model
+from simpmnct.models.liner import Linear
+model = Linear.load("model.best")
+
+Dataset Loader (Depth Estimation)
+from simpmnct.dataset.depth_dataset import DepthDataset
+dataset = DepthDataset(img_dir="images",depth_dir="depth")
+img,depth = dataset[0]
+Output:
+image -> Tensor (3,H,W)
+depth -> Tensor (1,H,W)
+
+lưu ý : model này là do thằng sinh viên năm 2 viết ko dùng cho dự án lớn hay dẫn đường tên lửa , có thể sai số hoặc nhiều bug tiềm ẩn , chỉ sử dụng để học hoặc làm dự án nhỏ
+
+Please note: this model was written by a second-year student and is not intended for large projects or missile guidance. It may contain errors or potential bugs; it is only for learning or small projects.

simpmnct-0.1.3/README.md

@@ -0,0 +1,66 @@
+simpmnct
+đây là thư viện cho người mới học Machine learning , chạy hết đá số các trường hợp , có hàm có sẵn nhiều bạn sẽ phải tự xử lí bằng tay và gần như nó giúp bạn hiểu hơn về ML thay vì cứ họi hàm sẵn có.
+dựa trên nền tẳng numpy , pickle , torch , torchvision , pillow 
+
+This is a library for beginners in Machine Learning. It runs through most cases, has built-in functions, and many users will have to handle manually. It helps you understand ML better than just relying on ready-made functions.
+It's based on NumPy, Pickle, Torch, TorchVision, and Pillow.
+
+Thư viện hỗ trợ:
+Linear Regression
+Logistic Regression
+Train/Test Split
+Normalize dữ liệu (data)
+Metrics cơ bản 
+Save/Load model (.best)
+
+Example 1 — Linear Regression
+import numpy as np
+from simpmnct.models.liner import Linear
+from simpmnct.utils.train_test_split import train_test_split
+X = np.random.rand(100,1)
+y = 3*X + 2
+X_train,X_test,y_train,y_test = train_test_split(X,y)
+model = Linear(lr=0.01,epochs=1000)
+model.fit(X_train,y_train)
+pred = model.predict(X_test)
+print(pred[:5])
+
+Example 2 — Logistic Regression
+import numpy as np
+from simpmnct.models.logictic import Logistic
+X = np.random.rand(100,2)
+y = (X[:,0] + X[:,1] > 1).astype(int)
+model = Logistic(lr=0.1,epochs=1000)
+model.fit(X,y)
+print(model.predict(X[:5]))
+
+Train Test Split
+from simpmnct.utils.train_test_split import train_test_split
+X_train,X_test,y_train,y_test = train_test_split(X,y)
+Normalize
+from simpmnct.utils.normalize import normalize
+X_norm = normalize(X)
+
+Metrics
+from simpmnct.metrics.metrics import accuracy
+from simpmnct.metrics.metrics import mse
+
+Save Model
+model.save("model.best")
+File .best sẽ chứa toàn bộ model đã train.
+
+Load Model
+from simpmnct.models.liner import Linear
+model = Linear.load("model.best")
+
+Dataset Loader (Depth Estimation)
+from simpmnct.dataset.depth_dataset import DepthDataset
+dataset = DepthDataset(img_dir="images",depth_dir="depth")
+img,depth = dataset[0]
+Output:
+image -> Tensor (3,H,W)
+depth -> Tensor (1,H,W)
+
+lưu ý : model này là do thằng sinh viên năm 2 viết ko dùng cho dự án lớn hay dẫn đường tên lửa , có thể sai số hoặc nhiều bug tiềm ẩn , chỉ sử dụng để học hoặc làm dự án nhỏ
+
+Please note: this model was written by a second-year student and is not intended for large projects or missile guidance. It may contain errors or potential bugs; it is only for learning or small projects.

simpmnct-0.1.3/pyproject.toml

@@ -0,0 +1,34 @@
+[build-system]
+requires = ["setuptools>=61"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "simpmnct"
+version = "0.1.3"
+description = "Simple Machine Learning library from scratch using NumPy"
+readme = "README.md"
+license = {text = "MIT"}
+authors = [
+  {name = "Nguyễn Chính Thanh"}
+]
+
+requires-python = ">=3.9"
+
+dependencies = [
+  "numpy"
+]
+
+[project.optional-dependencies]
+vision = [
+  "torch",
+  "torchvision",
+  "Pillow"
+]
+
+[project.urls]
+"Homepage" = "https://github.com/thanhtaysimplo/simpmnct"
+"Bug Tracker" = "https://github.com/thanhtaysimplo/simpmnct/issues"
+"Source Code" = "https://github.com/thanhtaysimplo/simpmnct"
+
+[tool.setuptools.packages.find]
+include = ["simpmnct*"]

simpmnct-0.1.3/setup.cfg

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

simpmnct-0.1.3/setup.py

@@ -0,0 +1,10 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="simpmnct",
+    version="0.1",
+    packages=find_packages(),
+    install_requires=[
+        "numpy"
+    ]
+)

simpmnct-0.1.3/simpmnct/dataset/loader.py

@@ -0,0 +1,35 @@
+import os
+import torch
+import numpy as np
+from torch.utils.data import Dataset
+from PIL import Image
+import torchvision.transforms.functional as TF
+import random
+class DepthDataset(Dataset):
+    def __init__(self, img_dir, depth_dir, transform=None):
+        self.img_dir = img_dir
+        self.depth_dir = depth_dir
+        self.transform = transform
+        self.images = sorted([f for f in os.listdir(img_dir) if not f.startswith('.')])
+        self.depths = sorted([f for f in os.listdir(depth_dir) if not f.startswith('.')])
+        assert len(self.images) == len(self.depths), "images == depths ( sổ ảnh phải bằng depths)"
+
+    def __len__(self):
+        return len(self.images)
+
+    def __getitem__(self, index):
+        img_path = os.path.join(self.img_dir, self.images[index])
+        depth_path = os.path.join(self.depth_dir, self.depths[index])
+        image = Image.open(img_path).convert('RGB')
+        depth = Image.open(depth_path) 
+        if self.transform:
+            image = TF.resize(image, (256, 256))
+            depth = TF.resize(depth, (256, 256), interpolation=TF.InterpolationMode.NEAREST)
+            if random.random() > 0.5:
+                image = TF.hflip(image)
+                depth = TF.hflip(depth)
+            image = TF.to_tensor(image)
+        depth = np.array(depth).astype(np.float32)
+        depth = torch.from_numpy(depth).unsqueeze(0)
+
+        return image, depth

simpmnct-0.1.3/simpmnct/models/__init__.py

@@ -0,0 +1,2 @@
+from .linear import Linear
+from .logistic import Logistic

simpmnct-0.1.3/simpmnct/models/base_model.py

@@ -0,0 +1,21 @@
+import numpy as np
+import pickle
+class BaseModel:
+    def fit(self, X, y):
+        pass
+
+    def predict(self, X):
+        pass
+
+    def score(self,X,y):
+        y_pred = self.predict(X)
+        return np.mean(y_pred == y)
+
+    def save(self, path="model.best"):
+        with open(path, "wb") as f:
+            pickle.dump(self, f)
+
+    @staticmethod
+    def load(path="model.best"):
+        with open(path, "rb") as f:
+            return pickle.load(f)

simpmnct-0.1.3/simpmnct/models/linear.py

@@ -0,0 +1,35 @@
+import numpy as np
+from .base_model import BaseModel
+class Linear(BaseModel):
+
+    def __init__(self,lr=0.01,epochs=1000):
+        self.lr=lr
+        self.epochs=epochs
+        self.weight = None
+        self.bias = None
+
+    def fit(self,X,y):
+        n_sample,n_feature=X.shape
+
+        self.weight = np.zeros(n_feature)
+        self.bias = 0
+
+        for i in range(self.epochs):
+            y_pred = X.dot(self.weight) + self.bias
+
+            loss = (1/n_sample) * np.sum((y-y_pred)**2)
+
+            dw = (2/n_sample) * X.T @ (y_pred-y)
+            gd = (2/n_sample) * np.sum(y_pred - y)
+        
+            self.weight = self.weight - self.lr * dw
+            self.bias = self.bias - self.lr * gd
+
+    def predict(self,X):
+        return X.dot(self.weight)+self.bias
+    def score(self, X, y):
+        y_pred = self.predict(X)
+        ss_res = np.sum((y - y_pred)**2)
+        ss_tot = np.sum((y - np.mean(y))**2)
+        return 1 - (ss_res / (ss_tot + 1e-8))
+

simpmnct-0.1.3/simpmnct/models/logistic.py

@@ -0,0 +1,33 @@
+from .base_model import BaseModel
+import numpy as np
+
+class logistic(BaseModel):
+
+    def __init__(self,lr=0.01,epochs=1000):
+        self.lr=lr
+        self.epochs=epochs
+    
+    def sigmoid(self,z):
+        return 1/(1+np.exp(-z))
+    
+    def fit(self,X,y):
+        n_sample , n_feature = X.shape
+        self.weight = np.zeros(n_feature)
+        self.bias=0
+
+        for i in range(self.epochs):
+            y_pred = 1 / (1 + np.exp(-(X.dot(self.weight) + self.bias)))
+
+            loss = (-1/n_sample) * np.sum(y*np.log(y_pred)+(1-y)*np.log(1-y_pred))
+            
+            dw = (1/n_sample)* X.T @ (y_pred-y)
+            gd = (1/n_sample) * np.sum(y_pred-y)
+
+            self.weight-= self.lr * dw
+            self.bias-= self.lr * gd
+
+    def predict(self,X):
+        z = X.dot(self.weight) + self.bias
+        y_pred = self.sigmoid(z)
+        return (y_pred > 0.5).astype(int)
+

simpmnct-0.1.3/simpmnct/utils/metrics.py

@@ -0,0 +1,17 @@
+import numpy as np
+
+
+
+
+def mse(y_true, y_pred):
+    return np.mean((y_true - y_pred)**2)
+
+def mae(y_true, y_pred):
+    return np.mean(np.abs(y_true - y_pred))
+
+def rmse(y_true, y_pred):
+    return np.sqrt(mse(y_true, y_pred))
+
+def accuracy(y_true, y_pred):
+    y_pred = (y_pred > 0.5).astype(int)
+    return np.mean(y_true == y_pred)

simpmnct-0.1.3/simpmnct/utils/normalize.py

@@ -0,0 +1,8 @@
+import numpy as np
+
+def normalize(X):
+    mean = np.mean(X, axis=0)
+    std = np.std(X, axis=0)
+    std[std ==0] = 1
+    X_norm = (X - mean) / std
+    return X_norm

simpmnct-0.1.3/simpmnct/utils/train_test_split.py

@@ -0,0 +1,14 @@
+import numpy as np
+
+def train_test_split(X,y,test_size=0.2):
+    n_sample = X.shape[0]
+    indices = np.arange(n_sample)
+    np.random.shuffle(indices)
+    n_test = int(n_sample*test_size)
+    test_index = indices[:n_test]
+    train_index = indices[n_test:]
+    X_train = X[train_index]
+    X_test = X[test_index]
+    y_train = y[train_index]
+    y_test = y[test_index]
+    return X_train, X_test, y_train, y_test

simpmnct-0.1.3/simpmnct.egg-info/PKG-INFO

@@ -0,0 +1,83 @@
+Metadata-Version: 2.4
+Name: simpmnct
+Version: 0.1.3
+Summary: Simple Machine Learning library from scratch using NumPy
+Author: Nguyễn Chính Thanh
+License: MIT
+Project-URL: Homepage, https://github.com/thanhtaysimplo/simpmnct
+Project-URL: Bug Tracker, https://github.com/thanhtaysimplo/simpmnct/issues
+Project-URL: Source Code, https://github.com/thanhtaysimplo/simpmnct
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: numpy
+Provides-Extra: vision
+Requires-Dist: torch; extra == "vision"
+Requires-Dist: torchvision; extra == "vision"
+Requires-Dist: Pillow; extra == "vision"
+
+simpmnct
+đây là thư viện cho người mới học Machine learning , chạy hết đá số các trường hợp , có hàm có sẵn nhiều bạn sẽ phải tự xử lí bằng tay và gần như nó giúp bạn hiểu hơn về ML thay vì cứ họi hàm sẵn có.
+dựa trên nền tẳng numpy , pickle , torch , torchvision , pillow 
+
+This is a library for beginners in Machine Learning. It runs through most cases, has built-in functions, and many users will have to handle manually. It helps you understand ML better than just relying on ready-made functions.
+It's based on NumPy, Pickle, Torch, TorchVision, and Pillow.
+
+Thư viện hỗ trợ:
+Linear Regression
+Logistic Regression
+Train/Test Split
+Normalize dữ liệu (data)
+Metrics cơ bản 
+Save/Load model (.best)
+
+Example 1 — Linear Regression
+import numpy as np
+from simpmnct.models.liner import Linear
+from simpmnct.utils.train_test_split import train_test_split
+X = np.random.rand(100,1)
+y = 3*X + 2
+X_train,X_test,y_train,y_test = train_test_split(X,y)
+model = Linear(lr=0.01,epochs=1000)
+model.fit(X_train,y_train)
+pred = model.predict(X_test)
+print(pred[:5])
+
+Example 2 — Logistic Regression
+import numpy as np
+from simpmnct.models.logictic import Logistic
+X = np.random.rand(100,2)
+y = (X[:,0] + X[:,1] > 1).astype(int)
+model = Logistic(lr=0.1,epochs=1000)
+model.fit(X,y)
+print(model.predict(X[:5]))
+
+Train Test Split
+from simpmnct.utils.train_test_split import train_test_split
+X_train,X_test,y_train,y_test = train_test_split(X,y)
+Normalize
+from simpmnct.utils.normalize import normalize
+X_norm = normalize(X)
+
+Metrics
+from simpmnct.metrics.metrics import accuracy
+from simpmnct.metrics.metrics import mse
+
+Save Model
+model.save("model.best")
+File .best sẽ chứa toàn bộ model đã train.
+
+Load Model
+from simpmnct.models.liner import Linear
+model = Linear.load("model.best")
+
+Dataset Loader (Depth Estimation)
+from simpmnct.dataset.depth_dataset import DepthDataset
+dataset = DepthDataset(img_dir="images",depth_dir="depth")
+img,depth = dataset[0]
+Output:
+image -> Tensor (3,H,W)
+depth -> Tensor (1,H,W)
+
+lưu ý : model này là do thằng sinh viên năm 2 viết ko dùng cho dự án lớn hay dẫn đường tên lửa , có thể sai số hoặc nhiều bug tiềm ẩn , chỉ sử dụng để học hoặc làm dự án nhỏ
+
+Please note: this model was written by a second-year student and is not intended for large projects or missile guidance. It may contain errors or potential bugs; it is only for learning or small projects.

simpmnct-0.1.3/simpmnct.egg-info/SOURCES.txt

@@ -0,0 +1,19 @@
+README.md
+pyproject.toml
+setup.py
+simpmnct/__init__.py
+simpmnct.egg-info/PKG-INFO
+simpmnct.egg-info/SOURCES.txt
+simpmnct.egg-info/dependency_links.txt
+simpmnct.egg-info/requires.txt
+simpmnct.egg-info/top_level.txt
+simpmnct/dataset/__init__.py
+simpmnct/dataset/loader.py
+simpmnct/models/__init__.py
+simpmnct/models/base_model.py
+simpmnct/models/linear.py
+simpmnct/models/logistic.py
+simpmnct/utils/__init__.py
+simpmnct/utils/metrics.py
+simpmnct/utils/normalize.py
+simpmnct/utils/train_test_split.py

simpmnct-0.1.3/simpmnct.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

simpmnct-0.1.3/simpmnct.egg-info/requires.txt

@@ -0,0 +1,6 @@
+numpy
+
+[vision]
+torch
+torchvision
+Pillow

simpmnct-0.1.3/simpmnct.egg-info/top_level.txt

@@ -0,0 +1 @@
+simpmnct