0.1.51

PyPI/setup.cfg

@@ -1,7 +1,7 @@
 [metadata]
 # replace with your username:
 name = guan
-version = 0.1.50
+version = 0.1.51
 author = guanjihuan
 author_email = guanjihuan@163.com
 description = An open source python package

PyPI/src/guan.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: guan
-Version: 0.1.50
+Version: 0.1.51
 Summary: An open source python package
 Home-page: https://py.guanjihuan.com
 Author: guanjihuan

PyPI/src/guan.egg-info/SOURCES.txt

@@ -10,6 +10,7 @@ src/guan/band_structures_and_wave_functions.py
 src/guan/basic_functions.py
 src/guan/data_processing.py
 src/guan/density_of_states.py
+src/guan/machine_learning.py
 src/guan/others.py
 src/guan/quantum_transport.py
 src/guan/topological_invariant.py

PyPI/src/guan/__init__.py

@@ -17,5 +17,6 @@ from .Green_functions import *
 from .density_of_states import *
 from .quantum_transport import *
 from .topological_invariant import *
+from .machine_learning import *
 from .data_processing import *
 from .others import *

PyPI/src/guan/basic_functions.py

@@ -4,7 +4,10 @@ import guan
 # 测试
 @guan.function_decorator
 def test():
-    print('\nSuccess in the installation of Guan package!\n')
+    import guan
+    current_version = guan.get_current_version('guan')
+    print(f'\nSuccess in the installation of Guan package! The installed version is guan-{current_version}.\n')
+    guan.notification_of_upgrade(timeout=5)
 
 # 泡利矩阵
 @guan.function_decorator

PyPI/src/guan/machine_learning.py

@@ -0,0 +1,115 @@
+# Module: machine_learning
+import guan
+
+# 全连接神经网络模型（包含一个隐藏层）
+@guan.function_decorator
+def fully_connected_neural_network_with_one_hidden_layer(input_size=1, hidden_size=10, output_size=1, activation='relu'):
+    import torch
+    class model_class(torch.nn.Module):
+        def __init__(self):
+            super().__init__()
+            self.hidden_layer = torch.nn.Linear(input_size, hidden_size)
+            self.output_layer = torch.nn.Linear(hidden_size, output_size)
+        def forward(self, x):
+            if activation == 'relu':
+                hidden_output = torch.nn.functional.relu(self.hidden_layer(x))
+            elif activation == 'leaky_relu':
+                hidden_output = torch.nn.functional.leaky_relu(self.hidden_layer(x))
+            elif activation == 'sigmoid':
+                hidden_output = torch.nn.functional.sigmoid(self.hidden_layer(x))
+            elif activation == 'tanh':
+                hidden_output = torch.nn.functional.tanh(self.hidden_layer(x))
+            else:
+                hidden_output = self.hidden_layer(x)
+            output = self.output_layer(hidden_output)
+            return output
+    model = model_class()
+    return model
+
+# 全连接神经网络模型（包含两个隐藏层）
+@guan.function_decorator
+def fully_connected_neural_network_with_two_hidden_layers(input_size=1, hidden_size_1=10, hidden_size_2=10, output_size=1, activation_1='relu', activation_2='relu'):
+    import torch
+    class model_class(torch.nn.Module):
+        def __init__(self):
+            super().__init__()
+            self.hidden_layer_1 = torch.nn.Linear(input_size, hidden_size_1)
+            self.hidden_layer_2 = torch.nn.Linear(hidden_size_1, hidden_size_2)
+            self.output_layer = torch.nn.Linear(hidden_size_2, output_size)
+        def forward(self, x):
+            if activation_1 == 'relu':
+                hidden_output_1 = torch.nn.functional.relu(self.hidden_layer_1(x))
+            elif activation_1 == 'leaky_relu':
+                hidden_output_1 = torch.nn.functional.leaky_relu(self.hidden_layer_1(x))
+            elif activation_1 == 'sigmoid':
+                hidden_output_1 = torch.nn.functional.sigmoid(self.hidden_layer_1(x))
+            elif activation_1 == 'tanh':
+                hidden_output_1 = torch.nn.functional.tanh(self.hidden_layer_1(x))
+            else:
+                hidden_output_1 = self.hidden_layer_1(x)
+            
+            if activation_2 == 'relu':
+                hidden_output_2 = torch.nn.functional.relu(self.hidden_layer_2(hidden_output_1))
+            elif activation_2 == 'leaky_relu':
+                hidden_output_2 = torch.nn.functional.leaky_relu(self.hidden_layer_2(hidden_output_1))
+            elif activation_2 == 'sigmoid':
+                hidden_output_2 = torch.nn.functional.sigmoid(self.hidden_layer_2(hidden_output_1))
+            elif activation_2 == 'tanh':
+                hidden_output_2 = torch.nn.functional.tanh(self.hidden_layer_2(hidden_output_1))
+            else:
+                hidden_output_2 = self.hidden_layer_2(hidden_output_1)
+            
+            output = self.output_layer(hidden_output_2)
+            return output
+    model = model_class()
+    return model
+
+# 全连接神经网络模型（包含三个隐藏层）
+@guan.function_decorator
+def fully_connected_neural_network_with_three_hidden_layers(input_size=1, hidden_size_1=10, hidden_size_2=10, hidden_size_3=10, output_size=1, activation_1='relu', activation_2='relu', activation_3='relu'):
+    import torch
+    class model_class(torch.nn.Module):
+        def __init__(self):
+            super().__init__()
+            self.hidden_layer_1 = torch.nn.Linear(input_size, hidden_size_1)
+            self.hidden_layer_2 = torch.nn.Linear(hidden_size_1, hidden_size_2)
+            self.hidden_layer_3 = torch.nn.Linear(hidden_size_2, hidden_size_3)
+            self.output_layer = torch.nn.Linear(hidden_size_3, output_size)
+        def forward(self, x):
+            if activation_1 == 'relu':
+                hidden_output_1 = torch.nn.functional.relu(self.hidden_layer_1(x))
+            elif activation_1 == 'leaky_relu':
+                hidden_output_1 = torch.nn.functional.leaky_relu(self.hidden_layer_1(x))
+            elif activation_1 == 'sigmoid':
+                hidden_output_1 = torch.nn.functional.sigmoid(self.hidden_layer_1(x))
+            elif activation_1 == 'tanh':
+                hidden_output_1 = torch.nn.functional.tanh(self.hidden_layer_1(x))
+            else:
+                hidden_output_1 = self.hidden_layer_1(x)
+            
+            if activation_2 == 'relu':
+                hidden_output_2 = torch.nn.functional.relu(self.hidden_layer_2(hidden_output_1))
+            elif activation_2 == 'leaky_relu':
+                hidden_output_2 = torch.nn.functional.leaky_relu(self.hidden_layer_2(hidden_output_1))
+            elif activation_2 == 'sigmoid':
+                hidden_output_2 = torch.nn.functional.sigmoid(self.hidden_layer_2(hidden_output_1))
+            elif activation_2 == 'tanh':
+                hidden_output_2 = torch.nn.functional.tanh(self.hidden_layer_2(hidden_output_1))
+            else:
+                hidden_output_2 = self.hidden_layer_2(hidden_output_1)
+
+            if activation_3 == 'relu':
+                hidden_output_3 = torch.nn.functional.relu(self.hidden_layer_3(hidden_output_2))
+            elif activation_3 == 'leaky_relu':
+                hidden_output_3 = torch.nn.functional.leaky_relu(self.hidden_layer_3(hidden_output_2))
+            elif activation_3 == 'sigmoid':
+                hidden_output_3 = torch.nn.functional.sigmoid(self.hidden_layer_3(hidden_output_2))
+            elif activation_3 == 'tanh':
+                hidden_output_3 = torch.nn.functional.tanh(self.hidden_layer_3(hidden_output_2))
+            else:
+                hidden_output_3 = self.hidden_layer_3(hidden_output_2)
+            
+            output = self.output_layer(hidden_output_3)
+            return output
+    model = model_class()
+    return model

PyPI/src/guan/others.py

@@ -1065,16 +1065,16 @@ def get_current_version(package_name='guan'):
         return None
 
 # Guan软件包升级提示
-def notification_of_upgrade():
+def notification_of_upgrade(timeout=2):
-    import random
+    try:
-    rand_number = random.randint(1, 10)
+        latest_version = get_latest_version(package_name='guan', timeout=timeout)
-    if rand_number == 5:
+        current_version = get_current_version('guan')
-        try:
+        if latest_version != None and current_version != None:
-            latest_version = get_latest_version(package_name='guan', timeout=2)
+            if latest_version != current_version:
-            current_version = get_current_version('guan')
+                print('提示：您当前使用的版本是 guan-'+current_version+'，目前已经有最新版本 guan-'+latest_version+'。您可以通过以下命令对软件包进行升级：pip install --upgrade guan')
-            if latest_version != None and current_version != None:
+    except:
-                if latest_version != current_version:
+        pass
-                    print('提示：您当前使用的版本是 guan-'+current_version+'，目前已经有最新版本 guan-'+latest_version+'。您可以通过以下命令对软件包进行升级：pip install --upgrade guan')
+import random
-        except:
+rand_number = random.randint(1, 10)
-            pass
+if rand_number == 5:
-notification_of_upgrade()
+    notification_of_upgrade(timeout=2)

README.md

@@ -22,6 +22,7 @@ import guan
 + density of states
 + quantum transport
 + topological invariant
++ machine learning
 + data processing
 + others