Upload files

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

client.ipynb

@@ -0,0 +1,76 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "df_train, df_temp = train_test_split(df, test_size=split_size, shuffle=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "\n",
+    "# Load your DataFrame (replace 'your_data.csv' with your actual data file)\n",
+    "df = pd.read_csv('train.csv')\n",
+    "\n",
+    "# Split the DataFrame into 5 random parts\n",
+    "num_splits = 3\n",
+    "split_size = 1.0 / num_splits\n",
+    "\n",
+    "# Create empty lists to store the splits\n",
+    "# data_splits = []\n",
+    "\n",
+    "# Loop to create 5 random splits\n",
+    "for i in range(num_splits):\n",
+    "    # Split the data into a training set and a temporary set (remaining data)\n",
+    "    df_train, df_temp = train_test_split(df, test_size=split_size, shuffle=True)\n",
+    "    \n",
+    "    # Append the training set to the list of splits\n",
+    "    # data_splits.append(df_train)\n",
+    "    df_train.to_csv(f'train_split{i}.csv', index=False)\n",
+    "    \n",
+    "    # Update df to the remaining data for the next iteration\n",
+    "    df = df_temp\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "env",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

client0.py

@@ -0,0 +1,66 @@
+import warnings
+import flwr as fl
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import log_loss
+import os
+import flwr as fl
+import tensorflow as tf
+import keras
+import numpy as np
+from sklearn.metrics import accuracy_score
+import utils
+
+import warnings
+warnings.filterwarnings("ignore")
+if __name__ == "__main__":
+    df_train=pd.read_csv("train_split0.csv",encoding='utf-8')
+    # X, y = utils.preprocess(df_train)
+    x_subclass, y_subclass = utils.preprocess(df_train)
+    X_train, X_test, y_train, y_test = train_test_split(x_subclass, y_subclass, test_size=0.1)
+# Make TensorFlow log less verbose
+    os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"
+
+    model3 = keras.Sequential()
+    model3.add(keras.layers.Dense(100, input_dim = 26, activation = 'relu'))
+    model3.add(keras.layers.Dense(48, activation = 'relu'))
+    model3.add(keras.layers.Dense(16, activation = 'relu'))
+    model3.add(keras.layers.Dense(8, activation = 'relu'))
+    model3.add(keras.layers.Dense(9, activation = "softmax"))
+
+    model3.compile(loss = 'categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy', 'Precision', 'Recall'])
+
+    epochs = 100
+    batch_size = 25
+
+
+    # Define Flower client
+    class HospitalClient(fl.client.NumPyClient):
+        def get_parameters(self, config):
+            return model3.get_weights()
+
+        def fit(self, parameters, config):
+            model3.set_weights(parameters)
+            model3.fit(X_train, y_train, epochs=epochs, batch_size=batch_size, validation_split=0.1, shuffle=True)
+            return model3.get_weights(), len(X_train), {}
+
+        # def evaluate(self, parameters, config):
+        #     model3.set_weights(parameters)
+        #     loss, accuracy, _, _ = model3.evaluate(X_test, y_test)
+        #     print(f"accuracy of test: {accuracy} ")
+        #     return loss, len(X_test), {"accuracy": accuracy}
+        def evaluate(self, parameters, config):
+            model3.set_weights(parameters)
+            y = model3.predict(X_test)
+            predicted_labels = np.argmax(y, axis=1)
+            true_labels = np.argmax(y_test, axis=1)
+            accuracy = accuracy_score(true_labels, predicted_labels)
+            # loss = log_loss(true_labels, y)
+            loss, _, _, _ = model3.evaluate(X_test, y_test)
+            print(f"accuracy of test: {accuracy} ")
+            return loss, len(X_test), {"accuracy": accuracy}
+
+
+    # Start Flower client
+    fl.client.start_numpy_client(server_address="localhost:3000", client=HospitalClient())

client1.py

@@ -0,0 +1,64 @@
+
+import warnings
+import flwr as fl
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import log_loss
+import os
+import flwr as fl
+import tensorflow as tf
+import keras
+from sklearn.metrics import accuracy_score
+import numpy as np
+
+
+import utils
+
+import warnings
+warnings.filterwarnings("ignore")
+if __name__ == "__main__":
+    df_train=pd.read_csv("train_split1.csv",encoding='utf-8')
+    # X, y = utils.preprocess(df_train)
+    x_subclass, y_subclass = utils.preprocess(df_train)
+    X_train, X_test, y_train, y_test = train_test_split(x_subclass, y_subclass, test_size=0.1)
+# Make TensorFlow log less verbose
+    os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"
+
+    model3 = keras.Sequential()
+    model3.add(keras.layers.Dense(100, input_dim = 26, activation = 'relu'))
+    model3.add(keras.layers.Dense(48, activation = 'relu'))
+    model3.add(keras.layers.Dense(16, activation = 'relu'))
+    model3.add(keras.layers.Dense(8, activation = 'relu'))
+    model3.add(keras.layers.Dense(9, activation = "softmax"))
+
+    model3.compile(loss = 'categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy', 'Precision', 'Recall'])
+
+    epochs = 100
+    batch_size = 25
+
+
+    # Define Flower client
+    class HospitalClient(fl.client.NumPyClient):
+        def get_parameters(self, config):
+            return model3.get_weights()
+
+        def fit(self, parameters, config):
+            model3.set_weights(parameters)
+            model3.fit(X_train, y_train, epochs=epochs, batch_size=batch_size, validation_split=0.1, shuffle=True)
+            return model3.get_weights(), len(X_train), {}
+
+        def evaluate(self, parameters, config):
+            model3.set_weights(parameters)
+            y = model3.predict(X_test)
+            predicted_labels = np.argmax(y, axis=1)
+            true_labels = np.argmax(y_test, axis=1)
+            accuracy = accuracy_score(true_labels, predicted_labels)
+            # loss = log_loss(true_labels, y)
+            loss, _, _, _ = model3.evaluate(X_test, y_test)
+            print(f"accuracy of test: {accuracy} ")
+            return loss, len(X_test), {"accuracy": accuracy}
+
+
+    # Start Flower client
+    fl.client.start_numpy_client(server_address="localhost:3000", client=HospitalClient())