Update app.py

app.py

@@ -1,5 +1,3 @@
-# %%writefile app.py
-
 import streamlit as st
 import matplotlib.pyplot as plt
 import torch
@@ -9,8 +7,6 @@ from evaluate import load as load_metric
 from torch.utils.data import DataLoader
 import pandas as pd
 import random
-import warnings
-from collections import OrderedDict
 import flwr as fl
 
 DEVICE = torch.device("cpu")
@@ -21,7 +17,6 @@ def load_data(dataset_name, train_size=20, test_size=20, num_clients=2):
     del raw_datasets["unsupervised"]
 
     tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
-
     def tokenize_function(examples):
         return tokenizer(examples["text"], truncation=True)
 
@@ -102,109 +97,273 @@ class CustomClient(fl.client.NumPyClient):
 
     def plot_metrics(self, round_num):
         if self.losses and self.accuracies:
-            st.write(f"#### Client {self.client_id} Metrics for Round {round_num}")
-            st.write(f"Loss: {self.losses[-1]:.4f}")
-            st.write(f"Accuracy: {self.accuracies[-1]:.4f}")
-
             fig, ax1 = plt.subplots()
 
-            ax2 = ax1.twinx()
-            ax1.plot(range(1, len(self.losses) + 1), self.losses, 'g-')
-            ax2.plot(range(1, len(self.accuracies) + 1), self.accuracies, 'b-')
-
+            color = 'tab:red'
             ax1.set_xlabel('Round')
-            ax1.set_ylabel('Loss', color='g')
-            ax2.set_ylabel('Accuracy', color='b')
+            ax1.set_ylabel('Loss', color=color)
+            ax1.plot(range(1, len(self.losses) + 1), self.losses, color=color)
+            ax1.tick_params(axis='y', labelcolor=color)
+
+            ax2 = ax1.twinx()  # instantiate a second axes that shares the same x-axis
+            color = 'tab:blue'
+            ax2.set_ylabel('Accuracy', color=color)  # we already handled the x-label with ax1
+            ax2.plot(range(1, len(self.accuracies) + 1), self.accuracies, color=color)
+            ax2.tick_params(axis='y', labelcolor=color)
 
-            plt.title(f'Client {self.client_id} Metrics')
+            fig.tight_layout()  # otherwise the right y-label is slightly clipped
             st.pyplot(fig)
+            st.write(f"Round {round_num} - Loss: {self.losses[-1]:.4f}, Accuracy: {self.accuracies[-1]:.4f}")
 
 def main():
-    st.write("## Federated Learning with Dynamic Models and Datasets for Mobile Devices")
-    dataset_name = st.selectbox("Dataset", ["imdb", "amazon_polarity", "ag_news"])
-    model_name = st.selectbox("Model", ["bert-base-uncased", "distilbert-base-uncased"])
+    st.title("Federated Learning with Dynamic Models and Datasets")
+    dataset_name = st.selectbox("Dataset", ["imdb", "amazon_polarity", "ag_news"], index=0)
+    model_name = st.selectbox("Model", ["bert-base-uncased", "distilbert-base-uncased"], index=0)
 
-    NUM_CLIENTS = st.slider("Number of Clients", min_value=1, max_value=10, value=2)
-    NUM_ROUNDS = st.slider("Number of Rounds", min_value=1, max_value=10, value=3)
+    NUM_CLIENTS = st.slider("Number of Clients", 1, 10, 3)
+    NUM_ROUNDS = st.slider("Number of Rounds", 1, 10, 5)
 
     train_datasets, test_datasets, data_collator = load_data(dataset_name, num_clients=NUM_CLIENTS)
 
-    trainloaders = []
-    testloaders = []
-    clients = []
+    if st.button("Initialize Clients"):
+        trainloaders = []
+        testloaders = []
+        clients = []
 
-    for i in range(NUM_CLIENTS):
-        st.write(f"### Client {i+1} Datasets")
+        for i in range(NUM_CLIENTS):
+            train_df = pd.DataFrame(train_datasets[i])
+            test_df = pd.DataFrame(test_datasets[i])
 
-        train_df = pd.DataFrame(train_datasets[i])
-        test_df = pd.DataFrame(test_datasets[i])
+            edited_train_dataset = Dataset.from_pandas(train_df)
+            edited_test_dataset = Dataset.from_pandas(test_df)
 
-        st.write("#### Train Dataset")
-        edited_train_df = st.experimental_data_editor(train_df, key=f"train_{i}")
-        st.write("#### Test Dataset")
-        edited_test_df = st.experimental_data_editor(test_df, key=f"test_{i}")
+            trainloader = DataLoader(edited_train_dataset, shuffle=True, batch_size=4, collate_fn=data_collator)
+            testloader = DataLoader(edited_test_dataset, batch_size=4, collate_fn=data_collator)
 
-        edited_train_dataset = Dataset.from_pandas(edited_train_df)
-        edited_test_dataset = Dataset.from_pandas(edited_test_df)
+            net = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=2).to(DEVICE)
+            client = CustomClient(net, trainloader, testloader, client_id=i+1)
+            clients.append(client)
 
-        trainloader = DataLoader(edited_train_dataset, shuffle=True, batch_size=32, collate_fn=data_collator)
-        testloader = DataLoader(edited_test_dataset, batch_size=32, collate_fn=data_collator)
+        for round_num in range(1, NUM_ROUNDS + 1):
+            st.write(f"### Round {round_num}")
+            for client in clients:
+                _, _, _ = client.fit({}, {})
+                client.plot_metrics(round_num)
 
-        trainloaders.append(trainloader)
-        testloaders.append(testloader)
+        st.success("Training completed successfully!")
 
-        net = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=2).to(DEVICE)
-        client = CustomClient(net, trainloader, testloader, client_id=i+1)
-        clients.append(client)
+if __name__ == "__main__":
+    main()
 
-    if st.button("Start Training"):
-        def client_fn(cid):
-            return clients[int(cid)]
 
-        def weighted_average(metrics):
-            accuracies = [num_examples * m["accuracy"] for num_examples, m in metrics]
-            losses = [num_examples * m["loss"] for num_examples, m in metrics]
-            examples = [num_examples for num_examples, _ in metrics]
-            return {"accuracy": sum(accuracies) / sum(examples), "loss": sum(losses) / sum(examples)}
 
-        strategy = fl.server.strategy.FedAvg(
-            fraction_fit=1.0,
-            fraction_evaluate=1.0,
-            evaluate_metrics_aggregation_fn=weighted_average,
-        )
+# # %%writefile app.py
 
-        for round_num in range(NUM_ROUNDS):
-            st.write(f"### Round {round_num + 1}")
+# import streamlit as st
+# import matplotlib.pyplot as plt
+# import torch
+# from transformers import AutoTokenizer, DataCollatorWithPadding, AutoModelForSequenceClassification, AdamW
+# from datasets import load_dataset, Dataset
+# from evaluate import load as load_metric
+# from torch.utils.data import DataLoader
+# import pandas as pd
+# import random
+# import warnings
+# from collections import OrderedDict
+# import flwr as fl
 
-            fl.simulation.start_simulation(
-                client_fn=client_fn,
-                num_clients=NUM_CLIENTS,
-                config=fl.server.ServerConfig(num_rounds=1),
-                strategy=strategy,
-                client_resources={"num_cpus": 1, "num_gpus": 0},
-                ray_init_args={"log_to_driver": False, "num_cpus": 1, "num_gpus": 0}
-            )
+# DEVICE = torch.device("cpu")
 
-            for client in clients:
-                client.plot_metrics(round_num + 1)
-                st.write(" ")
+# def load_data(dataset_name, train_size=20, test_size=20, num_clients=2):
+#     raw_datasets = load_dataset(dataset_name)
+#     raw_datasets = raw_datasets.shuffle(seed=42)
+#     del raw_datasets["unsupervised"]
 
-        st.success(f"Training completed successfully!")
+#     tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
 
-        # Display final metrics
-        st.write("## Final Client Metrics")
-        for client in clients:
-            st.write(f"### Client {client.client_id}")
-            st.write(f"Final Loss: {client.losses[-1]:.4f}")
-            st.write(f"Final Accuracy: {client.accuracies[-1]:.4f}")
-            client.plot_metrics(NUM_ROUNDS)
-            st.write(" ")
+#     def tokenize_function(examples):
+#         return tokenizer(examples["text"], truncation=True)
 
-    else:
-        st.write("Click the 'Start Training' button to start the training process.")
+#     tokenized_datasets = raw_datasets.map(tokenize_function, batched=True)
+#     tokenized_datasets = tokenized_datasets.remove_columns("text")
+#     tokenized_datasets = tokenized_datasets.rename_column("label", "labels")
 
-if __name__ == "__main__":
-    main()
+#     train_datasets = []
+#     test_datasets = []
+
+#     for _ in range(num_clients):
+#         train_dataset = tokenized_datasets["train"].select(random.sample(range(len(tokenized_datasets["train"])), train_size))
+#         test_dataset = tokenized_datasets["test"].select(random.sample(range(len(tokenized_datasets["test"])), test_size))
+#         train_datasets.append(train_dataset)
+#         test_datasets.append(test_dataset)
+
+#     data_collator = DataCollatorWithPadding(tokenizer=tokenizer)
+
+#     return train_datasets, test_datasets, data_collator
+
+# def train(net, trainloader, epochs):
+#     optimizer = AdamW(net.parameters(), lr=5e-5)
+#     net.train()
+#     for _ in range(epochs):
+#         for batch in trainloader:
+#             batch = {k: v.to(DEVICE) for k, v in batch.items()}
+#             outputs = net(**batch)
+#             loss = outputs.loss
+#             loss.backward()
+#             optimizer.step()
+#             optimizer.zero_grad()
+
+# def test(net, testloader):
+#     metric = load_metric("accuracy")
+#     net.eval()
+#     loss = 0
+#     for batch in testloader:
+#         batch = {k: v.to(DEVICE) for k, v in batch.items()}
+#         with torch.no_grad():
+#             outputs = net(**batch)
+#         logits = outputs.logits
+#         loss += outputs.loss.item()
+#         predictions = torch.argmax(logits, dim=-1)
+#         metric.add_batch(predictions=predictions, references=batch["labels"])
+#     loss /= len(testloader)
+#     accuracy = metric.compute()["accuracy"]
+#     return loss, accuracy
+
+# class CustomClient(fl.client.NumPyClient):
+#     def __init__(self, net, trainloader, testloader, client_id):
+#         self.net = net
+#         self.trainloader = trainloader
+#         self.testloader = testloader
+#         self.client_id = client_id
+#         self.losses = []
+#         self.accuracies = []
+
+#     def get_parameters(self, config):
+#         return [val.cpu().numpy() for _, val in self.net.state_dict().items()]
+
+#     def set_parameters(self, parameters):
+#         params_dict = zip(self.net.state_dict().keys(), parameters)
+#         state_dict = OrderedDict({k: torch.Tensor(v) for k, v in params_dict})
+#         self.net.load_state_dict(state_dict, strict=True)
+
+#     def fit(self, parameters, config):
+#         self.set_parameters(parameters)
+#         train(self.net, self.trainloader, epochs=1)
+#         loss, accuracy = test(self.net, self.testloader)
+#         self.losses.append(loss)
+#         self.accuracies.append(accuracy)
+#         return self.get_parameters(config={}), len(self.trainloader.dataset), {}
+
+#     def evaluate(self, parameters, config):
+#         self.set_parameters(parameters)
+#         loss, accuracy = test(self.net, self.testloader)
+#         return float(loss), len(self.testloader.dataset), {"accuracy": float(accuracy)}
+
+#     def plot_metrics(self, round_num):
+#         if self.losses and self.accuracies:
+#             st.write(f"#### Client {self.client_id} Metrics for Round {round_num}")
+#             st.write(f"Loss: {self.losses[-1]:.4f}")
+#             st.write(f"Accuracy: {self.accuracies[-1]:.4f}")
+
+#             fig, ax1 = plt.subplots()
+
+#             ax2 = ax1.twinx()
+#             ax1.plot(range(1, len(self.losses) + 1), self.losses, 'g-')
+#             ax2.plot(range(1, len(self.accuracies) + 1), self.accuracies, 'b-')
+
+#             ax1.set_xlabel('Round')
+#             ax1.set_ylabel('Loss', color='g')
+#             ax2.set_ylabel('Accuracy', color='b')
+
+#             plt.title(f'Client {self.client_id} Metrics')
+#             st.pyplot(fig)
+
+# def main():
+#     st.write("## Federated Learning with Dynamic Models and Datasets for Mobile Devices")
+#     dataset_name = st.selectbox("Dataset", ["imdb", "amazon_polarity", "ag_news"])
+#     model_name = st.selectbox("Model", ["bert-base-uncased", "distilbert-base-uncased"])
+
+#     NUM_CLIENTS = st.slider("Number of Clients", min_value=1, max_value=10, value=2)
+#     NUM_ROUNDS = st.slider("Number of Rounds", min_value=1, max_value=10, value=3)
+
+#     train_datasets, test_datasets, data_collator = load_data(dataset_name, num_clients=NUM_CLIENTS)
+
+#     trainloaders = []
+#     testloaders = []
+#     clients = []
+
+#     for i in range(NUM_CLIENTS):
+#         st.write(f"### Client {i+1} Datasets")
+
+#         train_df = pd.DataFrame(train_datasets[i])
+#         test_df = pd.DataFrame(test_datasets[i])
+
+#         st.write("#### Train Dataset")
+#         edited_train_df = st.experimental_data_editor(train_df, key=f"train_{i}")
+#         st.write("#### Test Dataset")
+#         edited_test_df = st.experimental_data_editor(test_df, key=f"test_{i}")
+
+#         edited_train_dataset = Dataset.from_pandas(edited_train_df)
+#         edited_test_dataset = Dataset.from_pandas(edited_test_df)
+
+#         trainloader = DataLoader(edited_train_dataset, shuffle=True, batch_size=32, collate_fn=data_collator)
+#         testloader = DataLoader(edited_test_dataset, batch_size=32, collate_fn=data_collator)
+
+#         trainloaders.append(trainloader)
+#         testloaders.append(testloader)
+
+#         net = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=2).to(DEVICE)
+#         client = CustomClient(net, trainloader, testloader, client_id=i+1)
+#         clients.append(client)
+
+#     if st.button("Start Training"):
+#         def client_fn(cid):
+#             return clients[int(cid)]
+
+#         def weighted_average(metrics):
+#             accuracies = [num_examples * m["accuracy"] for num_examples, m in metrics]
+#             losses = [num_examples * m["loss"] for num_examples, m in metrics]
+#             examples = [num_examples for num_examples, _ in metrics]
+#             return {"accuracy": sum(accuracies) / sum(examples), "loss": sum(losses) / sum(examples)}
+
+#         strategy = fl.server.strategy.FedAvg(
+#             fraction_fit=1.0,
+#             fraction_evaluate=1.0,
+#             evaluate_metrics_aggregation_fn=weighted_average,
+#         )
+
+#         for round_num in range(NUM_ROUNDS):
+#             st.write(f"### Round {round_num + 1}")
+
+#             fl.simulation.start_simulation(
+#                 client_fn=client_fn,
+#                 num_clients=NUM_CLIENTS,
+#                 config=fl.server.ServerConfig(num_rounds=1),
+#                 strategy=strategy,
+#                 client_resources={"num_cpus": 1, "num_gpus": 0},
+#                 ray_init_args={"log_to_driver": False, "num_cpus": 1, "num_gpus": 0}
+#             )
+
+#             for client in clients:
+#                 client.plot_metrics(round_num + 1)
+#                 st.write(" ")
+
+#         st.success(f"Training completed successfully!")
+
+#         # Display final metrics
+#         st.write("## Final Client Metrics")
+#         for client in clients:
+#             st.write(f"### Client {client.client_id}")
+#             st.write(f"Final Loss: {client.losses[-1]:.4f}")
+#             st.write(f"Final Accuracy: {client.accuracies[-1]:.4f}")
+#             client.plot_metrics(NUM_ROUNDS)
+#             st.write(" ")
+
+#     else:
+#         st.write("Click the 'Start Training' button to start the training process.")
+
+# if __name__ == "__main__":
+#     main()