Initial commit

Starting the coding.

I am using modular codes because I need to avoid error repetitions. And simplify the debugging.

project_1.py

@@ -0,0 +1,104 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Oct 23 14:50:24 2023
+
+@author: lrm22005
+"""
+
+import os
+import numpy as np
+import pandas as pd
+import torch
+from torch.utils.data import DataLoader, TensorDataset
+import matplotlib.pyplot as plt
+from sklearn.decomposition import PCA
+import seaborn as sns
+
+def load_data(data_path, dataset_size=10, train=True, standardize=True):
+    # Load data from the specified data_path
+    dir_list_UID = os.listdir(data_path)
+    UID_list = dir_list_UID[:dataset_size] if train else dir_list_UID[dataset_size:]
+
+    X_data = []
+    segment_names = []
+
+    for UID in UID_list:
+        data_path_UID = os.path.join(data_path, UID)
+        dir_list_seg = os.listdir(data_path_UID)
+
+        for seg in dir_list_seg[:50]:  # Limiting to 50 segments
+            seg_path = os.path.join(data_path_UID, seg)
+            time_freq_plot = np.array(pd.read_csv(seg_path, header=None))
+            time_freq_tensor = torch.Tensor(time_freq_plot).reshape(1, 128, 128)
+            X_data.append(time_freq_tensor)
+            segment_names.append(seg)  # Store segment names
+
+    X_data = torch.cat(X_data, 0)
+
+    if standardize:
+        X_data = standard_scaling(X_data)
+
+    return X_data, segment_names
+
+def standard_scaling(tensor):
+    # Z-score normalization (standardization)
+    mean = tensor.mean()
+    std = tensor.std()
+    tensor_standardized = (tensor - mean) / std
+    return tensor_standardized
+
+def create_dataloader(data, batch_size=64, shuffle=True):
+    dataset = TensorDataset(data, data)
+    data_loader = DataLoader(dataset, batch_size=batch_size, shuffle=shuffle)
+    return data_loader
+
+def visualize_trends(data, segment_names, num_plots=3):
+    # Visualize random trends/segments
+    num_samples, _, _ = data.shape
+    for _ in range(num_plots):
+        idx = np.random.randint(0, num_samples)
+        plt.imshow(data[idx].numpy())
+        plt.title(f"Segment: {segment_names[idx]}")
+        plt.colorbar()
+        plt.show()
+
+def perform_pca(data, num_components=2):
+    # Perform PCA for dimensionality reduction
+    data_flattened = data.view(data.size(0), -1)  # Flatten the data
+    pca = PCA(n_components=num_components)
+    reduced_data = pca.fit_transform(data_flattened.numpy())
+    return reduced_data, pca
+
+def visualize_correlation_matrix(data):
+    # Visualize the correlation matrix
+    data_flattened = data.view(data.size(0), -1).numpy()
+    correlation_matrix = np.corrcoef(data_flattened, rowvar=False)
+    sns.heatmap(correlation_matrix, cmap="coolwarm", xticklabels=False, yticklabels=False)
+    plt.title("Correlation Matrix")
+    plt.show()
+
+def main():
+    is_linux = False  # Set to True if running on Linux, False if on Windows
+    if is_linux:
+        data_path = "/mnt/r/ENGR_Chon/Dong/MATLAB_generate_results/NIH_PulseWatch/TFS_csv"
+    else:
+        data_path = r"R:\ENGR_Chon\Dong\MATLAB_generate_results\NIH_PulseWatch\TFS_csv"
+
+    train_data, segment_names = load_data(data_path, dataset_size=141, train=True)
+    test_data, _ = load_data(data_path, dataset_size=10, train=False)
+
+    train_dataloader = create_dataloader(train_data)
+    test_dataloader = create_dataloader(test_data)
+
+    # Visualize random trends/segments
+    visualize_trends(train_data, segment_names, num_plots=3)
+
+    # Perform PCA for dimensionality reduction
+    reduced_data, pca = perform_pca(train_data, num_components=2)
+    print("Explained variance ratio:", pca.explained_variance_ratio_)
+
+    # Visualize the correlation matrix
+    visualize_correlation_matrix(train_data)
+
+if __name__ == "__main__":
+    main()