Merge pull request #3 from lrm22005/Luis

Resolve issue with trends visualization

project_1.py

@@ -46,19 +46,20 @@ def get_data_paths(data_format, is_linux=False, is_hpc=False):
 
 def load_data(data_path, labels_path, dataset_size=10, train=True, standardize=True, data_format='csv'):
     if data_format not in ['csv', 'png']:
-        raise ValueError("Invalid data_format. Choose 'csv' or 'png'.")
+        raise ValueError("Invalid data_format. Choose 'csv' or 'png.")
 
     dir_list_UID = os.listdir(data_path)
     UID_list = dir_list_UID[:dataset_size] if train else dir_list_UID[dataset_size:]
 
     X_data = []
+    X_data_original = []  # Store original data without standardization
     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
+        for seg in dir_list_seg[:len(dir_list_seg)]:  # Limiting to 50 segments
             seg_path = os.path.join(data_path_UID, seg)
 
             if data_format == 'csv' and seg.endswith('.csv'):
@@ -71,18 +72,21 @@ def load_data(data_path, labels_path, dataset_size=10, train=True, standardize=T
             else:
                 continue  # Skip other file formats
 
+            X_data_original.append(time_freq_tensor.clone())  # Store a copy of the original data
             X_data.append(time_freq_tensor)
+
             segment_names.append(seg)  # Store segment names
 
     X_data = torch.cat(X_data, 0)
+    X_data_original = torch.cat(X_data_original, 0)
 
     if standardize:
-        X_data = standard_scaling(X_data)
+        X_data = standard_scaling(X_data)  # Standardize the data
 
     # Extract labels from CSV files
     labels = extract_labels(UID_list, labels_path)
 
-    return X_data, segment_names, labels
+    return X_data_original, X_data, segment_names, labels
 
 def extract_labels(UID_list, labels_path):
     labels = {}
@@ -105,20 +109,36 @@ def create_dataloader(data, batch_size=64, shuffle=True):
     data_loader = DataLoader(dataset, batch_size=batch_size, shuffle=shuffle)
     return data_loader
 
-def visualize_trends(data, segment_names, num_plots=3, save_path=None):
-    # Visualize random trends/segments
-    num_samples, _, _ = data.shape
-    for _ in range(num_plots):
-        idx = np.random.randint(0, num_samples)
-        plt.figure()  # Create a new figure for each plot
-        plt.imshow(data[idx].numpy())
-        plt.title(f"Segment: {segment_names[idx]}")
-        plt.colorbar()
-        if save_path:
-            subject_save_path = os.path.join(save_path, f"trends_visualization_segment_{segment_names}.png")
-            plt.savefig(subject_save_path)
-        plt.show()
+def visualize_trends(standardized_data, original_data, segment_names, num_plots=3, data_format='csv', save_path=None):
+    if data_format == 'csv':
+        num_samples, num_columns, num_rows = original_data.shape
+        for _ in range(num_plots):
+            idx = np.random.randint(0, num_samples)
+            # Create a figure with three subplots
+            fig, axes = plt.subplots(2, 1, figsize=(16, 5))
+
+            # Plot the trend matrix of the original data
+            axes[0].imshow(original_data[idx], aspect='auto', cmap='viridis')
+            axes[0].set_title(f"Trend Matrix (Original Data): Segment {segment_names[idx]}")
+            axes[0].set_xlabel("Matrix Width")
+            axes[0].set_ylabel("Matrix Height")
+
+            # Plot the trend matrix of the standardized data
+            axes[1].imshow(standardized_data[idx].numpy(), aspect='auto', cmap='viridis')
+            axes[1].set_title(f"Trend Matrix (Standardized Data): Segment {segment_names[idx]}")
+            axes[1].set_xlabel("Matrix Width")
+            axes[1].set_ylabel("Matrix Height")
+            plt.tight_layout()
 
+            if save_path:
+                subject_save_path = os.path.join(save_path, f"trends_visualization_segment_{segment_names[idx]}.png")
+                plt.savefig(subject_save_path)
+            plt.show()
+    elif data_format == 'png':
+        print("This is a trend analysis for PNG data format.")
+    else:
+        print("This is a trend analysis for data in an unsupported format.")
+
 def perform_pca(data, num_components=2):
     # Perform PCA for dimensionality reduction
     data_flattened = data.view(data.size(0), -1)  # Flatten the data
@@ -311,36 +331,35 @@ def main():
     is_linux = False  # Set to True if running on Linux, False if on Windows
     is_hpc = False # Set to True if running on hpc, False if on Windows
 
-    data_format = 'png'  # Choose 'csv' or 'png'
+    data_format = 'csv'  # Choose 'csv' or 'png'
 
     data_path, labels_path, saving_path = get_data_paths(data_format, is_linux=is_linux, is_hpc=is_hpc)
-
-    train_data, segment_names, labels = load_data(data_path, labels_path, dataset_size=10, train=True, data_format=data_format)
+    original_data, standardized_data, segment_names, labels = load_data(data_path, labels_path, dataset_size=10, train=True, data_format=data_format)
     # test_data, _, _ = load_data(data_path, labels_path, dataset_size=30, train=False)
 
-    train_dataloader = create_dataloader(train_data)
+    train_dataloader = create_dataloader(standardized_data)
     # test_dataloader = create_dataloader(test_data)
 
     # Visualize random trends/segments
-    visualize_trends(train_data, segment_names, num_plots=20)
+    visualize_trends(standardized_data, original_data, segment_names, num_plots=10, data_format=data_format, save_path=None)
 
     # Perform PCA for dimensionality reduction
-    # reduced_data, pca = perform_pca(train_data, num_components=2)
+    # reduced_data, pca = perform_pca(standardized_data, num_components=2)
     # print("Explained variance ratio:", pca.explained_variance_ratio_)
 
     # Visualize the correlation matrix
-    visualize_correlation_matrix(train_data, segment_names, subject_mode=True, num_subjects_to_visualize=None, save_path=saving_path)
-    # visualize_correlation_matrix(train_data, segment_names, subject_mode=False, num_subjects_to_visualize=None, save_path=saving_path)
-    # visualize_correlation_matrix(train_data, segment_names, subject_mode=False, num_subjects_to_visualize=None, save_path=saving_path)
+    visualize_correlation_matrix(standardized_data, segment_names, subject_mode=True, num_subjects_to_visualize=None, save_path=saving_path)
+    # visualize_correlation_matrix(standardized_data, segment_names, subject_mode=False, num_subjects_to_visualize=None, save_path=saving_path)
+    # visualize_correlation_matrix(standardized_data, segment_names, subject_mode=False, num_subjects_to_visualize=None, save_path=saving_path)
 
     # Perform MFVI for your data
     K = 4  # Number of clusters
-    miu_mfvi, pi_mfvi, resp_mfvi = perform_mfvi(train_data, K, n_optimization_iterations=1000, convergence_threshold=1e-5, run_until_convergence=False)
+    miu_mfvi, pi_mfvi, resp_mfvi = perform_mfvi(standardized_data, K, n_optimization_iterations=1000, convergence_threshold=1e-5, run_until_convergence=False)
 
     # Calculate clustering metrics for MFVI
     zi_mfvi = np.argmax(resp_mfvi, axis=1)
     # Perform PCA for dimensionality reduction
-    reduced_data, pca = perform_pca(train_data, num_components=2)
+    reduced_data, pca = perform_pca(standardized_data, num_components=2)
     print("Explained variance ratio:", pca.explained_variance_ratio_)
 
     # Create two plots: PCA results and original labels