spacr 0.0.81__py3-none-any.whl → 0.1.0__py3-none-any.whl

spacr/measure.py

@@ -920,7 +920,8 @@ def measure_crop(settings):
     from .io import _save_settings_to_db
     from .timelapse import _timelapse_masks_to_gif, _scmovie
     from .plot import _save_scimg_plot
-    from .utils import _list_endpoint_subdirectories, _generate_representative_images, get_measure_crop_settings, measure_test_mode
+    from .utils import _list_endpoint_subdirectories, _generate_representative_images, measure_test_mode
+    from .settings import get_measure_crop_settings
 
     settings = get_measure_crop_settings(settings)
     settings = measure_test_mode(settings)

spacr/models/cp/toxo_plaque_cyto_e25000_X1120_Y1120.CP_model_settings.csv

@@ -0,0 +1,23 @@
+Key,Value
+img_src,/nas_mnt/carruthers/patrick/Plaque_assay_training/train
+model_name,toxo_plaque
+model_type,cyto
+Signal_to_noise,10
+background,200
+remove_background,False
+learning_rate,0.2
+weight_decay,1e-05
+batch_size,8
+n_epochs,25000
+from_scratch,False
+diameter,30
+resize,True
+width_height,"[1120, 1120]"
+verbose,True
+channels,"[0, 0]"
+normalize,True
+percentiles,
+circular,False
+invert,False
+grayscale,True
+test,False

spacr/plot.py

@@ -1110,7 +1110,7 @@ def _imshow(img, labels, nrow=20, color='white', fontsize=12):
             idx = i * n_col + j
             if idx < n_images:
                 canvas[i * img_height:(i + 1) * img_height, j * img_width:(j + 1) * img_width] = np.transpose(img[idx], (1, 2, 0))        
-    plt.figure(figsize=(50, 50))
+    fig = plt.figure(figsize=(50, 50))
     plt.imshow(canvas)
     plt.axis("off")
     for i, label in enumerate(labels):
@@ -1119,7 +1119,7 @@ def _imshow(img, labels, nrow=20, color='white', fontsize=12):
         x = col * img_width + 2
         y = row * img_height + 15
         plt.text(x, y, label, color=color, fontsize=fontsize, fontweight='bold')
-    plt.show()
+    return fig
     
 def _plot_histograms_and_stats(df):
     conditions = df['condition'].unique()
@@ -1218,8 +1218,7 @@ def generate_plate_heatmap(df, plate_number, variable, grouping, min_max, min_co
         df = df[df['count'] >= min_count]
 
     # Explicitly set observed=True to avoid FutureWarning
-    grouped = df.groupby(['row', 'col'], observed=True) 
-
+    grouped = df.groupby(['row', 'col'], observed=True) # Group by row and column
     
     if grouping == 'mean':
         plate = grouped[variable].mean().reset_index()
@@ -1245,7 +1244,7 @@ def generate_plate_heatmap(df, plate_number, variable, grouping, min_max, min_co
         
     return plate_map, min_max
 
-def _plot_plates(df, variable, grouping, min_max, cmap, min_count=0):
+def plot_plates(df, variable, grouping, min_max, cmap, min_count=0, verbose=True):
     plates = df['prc'].str.split('_', expand=True)[0].unique()
     n_rows, n_cols = (len(plates) + 3) // 4, 4
     fig, ax = plt.subplots(n_rows, n_cols, figsize=(40, 5 * n_rows))
@@ -1260,7 +1259,8 @@ def _plot_plates(df, variable, grouping, min_max, cmap, min_count=0):
         fig.delaxes(ax[i])
     
     plt.subplots_adjust(wspace=0.1, hspace=0.4)
-    plt.show()
+    if verbose:
+        plt.show()
     return fig
 
 def print_mask_and_flows(stack, mask, flows, overlay=False):
@@ -1470,3 +1470,99 @@ def plot_object_outlines(src, objects=['nucleus','cell','pathogen'], channels=[0
                                overlay=True,
                                max_nr=10,
                                randomize=True)
+        
+def volcano_plot(coef_df, filename='volcano_plot.pdf'):
+    # Create the volcano plot
+    plt.figure(figsize=(10, 6))
+    sns.scatterplot(
+        data=coef_df, 
+        x='coefficient', 
+        y='-log10(p_value)', 
+        hue='highlight', 
+        palette={True: 'red', False: 'blue'}
+    )
+    plt.title('Volcano Plot of Coefficients')
+    plt.xlabel('Coefficient')
+    plt.ylabel('-log10(p-value)')
+    plt.axhline(y=-np.log10(0.05), color='red', linestyle='--')
+    plt.legend().remove()
+    plt.savefig(filename, format='pdf')
+    print(f'Saved Volcano plot: {filename}')
+    plt.show()
+
+def plot_histogram(df, dependent_variable):
+    # Plot histogram of the dependent variable
+    plt.figure(figsize=(10, 6))
+    sns.histplot(df[dependent_variable], kde=True)
+    plt.title(f'Histogram of {dependent_variable}')
+    plt.xlabel(dependent_variable)
+    plt.ylabel('Frequency')
+    plt.show()
+
+def plot_lorenz_curves(csv_files, remove_keys=['TGGT1_220950_1', 'TGGT1_233460_4']):
+    
+    def lorenz_curve(data):
+        """Calculate Lorenz curve."""
+        sorted_data = np.sort(data)
+        cumulative_data = np.cumsum(sorted_data)
+        lorenz_curve = cumulative_data / cumulative_data[-1]
+        lorenz_curve = np.insert(lorenz_curve, 0, 0)
+        return lorenz_curve
+    
+    combined_data = []
+
+    plt.figure(figsize=(10, 6))
+
+    for idx, csv_file in enumerate(csv_files):
+        if idx == 1:
+            save_fldr = os.path.dirname(csv_file)
+            save_path = os.path.join(save_fldr, 'lorenz_curve.pdf')
+            
+        df = pd.read_csv(csv_file)
+        for remove in remove_keys:
+            df = df[df['key'] != remove]
+        
+        values = df['value'].values
+        combined_data.extend(values)
+        
+        lorenz = lorenz_curve(values)
+        name = os.path.basename(csv_file)[:3]
+        plt.plot(np.linspace(0, 1, len(lorenz)), lorenz, label=name)
+
+    # Plot combined Lorenz curve
+    combined_lorenz = lorenz_curve(np.array(combined_data))
+    plt.plot(np.linspace(0, 1, len(combined_lorenz)), combined_lorenz, label="Combined Lorenz Curve", linestyle='--', color='black')
+    
+    plt.title('Lorenz Curves')
+    plt.xlabel('Cumulative Share of Individuals')
+    plt.ylabel('Cumulative Share of Value')
+    plt.legend()
+    plt.grid(False)
+    plt.savefig(save_path)
+    plt.show()
+
+def plot_permutation(permutation_df):
+    num_features = len(permutation_df)
+    fig_height = max(8, num_features * 0.3)  # Set a minimum height of 8 and adjust height based on number of features
+    fig_width = 10  # Width can be fixed or adjusted similarly
+    font_size = max(10, 12 - num_features * 0.2)  # Adjust font size dynamically
+
+    fig, ax = plt.subplots(figsize=(fig_width, fig_height))
+    ax.barh(permutation_df['feature'], permutation_df['importance_mean'], xerr=permutation_df['importance_std'], color="teal", align="center", alpha=0.6)
+    ax.set_xlabel('Permutation Importance', fontsize=font_size)
+    ax.tick_params(axis='both', which='major', labelsize=font_size)
+    plt.tight_layout()
+    return fig
+
+def plot_feature_importance(feature_importance_df):
+    num_features = len(feature_importance_df)
+    fig_height = max(8, num_features * 0.3)  # Set a minimum height of 8 and adjust height based on number of features
+    fig_width = 10  # Width can be fixed or adjusted similarly
+    font_size = max(10, 12 - num_features * 0.2)  # Adjust font size dynamically
+
+    fig, ax = plt.subplots(figsize=(fig_width, fig_height))
+    ax.barh(feature_importance_df['feature'], feature_importance_df['importance'], color="blue", align="center", alpha=0.6)
+    ax.set_xlabel('Feature Importance', fontsize=font_size)
+    ax.tick_params(axis='both', which='major', labelsize=font_size)
+    plt.tight_layout()
+    return fig