Formatting and linting

Author: mogres

cellpack_analysis/analysis/notebooks/grid_points_illustration.py

@@ -219,7 +219,7 @@ def add_distance_weights(axis_data, distance_type, distances, labels, decay_leng
         if measure == "distances":
             available_types = distance_configs.keys()
         else:  # weights
-            available_types = list(distance_configs.keys()) + ["mixed"]
+            available_types = [*list(distance_configs.keys()), "mixed"]
 
         for distance_type in available_types:
             # Skip mixed for distances since it doesn't exist

cellpack_analysis/analysis/notebooks/multi_structure_colocalization.py

@@ -66,7 +66,7 @@
         "distances": {dm: {} for dm in distance_measures},
     },
 }
-all_structures = list(set([v["structure_id"] for v in distance_dict.values()]))
+all_structures = list({v["structure_id"] for v in distance_dict.values()})
 row_modes = ["peroxisome", "endosome"]
 col_modes = ["ER", "golgi"]
 

cellpack_analysis/analysis/notebooks/multi_structure_colocalization_akaike.py

@@ -52,7 +52,7 @@
 # %% [markdown]
 # ### Load occupancy EMD data
 df_list = []
-for packing_id, comparison_mode in packing_id_info.items():
+for packing_id, _comparison_mode in packing_id_info.items():
     logger.info(f"Loading data for packing id: {packing_id}")
 
     occupancy_emd_df_path = occupancy_emd_folder / packing_id / "occupancy_emd.parquet"
@@ -122,14 +122,15 @@
 def calculate_aic(emd_values, n_params):
     """
     Calculate AIC for EMD values.
+
     AIC = 2k - 2ln(L)
-    where k is number of parameters and L is likelihood
+    where k is number of parameters and L is likelihood.
 
-    For EMD, we treat it as residuals and assume normal distribution
+    For EMD, we treat it as residuals and assume normal distribution.
     """
     n = len(emd_values)
     # Calculate log-likelihood assuming normal distribution
-    # L = -n/2 * ln(2π) - n/2 * ln(σ²) - 1/(2σ²) * Σ(residuals²)
+    # L = -n/2 * ln(2π) - n/2 * ln(sigma²) - 1/(2sigma²) * Σ(residuals²)
     # For simplicity, we use mean squared error as proxy for -2ln(L)
     mse = np.mean(emd_values**2)
     # sigma2 = np.var(emd_values, ddof=1)
@@ -273,7 +274,7 @@ def calculate_aic(emd_values, n_params):
     "Blue: 5-param preferred\nRed: 4-param preferred",
     transform=ax1.transAxes,
     verticalalignment="top",
-    bbox=dict(boxstyle="round", facecolor="white", alpha=0.8),
+    bbox={"boxstyle": "round", "facecolor": "white", "alpha": 0.8},
 )
 
 # Add strength indicators

cellpack_analysis/analysis/notebooks/multi_structure_colocalization_heatmap.py

@@ -75,7 +75,7 @@
     },
 }
 all_structures = list(
-    set([v["channel_map"][k] for v in distance_dict.values() for k in v["channel_map"]])
+    {v["channel_map"][k] for v in distance_dict.values() for k in v["channel_map"]}
 )
 
 # %% [markdown]

cellpack_analysis/lib/distance.py

@@ -266,7 +266,7 @@ def get_distance_dictionary(
                     break
 
                 all_distance_dict[distance_measure] = distance_dict
-                if not all([len(v) > 0 for v in distance_dict.values()]):
+                if not all(len(v) > 0 for v in distance_dict.values()):
                     logger.warning(
                         f"Cached data in {file_path.relative_to(PROJECT_ROOT)} is empty. "
                         f"Recalculating distances."
@@ -303,9 +303,7 @@ def get_distance_dictionary(
                     str(cell_id).split("_")[0],
                     positions,
                     mode_mesh_dict,
-                ): (
-                    str(cell_id).split("_")[0]
-                )
+                ): (str(cell_id).split("_")[0])
                 for cell_id, positions in position_dict.items()
             }
             for future in tqdm(

cellpack_analysis/lib/io.py

@@ -39,6 +39,8 @@ def load_dataframe(load_local: bool = True, prefix: str = "all_cell_ids") -> pd.
     ----------
     load_local
         If True, attempt to load from local file first. If False, load from S3.
+    prefix
+        Prefix for the parquet file name.
 
     Returns
     -------

cellpack_analysis/lib/label_tables.py

@@ -7,15 +7,15 @@ def adjust_color_saturation(hex_color, saturation):
     """
     Adjust the saturation of a hex color.
 
-    Parameters:
-    -----------
+    Parameters
+    ----------
     hex_color : str
         Hex color code (e.g., '#ff0000' or 'ff0000')
     saturation : float
         Saturation value between 0 and 1
 
-    Returns:
-    --------
+    Returns
+    -------
     str
         Hex color code with adjusted saturation
     """

cellpack_analysis/lib/mesh_tools.py

@@ -913,17 +913,17 @@ def get_grid_points_slice(
     """
     Select a slice of grid points at the median coordinate along the projection axis.
 
-    Parameters:
-    -----------
+    Parameters
+    ----------
     all_grid_points : np.ndarray
         All grid points in pixels
     projection_axis : str
         Axis to project along ('x', 'y', or 'z')
     spacing : float
         Spacing between grid points in pixels
 
-    Returns:
-    --------
+    Returns
+    -------
     grid_points_slice : np.ndarray
         Grid points for the selected slice in pixels
     """
@@ -985,6 +985,8 @@ def get_distances_from_mesh(
         Points to calculate distances for
     mesh
         Mesh to calculate distances to
+    invert
+        If True, invert the sign of the distances.
 
     Returns
     -------

cellpack_analysis/lib/occupancy.py

@@ -88,6 +88,10 @@ def get_kde_occupancy_dict(
         Maximum number of cells to sample per structure, by default None
     num_points
         Number of points for KDE evaluation, by default 100
+    x_min
+        Minimum x value for occupancy evaluation. Default is 0
+    x_max
+        Maximum x value for occupancy evaluation. Default is None
 
     Returns
     -------
@@ -336,7 +340,7 @@ def get_occupancy_emd_df(
 
     Parameters
     ----------
-    occupancy_dict
+    combined_occupancy_dict
         Dictionary containing occupancy measures for each packing mode
     packing_modes
         List of packing modes to calculate pairwise EMD for
@@ -541,6 +545,8 @@ def interpolate_occupancy_dict(
         Dictionary containing occupancy data for each packing mode
         Has the structure:
         {distance_measure:{mode:{"individual":{ ... },"combined": { ... }}}}
+    channel_map
+        Mapping from packing modes to structure IDs
     baseline_mode
         The baseline packing mode used for interpolation
     results_dir
@@ -672,10 +678,10 @@ def interpolate_occupancy_dict(
             "modes": {
                 mode: distance_data[mode]["combined"]["occupancy"] for mode in distance_data.keys()
             },
-            "coeffs_individual": {
-                mode: coeff for mode, coeff in zip(packing_modes, coeffs_individual)
-            },
-            "coeffs_joint": {mode: coeff for mode, coeff in zip(packing_modes, coeffs_joint)},
+            "coeffs_individual": dict(
+                zip(packing_modes, coeffs_individual, strict=False)
+            ),
+            "coeffs_joint": dict(zip(packing_modes, coeffs_joint, strict=False)),
             "relative_contribution_individual": {
                 mode: params["relative_contribution"]
                 for mode, params in interp_dict["interpolation"]["individual"][distance_measure][

cellpack_analysis/lib/visualization.py

@@ -705,6 +705,8 @@ def plot_occupancy_ratio(
         Dictionary containing occupancy information
     channel_map
         Dictionary mapping packing modes to channels
+    baseline_mode
+        The baseline packing mode for normalization. Default is None
     figures_dir
         Directory to save the figures
     suffix
@@ -719,6 +721,12 @@ def plot_occupancy_ratio(
         Y-axis limit for plots
     save_format
         Format to save the figures in
+    fig_params
+        Dictionary of figure parameters (dpi, figsize). Default is None
+    plot_individual
+        Whether to plot individual cell data. Default is True
+    show_legend
+        Whether to show the legend. Default is False
 
     Returns
     -------
@@ -838,6 +846,8 @@ def plot_occupancy_ratio_interpolation(
         Format to save the figures in
     plot_type
         Type of plot to generate: "individual" or "joint"
+    fig_params
+        Dictionary of figure parameters (dpi, figsize). Default is None
 
     Returns
     -------
@@ -1514,8 +1524,12 @@ def plot_grid_points_slice(
         Size of scatter plot points (default: 2)
     projection_axis
         Axis of projection ('x', 'y', or 'z')
+    cmap
+        Colormap to use for coloring. Default is None
     reverse_cmap
         Whether to reverse the colormap
+    clim
+        Color limits as (min, max) tuple. Default is None
 
     Returns
     -------