Chore: upadate copyright year

Signed-off-by: Dasun Abeykoon <Dasun20202020@gmail.com>

Author: dabeycorn

src/diffpy/__init__.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 ##############################################################################
 #
-# (c) 2025 The Trustees of Columbia University in the City of New York.
+# (c) 2024-2025 The Trustees of Columbia University in the City of New York.
 # All rights reserved.
 #
 # File coded by: Billinge Group members and community contributors.

src/diffpy/nmf_mapping/__init__.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 ##############################################################################
 #
-# (c) 2025 The Trustees of Columbia University in the City of New York.
+# (c) 2024-2025 The Trustees of Columbia University in the City of New York.
 # All rights reserved.
 #
 # File coded by: Billinge Group members and community contributors.

src/diffpy/nmf_mapping/main.py

@@ -20,8 +20,8 @@ def boolean_string(s):
 
 def main(args=None):
     """Parses directory argument supplied by user and conducts NMF
-    decomposition analysis (computes NMF decomposition and shows the weights
-    over time)."""
+    decomposition analysis (computes NMF decomposition and shows the
+    weights over time)."""
 
     _BANNER = """
     This is a package which takes a directory of 1D diffraction files
@@ -38,13 +38,17 @@ def main(args=None):
 
     def tup(s):
         if not isinstance(s, str):
-            raise TypeError("Input must be a string of two integers separated by a comma.")
+            raise TypeError(
+                "Input must be a string of two integers separated by a comma."
+            )
 
         try:
             l, h = map(int, s.split(","))
             return l, h
         except ValueError:
-            raise ValueError("Input must be two integers separated by a comma (e.g., '1,5')")
+            raise ValueError(
+                "Input must be two integers separated by a comma (e.g., '1,5')"
+            )
 
     # args
     parser.add_argument(
@@ -94,15 +98,19 @@ def tup(s):
         "--xrd",
         default=False,
         type=boolean_string,
-        help="whether to look for .xy files rather than .gr files\n" "default: False\n" "e.g. --xrd True",
+        help="whether to look for .xy files rather than .gr files\n"
+        "default: False\n"
+        "e.g. --xrd True",
     )
     parser.add_argument(
         "--x_units",
         default=None,
         type=str,
         choices=["twotheta", "q"],
         required="--xrd" in sys.argv,
-        help="x axis units for XRD data\n" "default: None\n" "e.g. --x_units twotheta",
+        help="x axis units for XRD data\n"
+        "default: None\n"
+        "e.g. --x_units twotheta",
     )
     parser.add_argument(
         "--xrange",
@@ -152,7 +160,9 @@ def tup(s):
 
     print(f"Number of components: {len(df_components.columns)}")
 
-    fig1 = nmf.component_plot(df_components, args1.xrd, args1.x_units, args1.show)
+    fig1 = nmf.component_plot(
+        df_components, args1.xrd, args1.x_units, args1.show
+    )
     fig2 = nmf.component_ratio_plot(df_component_weight_timeseries, args1.show)
     fig3 = nmf.reconstruction_error_plot(df_reconstruction_error, args1.show)
     if args1.pca_thresh:
@@ -161,10 +171,18 @@ def tup(s):
     if args1.save_files:
         if not os.path.exists(os.path.join(os.getcwd(), "nmf_result")):
             os.mkdir(os.path.join(os.getcwd(), "nmf_result"))
-        output_fn = datetime.fromtimestamp(time.time()).strftime("%Y%m%d%H%M%S%f")
-        df_components.to_json(os.path.join(os.getcwd(), "nmf_result", "x_index_vs_y_col_components.json"))
+        output_fn = datetime.fromtimestamp(time.time()).strftime(
+            "%Y%m%d%H%M%S%f"
+        )
+        df_components.to_json(
+            os.path.join(
+                os.getcwd(), "nmf_result", "x_index_vs_y_col_components.json"
+            )
+        )
         df_component_weight_timeseries.to_json(
-            os.path.join(os.getcwd(), "nmf_result", "component_index_vs_pratio_col.json")
+            os.path.join(
+                os.getcwd(), "nmf_result", "component_index_vs_pratio_col.json"
+            )
         )
         df_component_weight_timeseries.to_csv(
             os.path.join(
@@ -178,27 +196,47 @@ def tup(s):
             mode="a",
         )
         df_reconstruction_error.to_json(
-            os.path.join(os.getcwd(), "nmf_result", "component_index_vs_RE_value.json")
+            os.path.join(
+                os.getcwd(), "nmf_result", "component_index_vs_RE_value.json"
+            )
+        )
+        plot_file1 = os.path.join(
+            os.getcwd(), "nmf_result", output_fn + "comp_plot.png"
+        )
+        plot_file2 = os.path.join(
+            os.getcwd(), "nmf_result", output_fn + "ratio_plot.png"
+        )
+        plot_file3 = os.path.join(
+            os.getcwd(), "nmf_result", output_fn + "loss_plot.png"
         )
-        plot_file1 = os.path.join(os.getcwd(), "nmf_result", output_fn + "comp_plot.png")
-        plot_file2 = os.path.join(os.getcwd(), "nmf_result", output_fn + "ratio_plot.png")
-        plot_file3 = os.path.join(os.getcwd(), "nmf_result", output_fn + "loss_plot.png")
         if args1.pca_thresh:
-            plot_file7 = os.path.join(os.getcwd(), "nmf_result", output_fn + "pca_var_plot.png")
+            plot_file7 = os.path.join(
+                os.getcwd(), "nmf_result", output_fn + "pca_var_plot.png"
+            )
         plot_file4 = os.path.splitext(plot_file1)[0] + ".pdf"
         plot_file5 = os.path.splitext(plot_file2)[0] + ".pdf"
         plot_file6 = os.path.splitext(plot_file3)[0] + ".pdf"
         if args1.pca_thresh:
             plot_file8 = os.path.splitext(plot_file7)[0] + ".pdf"
-        txt_file = os.path.join(os.getcwd(), "nmf_result", output_fn + "_meta" + ".txt")
+        txt_file = os.path.join(
+            os.getcwd(), "nmf_result", output_fn + "_meta" + ".txt"
+        )
         with open(txt_file, "w+") as fi:
             fi.write("NMF Analysis\n\n")
-            fi.write(f"{len(df_component_weight_timeseries.columns)} files uploaded for analysis.\n\n")
+            fi.write(
+                f"{len(df_component_weight_timeseries.columns)} files uploaded for analysis.\n\n"
+            )
             fi.write(f"The selected active r ranges are:  {args1.xrange} \n\n")
             fi.write("Thesholding:\n")
-            fi.write(f"\tThe input component threshold was: {args1.threshold}\n")
-            fi.write(f"\tThe input improvement threshold was: {args1.improve_thresh}\n")
-            fi.write(f"\tThe input # of iterations to run was: {args1.n_iter}\n")
+            fi.write(
+                f"\tThe input component threshold was: {args1.threshold}\n"
+            )
+            fi.write(
+                f"\tThe input improvement threshold was: {args1.improve_thresh}\n"
+            )
+            fi.write(
+                f"\tThe input # of iterations to run was: {args1.n_iter}\n"
+            )
             fi.write(f"\tWas PCA thresholding used?: {args1.pca_thresh}\n")
             fi.write(f"{len(df_components.columns)} components were extracted")
 
@@ -214,7 +252,9 @@ def tup(s):
             fig4.savefig(plot_file8)
         columns = df_components.columns
         for i, col in enumerate(columns):
-            data = np.column_stack([df_components.index.to_list(), df_components[col].to_list()])
+            data = np.column_stack(
+                [df_components.index.to_list(), df_components[col].to_list()]
+            )
 
             if args1.xrd:
                 np.savetxt(
@@ -237,7 +277,8 @@ def tup(s):
                         output_fn + f"_comp{i}" + ".cgr",
                     ),
                     data,
-                    header=f"NMF Generated PDF\nSource: nmfMapping\n" f"Date: {output_fn}\nr g",
+                    header=f"NMF Generated PDF\nSource: nmfMapping\n"
+                    f"Date: {output_fn}\nr g",
                     fmt="%s",
                 )
 

src/diffpy/nmf_mapping/nmf_mapping_code.py

@@ -36,8 +36,8 @@ def natural_keys_file_name(text):
 
 
 def load_data(dir, xrd=False):
-    """Takes a directory and selects out the .gr or .xy or .xye files. Loads
-    these files into a 3D numpy array.
+    """Takes a directory and selects out the .gr or .xy or .xye files.
+    Loads these files into a 3D numpy array.
 
     Parameters
     ----------
@@ -80,7 +80,9 @@ def load_data(dir, xrd=False):
         x = new_dat[:, 0]
         y = new_dat[:, 1]
         if len(x) != len(x_set) or not all(x == x_set):
-            f = interpolate.interp1d(x, y, bounds_error=False, fill_value="extrapolate")
+            f = interpolate.interp1d(
+                x, y, bounds_error=False, fill_value="extrapolate"
+            )
             data_arr[i][:, 1] = f(x_set)
             data_arr[i][:, 0] = x_set
         else:
@@ -106,10 +108,10 @@ def NMF_decomposition(
     pca_thresh=None,
 ):
     """Takes a 3D array of PDFs and returns the structurally significant
-    components present in all of the PDFs (or XRD) provided in r vs gr format,
-    as well as the ratio of each in the data list, as well as the
-    reconstruction error found in the first 10 components regardless of the
-    threshold.
+    components present in all of the PDFs (or XRD) provided in r vs gr
+    format, as well as the ratio of each in the data list, as well as
+    the reconstruction error found in the first 10 components regardless
+    of the threshold.
 
     Parameters
     ----------
@@ -150,7 +152,8 @@ def NMF_decomposition(
             else:
                 df_list.append(
                     x_vs_y_df_preprocess[
-                        (x_vs_y_df_preprocess.index >= x_low) & (x_vs_y_df_preprocess.index <= x_high)
+                        (x_vs_y_df_preprocess.index >= x_low)
+                        & (x_vs_y_df_preprocess.index <= x_high)
                     ]
                 )
         x_vs_y_df = pd.concat(df_list)
@@ -173,7 +176,9 @@ def NMF_decomposition(
         pca.fit(x_vs_y_df.to_numpy().T)
         pca_number_components = len(pca.components_)
         pca_explained_variance = pca.explained_variance_ratio_
-        df_explained_var_ratio = pd.DataFrame(pd.Series(pca_explained_variance))
+        df_explained_var_ratio = pd.DataFrame(
+            pd.Series(pca_explained_variance)
+        )
         df_explained_var_ratio.index = df_explained_var_ratio.index + 1
     sweeping_grid = range(1, max_comp + 1, 1)
     for i in sweeping_grid:
@@ -186,7 +191,9 @@ def NMF_decomposition(
     if thresh is None:
         if improve_thresh is not None:
             if improve_thresh > 1 or improve_thresh < 0:
-                raise ValueError("Invalid improvement threshold ratio. Must be between 0 and 1.")
+                raise ValueError(
+                    "Invalid improvement threshold ratio. Must be between 0 and 1."
+                )
             thresh = nmf_ncomp_selection(nmf_loss, rtol=improve_thresh)
         elif pca_thresh:
             thresh = pca_number_components
@@ -209,7 +216,9 @@ def NMF_decomposition(
     nmf_weight /= nmf_weight.sum(1)[:, np.newaxis]
     nmf_weight = nmf_weight.T
     nmf_weight = np.array([nmf_weight[s, :] for s in range(n_comp)])
-    df_component_weight_timeseries = pd.DataFrame(nmf_weight, index=range(n_comp))
+    df_component_weight_timeseries = pd.DataFrame(
+        nmf_weight, index=range(n_comp)
+    )
 
     if pca_thresh:
         return (
@@ -226,8 +235,9 @@ def NMF_decomposition(
 
 
 def component_plot(df_components, xrd=False, x_units=None, show=True):
-    """Takes a dataframe containing the NMF components as columns and x index,
-    Returns a matplotlib figure representing the constituent component plot.
+    """Takes a dataframe containing the NMF components as columns and x
+    index, Returns a matplotlib figure representing the constituent
+    component plot.
 
     Parameters
     ----------
@@ -280,10 +290,10 @@ def component_plot(df_components, xrd=False, x_units=None, show=True):
 
 
 def component_ratio_plot(df_component_weight_timeseries, show=True):
-    """Takes a pandas df with the index representing the components and the
-    columns representing the different experiments, the values being the
-    weight. Returns a matplotlib figure of the component ratio across the files
-    provided.
+    """Takes a pandas df with the index representing the components and
+    the columns representing the different experiments, the values being
+    the weight. Returns a matplotlib figure of the component ratio
+    across the files provided.
 
     Parameters
     ----------
@@ -316,9 +326,9 @@ def component_ratio_plot(df_component_weight_timeseries, show=True):
 
 
 def reconstruction_error_plot(df_reconstruction_error, show=True):
-    """Takes a pandas df with one column representing the reconstruction error
-    and an index of the phase component. Returns a matplotlib figure of the
-    reconstruction error plot.
+    """Takes a pandas df with one column representing the reconstruction
+    error and an index of the phase component. Returns a matplotlib
+    figure of the reconstruction error plot.
 
     Parameters
     ----------
@@ -353,9 +363,9 @@ def reconstruction_error_plot(df_reconstruction_error, show=True):
 
 
 def explained_variance_plot(df_explained_var_ratio, show=True):
-    """Takes a pandas df with one column representing the reconstruction error
-    and an index of the phase component. Returns a matplotlib figure of the
-    reconstruction error plot.
+    """Takes a pandas df with one column representing the reconstruction
+    error and an index of the phase component. Returns a matplotlib
+    figure of the reconstruction error plot.
 
     Parameters
     ----------
@@ -407,10 +417,14 @@ def nmf_ncomp_selection(loss, rtol=None):
         rtol = 1e-2
         (inds,) = np.where(imp_ratio <= rtol)
         if not list(inds):
-            print("Improvement ratio of 1E-2 not met. Inspect data and impose manual cutoff")
+            print(
+                "Improvement ratio of 1E-2 not met. Inspect data and impose manual cutoff"
+            )
             len(loss)
             return starting_len
     if not list(inds):
-        print(f"Improvement ratio of {rtol} not met. Inspect data and impose manual cutoff")
+        print(
+            f"Improvement ratio of {rtol} not met. Inspect data and impose manual cutoff"
+        )
         return starting_len
     return inds[0] + 1

src/diffpy/nmf_mapping/version.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 ##############################################################################
 #
-# (c) 2025 The Trustees of Columbia University in the City of New York.
+# (c) 2024-2025 The Trustees of Columbia University in the City of New York.
 # All rights reserved.
 #
 # File coded by: Billinge Group members and community contributors.

src/diffpy/version.py

@@ -23,6 +23,8 @@
 __version__ = get_distribution("diffpy.nmf_mapping").version
 
 # we assume that tag_date was used and __version__ ends in YYYYMMDD
-__date__ = __version__[-8:-4] + "-" + __version__[-4:-2] + "-" + __version__[-2:]
+__date__ = (
+    __version__[-8:-4] + "-" + __version__[-4:-2] + "-" + __version__[-2:]
+)
 
 # End of file