Fix typing errors

biobb_dna/dna/dna_averages.py

@@ -158,11 +158,11 @@ def launch(self) -> int:
                 for i in self.seqpos]
 
         # rename duplicated subunits
-        while any(ser_data.columns.duplicated()):
+        while any(pd.Index(ser_data.columns).duplicated()):
             ser_data.columns = [
                 name if not duplicated else name + "_dup"
                 for duplicated, name
-                in zip(ser_data.columns.duplicated(), ser_data.columns)]
+                in zip(pd.Index(ser_data.columns).duplicated(), ser_data.columns)]
 
         # write output files for all selected bases
         means = ser_data.mean(axis=0).iloc[:len(xlabels)]

biobb_dna/dna/dna_bimodality.py

@@ -10,8 +10,7 @@
 import pandas as pd
 import numpy as np
 import matplotlib.pyplot as plt
-from sklearn.mixture import GaussianMixture
-
+from sklearn.mixture import GaussianMixture  # type: ignore
 from biobb_dna.utils import constants
 from biobb_common.generic.biobb_object import BiobbObject
 from biobb_common.configuration import settings
@@ -210,12 +209,12 @@ def launch(self) -> int:
             label1 = "Single State"
         out = plt.hist(
             synth1, bins=bins, alpha=alpha, density=True, label=label1)
-        ylim = max(out[0])
+        ylim = max(out[0])  # type: ignore
         plt.vlines(info['mean1'], 0, ylim, colors="r", linestyles="dashed")
         if binormal:
             out = plt.hist(
                 synth2, bins=bins, alpha=alpha, density=True, label="high state")
-            ylim = max(out[0])
+            ylim = max(out[0])  # type: ignore
             plt.vlines(info['mean2'], 0, ylim, colors="r", linestyles="dashed")
         plt.legend()
         plt.ylabel("Density")
@@ -255,10 +254,10 @@ def fit_to_model(self, data):
                 max_iter=self.max_iter,
                 tol=self.tol)
             gmm = gmm.fit(data)
-            m = gmm.means_.flatten()
-            v = gmm.covariances_.flatten()
+            m = gmm.means_.flatten()  # type: ignore
+            v = gmm.covariances_.flatten()  # type: ignore
             b = gmm.bic(data)
-            w = gmm.weights_.flatten()
+            w = gmm.weights_.flatten()  # type: ignore
             means.append(m)
             variances.append(v)
             bics.append(b)

biobb_dna/dna/dna_timeseries.py

@@ -175,9 +175,9 @@ def launch(self) -> int:
             # get removed items
             removed_items = [s for s in subunits if not pattern.fullmatch(s)]
             # get indices of removed items (in integer format and starting from 0)
-            removed_numbers = [re.match(r'\d+', item).group() for item in removed_items]
+            removed_numbers = [int(match.group()) for item in removed_items if (match := re.match(r'\d+', item))]
             removed_numbers = list(map(int, removed_numbers))
-            removed_numbers = [i-1 for i in removed_numbers]
+            removed_numbers = [int(i)-1 for i in removed_numbers]
             # remove non basepairs from subunits and indices
             subunits = [s for s in subunits if pattern.fullmatch(s)]
             indices = [i for i in indices if i not in removed_numbers]

biobb_dna/interbp_correlations/interbpcorr.py

@@ -185,12 +185,12 @@ def launch(self) -> int:
             ):
                 method = self.circlineal
             else:
-                method = "pearson"
+                method = "pearson"  # type: ignore
             corr_data = ser1.corrwith(ser2_shifted, method=method)
             corr_data.index = corr_index
             results[f"{ser1.name}/{ser2.name}"] = corr_data
         result_df = pd.DataFrame.from_dict(results)
-        result_df.index = corr_index
+        result_df.index = corr_index  # type: ignore
 
         # save csv data
         result_df.to_csv(self.stage_io_dict["out"]["output_csv_path"])
@@ -199,7 +199,7 @@ def launch(self) -> int:
         cmap = plt.get_cmap("bwr").copy()
         bounds = [-1, -.8, -.6, -.4, -.2, .2, .4, .6, .8, 1]
         num = cmap.N
-        norm = mpl.colors.BoundaryNorm(bounds, num)
+        norm = mpl.colors.BoundaryNorm(bounds, num)  # type: ignore
         cmap.set_bad(color="gainsboro")
         fig, ax = plt.subplots(
             1,
@@ -217,7 +217,7 @@ def launch(self) -> int:
 
         ylocs = np.arange(len(result_df.index))
         _ = ax.set_yticks(ylocs)
-        _ = ax.set_yticklabels(result_df.index.to_list())
+        _ = ax.set_yticklabels(result_df.index.to_list())  # type: ignore
 
         ax.set_title(
             "Correlation for neighboring basepairs "

biobb_dna/interbp_correlations/interhpcorr.py

@@ -130,11 +130,11 @@ def launch(self) -> int:
         # corr_matrix["shift"]["rise"] = shift.corrwith(rise, method="pearson")
         corr_matrix.loc["rise", "shift"] = shift.corrwith(rise, method="pearson").values[0]
         # corr_matrix["shift"]["tilt"] = shift.corrwith(tilt, method=self.circlineal)
-        corr_matrix.loc["tilt", "shift"] = shift.corrwith(tilt, method=self.circlineal).values[0]
+        corr_matrix.loc["tilt", "shift"] = shift.corrwith(tilt, method=self.circlineal).values[0]  # type: ignore
         # corr_matrix["shift"]["roll"] = shift.corrwith(roll, method=self.circlineal)
-        corr_matrix.loc["roll", "shift"] = shift.corrwith(roll, method=self.circlineal).values[0]
+        corr_matrix.loc["roll", "shift"] = shift.corrwith(roll, method=self.circlineal).values[0]  # type: ignore
         # corr_matrix["shift"]["twist"] = shift.corrwith(twist, method=self.circlineal)
-        corr_matrix.loc["twist", "shift"] = shift.corrwith(twist, method=self.circlineal).values[0]
+        corr_matrix.loc["twist", "shift"] = shift.corrwith(twist, method=self.circlineal).values[0]  # type: ignore
         # symmetric values
         # corr_matrix["slide"]["shift"] = corr_matrix["shift"]["slide"]
         corr_matrix.loc["shift", "slide"] = corr_matrix.loc["slide", "shift"]
@@ -151,11 +151,11 @@ def launch(self) -> int:
         # corr_matrix["slide"]["rise"] = slide.corrwith(rise, method="pearson")
         corr_matrix.loc["rise", "slide"] = slide.corrwith(rise, method="pearson").values[0]
         # corr_matrix["slide"]["tilt"] = slide.corrwith(tilt, method=self.circlineal)
-        corr_matrix.loc["tilt", "slide"] = slide.corrwith(tilt, method=self.circlineal).values[0]
+        corr_matrix.loc["tilt", "slide"] = slide.corrwith(tilt, method=self.circlineal).values[0]  # type: ignore
         # corr_matrix["slide"]["roll"] = slide.corrwith(roll, method=self.circlineal)
-        corr_matrix.loc["roll", "slide"] = slide.corrwith(roll, method=self.circlineal).values[0]
+        corr_matrix.loc["roll", "slide"] = slide.corrwith(roll, method=self.circlineal).values[0]  # type: ignore
         # corr_matrix["slide"]["twist"] = slide.corrwith(twist, method=self.circlineal)
-        corr_matrix.loc["twist", "slide"] = slide.corrwith(twist, method=self.circlineal).values[0]
+        corr_matrix.loc["twist", "slide"] = slide.corrwith(twist, method=self.circlineal).values[0]  # type: ignore
         # symmetric values
         # corr_matrix["rise"]["slide"] = corr_matrix["slide"]["rise"]
         corr_matrix.loc["slide", "rise"] = corr_matrix.loc["rise", "slide"]
@@ -168,11 +168,11 @@ def launch(self) -> int:
 
         # rise
         # corr_matrix["rise"]["tilt"] = rise.corrwith(tilt, method=self.circlineal)
-        corr_matrix.loc["tilt", "rise"] = rise.corrwith(tilt, method=self.circlineal).values[0]
+        corr_matrix.loc["tilt", "rise"] = rise.corrwith(tilt, method=self.circlineal).values[0]  # type: ignore
         # corr_matrix["rise"]["roll"] = rise.corrwith(roll, method=self.circlineal)
-        corr_matrix.loc["roll", "rise"] = rise.corrwith(roll, method=self.circlineal).values[0]
+        corr_matrix.loc["roll", "rise"] = rise.corrwith(roll, method=self.circlineal).values[0]  # type: ignore
         # corr_matrix["rise"]["twist"] = rise.corrwith(twist, method=self.circlineal)
-        corr_matrix.loc["twist", "rise"] = rise.corrwith(twist, method=self.circlineal).values[0]
+        corr_matrix.loc["twist", "rise"] = rise.corrwith(twist, method=self.circlineal).values[0]  # type: ignore
         # symmetric values
         # corr_matrix["tilt"]["rise"] = corr_matrix["rise"]["tilt"]
         corr_matrix.loc["rise", "tilt"] = corr_matrix.loc["tilt", "rise"]
@@ -183,9 +183,9 @@ def launch(self) -> int:
 
         # tilt
         # corr_matrix["tilt"]["roll"] = tilt.corrwith(roll, method=self.circular)
-        corr_matrix.loc["roll", "tilt"] = tilt.corrwith(roll, method=self.circular).values[0]
+        corr_matrix.loc["roll", "tilt"] = tilt.corrwith(roll, method=self.circular).values[0]  # type: ignore
         # corr_matrix["tilt"]["twist"] = tilt.corrwith(twist, method=self.circular)
-        corr_matrix.loc["twist", "tilt"] = tilt.corrwith(twist, method=self.circular).values[0]
+        corr_matrix.loc["twist", "tilt"] = tilt.corrwith(twist, method=self.circular).values[0]  # type: ignore
         # symmetric values
         # corr_matrix["roll"]["tilt"] = corr_matrix["tilt"]["roll"]
         corr_matrix.loc["tilt", "roll"] = corr_matrix.loc["roll", "tilt"]
@@ -194,7 +194,7 @@ def launch(self) -> int:
 
         # roll
         # corr_matrix["roll"]["twist"] = roll.corrwith(twist, method=self.circular)
-        corr_matrix.loc["twist", "roll"] = roll.corrwith(twist, method=self.circular).values[0]
+        corr_matrix.loc["twist", "roll"] = roll.corrwith(twist, method=self.circular).values[0]  # type: ignore
         # symmetric values
         # corr_matrix["twist"]["roll"] = corr_matrix["roll"]["twist"]
         corr_matrix.loc["roll", "twist"] = corr_matrix.loc["twist", "roll"]

biobb_dna/intrabp_correlations/intrabpcorr.py

@@ -185,12 +185,12 @@ def launch(self) -> int:
             ):
                 method = self.circlineal
             else:
-                method = "pearson"
+                method = "pearson"  # type: ignore
             corr_data = ser1.corrwith(ser2_shifted, method=method)
             corr_data.index = corr_index
             results[f"{ser1.name}/{ser2.name}"] = corr_data
         result_df = pd.DataFrame.from_dict(results)
-        result_df.index = corr_index
+        result_df.index = corr_index  # type: ignore
 
         # save csv data
         result_df.to_csv(self.stage_io_dict["out"]["output_csv_path"])
@@ -199,7 +199,7 @@ def launch(self) -> int:
         cmap = plt.get_cmap("bwr").copy()
         bounds = [-1, -.8, -.6, -.4, -.2, .2, .4, .6, .8, 1]
         num = cmap.N
-        norm = mpl.colors.BoundaryNorm(bounds, num)
+        norm = mpl.colors.BoundaryNorm(bounds, num)  # type: ignore
         cmap.set_bad(color="gainsboro")
         fig, ax = plt.subplots(
             1,
@@ -217,7 +217,7 @@ def launch(self) -> int:
 
         ylocs = np.arange(len(result_df.index))
         _ = ax.set_yticks(ylocs)
-        _ = ax.set_yticklabels(result_df.index.to_list())
+        _ = ax.set_yticklabels(result_df.index.to_list())  # type: ignore
 
         ax.set_title(
             "Correlation for neighboring basepairs "

biobb_dna/intrabp_correlations/intrahpcorr.py

@@ -132,11 +132,11 @@ def launch(self) -> int:
         # corr_matrix["shear"]["stagger"] = shear.corrwith(stagger, method="pearson")
         corr_matrix.loc["stagger", "shear"] = shear.corrwith(stagger, method="pearson").values[0]
         # corr_matrix["shear"]["buckle"] = shear.corrwith(buckle, method=self.circlineal)
-        corr_matrix.loc["buckle", "shear"] = shear.corrwith(buckle, method=self.circlineal).values[0]
+        corr_matrix.loc["buckle", "shear"] = shear.corrwith(buckle, method=self.circlineal).values[0]  # type: ignore
         # corr_matrix["shear"]["propel"] = shear.corrwith(propel, method=self.circlineal)
-        corr_matrix.loc["propel", "shear"] = shear.corrwith(propel, method=self.circlineal).values[0]
+        corr_matrix.loc["propel", "shear"] = shear.corrwith(propel, method=self.circlineal).values[0]  # type: ignore
         # corr_matrix["shear"]["opening"] = shear.corrwith(opening, method=self.circlineal)
-        corr_matrix.loc["opening", "shear"] = shear.corrwith(opening, method=self.circlineal).values[0]
+        corr_matrix.loc["opening", "shear"] = shear.corrwith(opening, method=self.circlineal).values[0]  # type: ignore
         # symmetric values
         # corr_matrix["stretch"]["shear"] = corr_matrix["shear"]["stretch"]
         corr_matrix.loc["shear", "stretch"] = corr_matrix.loc["stretch", "shear"]
@@ -153,11 +153,11 @@ def launch(self) -> int:
         # corr_matrix["stretch"]["stagger"] = stretch.corrwith(stagger, method="pearson")
         corr_matrix.loc["stagger", "stretch"] = stretch.corrwith(stagger, method="pearson").values[0]
         # corr_matrix["stretch"]["buckle"] = stretch.corrwith(buckle, method=self.circlineal)
-        corr_matrix.loc["buckle", "stretch"] = stretch.corrwith(buckle, method=self.circlineal).values[0]
+        corr_matrix.loc["buckle", "stretch"] = stretch.corrwith(buckle, method=self.circlineal).values[0]  # type: ignore
         # corr_matrix["stretch"]["propel"] = stretch.corrwith(propel, method=self.circlineal)
-        corr_matrix.loc["propel", "stretch"] = stretch.corrwith(propel, method=self.circlineal).values[0]
+        corr_matrix.loc["propel", "stretch"] = stretch.corrwith(propel, method=self.circlineal).values[0]  # type: ignore
         # corr_matrix["stretch"]["opening"] = stretch.corrwith(opening, method=self.circlineal)
-        corr_matrix.loc["opening", "stretch"] = stretch.corrwith(opening, method=self.circlineal).values[0]
+        corr_matrix.loc["opening", "stretch"] = stretch.corrwith(opening, method=self.circlineal).values[0]  # type: ignore
         # symmetric values
         # corr_matrix["stagger"]["stretch"] = corr_matrix["stretch"]["stagger"]
         corr_matrix.loc["stretch", "stagger"] = corr_matrix.loc["stagger", "stretch"]
@@ -170,11 +170,11 @@ def launch(self) -> int:
 
         # stagger
         # corr_matrix["stagger"]["buckle"] = stagger.corrwith(buckle, method=self.circlineal)
-        corr_matrix.loc["buckle", "stagger"] = stagger.corrwith(buckle, method=self.circlineal).values[0]
+        corr_matrix.loc["buckle", "stagger"] = stagger.corrwith(buckle, method=self.circlineal).values[0]  # type: ignore
         # corr_matrix["stagger"]["propel"] = stagger.corrwith(propel, method=self.circlineal)
-        corr_matrix.loc["propel", "stagger"] = stagger.corrwith(propel, method=self.circlineal).values[0]
+        corr_matrix.loc["propel", "stagger"] = stagger.corrwith(propel, method=self.circlineal).values[0]  # type: ignore
         # corr_matrix["stagger"]["opening"] = stagger.corrwith(opening, method=self.circlineal)
-        corr_matrix.loc["opening", "stagger"] = stagger.corrwith(opening, method=self.circlineal).values[0]
+        corr_matrix.loc["opening", "stagger"] = stagger.corrwith(opening, method=self.circlineal).values[0]  # type: ignore
         # symmetric values
         # corr_matrix["buckle"]["stagger"] = corr_matrix["stagger"]["buckle"]
         corr_matrix.loc["stagger", "buckle"] = corr_matrix.loc["buckle", "stagger"]
@@ -185,9 +185,9 @@ def launch(self) -> int:
 
         # buckle
         # corr_matrix["buckle"]["propel"] = buckle.corrwith(propel, method=self.circular)
-        corr_matrix.loc["propel", "buckle"] = buckle.corrwith(propel, method=self.circular).values[0]
+        corr_matrix.loc["propel", "buckle"] = buckle.corrwith(propel, method=self.circular).values[0]  # type: ignore
         # corr_matrix["buckle"]["opening"] = buckle.corrwith(opening, method=self.circular)
-        corr_matrix.loc["opening", "buckle"] = buckle.corrwith(opening, method=self.circular).values[0]
+        corr_matrix.loc["opening", "buckle"] = buckle.corrwith(opening, method=self.circular).values[0]  # type: ignore
         # symmetric values
         # corr_matrix["propel"]["buckle"] = corr_matrix["buckle"]["propel"]
         corr_matrix.loc["buckle", "propel"] = corr_matrix.loc["propel", "buckle"]
@@ -196,7 +196,7 @@ def launch(self) -> int:
 
         # propel
         # corr_matrix["propel"]["opening"] = propel.corrwith(opening, method=self.circular)
-        corr_matrix.loc["opening", "propel"] = propel.corrwith(opening, method=self.circular).values[0]
+        corr_matrix.loc["opening", "propel"] = propel.corrwith(opening, method=self.circular).values[0]  # type: ignore
         # symmetric values
         # corr_matrix["opening"]["propel"] = corr_matrix["propel"]["opening"]
         corr_matrix.loc["propel", "opening"] = corr_matrix.loc["opening", "propel"]

biobb_dna/utils/loader.py

@@ -13,7 +13,7 @@ def read_series(input_serfile, usecols=None):
         header=None,
         sep='\\s+',
         index_col=0)
-    ser_data = pd.read_csv(input_serfile, **extra_kwargs)
+    ser_data = pd.read_csv(input_serfile, **extra_kwargs)  # type: ignore
     if usecols is not None:
         if 0 in usecols:
             usecols.pop(usecols.index(0))