Linitin rule sim

alphastats/DataSet_Preprocess.py

@@ -128,9 +128,8 @@ def _remove_na_values(self, cut_off):
             count = column.isna().sum()
             try:
                 count = count.item()
-                if isinstance(count, int):
-                    if count < limit:
-                        keep_list += [column_name]
+                if isinstance(count, int) and count < limit:
+                    keep_list += [column_name]
 
             except ValueError:
                 invalid += 1
@@ -414,7 +413,7 @@ def preprocess(
             imputation (str, optional):  method to impute data: either "mean", "median", "knn" or "randomforest". Defaults to None.
             subset (bool, optional): filter matrix so only samples that are described in metadata found in matrix. Defaults to False.
         """
-        for k in kwargs.keys():
+        for k in kwargs:
             if k not in [
                 "batch",
             ]:

alphastats/gui/pages/04_Analysis.py

@@ -65,13 +65,13 @@ def select_analysis():
     with c1:
         method = select_analysis()
 
-        if method in st.session_state[StateKeys.PLOTTING_OPTIONS].keys():
+        if method in st.session_state[StateKeys.PLOTTING_OPTIONS]:
             analysis_result = get_analysis(
                 method=method, options_dict=st.session_state[StateKeys.PLOTTING_OPTIONS]
             )
             plot_to_display = True
 
-        elif method in st.session_state[StateKeys.STATISTIC_OPTIONS].keys():
+        elif method in st.session_state[StateKeys.STATISTIC_OPTIONS]:
             analysis_result = get_analysis(
                 method=method,
                 options_dict=st.session_state[StateKeys.STATISTIC_OPTIONS],

alphastats/gui/utils/analysis_helper.py

@@ -93,7 +93,7 @@ def st_general(method_dict):
         for parameter in settings_dict:
             parameter_dict = settings_dict[parameter]
 
-            if "options" in parameter_dict.keys():
+            if "options" in parameter_dict:
                 chosen_parameter = st.selectbox(
                     parameter_dict.get("label"), options=parameter_dict.get("options")
                 )
@@ -202,7 +202,7 @@ def get_analysis_options_from_dict(method, options_dict):
     elif method == "UMAP Plot":
         return st_plot_umap(method_dict)
 
-    elif "settings" not in method_dict.keys():
+    elif "settings" not in method_dict:
         if st.session_state[StateKeys.DATASET].mat.isna().values.any() == True:
             st.error(
                 "Data contains missing values impute your data before plotting (Preprocessing - Imputation)."
@@ -346,7 +346,7 @@ def helper_compare_two_groups():
 
 
 def get_analysis(method, options_dict):
-    if method in options_dict.keys():
+    if method in options_dict:
         obj = get_analysis_options_from_dict(method, options_dict=options_dict)
         return obj
 

alphastats/gui/utils/gpt_helper.py

@@ -158,7 +158,7 @@ def get_assistant_functions(
                     "properties": {
                         "protein_id": {
                             "type": "string",
-                            "enum": [i for i in gene_to_prot_id_dict.keys()],
+                            "enum": [i for i in gene_to_prot_id_dict],
                             "description": "Identifier for the protein of interest",
                         },
                         "group": {

alphastats/gui/utils/ui_helper.py

@@ -72,7 +72,7 @@ def empty_session_state():
     """
     remove all variables to avoid conflicts
     """
-    for key in st.session_state.keys():
+    for key in st.session_state:
         del st.session_state[key]
     st.empty()
 

alphastats/gui/utils/uniprot_utils.py

@@ -114,10 +114,10 @@ def extract_data(data: Dict) -> Dict:
     extracted = {}
 
     # 1. Entry Type
-    extracted["entryType"] = data.get("entryType", None)
+    extracted["entryType"] = data.get("entryType")
 
     # 2. Primary Accession
-    extracted["primaryAccession"] = data.get("primaryAccession", None)
+    extracted["primaryAccession"] = data.get("primaryAccession")
 
     # 3. Organism Details
     organism = data.get("organism", {})

alphastats/loader/AlphaPeptLoader.py

@@ -77,10 +77,7 @@ def standardize_protein_group_column(entry: str) -> str:
         protein_id_list = []
         for protein in proteins:
             # 'sp|P0DMV9|HS71B_HUMAN,sp|P0DMV8|HS71A_HUMAN',
-            if "|" in protein:
-                fasta_header_split = protein.split("|")
-            else:
-                fasta_header_split = protein
+            fasta_header_split = protein.split("|") if "|" in protein else protein
             if isinstance(fasta_header_split, str):
                 #  'ENSEMBL:ENSBTAP00000007350',
                 if "ENSEMBL:" in fasta_header_split:

alphastats/multicova/multicova.py

@@ -145,10 +145,7 @@ def get_tstat_cutoff(res_real, t_perm_avg, delta):
     # between the observed and average random t-stat is
     # larger than the selected delta.
     t_max = t_real_abs[t_diff > delta]
-    if t_max.shape[0] == 0:
-        t_max = np.ceil(np.max(t_real_abs))
-    else:
-        t_max = np.min(t_max)
+    t_max = np.ceil(np.max(t_real_abs)) if t_max.shape[0] == 0 else np.min(t_max)
     return t_max
 
 
@@ -226,16 +223,14 @@ def get_fdr(n_pos, n_false_pos, pi0):
     proportion of true null (unaffected) genes in the data set.
     """
     n = n_false_pos * pi0
+
+    fdr = 0
     if n != 0:
         if n_pos != 0:
             fdr = n / n_pos
-        else:
-            fdr = 0
-    else:
-        if n_pos > 0:
-            fdr = 0
-        else:
-            fdr = np.nan
+    elif n_pos <= 0:
+        fdr = np.nan
+
     return fdr
 
 
@@ -329,10 +324,9 @@ def get_fdr_line(
     for i in np.arange(0, len(fc_s)):
         for j in np.arange(0, len(s_s)):
             res_s = perform_ttest_getMaxS(fc=fc_s[i], s=s_s[j], s0=s0, n_x=n_x, n_y=n_y)
-            if res_s[3] >= t_limit:
-                if svals[i] < s_s[j]:
-                    svals[i] = s_s[j]
-                    pvals[i] = res_s[2]
+            if res_s[3] >= t_limit and svals[i] < s_s[j]:
+                svals[i] = s_s[j]
+                pvals[i] = res_s[2]
 
     s_df = pd.DataFrame(
         np.array([fc_s, svals, pvals]).T, columns=["fc_s", "svals", "pvals"]

pyproject.toml

@@ -12,7 +12,7 @@ extend-exclude = [".bumpversion.cfg", ".secrets.baseline"]
 #    # flake8-bugbear
 #    "B",
 #    # flake8-simplify
-#    "SIM",
+    "SIM",
     # isort
     "I",
  ]

tests/test_DataSet.py

@@ -370,7 +370,7 @@ def test_plot_sampledistribution_group(self):
         # check if there are two groups control and disease
         self.assertEqual(plot_dict.get("data")[0].get("legendgroup"), "control")
         #  check that it is boxplot and not violinplot
-        is_boxplot = "boxmode" in plot_dict.get("layout").keys()
+        is_boxplot = "boxmode" in plot_dict.get("layout")
         self.assertTrue(is_boxplot)
 
     def test_plot_correlation_matrix(self):
@@ -827,7 +827,7 @@ def test_plot_intensity_box(self):
         plot_dict = plot.to_plotly_json()
         #  log scale
         self.assertEqual(plot_dict.get("layout").get("yaxis").get("type"), "log")
-        is_boxplot = "boxmode" in plot_dict.get("layout").keys()
+        is_boxplot = "boxmode" in plot_dict.get("layout")
         self.assertTrue(is_boxplot)
 
     def test_plot_intensity_scatter(self):