test CICD after merging

Author: DakhliFirasQM

.flake8

@@ -1,8 +1,9 @@
 [flake8]
 exclude = .git,__pycache__,.vscode,tests
 max-line-length=99
-ignore=E302,E305,W503,E203,E203,E731,E402,E501,E266
+ignore=E302,E305,W503,E203,E731,E402,E501,E266,E712,F401,F821
 indent-size = 4
 per-file-ignores=
-    qolmat/imputations/models.py:F401
+    qolmat/imputations/imputers.py:F401
     */__init__.py:F401
+    examples/test.py:F401

.pre-commit-config.yaml

@@ -20,10 +20,3 @@ repos:
     rev: 4.0.1
     hooks:
       - id: flake8
-        exclude: (tests/)
-        args:
-          - --max-line-length=99
-          - --ignore=E302,E305,W503,E203,E203,E731,E402
-          - --per-file-ignores=
-            - */__init__.py:F401
-            - qolmat/imputations/models.py:F401

examples/test.py

@@ -1,12 +1,11 @@
-
-import numpy as np
-import timesynth as ts # package for generating time series
-
 import matplotlib.pyplot as plt
+import numpy as np
+import timesynth as ts  # package for generating time series
 
-from qolmat.utils import plot
 from qolmat.imputations.rpca.pcp_rpca import PcpRPCA
-from qolmat.imputations.rpca.temporal_rpca import TemporalRPCA, OnlineTemporalRPCA
+from qolmat.imputations.rpca.temporal_rpca import OnlineTemporalRPCA, TemporalRPCA
+from qolmat.utils import plot
+
 np.random.seed(402)
 
 ################################################################################
@@ -20,9 +19,12 @@
 
 n = len(samples)
 pc = 0.02
-indices_ano1 = np.random.choice(n, int(n*pc))
-samples[indices_ano1] = [np.random.uniform(low=2*np.min(samples), high=2*np.max(samples)) for i in range(int(n*pc))]
-indices = np.random.choice(n, int(n*pc))
+indices_ano1 = np.random.choice(n, int(n * pc))
+samples[indices_ano1] = [
+    np.random.uniform(low=2 * np.min(samples), high=2 * np.max(samples))
+    for i in range(int(n * pc))
+]
+indices = np.random.choice(n, int(n * pc))
 samples[indices] = np.nan
 
 
@@ -36,19 +38,29 @@
 samples2, signals2, errors2 = timeseries.sample(irregular_time_samples)
 
 n2 = len(samples2)
-indices_ano2 = np.random.choice(n2, int(n*pc))
-samples2[indices_ano2] = [np.random.uniform(low=2*np.min(samples2), high=2*np.max(samples2)) for i in range(int(n2*pc))]
-indices = np.random.choice(n2, int(n*pc))
+indices_ano2 = np.random.choice(n2, int(n * pc))
+samples2[indices_ano2] = [
+    np.random.uniform(low=2 * np.min(samples2), high=2 * np.max(samples2))
+    for i in range(int(n2 * pc))
+]
+indices = np.random.choice(n2, int(n * pc))
 samples2[indices] = np.nan
 
 samples += samples2
 signals += signals2
 errors += errors2
 
 
-
-online_temp_rpca = OnlineTemporalRPCA(n_rows=25, tau=1, lam=0.3, list_periods=[20], list_etas=[0.01],
-                       burnin=0.2, online_list_etas=[0.3], nwin=20)
+online_temp_rpca = OnlineTemporalRPCA(
+    n_rows=25,
+    tau=1,
+    lam=0.3,
+    list_periods=[20],
+    list_etas=[0.01],
+    burnin=0.2,
+    online_list_etas=[0.3],
+    nwin=20,
+)
 X, A = online_temp_rpca.fit_transform(X=samples)
 plot.plot_sig
 nal([samples, X, A], style="matplotlib")

qolmat/benchmark/comparator.py

@@ -150,7 +150,7 @@ def compare(self, df: pd.DataFrame, verbose: bool = True):
             print(f"Tested model: {type(imputer).__name__}")
 
             search_params = self.search_params.get(name, {})
-            
+
             # if imputer.columnwise:
             #     if len(self.selected_columns) > 0:
             #         search_params = {}

qolmat/benchmark/cross_validation.py

@@ -123,6 +123,7 @@ def objective(self, X):
         _type_
             objective function
         """
+
         @skopt.utils.use_named_args(self.list_spaces)
         def obj_func(**hyperparams_flat):
             self.imputer.hyperparams_optim = self.deflat_hyperparams(hyperparams_flat)
@@ -135,11 +136,11 @@ def obj_func(**hyperparams_flat):
                 df_corrupted[df_mask] = np.nan
                 cols_with_nans = X.columns[X.isna().any(axis=0)].tolist()
                 imputed = self.imputer.fit_transform(df_corrupted)
-                
+
                 error = self.loss_function(
                     df_origin.loc[:, cols_with_nans],
                     imputed.loc[:, cols_with_nans],
-                    df_mask.loc[:, cols_with_nans]
+                    df_mask.loc[:, cols_with_nans],
                 )
                 errors.append(error)
 

qolmat/benchmark/utils.py

@@ -23,12 +23,12 @@
 
 
 def get_dimension(dict_bounds: Dict, name_dimension: str) -> Dimension:
-        if dict_bounds["type"] == "Integer":
-            return Integer(low=dict_bounds["min"], high=dict_bounds["max"], name=name_dimension)
-        elif dict_bounds["type"] == "Real":
-            return Real(low=dict_bounds["min"], high=dict_bounds["max"], name=name_dimension)
-        elif dict_bounds["type"] == "Categorical":
-            return Categorical(categories=dict_bounds["categories"], name=name_dimension)
+    if dict_bounds["type"] == "Integer":
+        return Integer(low=dict_bounds["min"], high=dict_bounds["max"], name=name_dimension)
+    elif dict_bounds["type"] == "Real":
+        return Real(low=dict_bounds["min"], high=dict_bounds["max"], name=name_dimension)
+    elif dict_bounds["type"] == "Categorical":
+        return Categorical(categories=dict_bounds["categories"], name=name_dimension)
 
 
 def get_search_space(search_params: Dict) -> List[Dimension]:
@@ -187,10 +187,7 @@ def wasser_distance(
     wasserstein distances : pd.Series
     """
     cols = df1.columns.tolist()
-    wd = [
-        scipy.stats.wasserstein_distance(df1[col].dropna(), df2[col].dropna())
-        for col in cols
-    ]
+    wd = [scipy.stats.wasserstein_distance(df1[col].dropna(), df2[col].dropna()) for col in cols]
     return pd.Series(wd, index=cols)