Linking DataFrames Progress Bar added

measprocess/preprocess.py

@@ -6,6 +6,7 @@ from tqdm import tqdm
 def link_dataframes(A: pd.DataFrame, B: pd.DataFrame, ref_col: str, metric=None, verbose=True) -> (pd.DataFrame, np.ndarray):
     '''
     Merge two DataFrames A and B according to the reference colum based on minimum metric.
+    Note that the final dataframe will include duplicate entries from B, while entries from A will be unique
 
     :param ref_col: Reference Column to merge dataframes. Has to exist in both frames
     :param metric: Metric used to determine matches in ref_col. Default lambda a, b: (a - b).abs()
@@ -23,7 +24,7 @@ def link_dataframes(A: pd.DataFrame, B: pd.DataFrame, ref_col: str, metric=None,
         metric = lambda a, b: (a - b).abs()
 
     indices, deviations = [], []
-    for _, element in tqdm(A.iterrows(), total=A.shape[0], disable=(not verbose)):
+    for _, element in tqdm(A.iterrows(), total=A.shape[0], disable=(not verbose), desc="Linking Dataframes"):
         distances = metric(
             element[ref_col],
             B[ref_col]
@@ -37,7 +38,7 @@ def link_dataframes(A: pd.DataFrame, B: pd.DataFrame, ref_col: str, metric=None,
         )
 
     B_with_duplicates = pd.DataFrame(
-        (B.iloc[index] for index in indices)
+        tqdm((B.iloc[index] for index in indices), total=len(indices), disable=(not verbose), desc="Building combined DataFrame")
     )
 
     B_with_duplicates.columns = B.columns

setup.py

@@ -10,7 +10,7 @@ README = (HERE / "README.md").read_text()
 # This call to setup() does all the work
 setup(
     name="measprocess",
-    version="0.5.9",
+    version="0.5.10",
     description="Collection of measurement processing tools",
     long_description=README,
     long_description_content_type="text/markdown",