test added, but with some issues

Author: Saurabh Pandey

PostProcessing/test_functions.py

@@ -5,10 +5,14 @@
 
 from typing import List
 
-from dataframes import repair_dropped_frames
+from dataframes import repair_dropped_frames, compute_time_range, trim_into_interval
 
 import pandas as pd
 
+import pandas.testing as pd_testing
+
+import numpy as np
+
 RECSYNCH_SESSION_DIR_VAR = "RECSYNCH_SESSION_DIR"
 
 print(f"Getting data dir from {RECSYNCH_SESSION_DIR_VAR} environment variable...")
@@ -21,42 +25,77 @@
 #        raise Exception(f"Environment variable {RECSYNCH_SESSION_DIR_VAR} not defined")
 
 
-def client_IDs() -> List[str]:
+# def client_IDs() -> List[str]:
+
+#     out = []
+
+#     for p in Path(RECSYNCH_SESSION_DIR).iterdir():
+#         print("-->", p.stem)
+#         out.append(p)
+
+#     return out
+
+
+# def CSVs() -> List[str]:
 
-    out = []
+#     out = []
 
-    for p in Path(RECSYNCH_SESSION_DIR).iterdir():
-        print("-->", p.stem)
-        out.append(p)
+#     clients = client_IDs()
+#     for c in clients:
+#         client_dir = Path(RECSYNCH_SESSION_DIR) / c
+#         for csv_file in client_dir.glob("*.csv"):
+#             print("==>", csv_file)
+#             rel_filepath = str(csv_file.relative_to(RECSYNCH_SESSION_DIR))
+#             print("++>", rel_filepath)
+#             out.append(rel_filepath)
 
-    return out
+#     return out
 
 
-def CSVs() -> List[str]:
+# @pytest.mark.parametrize("csv_file", CSVs())
+# def test_df_reparation(csv_file):
 
-    out = []
+#     # Load the test dataframes
+#     csv_path = Path(RECSYNCH_SESSION_DIR) / csv_file
+#     df = pd.read_csv(csv_path)
 
-    clients = client_IDs()
-    for c in clients:
-        client_dir = Path(RECSYNCH_SESSION_DIR) / c
-        for csv_file in client_dir.glob("*.csv"):
-            print("==>", csv_file)
-            rel_filepath = str(csv_file.relative_to(RECSYNCH_SESSION_DIR))
-            print("++>", rel_filepath)
-            out.append(rel_filepath)
+#     assert len(df) >= 2
 
-    return out
+#     repaired_df = repair_dropped_frames(df)
 
+#     assert len(repaired_df) >= len(df)
 
-@pytest.mark.parametrize("csv_file", CSVs())
-def test_df_reparation(csv_file):
 
-    # Load the test dataframes
-    csv_path = Path(RECSYNCH_SESSION_DIR) / csv_file
-    df = pd.read_csv(csv_path)
+def test_df_trim():
+    # Create three sample dataframes with single column and no headers
+    df1 = pd.DataFrame([9, 10, 11, 16])
+    df2 = pd.DataFrame([7, 8, 12, 13])
+    df3 = pd.DataFrame([12, 15, 16, 19])
 
-    assert len(df) >= 2
+    # Add the dataframes to a list
+    df_list = [df1, df2, df3]
 
-    repaired_df = repair_dropped_frames(df)
+    # Compute time range and trim the dataframe 
+    min_val, max_val = compute_time_range(df_list)
+    trimmed_df_list = trim_into_interval(df_list, min_val, max_val, 3)
 
-    assert len(repaired_df) >= len(df)
+    # Create expected list of dataframes to compare with trimmed_df_list
+    compare_list = [
+        pd.DataFrame([9, 10, 11, 16]),
+        pd.DataFrame([12, 13]),
+        pd.DataFrame([12, 15, 16])
+    ]
+    
+    # print(trimmed_df_list.to_string(index=False))
+    # print(compare_list.to_string(index=False))
+    # try:
+    #     for df1, df2 in zip(trimmed_df_list, compare_list):
+    #         df1_reset = df1.reset_index(drop=True)
+    #         df2_reset = df2.reset_index(drop=True)
+    #         pd_testing.assert_frame_equal(df1_reset, df2_reset)
+    #     print("All dataframes match")
+    # except AssertionError as e:
+    #     print("Dataframes do not match:")
+    #     print(e)
+    # Assert if all dataframes in df_list match the corresponding dataframes in compare_list
+    assert trimmed_df_list == compare_list