@@ -70,18 +70,19 @@ from csvplus.load_optimized_csv import load_optimized_csv
7070from csvplus.data_correction import resolve_string_value
7171from csvplus.generate_report import summary_report
7272
73- df_v1 = load_optimized_csv(" large_dataset.csv" )
74- df_v2 = load_optimized_csv(" large_dataset2.csv" )
75-
76- diff = data_version_diff(df_v1, df_v2)
77- # Inspect the returned dictionary
78- print (diff[" columns_added" ])
79- print (diff[" row_count_change" ])
73+ # --- test data type change in csvplus.data_version_diff ---
74+ df1 = pd.DataFrame({" a" : [1 ,2 ,3 ]})
75+ df2 = pd.DataFrame({" a" : [" 1" ," 2" ," 3" ]})
76+ diff = data_version_diff(df1, df2)
77+ print (diff)
8078# Optionally display a formatted summary
8179display_data_version_diff(diff)
8280
83- resolve_string_value(df_v1, " company_name" , [" Google" , " Microsoft" ], 80 )
84- summary_report(df_v1)
81+ # --- csvplus.data_correction --
82+ df_v1 = load_optimized_csv(" large_dataset.csv" )
83+ df_v2 = load_optimized_csv(" large_dataset2.csv" )
84+ resolve_string_value(df1, " company_name" , [" Google" , " Microsoft" ], 80 )
85+ summary_report(df1)
8586```
8687
8788### Running Tests
0 commit comments