diff --git a/mbs_results/utilities/mapping_validation.py b/mbs_results/utilities/mapping_validation.py
new file mode 100644
index 00000000..e8cc8903
--- /dev/null
+++ b/mbs_results/utilities/mapping_validation.py
@@ -0,0 +1,100 @@
+import warnings
+
+import pandas as pd
+
+
+def wrap_mapping_validations(df: pd.DataFrame, mapping_folder: str):
+    """
+    wrapper to loop over the specified mapping files in file_and_column_names dict.
+    Calls mapping_validation for the specified files
+    Probably could move the files and column names to the config if needed.
+
+    Parameters
+    ----------
+    df : pd.DataFrame
+        input data to test against mapping files
+    mapping_folder : str
+        folder where the mapping files can be located.
+        String must end with a '/' as we need this to be a folder where other mapping
+        files are located
+    """
+    # Might be best to refactor this down the line and put into config if used
+    files_and_column_names = {
+        "sic_sut_mapping.csv": {
+            "df_column_name": "sic_5_digit",
+            "mapping_file_col_name": "sic",
+        },
+        "classification_sic_mapping.csv": {
+            "df_column_name": "sic_5_digit",
+            "mapping_file_col_name": "sic_5_digit",
+        },
+        "sic_domain_mapping.csv": {
+            "df_column_name": "sic_5_digit",
+            "mapping_file_col_name": "sic_5_digit",
+        },
+    }
+
+    for i in files_and_column_names:
+        mapping_path = mapping_folder + i
+        column_dict = files_and_column_names[i]
+        mapping_validation(
+            df,
+            mapping_path,
+            column_dict["df_column_name"],
+            column_dict["mapping_file_col_name"],
+        )
+
+
+def mapping_validation(
+    df: pd.DataFrame,
+    mapping_path: str,
+    df_column_name: str,
+    mapping_file_column_name: str,
+):
+    """
+    validation function to check mapping file against a column within a given dataframe
+    Only works with 'true' mapping files which two columns. Mapping files containing
+    three columns will produce an error.
+
+    Parameters
+    ----------
+    df : pd.DataFrame
+        input dataframe containing the data used in pipeline
+    mapping_path : str
+        path to mapping file to validate
+    df_column_name : str
+        column name of column to join on in df
+    mapping_file_column_name : str
+        column name of column to join on from mapping file
+
+    Raises
+    ------
+    Warning
+        Warns if data within the original dataframe has not been mapped using
+        the mapping file supplied
+    """
+
+    mapping_df = pd.read_csv(mapping_path)
+    df_subset = df[df_column_name]
+    new_column_name = [
+        x for x in mapping_df.columns if x not in mapping_file_column_name
+    ]
+    new_column_name = "".join(new_column_name)
+    df_subset = pd.merge(
+        left=df_subset,
+        right=mapping_df,
+        left_on=df_column_name,
+        right_on=mapping_file_column_name,
+        how="left",
+    )
+    unmatched = df_subset.loc[
+        df_subset[new_column_name].isna(), df_column_name
+    ].to_list()
+
+    if unmatched:
+        unmatched = set(unmatched)
+        mapping_file_name = mapping_path.split("/")[-1]
+        warnings.warn(
+            f"\n \n The following values from {df_column_name} in input dataframe "
+            + f"are not mapped using {mapping_file_name}: \n {unmatched}"
+        )
diff --git a/tests/data/utilities_data/mapping_missing.csv b/tests/data/utilities_data/mapping_missing.csv
new file mode 100644
index 00000000..c109e5d3
--- /dev/null
+++ b/tests/data/utilities_data/mapping_missing.csv
@@ -0,0 +1,4 @@
+sic,domain
+1,10
+2,20
+3,30
diff --git a/tests/test_utilities/test_mapping_validation.py b/tests/test_utilities/test_mapping_validation.py
new file mode 100644
index 00000000..38a81d39
--- /dev/null
+++ b/tests/test_utilities/test_mapping_validation.py
@@ -0,0 +1,19 @@
+import pandas as pd
+import pytest
+
+from mbs_results.utilities.mapping_validation import mapping_validation
+
+scenario_path_prefix = "tests/data/"
+
+
+def test_mapping_validation():
+    df = pd.DataFrame({"name": ["a", "b", "c", "d"], "sic": [1, 2, 3, 4]})
+
+    mapping_path = scenario_path_prefix + "utilities_data/mapping_missing.csv"
+    with pytest.warns(UserWarning):
+        mapping_validation(
+            df=df,
+            mapping_path=mapping_path,
+            df_column_name="sic",
+            mapping_file_column_name="sic",
+        )