Issue-6: Fix query parameter validation

Author: PiotrZakrzewski

mbdiff/__main__.py

@@ -1,19 +1,37 @@
 import click
-from mbdiff.diff_query import DiffQuery
+from mbdiff.diff_query import DiffQuery, OPS, InvalidQuery
 from mbdiff.diff import diff_file
 from mbdiff.pretty_print import present_explanations, present_invalid
 
 
+def validate_query(ctx, param, value):
+    if not value:
+        raise click.BadParameter("Cannot be empty")
+    value_sp = value.split()
+    if len(value_sp) != 3:
+        raise click.BadParameter(
+            """Query needs to be in format: "COLUMN OPERATOR VALUE" OPERATOR must be one of: <,>,=,<=,>="""
+        )
+    metric, op, value = value_sp
+    if op not in OPS:
+        raise click.BadParameter("Operator must be one of: <,>,=,<=,>=")
+    return value_sp
+        
+
+
 @click.command()
 @click.argument("data", type=click.Path(exists=True))
 @click.option("--min-support", default=0.1)
 @click.option("--min-risk", default=0.1)
 @click.option("--max-order", default=3)
-@click.option("--query")
+@click.option("--query", callback=validate_query, default=None)
 def main(data, min_support, min_risk, max_order, query):
-    metric, op, value = query.split()
+    metric, op, value = query
     query = DiffQuery(metric, op, value)
-    explanations, invalid = diff_file(data, query, max_order, min_risk, min_support)
+    try:
+        explanations, invalid = diff_file(data, query, max_order, min_risk, min_support)
+    except InvalidQuery as e:
+        raise click.BadParameter(e)
     if explanations:
         explanations = sorted(explanations, key=lambda x: x[0], reverse=True)
         print("Explanations")
@@ -27,6 +45,5 @@ def main(data, min_support, min_risk, max_order, query):
         print("There were no invalid or below threshold attribute combinations")
 
 
-
 if __name__ == "__main__":
     main()

mbdiff/diff.py

@@ -1,5 +1,5 @@
 from pandas import DataFrame, read_csv
-from mbdiff.diff_query import DiffQuery
+from mbdiff.diff_query import DiffQuery, InvalidQuery
 from mbdiff.risk_ratio import risk_ratio
 from mbdiff.attribute_mining import get_combs
 from numpy import nan
@@ -14,6 +14,8 @@ def diff_file(
 ):
     """Given a tab delimited file and a distinguishing metric return explanations."""
     df = read_csv(path_to_df)
+    if query.column not in df.columns:
+        raise InvalidQuery("Query column is not present in the data")
     print("Outliers:")
     print(query.apply(df).to_string())
     return diff(df, query, max_order, min_risk, min_support)

mbdiff/diff_query.py

@@ -54,3 +54,6 @@ def fn(row):
             return "outlier" if self.row_matches(row) else "inlier"
 
         df["outlier"] = df.apply(fn, axis=1)
+
+class InvalidQuery(ValueError):
+    pass

mbdiff/pretty_print.py

@@ -15,6 +15,7 @@ def present_explanations(explanations: List) -> str:
     pres_df.fillna("-", inplace=True)
     return tabulate(pres_df, headers="keys")
 
+
 def present_invalid(combinations: List[Dict]) -> str:
     """Pretty print invalid attr combinations."""
     pres_df = DataFrame(combinations)