validation lab 6

Homepage.py

@@ -1,14 +1,15 @@
 import matplotlib.pyplot as plt
 import requests
 import streamlit as st
-
-from tests.eia_part3 import (
+from tests_eia_part3 import (
     build_df_from_eia_data,
     filter_since,
     latest_value,
     sum_by_week,
 )
 
+from validation import eia_schema
+
 st.set_page_config(page_title="Weekly U.S. Petroleum Supply", layout="wide")
 st.title("The Correlation between Weekly U.S. Petroleum Product Supplied and WTI Crude Oil Price")
 st.subheader("Team Members: Irina, Indra")
@@ -59,6 +60,9 @@ def fetch_supply_json(url: str) -> dict:
 
 # Filter (2012–present)
 df = filter_since(df, date_col="week", start_date="2012-01-01")
+df = eia_schema.validate(df)
+
+weekly_total = sum_by_week(df, date_col="week", value_col="value")
 if df.empty:
     st.error("No data after filtering to 2012–present. Check parsing or EIA response.")
     st.stop()

requirements.txt

@@ -15,4 +15,5 @@ numpy
 requests
 altair==4.2.2
 pytest
-pytest-cov
+pytest-cov
+pandera

tests/test_validation.py

@@ -0,0 +1,17 @@
+import pandas as pd
+import pandera as pa
+import pytest
+
+from validation import eia_schema
+
+
+def test_schema_rejects_negative_values():
+    df = pd.DataFrame(
+        {
+            "week": pd.to_datetime(["2012-01-06"]),
+            "value": [-5],
+        }
+    )
+
+    with pytest.raises(pa.errors.SchemaError):
+        eia_schema.validate(df)

validation.py

@@ -0,0 +1,14 @@
+import pandera as pa
+from pandera import Check, Column, DataFrameSchema
+
+eia_schema = DataFrameSchema(
+    {
+        "week": Column(pa.DateTime),
+        "value": Column(
+            pa.Float,
+            coerce=True,
+            checks=Check.ge(0),
+            nullable=False,
+        ),
+    }
+)