Update validate.py

validate.py

@@ -1,75 +1,78 @@
-import pandas as pd
-import pickle
-import os
-from sklearn.metrics import classification_report
-from sklearn.model_selection import train_test_split
+from pydantic import ValidationError
+from app import TransactionData  # Reuse model from app.py
+import json
 
-# === File Paths ===
-DATA_PATH = "data.csv"  # Change this to your actual CSV
-TEXT_COLUMNS = [
-    "Transaction_Id", "Origin", "Designation", "Keywords", "Name", "SWIFT_Tag", "Currency",
-    "Entity", "Message", "City", "Country", "State", "Hit_Type", "Record_Matching_String",
-    "WatchList_Match_String", "Payment_Sender_Name", "Payment_Reciever_Name", "Swift_Message_Type",
-    "Text_Sanction_Data", "Matched_Sanctioned_Entity", "Red_Flag_Reason", "Risk_Level",
-    "Risk_Score", "CDD_Level", "PEP_Status", "Sanction_Description", "Checker_Notes",
-    "Sanction_Context", "Maker_Action", "Customer_Type", "Industry", "Transaction_Type",
-    "Transaction_Channel", "Geographic_Origin", "Geographic_Destination", "Risk_Category",
-    "Risk_Drivers", "Alert_Status", "Investigation_Outcome", "Source_Of_Funds",
-    "Purpose_Of_Transaction", "Beneficial_Owner"
-]
-
-LABEL_COLUMNS = [
-    "Red_Flag_Reason", "Maker_Action", "Escalation_Level",
-    "Risk_Category", "Risk_Drivers", "Investigation_Outcome"
-]
-
-VECTORIZER_PATH = "tfidf_vectorizer (2).pkl"
-MODELS_PATH = "xgb_model.pkl"
-ENCODERS_PATH = "label_encoders (5).pkl"
-
-RANDOM_STATE = 42
-TEST_SIZE = 0.2
-
-# === Utils ===
-def load_pickle(path):
-    with open(path, "rb") as f:
-        return pickle.load(f)
-
-# === Main ===
-def validate():
-    print("📥 Loading data...")
-    df = pd.read_csv(DATA_PATH)
-    df.dropna(subset=["Sanction_Context"] + LABEL_COLUMNS, inplace=True)
-
-    print("🧠 Loading vectorizer, models, encoders...")
-    tfidf = load_pickle(VECTORIZER_PATH)
-    models = load_pickle(MODELS_PATH)
-    label_encoders = load_pickle(ENCODERS_PATH)
-
-    print("📊 TF-IDF transforming text...")
-    def concat_text(row):
-        return "\n".join([str(row[col]) for col in TEXT_COLUMNS if col in row and pd.notna(row[col])])
-
-    df["combined_text"] = df.apply(concat_text, axis=1)
-    X = tfidf.transform(df["combined_text"])
-
-    for label in LABEL_COLUMNS:
-        print(f"\n🔍 Validating: {label}")
-        y_raw = df[label]
-        encoder = label_encoders[label]
-        y_encoded = encoder.transform(y_raw)
-
-        _, X_test, _, y_test = train_test_split(
-            X, y_encoded, test_size=TEST_SIZE, random_state=RANDOM_STATE
-        )
-
-        model = models[label]
-        y_pred = model.predict(X_test)
-
-        print(classification_report(
-            encoder.inverse_transform(y_test),
-            encoder.inverse_transform(y_pred)
-        ))
+# Example JSON input (update as needed)
+sample_input = {
+    "Transaction_Id": "T123456789",
+    "Hit_Seq": 1,
+    "Hit_Id_List": "HIT001",
+    "Origin": "USA",
+    "Designation": "Manager",
+    "Keywords": "Payment",
+    "Name": "John Doe",
+    "SWIFT_Tag": "TAG001",
+    "Currency": "USD",
+    "Entity": "CompanyX",
+    "Message": "This is a test message",
+    "City": "New York",
+    "Country": "USA",
+    "State": "NY",
+    "Hit_Type": "Name Match",
+    "Record_Matching_String": "Matching String Example",
+    "WatchList_Match_String": "Watchlist Match Example",
+    "Payment_Sender_Name": "Alice",
+    "Payment_Reciever_Name": "Bob",
+    "Swift_Message_Type": "MT103",
+    "Text_Sanction_Data": "Sanction text here",
+    "Matched_Sanctioned_Entity": "Entity XYZ",
+    "Is_Match": 1,
+    "Red_Flag_Reason": "High Risk",
+    "Risk_Level": "High",
+    "Risk_Score": 85.0,
+    "Risk_Score_Description": "High Risk Score",
+    "CDD_Level": "Enhanced",
+    "PEP_Status": "No",
+    "Value_Date": "2023-10-01",
+    "Last_Review_Date": "2023-11-01",
+    "Next_Review_Date": "2024-11-01",
+    "Sanction_Description": "Some sanctions",
+    "Checker_Notes": "Verified manually",
+    "Sanction_Context": "Transaction under review",
+    "Maker_Action": "Escalated",
+    "Customer_ID": 1001,
+    "Customer_Type": "Corporate",
+    "Industry": "Finance",
+    "Transaction_Date_Time": "2023-10-01T12:00:00",
+    "Transaction_Type": "Transfer",
+    "Transaction_Channel": "Online",
+    "Originating_Bank": "Bank A",
+    "Beneficiary_Bank": "Bank B",
+    "Geographic_Origin": "USA",
+    "Geographic_Destination": "UK",
+    "Match_Score": 0.95,
+    "Match_Type": "Fuzzy",
+    "Sanctions_List_Version": "v2023.10",
+    "Screening_Date_Time": "2023-10-01T10:00:00",
+    "Risk_Category": "Fraud",
+    "Risk_Drivers": "Transaction Volume",
+    "Alert_Status": "Open",
+    "Investigation_Outcome": "Pending",
+    "Case_Owner_Analyst": "Analyst1",
+    "Escalation_Level": "Level 2",
+    "Escalation_Date": "2023-10-02",
+    "Regulatory_Reporting_Flags": True,
+    "Audit_Trail_Timestamp": "2023-10-01T10:15:00",
+    "Source_Of_Funds": "Internal",
+    "Purpose_Of_Transaction": "Loan Repayment",
+    "Beneficial_Owner": "OwnerX",
+    "Sanctions_Exposure_History": False
+}
 
 if __name__ == "__main__":
-    validate()
+    try:
+        validated = TransactionData(**sample_input)
+        print(" Input is valid.")
+    except ValidationError as e:
+        print(" Validation failed:")
+        print(e.json())