[Bangalore] Sudipt Nigam - Vibe Coding Submission

data/city-test-files/test_bangalore.csv

@@ -0,0 +1,16 @@
+complaint_id,date_raised,city,ward,location,description,reported_by,days_open
+BLR-202401,2024-06-21,Bangalore,Ward 1 – Malleshwaram,Sampige Road near Malleshwaram Circle,Large pothole 50cm wide causing vehicle damage during peak hours.,Citizen Portal,4
+BLR-202402,2024-06-04,Bangalore,Ward 2 – Rajajinagar,Dr Rajkumar Road near Metro Station,Deep pothole near metro exit posing risk to pedestrians.,Councillor Referral,12
+BLR-202406,2024-06-08,Bangalore,Ward 3 – Shivajinagar,Queens Road underpass,Underpass flooded after continuous rain. Traffic diverted.,Councillor Referral,8
+BLR-202408,2024-06-05,Bangalore,Ward 4 – Indiranagar,100 Feet Road bus stop,Bus stop flooded. Commuters waiting on road.,Ward Office Walk-in,12
+BLR-202410,2024-06-04,Bangalore,Ward 5 – Jayanagar,4th Block Market Road,Multiple streetlights not working for over a week.,Email,18
+BLR-202411,2024-06-22,Bangalore,Ward 6 – Whitefield,ITPL Main Road,Streetlight flickering and sparking near tech park.,Social Media,9
+BLR-202413,2024-06-29,Bangalore,Ward 7 – Yeshwanthpur,Yeshwanthpur Market Area,Overflowing garbage bins near vegetable market.,WhatsApp Helpline,13
+BLR-202418,2024-06-02,Bangalore,Ward 8 – BTM Layout,2nd Stage Residential Area,Loud music from venue past midnight disturbing residents.,Citizen Portal,5
+BLR-202419,2024-06-01,Bangalore,Ward 9 – Koramangala,Sony World Junction,Road surface sinking near recent utility work.,Social Media,2
+BLR-202420,2024-06-03,Bangalore,Ward 10 – Banashankari,Outer Ring Road near PES University,Open manhole without cover creating accident risk.,Email,14
+BLR-202427,2024-06-07,Bangalore,Ward 11 – Hebbal,Hebbal Flyover Service Road,Waterlogging makes approach road inaccessible after rain.,Councillor Referral,12
+BLR-202428,2024-06-23,Bangalore,Ward 12 – Sadashivanagar,Bellary Road,Dead animal not removed for over a day. Health concern.,Email,1
+BLR-202430,2024-06-23,Bangalore,Ward 13 – Chickpet,Chickpet Market Area,Streetlights not working in heritage market area.,Social Media,19
+BLR-202433,2024-06-08,Bangalore,Ward 14 – Marathahalli,Outer Ring Road,Construction debris dumped on public road.,Phone Helpline,20
+BLR-202446,2024-06-09,Bangalore,Ward 15 – Basavanagudi,Bull Temple Road,Broken footpath tiles causing trips and falls.,Email,18

uc-0a/README.md

@@ -6,20 +6,20 @@
 
 ## Your Input File
 ```
-../data/city-test-files/test_[your-city].csv
+../data/city-test-files/test_bangalore.csv
 ```
 15 rows per city. `category` and `priority_flag` columns are stripped — you must classify them.
 
 ## Your Output File
 ```
-uc-0a/results_[your-city].csv
+uc-0a/results_bangalore.csv
 ```
 
 ## Run Command
 ```bash
 python classifier.py \
-  --input ../data/city-test-files/test_pune.csv \
-  --output results_pune.csv
+  --input ../data/city-test-files/test_bangalore.csv \
+  --output results_bangalore.csv
 ```
 
 ---

uc-0a/agents.md

@@ -1,18 +1,32 @@
-# agents.md — UC-0A Complaint Classifier
-# INSTRUCTIONS: Generate a draft using your RICE prompt, then manually refine this file.
-# Delete these comments before committing.
+# UC-0A Agents
 
-role: >
-  [FILL IN: Who is this agent? What is its operational boundary?]
+This document defines the agents responsible for executing UC-0A — Complaint Classifier.
 
-intent: >
-  [FILL IN: What does a correct output look like — make it verifiable]
+---
 
-context: >
-  [FILL IN: What information is the agent allowed to use? State exclusions explicitly.]
+## Complaint Classifier Agent
 
-enforcement:
-  - "[FILL IN: Specific testable rule 1 — e.g. Category must be exactly one of: Pothole, Flooding, ...]"
-  - "[FILL IN: Specific testable rule 2 — e.g. Priority must be Urgent if description contains: injury, child, school, ...]"
-  - "[FILL IN: Specific testable rule 3 — e.g. Every output row must include a reason field citing specific words from the description]"
-  - "[FILL IN: Refusal condition — e.g. If category cannot be determined from description alone, output category: Other and flag: NEEDS_REVIEW]"
+Responsible for category assignment, priority detection, reason generation, and ambiguity handling.
+
+**Key Constraints**
+- Never invent categories
+- Never downgrade priority when severity keywords exist
+- Always provide a one-sentence reason
+- Flag ambiguous cases conservatively
+
+---
+
+## Batch Processing Agent
+
+Handles CSV ingestion and output generation.
+
+Responsibilities:
+- Read input CSV
+- Invoke Complaint Classifier Agent per row
+- Write validated output CSV
+
+---
+
+## Reviewer Agent
+
+Validates rule compliance without reclassifying content.

uc-0a/classifier.py

@@ -1,35 +1,196 @@
+
 """
 UC-0A — Complaint Classifier
-Starter file. Build this using the RICE → agents.md → skills.md → CRAFT workflow.
+
+Built using README.md constraints + agents.md + skills.md
+Deterministic, rule-based implementation (no hallucination).
 """
+
 import argparse
 import csv
+import sys
+
+# --------------------------------------------------
+# UC-0A Constants (MUST match README exactly)
+# --------------------------------------------------
+
+ALLOWED_CATEGORIES = [
+    "Pothole",
+    "Flooding",
+    "Streetlight",
+    "Waste",
+    "Noise",
+    "Road Damage",
+    "Heritage Damage",
+    "Heat Hazard",
+    "Drain Blockage",
+    "Other",
+]
+
+SEVERITY_KEYWORDS = [
+    "injury",
+    "child",
+    "school",
+    "hospital",
+    "ambulance",
+    "fire",
+    "hazard",
+    "fell",
+    "collapse",
+]
+
+
+# --------------------------------------------------
+# Helper functions
+# --------------------------------------------------
+
+def contains_severity_keyword(text: str) -> bool:
+    text_lower = text.lower()
+    return any(word in text_lower for word in SEVERITY_KEYWORDS)
+
+
+def assign_category(text: str) -> tuple[str, str]:
+    """
+    Returns (category, flag)
+    Flag is NEEDS_REVIEW only when genuinely ambiguous.
+    """
+    t = text.lower()
+
+    matched = []
+
+    if "pothole" in t:
+        matched.append("Pothole")
+
+    if "flood" in t or "waterlogging" in t:
+        matched.append("Flooding")
+
+    if "streetlight" in t or "lamp" in t or "light not working" in t:
+        matched.append("Streetlight")
+
+    if "garbage" in t or "waste" in t or "trash" in t:
+        matched.append("Waste")
+
+    if "noise" in t or "loud" in t:
+        matched.append("Noise")
+
+    if "road" in t and "damage" in t:
+        matched.append("Road Damage")
+
+    if "heritage" in t or "monument" in t:
+        matched.append("Heritage Damage")
+
+    if "heat" in t or "heatwave" in t:
+        matched.append("Heat Hazard")
+
+    if "drain" in t or "sewage" in t or "blocked" in t:
+        matched.append("Drain Blockage")
+
+    if len(matched) == 1:
+        return matched[0], ""
+
+    if len(matched) > 1:
+        return matched[0], "NEEDS_REVIEW"
+
+    return "Other", ""
+
+
+# --------------------------------------------------
+# Core Skill: classify_complaint
+# --------------------------------------------------
 
 def classify_complaint(row: dict) -> dict:
     """
     Classify a single complaint row.
-    Returns: dict with keys: complaint_id, category, priority, reason, flag
-
-    TODO: Build this using your AI tool guided by your agents.md and skills.md.
-    Your RICE enforcement rules must be reflected in this function's behaviour.
+
+    Returns dict with keys:
+    complaint_id, category, priority, reason, flag
     """
-    raise NotImplementedError("Build this using your AI tool + RICE prompt")
 
+    try:
+        complaint_id = row.get("complaint_id", "").strip()
+        description = row.get("description", "").strip()
+
+        if not description:
+            return {
+                "complaint_id": complaint_id,
+                "category": "Other",
+                "priority": "Low",
+                "reason": "Description is missing or empty.",
+                "flag": "NEEDS_REVIEW",
+            }
+
+        category, flag = assign_category(description)
+
+        if contains_severity_keyword(description):
+            priority = "Urgent"
+            reason = (
+                "Marked Urgent due to severity keyword present in description such as "
+                f"'{next(w for w in SEVERITY_KEYWORDS if w in description.lower())}'."
+            )
+        else:
+            priority = "Standard"
+            reason = "Classified based on complaint description text."
+
+        return {
+            "complaint_id": complaint_id,
+            "category": category,
+            "priority": priority,
+            "reason": reason,
+            "flag": flag,
+        }
+
+    except Exception as e:
+        return {
+            "complaint_id": row.get("complaint_id", ""),
+            "category": "Other",
+            "priority": "Low",
+            "reason": f"Classification failed due to error: {str(e)}",
+            "flag": "NEEDS_REVIEW",
+        }
+
+
+# --------------------------------------------------
+# Core Skill: batch_classify
+# --------------------------------------------------
 
 def batch_classify(input_path: str, output_path: str):
     """
     Read input CSV, classify each row, write results CSV.
-
-    TODO: Build this using your AI tool.
-    Must: flag nulls, not crash on bad rows, produce output even if some rows fail.
+    Must not crash on bad rows.
     """
-    raise NotImplementedError("Build this using your AI tool + RICE prompt")
 
+    with open(input_path, newline="", encoding="utf-8") as infile, \
+         open(output_path, "w", newline="", encoding="utf-8") as outfile:
+
+        reader = csv.DictReader(infile)
+        fieldnames = ["complaint_id", "category", "priority", "reason", "flag"]
+        writer = csv.DictWriter(outfile, fieldnames=fieldnames)
+
+        writer.writeheader()
+
+        for row in reader:
+            result = classify_complaint(row)
+            writer.writerow(result)
+
+
+# --------------------------------------------------
+# CLI entrypoint
+# --------------------------------------------------
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="UC-0A Complaint Classifier")
-    parser.add_argument("--input",  required=True, help="Path to test_[city].csv")
-    parser.add_argument("--output", required=True, help="Path to write results CSV")
+    parser.add_argument(
+        "--input",
+        required=True,
+        help="./data/city-test-files/test_bangalore.csv",
+    )
+    parser.add_argument(
+        "--output",
+        required=True,
+        help="./results_bangalore.csv",
+    )
+
     args = parser.parse_args()
+
     batch_classify(args.input, args.output)
     print(f"Done. Results written to {args.output}")