Update searchschool.py

searchschool.py

@@ -1,5 +1,7 @@
-# searchschool.py
-import os
+# ====================================================
+# searchschool.py — Village Enabled
+# ====================================================
+
 import pandas as pd
 from huggingface_hub import hf_hub_download
 from rapidfuzz import process, fuzz
@@ -11,6 +13,7 @@ from web_search import tavily_search_codes
 MASTER_SCHOOL_COL   = "School_Name__c"
 MASTER_DISTRICT_COL = "School_District__c"
 MASTER_BLOCK_COL    = "School_Block__c"
+MASTER_VILLAGE_COL  = "School_Village__c"
 MASTER_UDISE_COL    = "School_Udise_Code__c"
 MASTER_STATE_COL    = "School_State__c"
 
@@ -20,10 +23,10 @@ MASTER_ALL_STATES_FILE = "master_all_states.xlsx"
 DEFAULT_STATE_KEY = "ARUNACHAL PRADESH"
 MAX_CANDIDATES = 5
 
-# global cache (loaded once)
+# global cache
 master_df = None
 
-# normalization helper (lazy import to avoid circular deps)
+# normalization helper
 try:
     from admin_patterns import normalize_with_patterns_dynamic
 except Exception:
@@ -31,7 +34,7 @@ except Exception:
 
 
 # ====================================================
-# INTERNAL: load master CSV once
+# INTERNAL: load master once
 # ====================================================
 def _load_master_if_needed():
     global master_df
@@ -44,7 +47,6 @@ def _load_master_if_needed():
         filename=MASTER_ALL_STATES_FILE,
     )
 
-    
     master_df = pd.read_excel(local_path, dtype=str).fillna("")
 
 
@@ -54,16 +56,16 @@ def _load_master_if_needed():
 def on_search_web(
     school_name: str,
     state_name: str,
-    district: str = None,
-    block: str = None
+    district: str | None = None,
+    block: str | None = None,
+    village: str | None = None,
 ):
     """
     1. Tavily search → list of UDISE codes
-    2. Lookup those UDISE codes in master_all_states.csv
+    2. Lookup those UDISE codes in master
     3. Return standardized DataFrame
     """
 
-    # Step 1: Tavily search
     udise_list = tavily_search_codes(
         school_name=school_name,
         state_name=state_name,
@@ -74,16 +76,24 @@ def on_search_web(
 
     if not udise_list:
         return pd.DataFrame(
-            columns=["School_Name", "State", "District", "Block", "UDISE_Code"]
+            columns=[
+                "School_Name", "State",
+                "District", "Block", "Village",
+                "UDISE_Code"
+            ]
         )
 
-    # Step 2: lookup
-    rows = get_school_rows_by_udise(state_name, udise_list)
+    rows = get_school_rows_by_udise(
+        state_name, udise_list, district, block, village
+    )
 
-    # Step 3: to DataFrame
     df = pd.DataFrame(rows)
 
-    expected = ["School_Name", "State", "District", "Block", "UDISE_Code"]
+    expected = [
+        "School_Name", "State",
+        "District", "Block", "Village",
+        "UDISE_Code"
+    ]
     for col in expected:
         if col not in df.columns:
             df[col] = None
@@ -91,32 +101,43 @@ def on_search_web(
     return df[expected]
 
 
-def get_school_rows_by_udise(state_name: str, udise_codes: list[str]):
-    """
-    UDISE → school rows lookup from master_all_states.csv
-    """
+def get_school_rows_by_udise(
+    state_name: str,
+    udise_codes: list[str],
+    district: str | None = None,
+    block: str | None = None,
+    village: str | None = None,
+):
     if not udise_codes:
         return []
 
     _load_master_if_needed()
 
+    df = master_df
     udise_codes = {str(u) for u in udise_codes}
 
-    df = master_df
-    matched = df[df[MASTER_UDISE_COL].isin(udise_codes)]
+    df = df[df[MASTER_UDISE_COL].isin(udise_codes)]
 
     if state_name:
-        matched = matched[
-            matched[MASTER_STATE_COL].str.upper() == state_name.upper()
-        ]
+        df = df[df[MASTER_STATE_COL].str.upper() == state_name.upper()]
+
+    if district:
+        df = df[df[MASTER_DISTRICT_COL] == district]
+
+    if block:
+        df = df[df[MASTER_BLOCK_COL] == block]
+
+    if village and MASTER_VILLAGE_COL in df.columns:
+        df = df[df[MASTER_VILLAGE_COL] == village]
 
     rows = []
-    for _, r in matched.iterrows():
+    for _, r in df.iterrows():
         rows.append({
             "School_Name": r.get(MASTER_SCHOOL_COL, ""),
             "State": r.get(MASTER_STATE_COL, ""),
             "District": r.get(MASTER_DISTRICT_COL, ""),
             "Block": r.get(MASTER_BLOCK_COL, ""),
+            "Village": r.get(MASTER_VILLAGE_COL, ""),
             "UDISE_Code": r.get(MASTER_UDISE_COL, ""),
         })
 
@@ -124,72 +145,15 @@ def get_school_rows_by_udise(state_name: str, udise_codes: list[str]):
 
 
 # ====================================================
-# MASTER LOAD FOR UI (STATE → DISTRICT → BLOCK)
-# ====================================================
-def load_master_for_state(state_key: str | None):
-    """
-    Load master_all_states.csv once.
-    Filter districts by selected state.
-    """
-    import gradio as gr
-
-    _load_master_if_needed()
-
-    df = master_df
-
-    if state_key:
-        df = df[df[MASTER_STATE_COL].str.upper() == state_key.upper()]
-
-    if MASTER_DISTRICT_COL in df.columns:
-        districts = sorted(df[MASTER_DISTRICT_COL].unique().tolist())
-        districts = ["All"] + districts
-    else:
-        districts = []
-
-    blocks = ["All"]
-
-    return (
-        gr.Dropdown(choices=districts, value="All" if districts else None),
-        gr.Dropdown(choices=blocks, value="All"),
-    )
-
-
-def update_blocks(district: str | None):
-    """
-    Update block dropdown when district changes
-    """
-    import gradio as gr
-
-    _load_master_if_needed()
-
-    df = master_df
-
-    if district and district != "All":
-        df = df[df[MASTER_DISTRICT_COL] == district]
-
-    if MASTER_BLOCK_COL in df.columns:
-        blocks = sorted(df[MASTER_BLOCK_COL].unique().tolist())
-        blocks = ["All"] + blocks if blocks else ["All"]
-    else:
-        blocks = ["All"]
-
-    return gr.Dropdown(choices=blocks, value="All")
-
-
-# ====================================================
-# RAPIDFUZZ SEARCH
+# RAPIDFUZZ SEARCH (Village-aware)
 # ====================================================
 def search_candidates(
     query_name: str,
     state_key: str | None,
     district: str | None,
     block: str | None,
+    village: str | None = None,
 ):
-    """
-    Given school name + filters, return:
-    - candidates table
-    - best candidate table
-    """
     global normalize_with_patterns_dynamic
 
     if normalize_with_patterns_dynamic is None:
@@ -202,18 +166,19 @@ def search_candidates(
 
     df = master_df
 
-    # Filter by state
+    # -------- Filters --------
     if state_key:
         df = df[df[MASTER_STATE_COL].str.upper() == state_key.upper()]
 
-    # Filter by district
-    if district and district != "All":
+    if district:
         df = df[df[MASTER_DISTRICT_COL] == district]
 
-    # Filter by block
-    if block and block != "All":
+    if block:
         df = df[df[MASTER_BLOCK_COL] == block]
 
+    if village and MASTER_VILLAGE_COL in df.columns:
+        df = df[df[MASTER_VILLAGE_COL] == village]
+
     if df.empty:
         return pd.DataFrame(), pd.DataFrame()
 
@@ -239,6 +204,7 @@ def search_candidates(
             "State": r.get(MASTER_STATE_COL, ""),
             "District": r.get(MASTER_DISTRICT_COL, ""),
             "Block": r.get(MASTER_BLOCK_COL, ""),
+            "Village": r.get(MASTER_VILLAGE_COL, ""),
             "UDISE_Code": r.get(MASTER_UDISE_COL, ""),
             "Score": score,
         })