Your commit message

app.py

@@ -43,18 +43,15 @@ def load_hf_dataset():
     """
     global dataset_cache
 
-    # Already loaded in memory
     if dataset_cache is not None:
         return dataset_cache
 
-    # Load from persistent cache
     if os.path.exists(CACHE_PATH):
         logger.info(f"Loading dataset from cache at {CACHE_PATH}")
         dataset_cache = load_from_disk(CACHE_PATH)
         logger.info(f"Loaded {len(dataset_cache)} rows from cached dataset")
         return dataset_cache
 
-    # Download once, then save
     logger.info(f"Downloading HF dataset: {DATASET_NAME}")
     ds = load_dataset(DATASET_NAME, split="train")
 
@@ -93,13 +90,13 @@ def serve_index():
 
 
 # ---------------------------------------------------------
-# List all tickers
+# List all symbols
 # ---------------------------------------------------------
 @app.get("/tickers")
 def get_tickers():
     ds = load_hf_dataset()
-    tickers = sorted(set([t.upper() for t in ds["ticker"]]))
-    return {"tickers": tickers}
+    symbols = sorted(set([s.upper() for s in ds["symbol"]]))
+    return {"tickers": symbols}
 
 
 # ---------------------------------------------------------
@@ -112,7 +109,7 @@ def get_transcript(symbol: str):
 
     logger.info(f"Fetching transcript for: {symbol}")
 
-    rows = [r for r in ds if r["ticker"].upper() == symbol]
+    rows = [r for r in ds if r["symbol"].upper() == symbol]
 
     if not rows:
         raise HTTPException(status_code=404, detail=f"No transcript found for {symbol}")
@@ -121,7 +118,53 @@ def get_transcript(symbol: str):
 
     return {"symbol": symbol, "records": safe_rows}
 
-@app.get("/run-once")
-def run_once():
-    import run_once
-    return {"status": "executed"}
+
+# ---------------------------------------------------------
+# Dataset info (size + columns)
+# ---------------------------------------------------------
+@app.get("/dataset-info")
+def dataset_info():
+    ds = load_hf_dataset()
+
+    info = {
+        "num_rows": len(ds),
+        "columns": ds.column_names,
+        "cache_path": CACHE_PATH,
+    }
+
+    return info
+
+
+# ---------------------------------------------------------
+# Dataset summary (high-level stats)
+# ---------------------------------------------------------
+@app.get("/dataset-summary")
+def dataset_summary():
+    ds = load_hf_dataset()
+
+    symbols = set([s.upper() for s in ds["symbol"]])
+    years = set(ds["year"])
+    quarters = set(ds["quarter"])
+
+    dates = [d for d in ds["date"] if d is not None]
+    min_date = min(dates) if dates else None
+    max_date = max(dates) if dates else None
+
+    summary = {
+        "total_rows": len(ds),
+        "unique_symbols": len(symbols),
+        "symbols_sample": sorted(list(symbols))[:20],
+        "year_range": {
+            "min_year": min(years),
+            "max_year": max(years)
+        },
+        "quarters_present": sorted(list(quarters)),
+        "date_range": {
+            "min_date": min_date,
+            "max_date": max_date
+        },
+        "company_count": len(set(ds["company_id"])),
+    }
+
+    return summary
+

hf_push.sh

@@ -1,30 +0,0 @@
-#!/bin/bash
-
-# -----------------------------
-# CONFIGURATION
-# -----------------------------
-HF_USERNAME="shyameati"
-HF_TOKEN="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"
-HF_SPACE="transcripts-api"
-
-# -----------------------------
-# GIT SETUP
-# -----------------------------
-echo "Configuring Git remote with embedded HF token..."
-
-git remote set-url origin https://$HF_USERNAME:$HF_TOKEN@huggingface.co/spaces/$HF_USERNAME/$HF_SPACE
-
-# -----------------------------
-# COMMIT + PUSH
-# -----------------------------
-echo "Staging changes..."
-git add .
-
-echo "Committing..."
-git commit -m "Auto-update from script" || echo "No changes to commit"
-
-echo "Pushing to Hugging Face..."
-git push origin main
-
-echo "Done."
-