Update app.py

app.py

@@ -4,23 +4,31 @@ import numpy as np
 from sklearn.ensemble import GradientBoostingClassifier
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import roc_auc_score
+from datetime import datetime
 
-from utils import generate_features, pick_top15, generate_system15_csv
+from utils import generate_features, pick_top15
+
+# In-memory history of predictions (max 12 rows for the month)
+prediction_history = []
 
 
 def train_and_predict(file_obj):
-    # Load dataset
-    df = pd.read_csv(file_obj.name, header=None)
-    df = df.iloc[:, :8]  # Keep only date + 6 main numbers + bonus
-    df.columns = ["draw_date", "n1", "n2", "n3", "n4", "n5", "n6", "bonus"]
+    # --- Load dataset correctly ---
+    df = pd.read_csv(file_obj.name, header=0)
+    df = df.iloc[:, :8]  # Keep first 8 cols: draw_no, draw_date, n1..n6
+    df.columns = ["draw_no", "draw_date", "n1", "n2", "n3", "n4", "n5", "n6"]
+
+    # Convert numbers to integers
+    for col in ["n1", "n2", "n3", "n4", "n5", "n6"]:
+        df[col] = pd.to_numeric(df[col], errors="coerce")
 
     debug_log = []
     debug_log.append(f"✅ Loaded dataset with {len(df)} draws")
-    debug_log.append(f"First draw date: {df['draw_date'].iloc[0]}, Last draw date: {df['draw_date'].iloc[-1]}")
+    debug_log.append(f"First draw: {df['draw_date'].iloc[0]}, Last draw: {df['draw_date'].iloc[-1]}")
 
-    # Generate features and labels
+    # --- Generate features ---
     features, labels = generate_features(df)
-    debug_log.append(f"Generated {len(features)} feature rows, Labels distribution: {np.bincount(labels)}")
+    debug_log.append(f"Generated {len(features)} rows, Label distribution: {np.bincount(labels)}")
 
     top15 = None
     auc = None
@@ -32,7 +40,6 @@ def train_and_predict(file_obj):
             X_train, X_test, y_train, y_test = train_test_split(
                 features, labels, test_size=0.2, random_state=42, stratify=labels
             )
-            debug_log.append(f"Train size: {len(X_train)}, Test size: {len(X_test)}")
 
             model = GradientBoostingClassifier(n_estimators=200, max_depth=3, random_state=42)
             model.fit(X_train, y_train)
@@ -49,43 +56,46 @@ def train_and_predict(file_obj):
             all_numbers["score"] = scores
 
             top15 = pick_top15(all_numbers)
-            debug_log.append(f"🎯 ML Top 15 Numbers: {top15}")
+            debug_log.append(f"🎯 ML Top 15: {top15}")
             debug_log.append(f"Model AUC: {auc:.3f}")
 
         except Exception as e:
-            debug_log.append(f"⚠️ ML training failed: {str(e)}")
+            debug_log.append(f"⚠️ ML failed: {str(e)}")
             used_fallback = True
     else:
-        debug_log.append("⚠️ Only one class found in labels — skipping ML")
+        debug_log.append("⚠️ Only one class found — using fallback")
         used_fallback = True
 
-    # --- Fallback: Frequency-based ---
+    # --- Fallback: frequency-based ---
     if used_fallback or top15 is None:
-        debug_log.append("👉 Using fallback: frequency-based Top 15")
-        # Count occurrences of each number in all draws
         nums = df[["n1", "n2", "n3", "n4", "n5", "n6"]].values.flatten()
         freq = pd.Series(nums).value_counts().reset_index()
         freq.columns = ["number", "count"]
         top15 = sorted(freq.head(15)["number"].tolist())
-        debug_log.append(f"🎯 Frequency Top 15 Numbers: {top15}")
+        debug_log.append(f"👉 Fallback Top 15: {top15}")
+
+    # --- Record in prediction history ---
+    today = datetime.now().strftime("%Y-%m-%d %H:%M")
+    prediction_history.append({"date": today, "numbers": top15})
+    # Keep last 12 only
+    if len(prediction_history) > 12:
+        prediction_history.pop(0)
 
-    # Generate System 15 CSV (5005 combos)
-    csv_path = "system15.csv"
-    generate_system15_csv(top15, csv_path)
-    debug_log.append("📂 system15.csv generated with 5005 combinations")
+    # Build table view
+    history_df = pd.DataFrame(prediction_history)
+    history_df["numbers"] = history_df["numbers"].apply(lambda x: " ".join(str(n).zfill(2) for n in x))
 
-    return "\n".join(debug_log), csv_path
+    table_view = history_df.to_string(index=False)
+
+    return "\n".join(debug_log) + "\n\n📊 Prediction History (last 12):\n" + table_view
 
 
 demo = gr.Interface(
     fn=train_and_predict,
     inputs=gr.File(file_types=[".txt", ".csv"], label="Upload Toto650.txt"),
-    outputs=[
-        gr.Textbox(label="Training & Prediction Log", lines=20),
-        gr.File(label="Download System15 CSV")
-    ],
+    outputs=gr.Textbox(label="Training, Prediction, and History Log", lines=25),
     title="Sure Win Club - Star Toto 6/50 Predictor",
-    description="Upload the latest Toto650.txt dataset every Monday. The system will train a fresh model (or fallback to frequency) and output Top 15 numbers + System15 (5005 tickets)."
+    description="Upload Toto650.txt after each draw. System trains fresh and shows Top 15 hot numbers + running history (up to 12 rows)."
 )
 
 if __name__ == "__main__":
@@ -95,3 +105,4 @@ if __name__ == "__main__":
 
 
 
+