Update app.py

app.py

@@ -1,32 +1,71 @@
-import requests
-from bs4 import BeautifulSoup
-
-# Open the file containing the URLs
-with open('draw_urls.txt', 'r') as file:
-    urls = file.readlines()
-
-# Iterate through each URL
-for url in urls:
-    url = url.strip()  # Remove any leading/trailing whitespace
-    response = requests.get(url)
-    soup = BeautifulSoup(response.text, 'html.parser')
-
-    # Extract the required data
-    draw_date = soup.find('span', text='Draw Date :').find_next('span').text.strip()
-    draw_number = soup.find('span', text='Draw No. :').find_next('span').text.strip()
-    prizes = soup.find_all('span', class_='prize')
-    first_prize = prizes[0].text.strip()
-    second_prize = prizes[1].text.strip()
-    third_prize = prizes[2].text.strip()
-    special_prizes = [prize.text.strip() for prize in prizes[3:13]]
-
-    # Print the extracted data (or save it to a file)
-    print(f"Draw Date: {draw_date}")
-    print(f"Draw Number: {draw_number}")
-    print(f"First Prize: {first_prize}")
-    print(f"Second Prize: {second_prize}")
-    print(f"Third Prize: {third_prize}")
-    print(f"Special Prizes: {special_prizes}")
-    print("-" * 40)
+import gradio as gr
+import pandas as pd
+import numpy as np
+from itertools import combinations
+from sklearn.ensemble import GradientBoostingClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import roc_auc_score
+import joblib
+import os
+
+from utils import generate_features, pick_top15, generate_system15_csv
+
+
+def train_and_predict(file_obj):
+    # Load dataset
+    df = pd.read_csv(file_obj.name, header=None)
+    # Columns: [draw_id?, draw_date, n1..n6, bonus, ...]
+    # Align to schema: we only keep date, n1..n6, bonus
+    df = df.iloc[:, :8]
+    df.columns = ["draw_date", "n1", "n2", "n3", "n4", "n5", "n6", "bonus"]
+
+    # Melt numbers into long format for training
+    features, labels = generate_features(df)
+
+    # Split into train/test
+    X_train, X_test, y_train, y_test = train_test_split(
+        features, labels, test_size=0.2, random_state=42, stratify=labels
+    )
+
+    # Train a simple gradient boosting model
+    model = GradientBoostingClassifier(n_estimators=200, max_depth=3, random_state=42)
+    model.fit(X_train, y_train)
+
+    # Evaluate
+    if len(np.unique(y_test)) > 1:
+        auc = roc_auc_score(y_test, model.predict_proba(X_test)[:, 1])
+    else:
+        auc = 0.5
+
+    # Score all numbers 1–50
+    all_numbers = pd.DataFrame({"number": range(1, 51)})
+    all_features, _ = generate_features(df, candidate_numbers=all_numbers["number"].tolist())
+    scores = model.predict_proba(all_features)[:, 1]
+    all_numbers["score"] = scores
+
+    # Pick top 15
+    top15 = pick_top15(all_numbers)
+
+    # Generate System 15 CSV (5005 combos)
+    csv_path = "system15.csv"
+    generate_system15_csv(top15, csv_path)
+
+    return f"Model AUC: {auc:.3f}\nTop 15 Numbers: {top15}", csv_path
+
+
+demo = gr.Interface(
+    fn=train_and_predict,
+    inputs=gr.File(file_types=[".txt", ".csv"], label="Upload Toto650.txt"),
+    outputs=[
+        gr.Textbox(label="Prediction Summary"),
+        gr.File(label="Download System15 CSV")
+    ],
+    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 and output Top 15 numbers + System15 (5005 tickets)."
+)
+
+if __name__ == "__main__":
+    demo.launch()
+