update analysestock

analysestock.py

@@ -11,7 +11,6 @@ from pathlib import Path
 from datetime import timedelta
 from collections import OrderedDict
 
-
 from rsistrategies import get_rsi_trade_signal
 from macdstrategies import get_macd_trade_signal
 from emastrategies import get_ema_trade_signal
@@ -59,6 +58,8 @@ MODEL_BUNDLE_PATH = (
 Path(MODEL_BUNDLE_PATH).parent.mkdir(parents=True, exist_ok=True)  # ensure writable dir when training
 # --- end snippet ---
 
+
+
 from predictedchart import run_stock_prediction
 
 # ===================== TA scoring =====================
@@ -77,8 +78,24 @@ def calculate_technical_analysis_score(indicator_scores):
     weight_values = list(indicator_weights.values())
     weighted_score = sum(score * weight for score, weight in zip(indicator_scores, weight_values))
     total_weight = sum(weight_values)
-    technical_analysis_score = (weighted_score / (total_weight * 100)) * 85    
-    return technical_analysis_score
+    technical_analysis_score = (weighted_score / (total_weight * 100)) * 85  
+    overall_ta_signal_100 = np.where(
+        technical_analysis_score > 65, 'Buy',
+        np.where(technical_analysis_score > 40, 'Neutral', 'DBuy')
+    )
+    return technical_analysis_score, overall_ta_signal_100
+  
+def signal_from_score(score, max_points, buy_frac=0.65, neutral_frac=0.40):
+    
+    buy_cutoff = buy_frac * max_points
+    neutral_cutoff = neutral_frac * max_points
+
+    if score > buy_cutoff:
+        return "Buy"
+    elif score > neutral_cutoff:
+        return "Neutral"
+    else:
+        return "DBuy"
 
 # ================== Pivot levels & trade ==================
 def calculate_pivot_points(ticker, score, live_price, atr_period=14):
@@ -163,16 +180,22 @@ def calculate_pivot_points(ticker, score, live_price, atr_period=14):
 
 # =================== Main: short-term swing ===================
 def analysestock(ticker):
-   
-    stock_data = yf.download(ticker, start="2023-01-01", end="2025-09-01", interval="1d") 
+    now = datetime.datetime.now()
+    formatted_datetime = now.strftime('%Y-%m-%d %H:%M:%S.%f')
+
+    threshold_time = now.replace(hour=17, minute=0, second=0, microsecond=0)
+    end_date = (now + datetime.timedelta(days=1)).strftime('%Y-%m-%d') if now >= threshold_time else now.strftime('%Y-%m-%d')
+
+    stock_data = yf.download(ticker, start="2023-01-01", end=end_date, interval="1d") 
     stock_data.columns = [col.lower() if isinstance(col, str) else col[0].lower() for col in stock_data.columns]
+    lasttradingdate = stock_data.index[-1].strftime('%d-%m-%Y')
     stockdetail = yf.Ticker(ticker)
     company_name = stockdetail.info.get("longName", "Company name not found")
     live_price = stockdetail.info["regularMarketPrice"]
     price_change = stockdetail.info['regularMarketChange']
     percentage_change = stockdetail.info['regularMarketChangePercent']
 
-    recentdays = stock_data.tail(20)
+    recentdays = stock_data.tail(30)
     ohlc_data = []
     for index, row in recentdays.iterrows():
         ohlc_data.append({
@@ -215,7 +238,7 @@ def analysestock(ticker):
         sr_trade_signal['sr_score']
     ]
 
-    overall_ta_score = calculate_technical_analysis_score(indicator_score)
+    overall_ta_score,overall_ta_signal = calculate_technical_analysis_score(indicator_score)
 
     #FA signals
 
@@ -233,8 +256,10 @@ def analysestock(ticker):
 
     #overallscore
 
-    overall_fa_score = fundamental_analysis["overall_fa_score"]
+    overall_fa_score = fundamental_analysis["overall_fa_score"]     
     overall_news_score = news_payload['overall_news_score']
+    overall_fa_signal = signal_from_score(overall_fa_score,15)
+    overall_news_signal = signal_from_score(overall_news_score,5)
     combined_overall_score = overall_ta_score + overall_fa_score + overall_news_score
     combined_overall_signal = np.where(combined_overall_score > 65, 'Buy',
                                        np.where(combined_overall_score > 50, 'Neutral', 'DBuy'))
@@ -284,6 +309,8 @@ def analysestock(ticker):
     response = {        
         "ticker": ticker,
         "company_name": company_name,
+        "lasttradingdate": lasttradingdate,
+        "currentdatetime": formatted_datetime,
         "live_price": round(live_price, 2),
         "price_change": round(price_change, 2),
         "percentage_change": round(percentage_change, 2),
@@ -298,9 +325,12 @@ def analysestock(ticker):
         "BB": bb_trade_signal['bollinger_signals'],
         "PA_MS": priceaction_trade_signal['priceaction_signals'],
         "final_trade_signal": final_trade_signal,
-        "overall_ta_score": round(overall_ta_score, 2),        
+        "overall_ta_score": round(overall_ta_score, 2),  
+        "overall_ta_signal": str(overall_ta_signal),
         "fundamental_analysis": fundamental_analysis,
         "overall_fa_score": overall_fa_score,
+        "overall_fa_signal": str(overall_fa_signal),
+        "overall_news_signal": str(overall_news_signal),
         "news_overall_score": overall_news_score,
         "news": news_payload["items"],
         "combined_overall_score": round(combined_overall_score, 2),

predictedchart.py

@@ -8,9 +8,9 @@ import torch.nn as nn
 from torch.utils.data import Dataset, DataLoader
 
 # Step 1: Download data with TA indicators
-def fetch_stock_data_with_indicators(ticker, start="2020-01-01", end="2025-09-03"):
+def fetch_stock_data_with_indicators(ticker, start="2020-01-01", end="2025-09-10"):
     df = yf.download(ticker, start=start, end=end)
-    actualdata = yf.download(ticker, start=start, end="2025-09-04")
+    actualdata = yf.download(ticker, start=start, end="2025-09-11")
     df = df[["Open", "High", "Low", "Close", "Volume"]]
     close_prices = df['Close'].to_numpy().flatten()
     low_prices = df['Low'].to_numpy().flatten()
@@ -90,7 +90,7 @@ def run_stock_prediction(ticker):
     predictions = []
     input_seq = scaled_data[-window_size:].copy()  # shape: [20, features]
 
-    for i in range(15):
+    for i in range(30):
         seq_tensor = torch.tensor(input_seq, dtype=torch.float32).unsqueeze(1)  # [seq_len, 1, features]
 
         with torch.no_grad():
@@ -110,7 +110,7 @@ def run_stock_prediction(ticker):
 
     # Get the last date from the dataset
     last_date = df.index[-1]
-    predicted_dates = pd.date_range(start=last_date + pd.Timedelta(days=1), periods=15, freq='B')  # Business days
+    predicted_dates = pd.date_range(start=last_date + pd.Timedelta(days=1), periods=30, freq='B')  # Business days
 
    
     prediction_results = pd.DataFrame({