WIP

Author: Telijas

src/data_extract/data_extract.py

@@ -14,6 +14,8 @@
 
 def extract_market_data(symbol: str, date: datetime, day_records_negative: int,
                         day_records_positive: int) -> pd.DataFrame:
+    """Returns dataframe with columns: business_date, offset, stock_price_rel, stock_traded_rel and the columns from the market_data table:\n
+     symbol, business_date, year_month, stock_price, open, close, stock_traded, order_amount, after_hours, pre_market, market_capitalization"""
     connection = _get_connection()
     upper_date = (date + timedelta(int(day_records_positive * (7 / 5) + 10))).strftime('%Y-%m-%d')
     lower_date = (date - timedelta(int(day_records_negative * (7 / 5) + 10))).strftime('%Y-%m-%d')
@@ -26,6 +28,10 @@ def extract_market_data(symbol: str, date: datetime, day_records_negative: int,
     connection.close()
 
     df['business_date'] = pd.to_datetime(df['business_date'])
+    if df.empty:
+        print("No data returned for symbol:", symbol)
+        return pd.DataFrame()
+
     reference_index = df[df['business_date'] == date].index[0]
     df['offset'] = df.index - reference_index
     df = df[(-1) * day_records_negative <= df['offset']]

src/displaying/__init__.py

@@ -5,14 +5,15 @@
 
 import src.data_extract.data_extract as data_extract
 
-market_capitalization_lower_limit = 12700000000
+market_capitalization_lower_limit = 18000000000
+# market_capitalization_lower_limit = 30000000000
 monthly_shares_traded_lower_limit = 250000
 
 
 def get_sp500_master_data_candidate(date: datetime) -> list[str]:
     candidates = data_extract.get_master_data_eligible_symbols()
     candidates = list(set(candidates) - set(data_extract.get_current_sp500_list(date)))
-    return candidates
+    return sorted(candidates)
 
 
 def fetch_data(symbol: str, include_month=6):
@@ -21,6 +22,13 @@ def fetch_data(symbol: str, include_month=6):
 
 def get_sp500_candidates(date: datetime, include_month=6, tolerance=0) -> list[str]:
     eligible_symbols = get_sp500_master_data_candidate(date)
+    # eligible_symbols = ['SW', 'ALNY', 'APO', 'ARES', 'ATVI', 'BCE', 'BMRN', 'BSY', 'BUD', 'CCEP', 'CHKP', 'CM', 'CP',
+    #                     'CPNG', 'CQP', 'CVE', 'DASH', 'DB', 'DDOG', 'DELL', 'EC', 'FCNCA', 'FLT', 'FWONA', 'FWONK',
+    #                     'GFS', 'GIB', 'GLD', 'HEI', 'HUBS', 'ICLR', 'ILMN', 'IMO', 'LNG', 'LPLA', 'MBLY', 'MDB', 'MELI',
+    #                     'MFC', 'MGA', 'MKL', 'MRVL', 'NET', 'NU', 'PINS', 'PKI', 'PLTR', 'PXD', 'RBLX', 'RCI', 'RS',
+    #                     'SCCO', 'SE', 'SIRI', 'SNOW', 'SPLK', 'SPOT', 'SQ', 'SUI', 'TEAM', 'TTD', 'TW', 'VEEV', 'VO',
+    #                     'WDAY', 'WLK', 'YUMC', 'ZM', 'ZS']
+
     with ThreadPoolExecutor() as executor:
         list_sp500_el = list(executor.map(fetch_data, eligible_symbols, [include_month] * len(eligible_symbols)))
     sp500_list = pd.concat(list_sp500_el, ignore_index=True)

src/displaying/data_display.py

@@ -41,15 +41,15 @@ def do_show_analysis():
     plt.legend()
     plt.show()
 
-    for symbol, group in grouped:
-        plt.plot(group['offset'], group['stock_traded_rel'], linestyle='-', label=symbol)
-    plt.xlabel("Offset")
-    plt.ylabel("Relative Change")
-    plt.title("Relative Change vs Offset for Multiple Symbols")
-    plt.axhline(0, color='gray', linestyle='--', linewidth=0.8)  # Add a horizontal line at y=0
-    plt.grid(True)
-    plt.legend()
-    plt.show()
+    # for symbol, group in grouped:
+    #     plt.plot(group['offset'], group['stock_traded_rel'], linestyle='-', label=symbol)
+    # plt.xlabel("Offset")
+    # plt.ylabel("Relative Change")
+    # plt.title("Relative Change vs Offset for Multiple Symbols")
+    # plt.axhline(0, color='gray', linestyle='--', linewidth=0.8)  # Add a horizontal line at y=0
+    # plt.grid(True)
+    # plt.legend()
+    # plt.show()
 
     print("done")
 
@@ -59,7 +59,40 @@ def do_show_analysis():
 
 
 if __name__ == "__main__":
-    # sp500_stock_quality.display_sp500_quality_of_year(2024)
-    candidates = preprocessing.get_sp500_candidates(datetime(2023, 10, 18))
+    sp500_stock_quality.display_sp500_quality_of_year(2024)
+    sp500_stock_quality.display_sp500_quality_of_year(2025)
+    check_date = datetime(2024, 7, 8)
+    candidates = preprocessing.get_sp500_candidates(check_date, 12, 0)
     print("Candidates found: ", len(candidates))
-    print("List of candidates: ", candidates)
+    # print("List of candidates: ", candidates)
+    sp500_entries = [(symbol, check_date) for symbol in candidates]
+    stock_data = pd.DataFrame()
+    stock_data: pd.DataFrame
+    for symbol, date in sp500_entries:
+        if stock_data is pd.DataFrame.empty:
+            stock_data = data_extract.extract_market_data(symbol, date, 40, 10)
+        else:
+            symbol_stock_data = data_extract.extract_market_data(symbol, date, 40, 10)
+            stock_data = pd.concat([stock_data, symbol_stock_data])
+
+        # Group by symbol
+    grouped = stock_data.groupby('symbol')
+    for symbol, group in grouped:
+        plt.plot(group['offset'], group['stock_price_rel'], linestyle='-', label=symbol)
+    plt.xlabel("Offset")
+    plt.ylabel("Relative Change")
+    plt.title("Relative Change vs Offset for Multiple Symbols")
+    plt.axhline(0, color='gray', linestyle='--', linewidth=0.8)  # Add a horizontal line at y=0
+    plt.grid(True)
+    plt.legend()
+    plt.show()
+
+    # for symbol, group in grouped:
+    #     plt.plot(group['offset'], group['stock_traded_rel'], linestyle='-', label=symbol)
+    # plt.xlabel("Offset")
+    # plt.ylabel("Relative Change")
+    # plt.title("Relative Change vs Offset for Multiple Symbols")
+    # plt.axhline(0, color='gray', linestyle='--', linewidth=0.8)  # Add a horizontal line at y=0
+    # plt.grid(True)
+    # plt.legend()
+    # plt.show()