neurostats-API 0.0.21b0__py3-none-any.whl → 0.0.23b0__py3-none-any.whl

neurostats_API/fetchers/tech.py

@@ -12,7 +12,10 @@ class TechFetcher(StatsFetcher):
         """
 
         super().__init__(ticker, db_client)
-        self.collection = self.db["TWN/APIPRCD"]
+        if (ticker in self.tw_company_list.keys()):
+            self.twse_collection = self.db['twse_stats']
+            self.tej_collection = self.db["TWN/APIPRCD"]
+
         self.full_ohlcv = self._get_ohlcv()
         self.basic_indexes = [
             'SMA5', 'SMA20', 'SMA60', 'EMA5', 'EMA20', 'EMA40', 'EMA12',
@@ -51,53 +54,47 @@ class TechFetcher(StatsFetcher):
 
         required_cols = ['date', 'open', 'high', 'low', 'close', 'volume']
 
-        try:
-            # 先對yf search
-            if self.ticker in ['GSPC', 'IXIC', 'DJI', 'TWII']:
-                full_tick = f'^{self.ticker}'
-            else:
-                full_tick = f'{self.ticker}.tw'
-
+        if self.ticker in ['GSPC', 'IXIC', 'DJI', 'TWII']:
+            full_tick = f'^{self.ticker}'
             df = self.conduct_yf_search(full_tick)
 
-            if not self.has_required_columns(df, required_cols):
-
-                print(f".tw failed, try .two")
-
-                full_tick = f'{self.ticker}.two'
+            return df[required_cols]
 
-                df = self.conduct_yf_search(full_tick)
-
-                if (df.empty):
-                    raise ValueError(f"No data found for ticker: {self.ticker}")
-
-        except (KeyError, ValueError, TypeError) as e:
-            # 再對TEJ search
-            tej_required_cols = [
-                "mdate", "open_d", 'high_d', 'low_d', 'close_d', 'vol'
+        elif(self.ticker in self.tw_company_list.keys()):
+            search_fns = [
+                self.conduct_db_search_twse, 
+                self.conduct_db_search_tej, 
+                lambda: self.conduct_yf_search(f'{self.ticker}.tw'),
+                lambda: self.conduct_yf_search(f'{self.ticker}.two')
             ]
-            tej_name_proj = {
-                tej_name: org_name
-                for tej_name, org_name in zip(tej_required_cols, required_cols)
-            }
-
-            query = {'ticker': self.ticker}
-            ticker_full = self.collection.find_one(query)
 
-            if not ticker_full:
-                raise ValueError("No ticker found in database")
-
-            daily_data = ticker_full.get("data", [])
-            if not isinstance(daily_data, list):
-                raise TypeError("Expected 'daily_data' to be a list.")
-
-            df = pd.DataFrame(daily_data)
-
-            if not self.has_required_columns(df, tej_required_cols):
-                raise KeyError(f"Missing required columns")
-            df = df.rename(columns=tej_name_proj)
+            for search_method in search_fns:
+                try:
+                    df = search_method()
+                    break
+                except (KeyError, ValueError, TypeError):
+                    continue
+            else:
+                return pd.DataFrame(columns=required_cols)
+
+            # break跳出後
+            return df[required_cols]
+        else:  # 美股
+            search_fns = [
+                self.conduct_db_search_us,
+                lambda : self.conduct_yf_search(f"{self.ticker}")
+            ]
+            for search_method in search_fns:
+                try:
+                    df = search_method()
+                    break
+                except (KeyError, ValueError, TypeError):
+                    continue
+            else:
+                df = pd.DataFrame()
 
-        return df[required_cols]
+            return df
+        
 
     def get_daily(self):
 
@@ -141,6 +138,142 @@ class TechFetcher(StatsFetcher):
         )
 
         return df
+    
+    def conduct_db_search_tej(self):
+        # 再對TEJ search
+        tej_required_cols = [
+            "mdate", "open_d", 'high_d', 'low_d', 'close_d', 'vol'
+        ]
+
+        required_cols = ['date', 'open', 'high', 'low', 'close', 'volume']
+        tej_name_proj = {
+            tej_name: org_name
+            for tej_name, org_name in zip(tej_required_cols, required_cols)
+        }
+
+        query = {'ticker': self.ticker}
+        ticker_full = self.collection.find_one(query)
+
+        if not ticker_full:
+            raise ValueError("No ticker found in database")
+
+        daily_data = ticker_full.get("data", [])
+        if not isinstance(daily_data, list):
+            raise TypeError("Expected 'daily_data' to be a list.")
+
+        df = pd.DataFrame(daily_data)
+
+        if not self.has_required_columns(df, tej_required_cols):
+            raise KeyError(f"Missing required columns")
+        df = df.rename(columns=tej_name_proj)
+
+        return df[required_cols]
+    
+    def conduct_db_search_us(self):
+        required_cols = ['date', 'open', 'high', 'low', 'close', 'volume']
+
+        query = {'ticker': self.ticker}
+        filter_query = {"daily_data" : 1, "_id": 0}
+        ticker_full = self.collection.find_one(query, filter_query)
+
+        if not ticker_full:
+            raise ValueError("No ticker found in database")
+
+        daily_data = ticker_full.get("daily_data", [])
+        if not isinstance(daily_data, list):
+            raise TypeError("Expected 'daily_data' to be a list.")
+
+        df = pd.DataFrame(daily_data)
+
+        if not self.has_required_columns(df, required_cols):
+            missing_cols = [col for col in required_cols if col not in df.columns]
+            missing_cols = ",".join(missing_cols)
+            print(Warning(f"{missing_cols} not in columns"))
+            for col in missing_cols:
+                df[col] = pd.NA
+            # raise KeyError(f"Missing required columns")
+
+        return df[required_cols]
+
+    
+    def conduct_db_search_twse(self):
+        required_cols = ['date', 'open', 'high', 'low', 'close', 'volume']
+        match_query = {"ticker" : self.ticker}
+        proj_query = {"_id": 0, "daily_data": 1}
+
+        full_data = self.twse_collection.find_one(match_query, proj_query)
+
+        if (not full_data):
+            raise ValueError("No ticker found in database twse_stats")
+
+        daily_data = full_data.get("daily_data", [])
+
+        if (not isinstance(daily_data, list)):
+            raise ValueError("No ticker found in database twse_stats")
+
+        df = pd.DataFrame(daily_data)
+        if not self.has_required_columns(df, required_cols):
+            raise KeyError(f"Missing required columns")
+        
+        df = df[required_cols]
+        df = df.sort_values(by = 'date').drop_duplicates(subset=['date'])
+
+        return df
+    
+    def conduct_db_search_tej(self):
+        # 再對TEJ search
+        tej_required_cols = [
+            "mdate", "open_d", 'high_d', 'low_d', 'close_d', 'vol'
+        ]
+
+        required_cols = ['date', 'open', 'high', 'low', 'close', 'volume']
+        tej_name_proj = {
+            tej_name: org_name
+            for tej_name, org_name in zip(tej_required_cols, required_cols)
+        }
+
+        query = {'ticker': self.ticker}
+        ticker_full = self.tej_collection.find_one(query)
+
+        if not ticker_full:
+            raise ValueError("No ticker found in database")
+
+        daily_data = ticker_full.get("data", [])
+        if not isinstance(daily_data, list):
+            raise TypeError("Expected 'daily_data' to be a list.")
+
+        df = pd.DataFrame(daily_data)
+
+        if not self.has_required_columns(df, tej_required_cols):
+            raise KeyError(f"Missing required columns")
+        df = df.rename(columns=tej_name_proj)
+
+        return df[required_cols]
+    
+    def conduct_db_search_us(self):
+        required_cols = ['date', 'open', 'high', 'low', 'close', 'volume']
+
+        query = {'ticker': self.ticker}
+        filter_query = {"daily_data" : 1, "_id": 0}
+        ticker_full = self.collection.find_one(query, filter_query)
+
+        if not ticker_full:
+            raise ValueError("No ticker found in database")
+
+        daily_data = ticker_full.get("daily_data", [])
+        if not isinstance(daily_data, list):
+            raise TypeError("Expected 'daily_data' to be a list.")
+
+        df = pd.DataFrame(daily_data)
+
+        if not self.has_required_columns(df, required_cols):
+            missing_cols = [col for col in required_cols if col not in df.columns]
+            missing_cols = ",".join(missing_cols)
+            for col in missing_cols:
+                df[col] = pd.NA
+            # raise KeyError(f"Missing required columns")
+
+        return df[required_cols]
 
 
 class TechProcessor: