neurostats-API 0.0.22__tar.gz → 0.0.23b0__tar.gz

{neurostats_api-0.0.22 → neurostats_api-0.0.23b0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: neurostats_API
-Version: 0.0.22
+Version: 0.0.23b0
 Summary: The service of NeuroStats website
 Home-page: https://github.com/NeurowattStats/NeuroStats_API.git
 Author: JasonWang@Neurowatt
@@ -89,7 +89,7 @@ pip install neurostats-API
 ```Python 
 >>> import neurostats_API
 >>> print(neurostats_API.__version__)
-0.0.22
+0.0.23b
 ```
 
 ### 得到最新一期的評價資料與歷年評價

{neurostats_api-0.0.22 → neurostats_api-0.0.23b0}/README.md

@@ -73,7 +73,7 @@ pip install neurostats-API
 ```Python 
 >>> import neurostats_API
 >>> print(neurostats_API.__version__)
-0.0.22
+0.0.23b
 ```
 
 ### 得到最新一期的評價資料與歷年評價

{neurostats_api-0.0.22 → neurostats_api-0.0.23b0}/neurostats_API/__init__.py

@@ -1,4 +1,4 @@
-__version__='0.0.22'
+__version__='0.0.23b'
 
 from .fetchers import (
     BalanceSheetFetcher,

{neurostats_api-0.0.22 → neurostats_api-0.0.23b0}/neurostats_API/fetchers/tech.py

@@ -13,7 +13,8 @@ class TechFetcher(StatsFetcher):
 
         super().__init__(ticker, db_client)
         if (ticker in self.tw_company_list.keys()):
-            self.collection = self.db["TWN/APIPRCD"]
+            self.twse_collection = self.db['twse_stats']
+            self.tej_collection = self.db["TWN/APIPRCD"]
 
         self.full_ohlcv = self._get_ohlcv()
         self.basic_indexes = [
@@ -53,35 +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}'
-            elif(self.ticker in self.tw_company_list.keys()):
-                full_tick = f'{self.ticker}.tw'
-            else:
-                full_tick = f"{self.ticker}"
-
+        if self.ticker in ['GSPC', 'IXIC', 'DJI', 'TWII']:
+            full_tick = f'^{self.ticker}'
             df = self.conduct_yf_search(full_tick)
 
-            if (
-                self.ticker in self.tw_company_list.keys() and
-                not self.has_required_columns(df, required_cols)
-            ):
-                full_tick = f'{self.ticker}.two'
+            return df[required_cols]
 
-                df = self.conduct_yf_search(full_tick)
+        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')
+            ]
+
+            for search_method in search_fns:
+                try:
+                    df = search_method()
+                    break
+                except (KeyError, ValueError, TypeError):
+                    continue
+            else:
+                return pd.DataFrame(columns=required_cols)
 
-                if (df.empty):
-                    raise ValueError(f"No data found for ticker: {self.ticker}")\
-            
+            # 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()
 
-        except (KeyError, ValueError, TypeError) as e:
-            if (self.collection_name in ['TWN/APIPRCD']):
-                return self.conduct_db_search_tej()
-            elif (self.collection_name == 'us_stats'):
-                return self.conduct_db_search_us()
+            return df
+        
 
     def get_daily(self):
 
@@ -182,6 +195,86 @@ class TechFetcher(StatsFetcher):
 
         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:
 

{neurostats_api-0.0.22 → neurostats_api-0.0.23b0}/neurostats_API.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: neurostats_API
-Version: 0.0.22
+Version: 0.0.23b0
 Summary: The service of NeuroStats website
 Home-page: https://github.com/NeurowattStats/NeuroStats_API.git
 Author: JasonWang@Neurowatt
@@ -89,7 +89,7 @@ pip install neurostats-API
 ```Python 
 >>> import neurostats_API
 >>> print(neurostats_API.__version__)
-0.0.22
+0.0.23b
 ```
 
 ### 得到最新一期的評價資料與歷年評價

{neurostats_api-0.0.22 → neurostats_api-0.0.23b0}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name='neurostats_API',
-    version='0.0.22',
+    version='0.0.23b',
     long_description=open('README.md', 'r', encoding='utf-8').read(),
     long_description_content_type='text/markdown',
     install_requires=[

{neurostats_api-0.0.22 → neurostats_api-0.0.23b0}/test/test_fetchers.py

@@ -12,10 +12,8 @@ pp = PrettyPrinter(
     indent=2
 )
 
-company_list = {
-        "1260": "富味香",
-        "AAPL": "APPLE.Inc"
-    }
+with open(f"./tw50_company_list.json") as f:
+    company_list = json.load(f)
 db_client = DBClient("mongodb://neurowatt:neurodb123@db.neurowatt.ai:27017/neurowatt").get_client()
 
 def test_value_serie():
@@ -113,7 +111,6 @@ def test_balance_sheet():
     from neurostats_API.fetchers import BalanceSheetFetcher
     company_list = {
         "2330": "台積電",
-        "AAPL": "APPLE.Inc"
     }
     for ticker in company_list.keys():