neurostats-API 0.0.17__py3-none-any.whl → 0.0.19__py3-none-any.whl

neurostats_API/__init__.py

@@ -1,4 +1,4 @@
-__version__='0.0.16'
+__version__='0.0.19'
 
 from .fetchers import (
     BalanceSheetFetcher,
@@ -9,5 +9,6 @@ from .fetchers import (
     MarginTradingFetcher,
     MonthRevenueFetcher,
     TechFetcher,
-    ProfitLoseFetcher
+    TEJStockPriceFetcher,
+    ProfitLoseFetcher,
 )

neurostats_API/fetchers/__init__.py

@@ -2,7 +2,7 @@ from .base import StatsDateTime, StatsFetcher
 from .balance_sheet import BalanceSheetFetcher
 from .cash_flow import CashFlowFetcher
 from .finance_overview import FinanceOverviewFetcher
-from .tej_finance_report import FinanceReportFetcher
+from .tej_finance_report import FinanceReportFetcher, TEJStockPriceFetcher
 from .tech import TechFetcher
 from .institution import InstitutionFetcher
 from .margin_trading import MarginTradingFetcher

neurostats_API/fetchers/base.py

@@ -1,4 +1,5 @@
 import abc
+from typing import Union
 from pymongo import MongoClient
 import pandas as pd
 import json
@@ -53,8 +54,8 @@ class StatsFetcher:
         season = (month - 1) // 3 + 1
 
         return StatsDateTime(date, year, month, day, season)
-    
-    def has_required_columns(self, df:pd.DataFrame, required_cols=None):
+
+    def has_required_columns(self, df: pd.DataFrame, required_cols=None):
         """
         Check if the required columns are present in the DataFrame.
 
@@ -68,23 +69,22 @@ class StatsFetcher:
         """
         if required_cols is None:
             required_cols = ['date', 'open', 'high', 'low', 'close', 'volume']
-        
+
         return all(col in df.columns for col in required_cols)
 
 
 class BaseTEJFetcher(abc.ABC):
 
-    def __init__(self):
-        self.client = None
-        self.db = None
-        self.collection = None
-
     @abc.abstractmethod
     def get(self):
         pass
 
     def get_latest_data_time(self, ticker):
-        latest_data = self.collection.find_one({"ticker": ticker}, {"last_update": 1, "_id": 0})
+        latest_data = self.collection.find_one(
+            {"ticker": ticker}, {
+                "last_update": 1,
+                "_id": 0
+            })
 
         try:
             latest_date = latest_data['last_update']["latest_data_date"]
@@ -93,11 +93,16 @@ class BaseTEJFetcher(abc.ABC):
 
         return latest_date
 
-    def cal_YoY(self, data_dict: dict, start_year: int, end_year: int, season: int):
+    def cal_YoY(
+            self, data_dict: dict, start_year: int, end_year: int, season: int):
         year_shifts = [1, 3, 5, 10]
         return_dict = {}
         for year in range(start_year, end_year + 1):
-            year_data = data_dict[f"{year}Q{season}"]
+            try:
+                year_data = data_dict[f"{year}Q{season}"].copy()
+            except KeyError as e:
+                continue
+
             year_keys = list(year_data.keys())
             for key in year_keys:
                 if (key in 'season'):
@@ -109,9 +114,11 @@ class BaseTEJFetcher(abc.ABC):
                     for shift in year_shifts:
                         this_value = year_data[key]
                         try:
-                            past_year = str(year - shift)
+                            past_year = year - shift
                             last_value = data_dict[f"{past_year}Q{season}"][key]
-                            temp_dict[f"YoY_{shift}"] = YoY_Calculator.cal_growth(this_value, last_value, delta=shift)
+                            temp_dict[
+                                f"YoY_{shift}"] = YoY_Calculator.cal_growth(
+                                    this_value, last_value, delta=shift)
                         except Exception as e:
                             temp_dict[f"YoY_{shift}"] = None
 
@@ -149,9 +156,11 @@ class BaseTEJFetcher(abc.ABC):
                     temp_dict = {"value": this_value}
 
                     try:
-                        last_value = data_dict[f"{last_year}Q{last_season}"][key]['value']
+                        last_value = data_dict[f"{last_year}Q{last_season}"][
+                            key]['value']
 
-                        temp_dict['growth'] = YoY_Calculator.cal_growth(this_value, last_value, delta=1)
+                        temp_dict['growth'] = YoY_Calculator.cal_growth(
+                            this_value, last_value, delta=1)
                     except Exception as e:
                         temp_dict['growth'] = None
 
@@ -169,3 +178,33 @@ class BaseTEJFetcher(abc.ABC):
         for key in data_dict.keys():
             data_dict[key] = pd.DataFrame.from_dict(data_dict[key])
         return data_dict
+
+    def set_time_shift(self, date: Union[str, datetime], period: str):
+        if (isinstance(date, str)):
+            date = datetime.strptime(date, "%Y-%m-%d")
+        if (period == '1d'):
+            return date - timedelta(days=1)
+
+        elif (period == '7d'):
+            return date - timedelta(days=7)
+
+        elif (period == '1m'):
+            return date - timedelta(days=30)
+
+        elif (period == '3m'):
+            return date - timedelta(days=90)
+
+        elif (period == '1y'):
+            return date - timedelta(days=365)
+
+        elif (period == '3y'):
+            return date - timedelta(days=365 * 3)
+
+        elif (period == '5y'):
+            return date - timedelta(days=365 * 5)
+
+        elif (period == '10y'):
+            return date - timedelta(days=365 * 10)
+
+        elif (period == 'all'):
+            return datetime.strptime("1991-01-01", "%Y-%m-%d")

neurostats_API/fetchers/tech.py

@@ -2,48 +2,49 @@ from .base import StatsFetcher
 import pandas as pd
 import yfinance as yf
 
+
 class TechFetcher(StatsFetcher):
-    
-    def __init__(self, ticker:str, db_client):
 
+    def __init__(self, ticker: str, db_client):
         """
         The Capitalization-Weighted Index includes the following tickers:
         ['GSPC', 'IXIC', 'DJI', 'TWII']   
         """
-        
+
         super().__init__(ticker, db_client)
+        self.collection = self.db["TWN/APIPRCD"]
         self.full_ohlcv = self._get_ohlcv()
-        self.basic_indexes = ['SMA5', 'SMA20', 'SMA60', 'EMA5', 'EMA20', 
-                              'EMA40', 'EMA12', 'EMA26', 'RSI7', 'RSI14',
-                              'RSI21', 'MACD', 'Signal Line', 'Middle Band', 
-                              'Upper Band', 'Lower Band', '%b', 'ATR', 
-                              'BBW','EMA Cycle','EMA Cycle Instructions',
-                              'Day Trading Signal']
-        
+        self.basic_indexes = [
+            'SMA5', 'SMA20', 'SMA60', 'EMA5', 'EMA20', 'EMA40', 'EMA12',
+            'EMA26', 'RSI7', 'RSI14', 'RSI21', 'MACD', 'Signal Line',
+            'Middle Band', 'Upper Band', 'Lower Band', '%b', 'ATR', 'BBW',
+            'EMA Cycle', 'EMA Cycle Instructions', 'Day Trading Signal'
+        ]
+
         self.daily_index = TechProcessor.cal_basic_index(self.full_ohlcv)
 
         self.weekly_index = TechProcessor.resample(
-            self.daily_index, 
-            period= 'W',
-            technical_indicators = self.basic_indexes
+            self.daily_index,
+            period='W',
+            technical_indicators=self.basic_indexes
         )
 
         self.monthly_index = TechProcessor.resample(
-            self.daily_index, 
-            period= 'ME',
-            technical_indicators = self.basic_indexes
+            self.daily_index,
+            period='ME',
+            technical_indicators=self.basic_indexes
         )
 
         self.quarterly_index = TechProcessor.resample(
-            self.daily_index, 
-            period= 'QE',
-            technical_indicators = self.basic_indexes
+            self.daily_index,
+            period='QE',
+            technical_indicators=self.basic_indexes
         )
 
         self.yearly_index = TechProcessor.resample(
-            self.daily_index, 
-            period= 'YE',
-            technical_indicators = self.basic_indexes
+            self.daily_index,
+            period='YE',
+            technical_indicators=self.basic_indexes
         )
 
     def _get_ohlcv(self):
@@ -51,25 +52,7 @@ class TechFetcher(StatsFetcher):
         required_cols = ['date', 'open', 'high', 'low', 'close', 'volume']
 
         try:
-            query = {'ticker': self.ticker}
-            ticker_full = self.collection.find_one(query)
-
-            if not ticker_full:
-                raise ValueError(f"No data found for ticker: {self.ticker}")
-
-            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):
-                raise KeyError(f"Missing required columns")
-
-        except (KeyError, ValueError, TypeError) as e:
-
-            print(f"Conduct yf searching")
-
+            # 先對yf search
             if self.ticker in ['GSPC', 'IXIC', 'DJI', 'TWII']:
                 full_tick = f'^{self.ticker}'
             else:
@@ -80,13 +63,41 @@ class TechFetcher(StatsFetcher):
             if not self.has_required_columns(df, required_cols):
 
                 print(f".tw failed, try .two")
-            
+
                 full_tick = f'{self.ticker}.two'
 
                 df = self.conduct_yf_search(full_tick)
-                
-        return df[required_cols]
 
+                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'
+            ]
+            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
+
+            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 get_daily(self):
 
@@ -95,7 +106,7 @@ class TechFetcher(StatsFetcher):
     def get_weekly(self):
 
         return self.weekly_index
-    
+
     def get_monthly(self):
 
         return self.monthly_index
@@ -103,19 +114,19 @@ class TechFetcher(StatsFetcher):
     def get_quarterly(self):
 
         return self.quarterly_index
-    
+
     def get_yearly(self):
 
         return self.yearly_index
-    
-    def conduct_yf_search(self, ticker:str):
+
+    def conduct_yf_search(self, ticker: str):
 
         yf_ticker = yf.Ticker(ticker)
         origin_df = yf_ticker.history(period="10y")
-        
+
         if origin_df.empty:
             return origin_df
-            
+
         origin_df = origin_df.reset_index()
         origin_df["Date"] = pd.to_datetime(origin_df["Date"])
         df = origin_df.rename(
@@ -131,8 +142,9 @@ class TechFetcher(StatsFetcher):
 
         return df
 
+
 class TechProcessor:
-    
+
     @staticmethod
     def cal_sma(closes: pd.Series, n_days: int) -> pd.Series:
         return closes.rolling(window=n_days).mean()
@@ -158,7 +170,9 @@ class TechProcessor:
         return macds.ewm(span=n_days, adjust=False).mean()
 
     @staticmethod
-    def cal_bollinger_bands(closes: pd.Series, n_days: int = 20) -> pd.DataFrame:
+    def cal_bollinger_bands(
+        closes: pd.Series, n_days: int = 20
+    ) -> pd.DataFrame:
         middle = closes.rolling(window=n_days).mean()
         upper = middle + 2 * closes.rolling(window=n_days).std()
         lower = middle - 2 * closes.rolling(window=n_days).std()
@@ -174,12 +188,15 @@ class TechProcessor:
         )
 
     @staticmethod
-    def cal_atr(highes: pd.Series, lows: pd.Series, closes: pd.Series, n_days: int) -> pd.Series:
+    def cal_atr(
+        highes: pd.Series, lows: pd.Series, closes: pd.Series, n_days: int
+    ) -> pd.Series:
         high_low = highes - lows
         high_close = (highes - closes.shift(1)).abs()
         low_close = (lows - closes.shift(1)).abs()
 
-        true_range = pd.concat([high_low, high_close, low_close], axis=1).max(axis=1)
+        true_range = pd.concat([high_low, high_close, low_close],
+                               axis=1).max(axis=1)
         atr = true_range.rolling(window=n_days, min_periods=1).mean()
 
         return atr
@@ -233,15 +250,15 @@ class TechProcessor:
             return '今日此股票為好的當沖標的'
         else:
             return f'今日此股票並非好的當沖標的, 原因: {", ".join(reasons)}'
-    
+
     @staticmethod
-    def cal_basic_index(ohlcvs:pd.DataFrame):
-        
+    def cal_basic_index(ohlcvs: pd.DataFrame):
+
         # SMA
-        ohlcvs['SMA5'] = TechProcessor.cal_sma(ohlcvs['close'], 5) 
+        ohlcvs['SMA5'] = TechProcessor.cal_sma(ohlcvs['close'], 5)
         ohlcvs['SMA20'] = TechProcessor.cal_sma(ohlcvs['close'], 20)
         ohlcvs['SMA60'] = TechProcessor.cal_sma(ohlcvs['close'], 40)
-            
+
         # EMA
         ohlcvs['EMA5'] = TechProcessor.cal_ema(ohlcvs['close'], 5)
         ohlcvs['EMA20'] = TechProcessor.cal_ema(ohlcvs['close'], 20)
@@ -256,34 +273,42 @@ class TechProcessor:
         ohlcvs['RSI21'] = TechProcessor.cal_rsi(ohlcvs['close'], 21)
 
         # MACD
-        ohlcvs['MACD'] = TechProcessor.cal_macd(ohlcvs['EMA12'], ohlcvs['EMA26'])
+        ohlcvs['MACD'] = TechProcessor.cal_macd(
+            ohlcvs['EMA12'], ohlcvs['EMA26']
+        )
         ohlcvs['Signal Line'] = TechProcessor.cal_single_line(ohlcvs['MACD'], 9)
-        
+
         # BANDS
         bands = TechProcessor.cal_bollinger_bands(ohlcvs['close'], 20)
         ohlcvs['Middle Band'] = bands['middle']
         ohlcvs['Upper Band'] = bands['upper']
         ohlcvs['Lower Band'] = bands['lower']
         ohlcvs['%b'] = bands['%b']
-        ohlcvs['BBW'] = (ohlcvs["Upper Band"] - ohlcvs["Lower Band"]) / ohlcvs["Middle Band"]
+        ohlcvs['BBW'] = (ohlcvs["Upper Band"] -
+                         ohlcvs["Lower Band"]) / ohlcvs["Middle Band"]
 
         # ATR
-        ohlcvs['ATR'] = TechProcessor.cal_atr(ohlcvs['high'],ohlcvs['low'],ohlcvs['close'],14)
+        ohlcvs['ATR'] = TechProcessor.cal_atr(
+            ohlcvs['high'], ohlcvs['low'], ohlcvs['close'], 14
+        )
 
         # EMA CYCLE
         ohlcvs['EMA Cycle'] = ohlcvs.apply(
-            lambda row: TechProcessor.check_tech_trend(row['EMA5'], row['EMA20'], row['EMA40']),
+            lambda row: TechProcessor.
+            check_tech_trend(row['EMA5'], row['EMA20'], row['EMA40']),
             axis=1
         )
         guidance_map = {
             '穩定上升期': "三條移動平均線都左下右上, 買方優勢, 三線間隔越來越遠時, 進一步強攻",
-            '牛市結束期': "ema20 & 40 左下右上, ema5 緩慢下滑, 行情仍強, 賣出條件為 ema5 持續下跌, ema20 停止上漲",
+            '牛市結束期':
+            "ema20 & 40 左下右上, ema5 緩慢下滑, 行情仍強, 賣出條件為 ema5 持續下跌, ema20 停止上漲",
             '熊市入口期': "全數出清穩定上升期布局的多頭部位, 考慮提早佈局建立空頭部位",
             '穩定下跌期': "三條移動平均線都是左上右下, 賣方優勢, 三線間隔越來越遠時, 進一步強攻",
-            '熊市結束期': "ema20 & 40 左上右下, ema5 緩慢上升, 行情仍走弱, 布局買進的條件是 ema 持續上漲, ema20 停止下降, 幾乎持平",
+            '熊市結束期':
+            "ema20 & 40 左上右下, ema5 緩慢上升, 行情仍走弱, 布局買進的條件是 ema 持續上漲, ema20 停止下降, 幾乎持平",
             '牛市入口期': "全數出清穩定下跌期布局的空頭部位, 考慮提早佈局多頭部位",
             '未定義': "無對應指導"
-        }    
+        }
 
         ohlcvs['EMA Cycle Instructions'] = ohlcvs['EMA Cycle'].map(guidance_map)
 
@@ -292,7 +317,7 @@ class TechProcessor:
         ohlcvs['Day Trading Signal'] = ohlcvs.apply(
             lambda row: TechProcessor.check_day_trading(
                 close_today=row['close'],
-                close_yesterday=row['close_yesterday'],  # 使用前一天的收盤價
+                close_yesterday=row['close_yesterday'],    # 使用前一天的收盤價
                 today_atr=row['ATR'],
                 today_rsi7=row['RSI7']
             ),
@@ -302,7 +327,12 @@ class TechProcessor:
         return ohlcvs
 
     @staticmethod
-    def resample(df: pd.DataFrame, period='W', technical_indicators=None, date_col='date'):
+    def resample(
+        df: pd.DataFrame,
+        period='W',
+        technical_indicators=None,
+        date_col='date'
+    ):
         """
         將 DataFrame 中的技術指標數據重新取樣為指定的時間週期。
         參數:
@@ -344,11 +374,16 @@ class TechProcessor:
                 agg_dict[indicator] = 'mean'
 
         # 過濾出存在於 DataFrame 中的列
-        existing_cols = {col: agg_dict[col] for col in agg_dict if col in numeric_df.columns}
-        
+        existing_cols = {
+            col: agg_dict[col]
+            for col in agg_dict if col in numeric_df.columns
+        }
+
         # 確保索引為 DatetimeIndex，進行重新取樣
         if not isinstance(df.index, pd.DatetimeIndex):
-            raise TypeError("The DataFrame index must be a DatetimeIndex for resampling.")
+            raise TypeError(
+                "The DataFrame index must be a DatetimeIndex for resampling."
+            )
 
         resampled_df = numeric_df.resample(period).agg(existing_cols)
 
@@ -357,11 +392,3 @@ class TechProcessor:
             resampled_df.reset_index(inplace=True)
 
         return resampled_df
-
-
-            
-
-    
-
-
-    

neurostats_API/fetchers/tej_finance_report.py

@@ -3,8 +3,10 @@ from datetime import datetime
 from enum import Enum
 import pandas as pd
 from pymongo import MongoClient
+from .tech import TechProcessor
 from ..utils import StatsProcessor, YoY_Calculator
 import warnings
+import yaml
 
 
 class FinanceReportFetcher(BaseTEJFetcher):
@@ -15,23 +17,18 @@ class FinanceReportFetcher(BaseTEJFetcher):
         YOY_NOCAL = 3
         QOQ_NOCAL = 4
 
-    def __init__(self, mongo_uri, db_name="company", collection_name="TWN/AINVFQ1"):
+    def __init__(
+            self,
+            mongo_uri,
+            db_name=".company",
+            collection_name="TWN/AINVFQ1"
+        ):
         self.client = MongoClient(mongo_uri)
         self.db = self.client[db_name]
         self.collection = self.db[collection_name]
 
-        # yapf: disabled
-        self.check_index = {
-            'coid', 'mdate', 'key3', 'no', 'sem', 'merg', 'curr', 'annd', 'fin_ind', 'bp11', 'bp21', 'bp22', 'bp31',
-            'bp41', 'bp51', 'bp53', 'bp61', 'bp62', 'bp63', 'bp64', 'bp65', 'bf11', 'bf12', 'bf21', 'bf22', 'bf41',
-            'bf42', 'bf43', 'bf44', 'bf45', 'bf99', 'bsca', 'bsnca', 'bsta', 'bscl', 'bsncl', 'bstl', 'bsse', 'bslse',
-            'debt', 'quick', 'ppe', 'ar', 'ip12', 'ip22', 'ip31', 'ip51', 'iv41', 'if11', 'isibt', 'isni', 'isnip',
-            'eps', 'ispsd', 'gm', 'opi', 'nri', 'ri', 'nopi', 'ebit', 'cip31', 'cscfo', 'cscfi', 'cscff', 'person',
-            'shares', 'wavg', 'taxrate', 'r104', 'r115', 'r105', 'r106', 'r107', 'r108', 'r201', 'r112', 'r401', 'r402',
-            'r403', 'r404', 'r405', 'r408', 'r409', 'r410', 'r502', 'r501', 'r205', 'r505', 'r517', 'r512', 'r509',
-            'r608', 'r616', 'r610', 'r607', 'r613', 'r612', 'r609', 'r614', 'r611', 'r307', 'r304', 'r305', 'r306',
-            'r316', 'r834'
-        }    # yapf: enabled
+        index_dict = StatsProcessor.load_yaml("tej_db_index.yaml")
+        self.check_index = set(index_dict[collection_name])
 
     def get(
             self,
@@ -57,19 +54,23 @@ class FinanceReportFetcher(BaseTEJFetcher):
             indexes = set(indexes)
             difference = indexes - self.check_index
             if (difference):
-                warnings.warn(f"{list(difference)} 沒有出現在資料表中，請確認column名稱是否正確", UserWarning)
+                warnings.warn(
+                    f"{list(difference)} 沒有出現在資料表中，請確認column名稱是否正確",
+                    UserWarning)
+
+        if (not start_date):
+            start_date = datetime.strptime("2005-01-01", "%Y-%m-%d")
+        else:
+            start_date = datetime.strptime(start_date, "%Y-%m-%d")
 
         if (fetch_mode in {self.FetchMode.QOQ, self.FetchMode.QOQ_NOCAL}):
-            if (not start_date):
-                warnings.warn("No start_date specified, use default date = \"2005-01-01\"", UserWarning)
-                start_date = datetime.strptime("2005-01-01", "%Y-%m-%d")
+
             if (not end_date):
-                warnings.warn("No end_date specified, use default date = today", UserWarning)
                 end_date = datetime.today()
+            else:
+                end_date = datetime.strptime(end_date, "%Y-%m-%d")
 
             assert (start_date <= end_date)
-            start_date = datetime.strptime(start_date, "%Y-%m-%d")
-            end_date = datetime.strptime(end_date, "%Y-%m-%d")
 
             start_year = start_date.year
             start_season = (start_date.month - 1) // 4 + 1
@@ -94,7 +95,6 @@ class FinanceReportFetcher(BaseTEJFetcher):
             return data_df
 
         elif (fetch_mode in {self.FetchMode.YOY, self.FetchMode.YOY_NOCAL}):
-            start_date = datetime.strptime(start_date, "%Y-%m-%d")
             start_year = start_date.year
             end_date = self.get_latest_data_time(ticker)
             if (not end_date):
@@ -120,7 +120,15 @@ class FinanceReportFetcher(BaseTEJFetcher):
             return data_df
 
     def get_QoQ_data(
-            self, ticker, start_year, start_season, end_year, end_season, report_type="Q", indexes=[], use_cal=False):
+            self,
+            ticker,
+            start_year,
+            start_season,
+            end_year,
+            end_season,
+            report_type="Q",
+            indexes=[],
+            use_cal=False):
         """
             取得時間範圍內每季資料
         """
@@ -146,31 +154,29 @@ class FinanceReportFetcher(BaseTEJFetcher):
                 }, {
                     "$unwind": "$data"
                 }, {
-                    "$match":
-                        {
-                            "$or":
-                                [
-                                    {
-                                        "data.year": {
-                                            "$gt": start_year,
-                                            "$lt": end_year
-                                        }
-                                    }, {
-                                        "data.year": start_year,
-                                        "data.season": {
-                                            "$gte": start_season
-                                        }
-                                    }, {
-                                        "data.year": end_year,
-                                        "data.season": {
-                                            "$lte": end_season
-                                        }
-                                    }, {
-                                        "data.year": lower_bound_year,
-                                        "data.season": lower_bound_season
-                                    }
-                                ]
-                        }
+                    "$match": {
+                        "$or": [
+                            {
+                                "data.year": {
+                                    "$gt": start_year,
+                                    "$lt": end_year
+                                }
+                            }, {
+                                "data.year": start_year,
+                                "data.season": {
+                                    "$gte": start_season
+                                }
+                            }, {
+                                "data.year": end_year,
+                                "data.season": {
+                                    "$lte": end_season
+                                }
+                            }, {
+                                "data.year": lower_bound_year,
+                                "data.season": lower_bound_season
+                            }
+                        ]
+                    }
                 }, {
                     "$project": {
                         "data.year": 1,
@@ -194,40 +200,40 @@ class FinanceReportFetcher(BaseTEJFetcher):
                 }, {
                     "$unwind": "$data"
                 }, {
-                    "$match":
-                        {
-                            "$or":
-                                [
-                                    {
-                                        "data.year": {
-                                            "$gt": start_year,
-                                            "$lt": end_year
-                                        }
-                                    }, {
-                                        "data.year": start_year,
-                                        "data.season": {
-                                            "$gte": start_season
-                                        }
-                                    }, {
-                                        "data.year": end_year,
-                                        "data.season": {
-                                            "$lte": end_season
-                                        }
-                                    }, {
-                                        "data.year": lower_bound_year,
-                                        "data.season": lower_bound_season
-                                    }
-                                ]
-                        }
+                    "$match": {
+                        "$or": [
+                            {
+                                "data.year": {
+                                    "$gt": start_year,
+                                    "$lt": end_year
+                                }
+                            }, {
+                                "data.year": start_year,
+                                "data.season": {
+                                    "$gte": start_season
+                                }
+                            }, {
+                                "data.year": end_year,
+                                "data.season": {
+                                    "$lte": end_season
+                                }
+                            }, {
+                                "data.year": lower_bound_year,
+                                "data.season": lower_bound_season
+                            }
+                        ]
+                    }
                 }, {
                     "$project": project_stage
                 }
             ]
 
         fetched_data = self.collection.aggregate(pipeline).to_list()
-
         data_dict = StatsProcessor.list_of_dict_to_dict(
-            fetched_data, keys=["year", "season"], delimeter="Q", data_key=report_type)
+            fetched_data,
+            keys=["year", "season"],
+            delimeter="Q",
+            data_key=report_type)
 
         if (use_cal):
             data_with_QoQ = self.cal_QoQ(data_dict)
@@ -242,7 +248,15 @@ class FinanceReportFetcher(BaseTEJFetcher):
             data_df = data_df.iloc[:, ::-1]
             return data_df
 
-    def get_YoY_data(self, ticker, start_year, end_year, season, report_type="Q", indexes=[], use_cal=False):
+    def get_YoY_data(
+            self,
+            ticker,
+            start_year,
+            end_year,
+            season,
+            report_type="Q",
+            indexes=[],
+            use_cal=False):
         """
         取得某季歷年資料
         """
@@ -267,20 +281,23 @@ class FinanceReportFetcher(BaseTEJFetcher):
                 }, {
                     "$unwind": "$data"
                 }, {
-                    "$match":
-                        {
-                            "$or": [{
-                                "$and": [{
-                                    "data.year": {
-                                        "$in": select_year
-                                    }
-                                }, {
-                                    "data.season": {
-                                        "$eq": season
+                    "$match": {
+                        "$or": [
+                            {
+                                "$and": [
+                                    {
+                                        "data.year": {
+                                            "$in": select_year
+                                        }
+                                    }, {
+                                        "data.season": {
+                                            "$eq": season
+                                        }
                                     }
-                                }]
-                            },]
-                        }
+                                ]
+                            },
+                        ]
+                    }
                 }, {
                     "$project": {
                         "data.year": 1,
@@ -305,15 +322,17 @@ class FinanceReportFetcher(BaseTEJFetcher):
                     "$unwind": "$data"
                 }, {
                     "$match": {
-                        "$and": [{
-                            "data.year": {
-                                "$in": select_year
-                            }
-                        }, {
-                            "data.season": {
-                                "$eq": season
+                        "$and": [
+                            {
+                                "data.year": {
+                                    "$in": select_year
+                                }
+                            }, {
+                                "data.season": {
+                                    "$eq": season
+                                }
                             }
-                        }]
+                        ]
                     }
                 }, {
                     "$project": project_stage
@@ -324,10 +343,14 @@ class FinanceReportFetcher(BaseTEJFetcher):
 
         # 處理計算YoY
         data_dict = StatsProcessor.list_of_dict_to_dict(
-            fetched_data, keys=['year', 'season'], data_key=report_type, delimeter='Q')
+            fetched_data,
+            keys=['year', 'season'],
+            data_key=report_type,
+            delimeter='Q')
 
         if (use_cal):
-            data_with_YoY = self.cal_YoY(data_dict, start_year, end_year, season)
+            data_with_YoY = self.cal_YoY(
+                data_dict, start_year, end_year, season)
             data_df = pd.DataFrame.from_dict(data_with_YoY)
             data_df = data_df.iloc[:, ::-1].T
             data_dict = data_df.to_dict()
@@ -337,3 +360,73 @@ class FinanceReportFetcher(BaseTEJFetcher):
             data_df = pd.DataFrame.from_dict(data_dict)
             data_df = data_df.iloc[:, ::-1]
             return data_df
+
+
+class TEJStockPriceFetcher(BaseTEJFetcher):
+
+    def __init__(
+            self,
+            mongo_uri,
+            db_name: str = "company",
+            collection_name: str = None):
+        self.mongo_uri = mongo_uri
+        self.db_name = db_name
+        self.collection_name = collection_name
+
+        self.client = MongoClient(self.mongo_uri)
+        self.db = self.client[self.db_name]
+        self.collection = self.db[self.collection_name]
+
+        self.check_period = ['1d', '7d', '1m', '3m', '1y', '3y', '5y', '10y', 'all']
+
+    def get(
+            self,
+            ticker: str = "2330",
+            start_date: str = "2024-10-01",
+            period: str = None
+        ):
+        """
+        取得開高低收資料
+        start_date: str: 起始的日期
+        period: 指定日期範圍(E.g. 1天, 7天...etc)
+        如果宣告period, 以period為優先
+        """
+
+        assert (
+            period is None or period in self.check_period
+        ), f"period should be None or {','.join(self.check_period)}"
+
+        if (period is not None):
+            latest_date = self.get_latest_data_time(ticker)
+            start_date = self.set_time_shift(date=latest_date, period=period)
+        else:
+            start_date = datetime.strptime(start_date, "%Y-%m-%d")
+
+        pipeline = [
+            {
+                "$match": {
+                    "ticker": ticker
+                }
+            }, {
+                "$unwind": "$data"
+            }, {
+                "$match": {
+                    "data.mdate": {
+                        "$gt": start_date
+                    }
+                }
+            }, {
+                "$project": {
+                    "ticker": 1,
+                    "data": 1,
+                    "_id": 0
+                }
+            }
+        ]
+        datas = self.collection.aggregate(pipeline).to_list()
+
+        elements = [element['data'] for element in datas]
+
+        data_df = pd.DataFrame(elements).set_index('mdate')
+
+        return data_df

neurostats_API/tools/tej_db_index.yaml

@@ -0,0 +1,135 @@
+TWN/AINVFQ1:
+- coid
+- mdate
+- key3
+- 'no'
+- sem
+- merg
+- curr
+- annd
+- fin_ind
+- bp11
+- bp21
+- bp22
+- bp31
+- bp41
+- bp51
+- bp53
+- bp61
+- bp62
+- bp63
+- bp64
+- bp65
+- bf11
+- bf12
+- bf21
+- bf22
+- bf41
+- bf42
+- bf43
+- bf44
+- bf45
+- bf99
+- bsca
+- bsnca
+- bsta
+- bscl
+- bsncl
+- bstl
+- bsse
+- bslse
+- debt
+- quick
+- ppe
+- ar
+- ip12
+- ip22
+- ip31
+- ip51
+- iv41
+- if11
+- isibt
+- isni
+- isnip
+- eps
+- ispsd
+- gm
+- opi
+- nri
+- ri
+- nopi
+- ebit
+- cip31
+- cscfo
+- cscfi
+- cscff
+- person
+- shares
+- wavg
+- taxrate
+- r104
+- r115
+- r105
+- r106
+- r107
+- r108
+- r201
+- r112
+- r401
+- r402
+- r403
+- r404
+- r405
+- r408
+- r409
+- r410
+- r502
+- r501
+- r205
+- r505
+- r517
+- r512
+- r509
+- r608
+- r616
+- r610
+- r607
+- r613
+- r612
+- r609
+- r614
+- r611
+- r307
+- r304
+- r305
+- r306
+- r316
+- r834
+TWN/AFESTM1:
+- coid
+- mdate
+- key3
+- 'no'
+- sem
+- merg
+- curr
+- annd
+- fin_ind
+- ip12
+- gm
+- opi
+- isibt
+- isni
+- isnip
+- r306
+- r316
+- eps
+- r105
+- r106
+- r107
+- r108
+- r401
+- r402
+- r403
+- r404
+- r405

{neurostats_API-0.0.17.dist-info → neurostats_API-0.0.19.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: neurostats_API
-Version: 0.0.17
+Version: 0.0.19
 Summary: The service of NeuroStats website
 Home-page: https://github.com/NeurowattStats/NeuroStats_API.git
 Author: JasonWang@Neurowatt
@@ -774,43 +774,73 @@ YoY_10  1.420500e-01  1.586797e-01  1.551364e-01
 }
 ```
 
+### 公司自結資料
+```Python
+from neurostats_API import FinanceReportFetcher
 
-## 版本紀錄
-## 0.0.16
-- 處理ValueFetcher的error #issue76
+fetcher = FinanceReportFetcher(
+    mongo_uri = mongo_uri,
+    db_name = db_name,
+    collection_name = collection_name
+)
 
-- tej_fetcher新增 QOQ, YOY功能
+data = fetcher.get(
+    ticker = "2330" # 任意的股票代碼
+    fetch_mode = fetcher.FetchMode.QOQ_NOCAL # 取得模式
+    start_date = "2005-01-01",
+    end_date = "2024-12-31",
+    report_type = "Q",
+    indexes = []
+) # -> pd.DataFrame or Dict[pd.DataFrame] 
+```
+- `ticker`: 股票代碼
 
-## 0.0.15
-- TechFetcher中新增指數條件
+- `fetch_mode` : 取得模式，為`fetcher.YOY_NOCAL` 或 `fetcher.QOQ_NOCAL`
+    - `YOY_NOCAL`: 以end_date為準，取得與end_date同季的歷年資料，時間範圍以start_date為起始
+        > 例如`start_date = "2020-07-01"`, `end_date = "2024-01-01"`，會回傳2020~2024的第一季資料
 
-- 新增tej_fetcher索取TEJ相關的資料
+    - `QOQ_NOCAL`: 時間範圍內的每季資料
 
-- package新增depensnecy，可以安裝需要的相關package
+    - `QOQ`: 時間範圍內每季的每個index的數值以及QoQ
 
-## 0.0.14
-- 修改部分財報資料錯誤的乘以1000的問題
+    - `YoY`: 以end_date為準，取得與end_date同季的歷年資料以及成長率，時間範圍以start_date為起始
 
-- 新增例外處理: 若資料庫對於季資料一部分index缺失的情況下仍會盡可能去將資料蒐集並呈現
+- `start_date`: 開始日期，不設定時預設為`2005-01-01`
 
-### 0.0.13
-- value_fetcher 新增獲得一序列評價的功能
+- `end_date`: 結束日期，不設定時預設為資料庫最新資料的日期
 
-### 0.0.12
-- 新增資券變化(margin trading)
+- `report_type`: 選擇哪種報告，預設為`Q`
+    - `A`: 當年累計
+    - `Q`: 當季數值
+    - `TTM`: 移動四季 (包括當季在內，往前累計四個季度)
 
-- 修改法人買賣(institution_trading)的query方式
+- `indexes`: 選擇的column，需要以TEJ提供的欄位名稱為準，不提供時或提供`[]`會回傳全部column
+   - 範例輸入: `['bp41', 'bp51']`
 
-### 0.0.11
-- 修復財務分析的千元計算問題
+[TEJ資料集連結](https://tquant.tejwin.com/%E8%B3%87%E6%96%99%E9%9B%86/)
+請看 `公司自結數`
 
-- 籌碼面新增法人買賣(institution_trading)
+### 開高低收
+```Python
+mongo_uri = <MongoDB 的 URI>
+db_name = 'company' # 連接的DB名稱
+collection_name = "TWN/APIPRCD" # 連接的collection對象
+from neurostats_API import TEJStockPriceFetcher
 
-- 將財報三表與月營收的資料型態與數值做轉換(%轉字串, 千元乘以1000)
-### 0.0.10
-- 更新指標的資料型態: 單位為千元乘以1000之後回傳整數
+fetcher = TEJStockPriceFetcher(
+    mongo_uri = mongo_uri,
+    db_name = db_name,
+    collection_name = collection_name
+)
 
-- 處理銀行公司在finanace_overview會報錯誤的問題(未完全解決，因銀行公司財報有許多名稱不同，目前都會顯示為None)
+data = fetcher.get(
+    ticker = "2330" # 任意的股票代碼
+    start_date = "2005-01-01",
+    period = "3m"
+) # -> pd.DataFrame
+```
+- `ticker`: 股票代碼
+- `start_date`: 搜尋範圍的開始日期
+- `period`: 搜尋的時間範圍長度
 
-### 0.0.9
-- 更新指標的資料型態: 單位為日, %, 倍轉為字串
+`period`與`start_date`同時存在時以period優先

{neurostats_API-0.0.17.dist-info → neurostats_API-0.0.19.dist-info}/RECORD

@@ -1,30 +1,31 @@
-neurostats_API/__init__.py,sha256=5ToELVqNOIdVJrMj5G8JvbyRIjvo1FxcP6e-a-iMe1Y,261
+neurostats_API/__init__.py,sha256=U-0Tn9McUXzABJINU15pYkGchFGI5R3njBMgn-F4CzM,288
 neurostats_API/cli.py,sha256=UJSWLIw03P24p-gkBb6JSEI5dW5U12UvLf1L8HjQD-o,873
 neurostats_API/main.py,sha256=QcsfmWivg2Dnqw3MTJWiI0QvEiRs0VuH-BjwQHFCv00,677
-neurostats_API/fetchers/__init__.py,sha256=B4aBwVzf_X-YieEf3fZteU0qmBPVIB9VjrmkyWhLK18,489
+neurostats_API/fetchers/__init__.py,sha256=KCw-yRSDFa3fw83u73LJ9OVop7gRl_YQYlQq-cITxuo,511
 neurostats_API/fetchers/balance_sheet.py,sha256=sQv4Gk5uoKURLEdh57YknOQWiyVwaXJ2Mw75jxNqUS0,5804
-neurostats_API/fetchers/base.py,sha256=Rl88Mhvi0uFpPupUvy0iyS7IA4B3fnn6ovMNzS7EU34,5594
+neurostats_API/fetchers/base.py,sha256=hlHtCDKpVFFs2n0uJ0yjz26dTzgc2ZtOKleiguT_HxY,6673
 neurostats_API/fetchers/cash_flow.py,sha256=TY7VAWVXkj5-mzH5Iu0sIE-oV8MvGmmDy0URNotNV1E,7614
 neurostats_API/fetchers/finance_overview.py,sha256=PxUdWY0x030olYMLcCHDBn068JLmCE2RTOce1dxs5vM,27753
 neurostats_API/fetchers/institution.py,sha256=UrcBc6t7u7CnEwUsf6YmLbbJ8VncdWpq8bCz17q2dgs,11168
 neurostats_API/fetchers/margin_trading.py,sha256=lQImtNdvaBoSlKhJvQ3DkH3HjSSgKRJz4ZZpyR5-Z4I,10433
 neurostats_API/fetchers/month_revenue.py,sha256=nixX2llzjCFr2m2YVjxrSfkBusnZPrPb2dRDq1XLGhw,4251
 neurostats_API/fetchers/profit_lose.py,sha256=EN9Y0iamcAaHMZdjHXO6b_2buLnORssf8ZS7A0hi74s,5896
-neurostats_API/fetchers/tech.py,sha256=8U6kn7cvWJsmKIMn_f2l6U9H_NBy_OwOXlS26XhFIv0,12926
-neurostats_API/fetchers/tej_finance_report.py,sha256=laXph2ca1LCFocZjjdvtzmm5fcUecHk2Gs5h6-XMSWY,12967
+neurostats_API/fetchers/tech.py,sha256=116UQP00FyZUGwOttHsauJLxAMNE99rPL6nl4U3ETK4,13386
+neurostats_API/fetchers/tej_finance_report.py,sha256=1q_c2B_Dd7qIagdlXt9eNT7O53JmsquCrgdi2OOeQ6w,14008
 neurostats_API/fetchers/value_invest.py,sha256=b_x2Dpgs8VBU5HdG8ocKtfIEkqhU-Q0S5n6RxuFuM2g,7467
 neurostats_API/tools/balance_sheet.yaml,sha256=6XygNG_Ybb1Xkk1e39LMLKr7ATvaCP3xxuwFbgNl6dA,673
 neurostats_API/tools/cash_flow_percentage.yaml,sha256=fk2Z4eb1JjGFvP134eJatHacB7BgTkBenhDJr83w8RE,1345
 neurostats_API/tools/finance_overview_dict.yaml,sha256=B9nV75StXkrF3yv2-eezzitlJ38eEK86RD_VY6588gQ,2884
 neurostats_API/tools/profit_lose.yaml,sha256=iyp9asYJ04vAxk_HBUDse_IBy5oVvYHpwsyACg5YEeg,3029
 neurostats_API/tools/seasonal_data_field_dict.txt,sha256=X8yc_el6p8BH_3FikTqBVFGsvWdXT6MHXLfKfi44334,8491
+neurostats_API/tools/tej_db_index.yaml,sha256=lu-cmbB6dhx0eUlBSkyzXWqPKlwRtEvqlMTAh2y0oHs,969
 neurostats_API/utils/__init__.py,sha256=0tJCRmlJq2aDwcNNW-oEaA9H0OxTJMFvjpVYtG4AvZU,186
 neurostats_API/utils/calculate_value.py,sha256=lUKSsWU76XRmDUcmi4eDjoQxjb3vWpAAKInF9w49VNI,782
 neurostats_API/utils/data_process.py,sha256=A--dzOsu42jRxqqCD41gTtjE5rhEBYmhB6y-AnCvo5U,8986
 neurostats_API/utils/datetime.py,sha256=XJya4G8b_-ZOaBbMXgQjWh2MC4wc-o6goQ7EQJQMWrQ,773
 neurostats_API/utils/db_client.py,sha256=OYe6yazcR4Aa6jYmy47JrryUeh2NnKGqY2K_lSZe6i8,455
 neurostats_API/utils/fetcher.py,sha256=VbrUhjA-GG5AyjPX2SHtFIbZM4dm3jo0RgZzuCbb_Io,40927
-neurostats_API-0.0.17.dist-info/METADATA,sha256=_MqEN2Yi-tDE8i4UzX9WGUi25Z7SzyNgDR2kj0p2vhw,29848
-neurostats_API-0.0.17.dist-info/WHEEL,sha256=R06PA3UVYHThwHvxuRWMqaGcr-PuniXahwjmQRFMEkY,91
-neurostats_API-0.0.17.dist-info/top_level.txt,sha256=nSlQPMG0VtXivJyedp4Bkf86EOy2TpW10VGxolXrqnU,15
-neurostats_API-0.0.17.dist-info/RECORD,,
+neurostats_API-0.0.19.dist-info/METADATA,sha256=2YG4AS_jlIEZ8gPBxd7rZ9CEOyuAqTiBStFDH4k9ntM,30981
+neurostats_API-0.0.19.dist-info/WHEEL,sha256=R06PA3UVYHThwHvxuRWMqaGcr-PuniXahwjmQRFMEkY,91
+neurostats_API-0.0.19.dist-info/top_level.txt,sha256=nSlQPMG0VtXivJyedp4Bkf86EOy2TpW10VGxolXrqnU,15
+neurostats_API-0.0.19.dist-info/RECORD,,