neurostats-API 0.0.19__tar.gz → 0.0.21__tar.gz

{neurostats_api-0.0.19 → neurostats_api-0.0.21}/PKG-INFO

@@ -1,13 +1,13 @@
 Metadata-Version: 2.1
 Name: neurostats_API
-Version: 0.0.19
+Version: 0.0.21
 Summary: The service of NeuroStats website
 Home-page: https://github.com/NeurowattStats/NeuroStats_API.git
 Author: JasonWang@Neurowatt
 Author-email: jason@neurowatt.ai
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
-Requires-Dist: numpy>=2.1.0
+Requires-Dist: numpy
 Requires-Dist: pandas>=2.2.0
 Requires-Dist: pymongo
 Requires-Dist: pytz
@@ -89,7 +89,7 @@ pip install neurostats-API
 ```Python 
 >>> import neurostats_API
 >>> print(neurostats_API.__version__)
-0.0.16
+0.0.21
 ```
 
 ### 得到最新一期的評價資料與歷年評價
@@ -236,6 +236,15 @@ data = fetcher.query_data()
         grand_total_YoY_5            1.691300e+02  ...           NaN
         grand_total_YoY_10                    NaN  ...           NaN
 
+        "recent_month_revenue":
+        date           2024/11      2024/10  ...       2024/1      2023/12
+        revenue    51243946000  45451116000  ...  56451418000  55329015000
+        MoM             12.75%      -14.77%  ...        2.03%       -0.52%
+        YoY             -7.87%      -30.00%  ...       -7.36%      -11.13%
+        total_YoY       -6.93%       -6.84%  ...       -7.36%      -15.97%
+        accum_YoY       85.84%       78.65%  ...        7.92%       84.03%
+        # total_YoY為當月累計營收 / 上一年的當月累計營收
+        # accum_YoY為當月累計營收 / 上一年的總營收
 
 }
 ```
@@ -728,6 +737,7 @@ data = fetcher.get(
 #### 回傳資料
 ##### `YOY_NOCAL` 與 `QOQ_NOCAL` 
 為回傳`pd.DataFrame`，column名稱為<年份>Q<季>， row名稱為指定財報項目
+
 ```Python
 # fetch_mode = fetcher.FetchMode.QOQ_NOCAL
         2024Q3        2024Q2        2024Q1
@@ -742,17 +752,18 @@ bp51  3.111298e+09  3.173919e+09  2.453840e+09
 
 ##### `YOY` 與 `QOQ`
 回傳為`Dict[pd.DataFrame]`, key 為指定的index, DataFrame中則是該index歷年的數值與成長率
+成長率單位為`%`
 ```Python
 # fetch_mode = fetcher.FetchMode.QOQ
 {
-        'bp41':               
+'bp41':               
         2024Q3        2024Q2        2024Q1
 value   7.082005e+07  6.394707e+07  5.761001e+07
-growth  1.074791e-01  1.099994e-01  5.532101e-03, 
-        'bp51':               
+growth        10.75%        11.00%         0.55%, 
+'bp51':               
         2024Q3        2024Q2        2024Q1
 value   3.111298e+09  3.145373e+09  3.091985e+09
-growth -1.083335e-02  1.726663e-02 -4.159542e-03
+growth        -1.08%         1.73%         -0.42%
 }
 
 # fetch_mode = fetcher.FetchMode.YOY
@@ -760,17 +771,17 @@ growth -1.083335e-02  1.726663e-02 -4.159542e-03
 'bp41':               
         2024Q3        2023Q3        2022Q3
 value   7.082005e+07  5.377231e+07  6.201822e+07
-YoY_1            NaN           NaN  4.130744e-01
-YoY_3   1.729171e-01  9.556684e-02  1.883274e-01
-YoY_5   1.389090e-01  1.215242e-01  1.642914e-01
-YoY_10  1.255138e-01  1.356297e-01  1.559702e-01, 
+YoY_1    31.70%        -13.30%         41.31%
+YoY_3    17.29%          9.56%         18.83%
+YoY_5    13.89%         12.15%         16.43%
+YoY_10   12.55%         13.56%         15.60% ,
 'bp51':               
         2024Q3        2023Q3        2022Q3
 value   3.111298e+09  3.173919e+09  2.453840e+09
-YoY_1            NaN           NaN  3.179539e-01
-YoY_3   1.866752e-01  2.766851e-01  2.638677e-01
-YoY_5   2.068132e-01  2.479698e-01  1.815106e-01
-YoY_10  1.420500e-01  1.586797e-01  1.551364e-01
+YoY_1         -1.97%        29.34%        31.80%           
+YoY_3         18.67%        27.67%        26.39% 
+YoY_5         20.68%        24.80%        18.15%           
+YoY_10        14.20%        15.87%        15.51%           
 }
 ```
 

{neurostats_api-0.0.19 → neurostats_api-0.0.21}/README.md

@@ -73,7 +73,7 @@ pip install neurostats-API
 ```Python 
 >>> import neurostats_API
 >>> print(neurostats_API.__version__)
-0.0.16
+0.0.21
 ```
 
 ### 得到最新一期的評價資料與歷年評價
@@ -220,6 +220,15 @@ data = fetcher.query_data()
         grand_total_YoY_5            1.691300e+02  ...           NaN
         grand_total_YoY_10                    NaN  ...           NaN
 
+        "recent_month_revenue":
+        date           2024/11      2024/10  ...       2024/1      2023/12
+        revenue    51243946000  45451116000  ...  56451418000  55329015000
+        MoM             12.75%      -14.77%  ...        2.03%       -0.52%
+        YoY             -7.87%      -30.00%  ...       -7.36%      -11.13%
+        total_YoY       -6.93%       -6.84%  ...       -7.36%      -15.97%
+        accum_YoY       85.84%       78.65%  ...        7.92%       84.03%
+        # total_YoY為當月累計營收 / 上一年的當月累計營收
+        # accum_YoY為當月累計營收 / 上一年的總營收
 
 }
 ```
@@ -712,6 +721,7 @@ data = fetcher.get(
 #### 回傳資料
 ##### `YOY_NOCAL` 與 `QOQ_NOCAL` 
 為回傳`pd.DataFrame`，column名稱為<年份>Q<季>， row名稱為指定財報項目
+
 ```Python
 # fetch_mode = fetcher.FetchMode.QOQ_NOCAL
         2024Q3        2024Q2        2024Q1
@@ -726,17 +736,18 @@ bp51  3.111298e+09  3.173919e+09  2.453840e+09
 
 ##### `YOY` 與 `QOQ`
 回傳為`Dict[pd.DataFrame]`, key 為指定的index, DataFrame中則是該index歷年的數值與成長率
+成長率單位為`%`
 ```Python
 # fetch_mode = fetcher.FetchMode.QOQ
 {
-        'bp41':               
+'bp41':               
         2024Q3        2024Q2        2024Q1
 value   7.082005e+07  6.394707e+07  5.761001e+07
-growth  1.074791e-01  1.099994e-01  5.532101e-03, 
-        'bp51':               
+growth        10.75%        11.00%         0.55%, 
+'bp51':               
         2024Q3        2024Q2        2024Q1
 value   3.111298e+09  3.145373e+09  3.091985e+09
-growth -1.083335e-02  1.726663e-02 -4.159542e-03
+growth        -1.08%         1.73%         -0.42%
 }
 
 # fetch_mode = fetcher.FetchMode.YOY
@@ -744,17 +755,17 @@ growth -1.083335e-02  1.726663e-02 -4.159542e-03
 'bp41':               
         2024Q3        2023Q3        2022Q3
 value   7.082005e+07  5.377231e+07  6.201822e+07
-YoY_1            NaN           NaN  4.130744e-01
-YoY_3   1.729171e-01  9.556684e-02  1.883274e-01
-YoY_5   1.389090e-01  1.215242e-01  1.642914e-01
-YoY_10  1.255138e-01  1.356297e-01  1.559702e-01, 
+YoY_1    31.70%        -13.30%         41.31%
+YoY_3    17.29%          9.56%         18.83%
+YoY_5    13.89%         12.15%         16.43%
+YoY_10   12.55%         13.56%         15.60% ,
 'bp51':               
         2024Q3        2023Q3        2022Q3
 value   3.111298e+09  3.173919e+09  2.453840e+09
-YoY_1            NaN           NaN  3.179539e-01
-YoY_3   1.866752e-01  2.766851e-01  2.638677e-01
-YoY_5   2.068132e-01  2.479698e-01  1.815106e-01
-YoY_10  1.420500e-01  1.586797e-01  1.551364e-01
+YoY_1         -1.97%        29.34%        31.80%           
+YoY_3         18.67%        27.67%        26.39% 
+YoY_5         20.68%        24.80%        18.15%           
+YoY_10        14.20%        15.87%        15.51%           
 }
 ```
 

{neurostats_api-0.0.19 → neurostats_api-0.0.21}/neurostats_API/__init__.py

@@ -1,4 +1,4 @@
-__version__='0.0.19'
+__version__='0.0.20'
 
 from .fetchers import (
     BalanceSheetFetcher,

{neurostats_api-0.0.19 → neurostats_api-0.0.21}/neurostats_API/fetchers/base.py

@@ -81,10 +81,14 @@ class BaseTEJFetcher(abc.ABC):
 
     def get_latest_data_time(self, ticker):
         latest_data = self.collection.find_one(
-            {"ticker": ticker}, {
+            {
+                "ticker": ticker
+            }, 
+            {
                 "last_update": 1,
                 "_id": 0
-            })
+            }
+        )
 
         try:
             latest_date = latest_data['last_update']["latest_data_date"]
@@ -93,82 +97,78 @@ class BaseTEJFetcher(abc.ABC):
 
         return latest_date
 
-    def cal_YoY(
-            self, data_dict: dict, start_year: int, end_year: int, season: int):
+    def process_value(self, value):
+        if isinstance(value, str) and "%" in value:
+            value = value.replace("%", "")
+        try:
+            return float(value)
+        except (ValueError, TypeError):
+            return None
+
+    def calculate_growth(self, this_value, last_value, delta):
+        try:
+            return YoY_Calculator.cal_growth(this_value, last_value, delta) * 100
+        except Exception:
+            return None
+
+    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):
-            try:
-                year_data = data_dict[f"{year}Q{season}"].copy()
-            except KeyError as e:
+            year_data = data_dict.get(f"{year}Q{season}", {}).copy()
+            if not year_data:
                 continue
-
-            year_keys = list(year_data.keys())
-            for key in year_keys:
-                if (key in 'season'):
+            
+            for key in list(year_data.keys()):
+                if key == "season":
                     continue
-
-                if (isinstance(year_data[key], (int, float))):
-                    temp_dict = {"value": year_data[key]}
-
-                    for shift in year_shifts:
-                        this_value = year_data[key]
-                        try:
-                            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)
-                        except Exception as e:
-                            temp_dict[f"YoY_{shift}"] = None
-
-                    year_data[key] = temp_dict
-
-                else:
+                
+                this_value = self.process_value(year_data[key])
+                if this_value is None:
                     year_data.pop(key)
-
+                    continue
+                
+                temp_dict = {"value": year_data[key]}
+                for shift in year_shifts:
+                    past_year = year - shift
+                    last_value = data_dict.get(f"{past_year}Q{season}", {}).get(key)
+                    last_value = self.process_value(last_value)
+                    growth = self.calculate_growth(this_value, last_value, shift) if last_value is not None else None
+
+                    temp_dict[f"YoY_{shift}"] = (f"{growth:.2f}%" if growth else None)
+                year_data[key] = temp_dict
+            
             return_dict[f"{year}Q{season}"] = year_data
-
+        
         return return_dict
 
     def cal_QoQ(self, data_dict):
         return_dict = {}
-        for i, time_index in enumerate(data_dict.keys()):
-            year, season = time_index.split("Q")
-            year = int(year)
-            season = int(season)
-            if (season == 1):
-                last_year = year - 1
-                last_season = 4
-            else:
-                last_year = year
-                last_season = season - 1
-
-            this_data = data_dict[time_index]
-            this_keys = list(this_data.keys())
-            for key in this_keys:
-                if (key in 'season'):
+        
+        for time_index, this_data in data_dict.items():
+            year, season = map(int, time_index.split("Q"))
+            last_year, last_season = (year - 1, 4) if season == 1 else (year, season - 1)
+            
+            for key in list(this_data.keys()):
+                if key == "season":
                     continue
-
-                this_value = this_data[key]
-
-                if (isinstance(this_value, (int, float))):
-                    temp_dict = {"value": this_value}
-
-                    try:
-                        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)
-                    except Exception as e:
-                        temp_dict['growth'] = None
-
-                    this_data[key] = temp_dict
-
-                else:
+                
+                this_value = self.process_value(this_data[key])
+                if this_value is None:
                     this_data.pop(key)
+                    continue
+                
+                temp_dict = {"value": this_data[key]}
+                last_value = data_dict.get(f"{last_year}Q{last_season}", {}).get(key, {}).get('value')
+                last_value = self.process_value(last_value)
+                growth = self.calculate_growth(this_value, last_value, 1) if last_value is not None else None
+                temp_dict['growth'] = (f"{growth:.2f}%" if growth else None)
+                
+                this_data[key] = temp_dict
+            
             return_dict[time_index] = this_data
+        
         return return_dict
 
     def get_dict_of_df(self, data_dict):
@@ -180,31 +180,21 @@ class BaseTEJFetcher(abc.ABC):
         return data_dict
 
     def set_time_shift(self, date: Union[str, datetime], period: str):
-        if (isinstance(date, 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)
+        period_mapping = {
+            "1d": timedelta(days=1),
+            "7d": timedelta(days=7),
+            "1m": timedelta(days=30),
+            "3m": timedelta(days=90),
+            "1y": timedelta(days=365),
+            "3y": timedelta(days=365 * 3),
+            "5y": timedelta(days=365 * 5),
+            "10y": timedelta(days=365 * 10),
+        }
 
-        elif (period == 'all'):
+        if period == "all":
             return datetime.strptime("1991-01-01", "%Y-%m-%d")
+
+        return date - period_mapping.get(period, timedelta(days=0))  # 預設為不變"

{neurostats_api-0.0.19 → neurostats_api-0.0.21}/neurostats_API/fetchers/month_revenue.py

@@ -1,7 +1,7 @@
 from .base import StatsFetcher, StatsDateTime
 import json
 import pandas as pd
-from ..utils import StatsDateTime, StatsProcessor
+from ..utils import StatsDateTime, StatsProcessor, YoY_Calculator
 import importlib.resources as pkg_resources
 import yaml
 
@@ -77,7 +77,9 @@ class MonthRevenueFetcher(StatsFetcher):
                                                                   postfix="千元")
         target_month = monthly_data[0]['month']
         monthly_df = pd.DataFrame(monthly_data)
+
         target_month_df = monthly_df[monthly_df['month'] == target_month]
+        annual_month_df = monthly_df[monthly_df['month'] == 12]
         month_revenue_df = monthly_df.pivot(index='month',
                                             columns='year',
                                             values='revenue')
@@ -86,6 +88,10 @@ class MonthRevenueFetcher(StatsFetcher):
                                                columns='year',
                                                values='grand_total')
 
+        annual_total_df = annual_month_df.pivot(index='month',
+                                               columns='year',
+                                               values='grand_total')
+
         grand_total_df.rename(index={target_month: f"grand_total"},
                               inplace=True)
         month_revenue_df = month_revenue_df.sort_index(ascending=False)
@@ -111,4 +117,45 @@ class MonthRevenueFetcher(StatsFetcher):
 
         fetched_data.pop("monthly_data")
 
+        fetched_data['recent_month_revenue'] = self.get_recent_revenue_grwoth(
+            monthly_data, grand_total_dict=annual_total_df.to_dict(), interval = 12
+        )
+
         return fetched_data
+
+    def get_recent_revenue_grwoth(self, monthly_data, grand_total_dict, interval: int = 12):
+        recent_month_data = monthly_data[:interval + 1]
+
+        MoMs = [
+            YoY_Calculator.cal_growth(this_value['revenue'], last_value['revenue'], delta = 1)
+            for this_value, last_value in zip(
+                recent_month_data[:12], recent_month_data[1:13]
+            )
+        ]
+
+        recent_month_data = {
+            "date" : [f"{data['year']}/{data['month']}" for data in recent_month_data[:interval]],
+            "revenue" : [data['revenue'] for data in recent_month_data[:interval]],
+            "MoM" : [f"{(data * 100):.2f}%" for data in MoMs],
+            "YoY" : [f"{data['revenue_increment_ratio']}" for data in recent_month_data[:interval]],
+            "total_YoY":  [f"{data['grand_total_increment_ratio']}" for data in recent_month_data[:interval]],
+        }
+
+        # accum_YoY
+        # accum_YoY 為 Davis提出的定義
+        # 2024/6的累計YoY(accum_YoY) 為 2024累計到6月為止的總營收/2023年度總營收
+        accum_YoYs = []
+        for data in monthly_data[:interval]:
+            try:
+                year = data['year'] - 1
+                total = grand_total_dict[year][12]
+                accum_YoY = round((data['grand_total'] / total) * 100, 2)
+                accum_YoYs.append(f"{accum_YoY}%")
+            except Exception as e:
+                accum_YoYs.append(None)
+        
+        recent_month_data['accum_YoY'] = accum_YoYs
+
+        recent_month_df = pd.DataFrame(recent_month_data).set_index('date').T
+
+        return recent_month_df

{neurostats_api-0.0.19 → neurostats_api-0.0.21}/neurostats_API/fetchers/tech.py

@@ -85,7 +85,7 @@ class TechFetcher(StatsFetcher):
             ticker_full = self.collection.find_one(query)
 
             if not ticker_full:
-                raise
+                raise ValueError("No ticker found in database")
 
             daily_data = ticker_full.get("data", [])
             if not isinstance(daily_data, list):

{neurostats_api-0.0.19 → neurostats_api-0.0.21}/neurostats_API/fetchers/tej_finance_report.py

@@ -20,15 +20,23 @@ class FinanceReportFetcher(BaseTEJFetcher):
     def __init__(
             self,
             mongo_uri,
-            db_name=".company",
+            db_name="company",
             collection_name="TWN/AINVFQ1"
         ):
         self.client = MongoClient(mongo_uri)
         self.db = self.client[db_name]
         self.collection = self.db[collection_name]
 
-        index_dict = StatsProcessor.load_yaml("tej_db_index.yaml")
+        index_dict = StatsProcessor.load_yaml("tej_db/tej_db_index.yaml")
+        thousand_dict = StatsProcessor.load_yaml("tej_db/tej_db_thousand_index.yaml")
+        percent_dict = StatsProcessor.load_yaml("tej_db/tej_db_percent_index.yaml")
+        skip_dict = StatsProcessor.load_yaml("tej_db/tej_db_percent_index.yaml")
         self.check_index = set(index_dict[collection_name])
+        self.skip_index = set(skip_dict[collection_name])
+
+        self.thousand_index_list = list(thousand_dict[collection_name])
+        self.percent_index_list = list(percent_dict[collection_name])
+
 
     def get(
             self,
@@ -234,6 +242,8 @@ class FinanceReportFetcher(BaseTEJFetcher):
             keys=["year", "season"],
             delimeter="Q",
             data_key=report_type)
+        
+        data_dict = self.transform_value(data_dict)
 
         if (use_cal):
             data_with_QoQ = self.cal_QoQ(data_dict)
@@ -347,6 +357,8 @@ class FinanceReportFetcher(BaseTEJFetcher):
             keys=['year', 'season'],
             data_key=report_type,
             delimeter='Q')
+        
+        data_dict = self.transform_value(data_dict)
 
         if (use_cal):
             data_with_YoY = self.cal_YoY(
@@ -360,7 +372,29 @@ class FinanceReportFetcher(BaseTEJFetcher):
             data_df = pd.DataFrame.from_dict(data_dict)
             data_df = data_df.iloc[:, ::-1]
             return data_df
+        
+    def transform_value(self, data_dict):
+        """
+        處理千元, %等單位
+        """
 
+        data_df = pd.DataFrame.from_dict(data_dict)
+        
+        process_set = set(data_df.index).intersection(set(self.thousand_index_list))
+        process_list = list(process_set)
+        data_df.loc[process_list] = data_df.loc[process_list].map(
+            lambda x : StatsProcessor.cal_non_percentage(x, postfix="千元")
+        )
+
+        process_set = set(data_df.index).intersection(set(self.percent_index_list))
+        process_list = list(process_set)
+        data_df.loc[process_list] = data_df.loc[process_list].map(
+            lambda x : f"{x}%"
+        )
+
+        data_dict = data_df.to_dict()
+        
+        return data_dict
 
 class TEJStockPriceFetcher(BaseTEJFetcher):
 

neurostats_api-0.0.21/neurostats_API/tools/tej_db/tej_db_percent_index.yaml

@@ -0,0 +1,44 @@
+TWN/AINVFQ1:
+- 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
+TWN/AFESTM1:
+- r105
+- r106
+- r107
+- r108
+- r401
+- r402
+- r403
+- r404
+- r405

neurostats_api-0.0.21/neurostats_API/tools/tej_db/tej_db_skip_index.yaml

@@ -0,0 +1,20 @@
+TWN/AINVFQ1:
+- coid
+- mdate
+- key3
+- 'no'
+- sem
+- merg
+- curr
+- annd
+- fin_ind
+TWN/AFESTM1:
+- coid
+- mdate
+- key3
+- 'no'
+- sem
+- merg
+- curr
+- annd
+- fin_ind

neurostats_api-0.0.21/neurostats_API/tools/tej_db/tej_db_thousand_index.yaml

@@ -0,0 +1,71 @@
+TWN/AINVFQ1:
+- 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
+- r304
+- r305
+- r306
+- r316
+- r834
+TWN/AFESTM1:
+- ip12
+- gm
+- opi
+- isibt
+- isni
+- isnip