neurostats-API 1.0.0rc2__tar.gz → 1.0.0rc4__tar.gz

{neurostats_api-1.0.0rc2 → neurostats_api-1.0.0rc4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: neurostats_API
-Version: 1.0.0rc2
+Version: 1.0.0rc4
 Summary: The service of NeuroStats website
 Home-page: https://github.com/NeurowattStats/NeuroStats_API.git
 Author: JasonWang@Neurowatt
@@ -71,7 +71,7 @@ pip install neurostats-API
 ```Python 
 >>> import neurostats_API
 >>> print(neurostats_API.__version__)
-1.0.0rc2
+1.0.0rc4
 ```
 
 ### 下載舊版

{neurostats_api-1.0.0rc2 → neurostats_api-1.0.0rc4}/README.md

@@ -54,7 +54,7 @@ pip install neurostats-API
 ```Python 
 >>> import neurostats_API
 >>> print(neurostats_API.__version__)
-1.0.0rc2
+1.0.0rc4
 ```
 
 ### 下載舊版

neurostats_api-1.0.0rc4/neurostats_API/__init__.py

@@ -0,0 +1,29 @@
+__version__='1.0.0rc4'
+
+from .fetchers import (
+    AgentFinanceOverviewFetcher,
+    BalanceSheetFetcher,
+    CashFlowFetcher,
+    FinanceOverviewFetcher,
+    FinanceReportFetcher,
+    InstitutionFetcher,
+    MarginTradingFetcher,
+    MonthRevenueFetcher,
+    TechFetcher,
+    TEJStockPriceFetcher,
+    ProfitLoseFetcher,
+)
+
+from .async_mode import (
+    AsyncAgentOverviewFetcher,
+    AsyncBalanceSheetFetcher,
+    AsyncCashFlowFetcher,
+    AsyncFinanceOverviewFetcher,
+    AsyncMonthlyRevenueFetcher,
+    AsyncProfitLoseFetcher,
+    AsyncTechFetcher,
+    AsyncTEJSeasonalFetcher,
+    AsyncTWSEInstitutionFetcher,
+    AsyncTWSEMarginFetcher,
+    AsyncTWSEStatsValueFetcher
+)

{neurostats_api-1.0.0rc2 → neurostats_api-1.0.0rc4}/neurostats_API/async_mode/db_extractors/seasonal/base.py

@@ -68,7 +68,7 @@ class AsyncBaseSeasonalDBExtractor(BaseDBExtractor):
 
         query = {
             "ticker": self.ticker,
-            "chart_name": {"$exists": True}
+            chart_name: {"$exists": True}
         }
 
         query = self._update_query_with_year_season(

{neurostats_api-1.0.0rc2 → neurostats_api-1.0.0rc4}/neurostats_API/transformers/balance_sheet/twse.py

@@ -1,19 +1,24 @@
 from .base import BaseBalanceSheetTransformer
 from neurostats_API.utils import StatsProcessor
 
+
 class TWSEBalanceSheetTransformer(BaseBalanceSheetTransformer):
+
     def __init__(self, ticker, company_name, zone):
         super().__init__(ticker, company_name, zone)
 
-        self.table_settings = StatsProcessor.load_yaml("twse/balance_sheet.yaml")
+        self.table_settings = StatsProcessor.load_yaml(
+            "twse/balance_sheet.yaml"
+        )
         self.return_keys = [
-            'balance_sheet', 'total_asset', 'current_asset', 'non_current_asset', 
-            'current_debt', 'non_current_debt', 'equity', 'balance_sheet_all', 'balance_sheet_YoY'
+            'balance_sheet', 'total_asset', 'current_asset',
+            'non_current_asset', 'current_debt', 'non_current_debt', 'equity',
+            'balance_sheet_all', 'balance_sheet_YoY'
         ]
 
         self.stats_df = None
         self.new_df = None
-    
+
     def process_transform(self, fetched_data):
         if (not fetched_data):
             return self._get_empty_structure()
@@ -21,12 +26,10 @@ class TWSEBalanceSheetTransformer(BaseBalanceSheetTransformer):
         processed_data = self._process_fn(fetched_data)
 
         return processed_data
+
     def _process_fn(self, fetched_data):
-        
-        return_dict = {
-            "ticker": self.ticker,
-            "company_name": self.company_name
-        }
+
+        return_dict = {"ticker": self.ticker, "company_name": self.company_name}
 
         target_season = fetched_data[0]['season']
 
@@ -36,18 +39,22 @@ class TWSEBalanceSheetTransformer(BaseBalanceSheetTransformer):
         # 轉換格式 (元 / 千元 / %)
         self.stats_df = StatsProcessor.expand_value_percentage(self.stats_df)
         self.stats_df = self._apply_process_unit_pipeline(
-            self.stats_df, 
-            postfix_list=['_value', "_percentage"]
+            self.stats_df, postfix_list=['_value', "_percentage"]
         )
 
         self.new_df = self._process_twse_to_tej_format(fetched_data)
         # 轉換格式 (元 / 千元 / %)
         self.new_df = self._apply_process_unit_pipeline(
-            self.new_df,
-            postfix_list=['_value', "_percentage"]
+            self.new_df, postfix_list=['_value', "_percentage"]
         )
 
-        total_table_YoY = self._slice_target_season(self.new_df.T, target_season)
+        self.new_dict = self.new_df.to_dict()
+        self.new_df = self._cal_QoQ(self.new_dict)
+        self.new_df = self.new_df.T
+
+        total_table_YoY = self._slice_target_season(
+            self.new_df, target_season
+        )
 
         return_dict.update(
             {
@@ -60,17 +67,15 @@ class TWSEBalanceSheetTransformer(BaseBalanceSheetTransformer):
         self._process_target_columns(return_dict, self.stats_df)
 
         return return_dict
-    
+
     def _process_target_columns(self, return_dict, stats_df):
         for name, setting in self.table_settings.items():
             target_indexes = setting.get('target_index', [None])
             for target_index in target_indexes:
                 try:
                     return_dict[name] = StatsProcessor.slice_old_table(
-                        total_table=stats_df,
-                        target_index=target_index
+                        total_table=stats_df, target_index=target_index
                     )
                     break
                 except Exception as e:
                     continue
-

neurostats_api-1.0.0rc4/neurostats_API/transformers/base.py

@@ -0,0 +1,158 @@
+import abc
+from neurostats_API.utils import StatsProcessor, YoY_Calculator
+import pandas as pd
+
+
+class BaseTransformer(abc.ABC):
+    """
+    Transformer用途: 轉換資料為fetcher可使用的格式
+    """
+
+    def __init__(self, ticker, company_name, zone):
+        self.ticker = ticker
+        self.company_name = company_name
+
+        self.zone = zone
+        self.return_keys = []
+
+    @abc.abstractmethod
+    def process_transform(self):
+        pass
+
+    @classmethod
+    def flatten_dict(cls, value_dict, target_keys):
+        indexes = value_dict.keys()
+        new_dict = {}
+
+        for key in indexes:
+            new_dict.update(
+                {
+                    f"{key}_{sub_key}": value_dict[key].get(sub_key, None)
+                    for sub_key in target_keys
+                }
+            )
+        
+        return new_dict
+
+    @staticmethod
+    def _process_unit(data_df, postfix):
+
+        lambda_map = {
+            "_value":
+            lambda x: StatsProcessor.cal_non_percentage(x, postfix="千元"),
+            "_percentage":
+            lambda x: StatsProcessor.
+            cal_non_percentage(x, to_str=True, postfix="%"),
+            '_growth':
+            lambda x: StatsProcessor.
+            cal_non_percentage(x, to_str=True, postfix="%"),
+            "_YoY_1":
+            StatsProcessor.cal_percentage,
+            "_YoY_3":
+            StatsProcessor.cal_percentage,
+            "_YoY_5":
+            StatsProcessor.cal_percentage,
+            "_YoY_10":
+            StatsProcessor.cal_percentage
+        }
+
+        process_fn = lambda_map.get(postfix)
+        postfix_cols = data_df.columns.str.endswith(postfix)
+        postfix_cols = data_df.loc[:, postfix_cols].columns
+
+        if (postfix == "_value"):
+            postfix_cols = [
+                col for col in postfix_cols
+                if not ("eps" in col or "每股盈餘" in col)
+            ]
+
+        if (postfix == '_growth'):
+            data_df[postfix_cols] = data_df[postfix_cols].map(
+                lambda x: x * 100.0 if isinstance(x, float) else x
+            )
+
+        data_df[postfix_cols] = (data_df[postfix_cols].map(process_fn))
+
+        return data_df
+
+    def _apply_process_unit_pipeline(
+        self, data_df, postfix_list=["_value", "percentage"]
+    ):
+        for postfix in postfix_list:
+            data_df = self._process_unit(data_df, postfix)
+        return data_df
+
+    @staticmethod
+    def _slice_target_season(stats_df, target_season):
+        target_season_columns = stats_df.columns.str.endswith(
+            f"Q{target_season}"
+        )
+        stats_df = stats_df.loc[:, target_season_columns]
+
+        return stats_df
+
+    def _get_empty_structure(self):
+        return_dict = {
+            "warning": "No data fetched",
+            "ticker": self.ticker,
+            "company_name": self.company_name
+        }
+
+        return_dict.update(
+            {
+                key: pd.DataFrame(columns=pd.Index([], name='date'))
+                for key in self.return_keys
+            }
+        )
+        return return_dict
+
+    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_QoQ(self, data_dict):
+        """
+        data_dict: {"<key>_value": {"2020Q1": <value>, ....}, "<key>_percentage": {"2020Q1": <value>, ....}}
+        """
+
+        return_dict = data_dict.copy()
+
+        for key, datas in data_dict.items():
+            if (key.endswith("_value")):
+                main_key = key.split("_")[0]
+                temp_growth_dict = dict()
+                for year_season, value in datas.items():
+
+                    year, season = year_season.split('Q')
+                    year, season = int(year), int(season)
+
+                    last_year, last_season = (
+                        year, season - 1
+                    ) if season != 1 else (year - 1, 4)
+
+                    last_value = datas.get(f"{last_year}Q{last_season}", None)
+
+                    growth = YoY_Calculator.cal_growth(
+                        value, last_value, delta=1
+                    )
+                    if (growth):
+                        growth = growth * 100
+                        growth = f"{growth:.2f}%"
+
+                    temp_growth_dict[year_season] = growth
+
+                return_dict[f"{main_key}_growth"] = growth
+        return_df = pd.DataFrame.from_dict(return_dict)
+        return return_df

{neurostats_api-1.0.0rc2 → neurostats_api-1.0.0rc4}/neurostats_API/transformers/cash_flow/twse.py

@@ -52,6 +52,8 @@ class TWSECashFlowTransformer(BaseCashFlowTransformer):
             return self._get_empty_structure()
         
         data_df = self._process_twse_to_tej_format(fetched_data)
+        data_df = self._cal_QoQ(data_df.T.to_dict())
+        data_df = data_df.T
         target_season = fetched_data[0]['season']
 
         data_df_YoY = self._slice_target_season(data_df, target_season)

{neurostats_api-1.0.0rc2 → neurostats_api-1.0.0rc4}/neurostats_API/transformers/finance_overview/stats_overview.py

@@ -27,12 +27,27 @@ class FinanceOverviewTransformer(BaseFinanceOverviewTransformer):
         return processed_data_dict
 
     def _filter_target_data(self, balance_sheet, profit_lose, cash_flow):
+        balance_sheet = balance_sheet[-1]
+        cash_flow = cash_flow[-1]
+        profit_lose = profit_lose[-1]
+        seasons = [
+            (int(report['year']), int(report['season']))
+            for report in (balance_sheet, profit_lose, cash_flow)
+        ]
+
+        max_date = max(seasons)
+        year, season = max_date
+
         data_dict = {
-            'balance_sheet': balance_sheet[-1]['balance_sheet'],
-            'profit_lose': profit_lose[-1]['profit_lose'],
-            "cash_flow": cash_flow[-1]['cash_flow']
+            'balance_sheet': balance_sheet['balance_sheet'],
+            'profit_lose': profit_lose['profit_lose'],
+            "cash_flow": cash_flow['cash_flow']
         }
-        filtered_dict = {}
+        filtered_dict = {
+            "year": year,
+            "season": season
+        }
+
 
         for key, target_sets in self.target_fields.items():
             try:

{neurostats_api-1.0.0rc2 → neurostats_api-1.0.0rc4}/neurostats_API/transformers/profit_lose/twse.py

@@ -105,7 +105,7 @@ class TWSEProfitLoseTransformer(BaseProfitLoseTransformer):
         return_dict.update({
             "profit_lose": stats_main_page_df,
             "grand_total_profit_lose": stats_grand_total_df,
-            "profit_lose_all": self.new_df.T,
+            "profit_lose_all": self.new_df,
             "profit_lose_YoY": new_df_YoY
         })
 

{neurostats_api-1.0.0rc2 → neurostats_api-1.0.0rc4}/neurostats_API.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: neurostats_API
-Version: 1.0.0rc2
+Version: 1.0.0rc4
 Summary: The service of NeuroStats website
 Home-page: https://github.com/NeurowattStats/NeuroStats_API.git
 Author: JasonWang@Neurowatt
@@ -71,7 +71,7 @@ pip install neurostats-API
 ```Python 
 >>> import neurostats_API
 >>> print(neurostats_API.__version__)
-1.0.0rc2
+1.0.0rc4
 ```
 
 ### 下載舊版

{neurostats_api-1.0.0rc2 → neurostats_api-1.0.0rc4}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name='neurostats_API',
-    version='1.0.0rc2',
+    version='1.0.0rc4',
     long_description=open('README.md', 'r', encoding='utf-8').read(),
     long_description_content_type='text/markdown',
     install_requires=[

{neurostats_api-1.0.0rc2 → neurostats_api-1.0.0rc4}/test/test_async_fetcher.py

@@ -7,7 +7,7 @@ from pymongo import AsyncMongoClient
 
 
 mongo_uri = "mongodb://neurowatt:neurodb123@db.neurowatt.ai:27017/neurowatt"
-tickers = ["AAPL"]
+tickers = ["AAPL", "2330", "1260", "-1234"]
 
 client = AsyncMongoClient(mongo_uri)
 
@@ -229,6 +229,7 @@ def print_dict_summary(data: dict, indent: int = 1):
     prefix = " " * indent
     for key, value in data.items():
         if isinstance(value, pd.DataFrame):
+            assert value.shape!= (0, 0)
             print(f"{prefix} \"{key}\": DataFrame shape = {value.shape}")
         elif isinstance(value, pd.Series):
             print(f"{prefix} \"{key}\": Series shape = {value.shape}")

neurostats_api-1.0.0rc2/neurostats_API/__init__.py

@@ -1,15 +0,0 @@
-__version__='1.0.0rc2'
-
-from .fetchers import (
-    AgentFinanceOverviewFetcher,
-    BalanceSheetFetcher,
-    CashFlowFetcher,
-    FinanceOverviewFetcher,
-    FinanceReportFetcher,
-    InstitutionFetcher,
-    MarginTradingFetcher,
-    MonthRevenueFetcher,
-    TechFetcher,
-    TEJStockPriceFetcher,
-    ProfitLoseFetcher,
-)

neurostats_api-1.0.0rc2/neurostats_API/transformers/base.py

@@ -1,110 +0,0 @@
-import abc
-from neurostats_API.utils import StatsProcessor, YoY_Calculator
-import pandas as pd
-
-class BaseTransformer(abc.ABC):
-    """
-    Transformer用途: 轉換資料為fetcher可使用的格式
-    """
-    def __init__(self, ticker, company_name, zone):
-        self.ticker = ticker
-        self.company_name = company_name
-
-        self.zone = zone
-        self.return_keys = []
-
-
-    @abc.abstractmethod
-    def process_transform(self):
-        pass
-
-    @classmethod
-    def flatten_dict(cls, value_dict, target_keys):
-        indexes = value_dict.keys()
-        new_dict = {}
-
-
-        for key in indexes:
-            new_dict.update(
-                {
-                    f"{key}_{sub_key}": value_dict[key].get(sub_key, None) 
-                    for sub_key in target_keys
-                }
-            )
-        return new_dict
-    
-    @staticmethod
-    def _process_unit(data_df, postfix):
-
-        lambda_map = {
-            "_value":  lambda x: StatsProcessor.cal_non_percentage(x, postfix="千元"),
-            "_percentage": lambda x : StatsProcessor.cal_non_percentage(x, to_str=True, postfix="%"),
-            '_growth': lambda x : StatsProcessor.cal_non_percentage(x, to_str=True, postfix="%"),
-            "_YoY_1": StatsProcessor.cal_percentage,
-            "_YoY_3": StatsProcessor.cal_percentage,
-            "_YoY_5": StatsProcessor.cal_percentage,
-            "_YoY_10": StatsProcessor.cal_percentage
-        }
-
-        process_fn = lambda_map.get(postfix)
-        postfix_cols = data_df.columns.str.endswith(postfix)
-        postfix_cols = data_df.loc[:, postfix_cols].columns
-
-        if (postfix == "_value"):
-            postfix_cols = [col for col in postfix_cols if not ("eps" in col or "每股盈餘" in col)]
-        
-        if (postfix == '_growth'):
-            data_df[postfix_cols] =data_df[postfix_cols].map(
-               lambda x: x * 100.0 if isinstance(x, float) else x
-            )
-
-        data_df[postfix_cols] = (
-            data_df[postfix_cols].map(
-               process_fn
-            )
-        )
-
-        return data_df
-
-    def _apply_process_unit_pipeline(self, data_df, postfix_list = ["_value", "percentage"]):
-        for postfix in postfix_list:
-            data_df = self._process_unit(data_df, postfix)
-        return data_df
-
-    @staticmethod
-    def _slice_target_season(stats_df, target_season):
-        target_season_columns = stats_df.columns.str.endswith(f"Q{target_season}")
-        stats_df = stats_df.loc[:, target_season_columns]
-
-        return stats_df
-    
-    def _get_empty_structure(self):
-        return_dict = {
-            "warning": "No data fetched",
-            "ticker": self.ticker,
-            "company_name": self.company_name
-        }
-
-        return_dict.update(
-            {
-                key: pd.DataFrame(columns= pd.Index([], name = 'date')) for key in self.return_keys
-            }
-        )
-        return return_dict
-    
-    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
-