neurostats-API 0.0.10__tar.gz → 0.0.11__tar.gz

{neurostats_API-0.0.10 → neurostats_API-0.0.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: neurostats_API
-Version: 0.0.10
+Version: 0.0.11
 Summary: The service of NeuroStats website
 Home-page: https://github.com/NeurowattStats/NeuroStats_API.git
 Author: JasonWang@Neurowatt

neurostats_API-0.0.11/neurostats_API/__init__.py

@@ -0,0 +1 @@
+__version__='0.0.11'

{neurostats_API-0.0.10 → neurostats_API-0.0.11}/neurostats_API/fetchers/__init__.py

@@ -2,6 +2,7 @@ from .base import StatsDateTime, StatsFetcher
 from .balance_sheet import BalanceSheetFetcher
 from .cash_flow import CashFlowFetcher
 from .finance_overview import FinanceOverviewFetcher
+from .institution import InstitutionFetcher
 from .month_revenue import MonthRevenueFetcher
 from .profit_lose import ProfitLoseFetcher
 from .value_invest import ValueFetcher

{neurostats_API-0.0.10 → neurostats_API-0.0.11}/neurostats_API/fetchers/balance_sheet.py

@@ -116,10 +116,13 @@ class BalanceSheetFetcher(StatsFetcher):
                     try:  # table_dict[項目][(2020Q1, '%')]
                         if (item_name == 'percentage'):
                             if (isinstance(item, (float, int))):
-                                item = np.round(item, 2)
-                        if ("YoY" in item_name):
+                                item = StatsProcessor.cal_non_percentage(item, to_str=True, postfix="%")
+                        elif ("YoY" in item_name):
                             if (isinstance(item, (float, int))):
-                                item = np.round(item * 100, 2)
+                                item = StatsProcessor.cal_percentage(item)
+                        else:
+                            if (isinstance(item, (float, int))):
+                                item = StatsProcessor.cal_non_percentage(item,  postfix="千元")
                         table_dict[index_name][(time_index, item_name)] = item
 
                     except KeyError:

{neurostats_API-0.0.10 → neurostats_API-0.0.11}/neurostats_API/fetchers/cash_flow.py

@@ -132,14 +132,15 @@ class CashFlowFetcher(StatsFetcher):
                     table_dict[time_index][index_name]['value'] = value[
                         'value']
                     if (value['value']):
-                        table_dict[time_index][index_name][
-                            'percentage'] = np.round(
+                        ratio = np.round(
                                 (value['value'] / cash_flow[
                                 main_cash_flow_name]['value']) * 100, 2)
+                        table_dict[time_index][index_name][
+                            'percentage'] = f"{ratio}%"
                     else:
                         table_dict[time_index][index_name][
                             'percentage'] = None
-                except:
+                except: # 新增index再做一次
                     if (time_index not in table_dict.keys()):
                         table_dict[time_index] = dict()
                     table_dict[time_index][index_name] = dict()
@@ -147,14 +148,15 @@ class CashFlowFetcher(StatsFetcher):
                     table_dict[time_index][index_name]['value'] = value[
                         'value']
                     if (value['value']):
-                        table_dict[time_index][index_name][
-                            'percentage'] = np.round(
+                        ratio = np.round(
                                 (value['value'] / cash_flow[
                                 main_cash_flow_name]['value']) * 100, 2) 
+                        table_dict[time_index][index_name][
+                            'percentage'] = f"{ratio}%"
                     else:
                         table_dict[time_index][index_name][
                             'percentage'] = None
-
+                table_dict[time_index][index_name]['value'] = StatsProcessor.cal_non_percentage(value['value'], postfix="千元")
                 try:
                     partial_cash_flow[time_index][index_name] = table_dict[
                         time_index][index_name]

{neurostats_API-0.0.10 → neurostats_API-0.0.11}/neurostats_API/fetchers/finance_overview.py

@@ -156,6 +156,7 @@ class FinanceOverviewProcessor(StatsProcessor):
                 finance_dict[index] = StatsProcessor.cal_non_percentage(finance_dict[index], postfix="千元")
             except Exception as e:
                 finance_dict[index] = None
+            
 
     @classmethod
     def process_all(cls, finance_dict):
@@ -176,9 +177,6 @@ class FinanceOverviewProcessor(StatsProcessor):
             cls.cal_net_debt_to_equity_ratio, cls.cal_interest_coverage_ratio,
             cls.cal_debt_to_operating_cash_flow,
             cls.cal_debt_to_free_cash_flow, cls.cal_cash_flow_ratio,
-
-            # process to 千元
-            cls.process_thousand_dollar
         ]
 
         for method in methods:

neurostats_API-0.0.11/neurostats_API/fetchers/institution.py

@@ -0,0 +1,214 @@
+from .base import StatsFetcher
+from datetime import datetime, timedelta
+import json
+import numpy as np
+import pandas as pd
+from ..utils import StatsDateTime, StatsProcessor
+import importlib.resources as pkg_resources
+import yaml
+
+
+class InstitutionFetcher(StatsFetcher):
+    """
+    iFa -> 交易資訊 -> 法人買賣
+
+    包括: 
+    1. 當日交易
+    2. 一年內交易
+    """
+
+    def __init__(self, ticker, db_client):
+        super().__init__(ticker, db_client)
+
+    def prepare_query(self, start_date, end_date):
+        pipeline = super().prepare_query()
+
+        # target_query = {
+        #     "date": date,
+        #     "institution_trading": "$$target_season_data.institution_trading"
+        # }
+
+        pipeline.append({
+            "$project": {
+                "_id": 0,
+                "ticker": 1,
+                "company_name": 1,
+                "daily_data": {
+                    "$map": {
+                        "input": {
+                            "$filter": {
+                                "input": "$daily_data",
+                                "as": "daily",
+                                "cond": {
+                                    "$and": [{
+                                        "$gte": ["$$daily.date", start_date]
+                                    }, {
+                                        "$lte": ["$$daily.date", end_date]
+                                    }]
+                                }
+                            }
+                        },
+                        "as": "target_daily_data",
+                        "in": "$$target_daily_data"
+                    }
+                }
+            }
+        })
+
+        return pipeline
+
+    def collect_data(self, start_date, end_date):
+        pipeline = self.prepare_query(start_date, end_date)
+
+        fetched_data = self.collection.aggregate(pipeline).to_list()
+
+        return fetched_data[-1]
+
+    def query_data(self):
+        try:
+            latest_time = StatsDateTime.get_latest_time(
+                self.ticker, self.collection)['last_update_time']
+            latest_date = latest_time['institution_trading'][
+                'latest_date']
+            date = latest_date.replace(hour=0,
+                                       minute=0,
+                                       second=0,
+                                       microsecond=0)
+        except Exception as e:
+            print(
+                f"No updated time for institution_trading in {self.ticker}, use current time instead"
+            )
+            date = datetime.now(self.timezone)
+            date = date.replace(hour=0, minute=0, second=0, microsecond=0)
+
+            if (date.hour < 17):  # 拿不到今天的資料
+                date = date - timedelta(days=1)
+
+        start_date = date - timedelta(days=365)
+
+        daily_data = self.collect_data(start_date, end_date=date)
+
+        daily_data = sorted(daily_data['daily_data'],
+                            key=lambda x: x['date'],
+                            reverse=True)
+
+        table_dict = self.process_data(daily_data)
+
+        return table_dict
+
+    def process_data(self, daily_data):
+        table_dict = dict()
+
+        latest_data = daily_data[0]
+        yesterday_data = daily_data[1]
+
+        # 交易價格與昨天交易
+        price_dict = {
+            "open": latest_data['open'],
+            'close': latest_data['close'],
+            'range': f"{latest_data['low']}-{latest_data['high']}",
+            'volumn': latest_data['volume'] / 1000,
+            'last_open': yesterday_data['open'],
+            'last_close': yesterday_data['close'],
+            'last_range': f"{yesterday_data['low']}-{yesterday_data['high']}",
+            'last_volumn': yesterday_data['volume'] / 1000
+        }
+        # 一年範圍
+        annual_lows = [data['low'] for data in daily_data]
+        annual_highs = [data['high'] for data in daily_data]
+        lowest = np.min(annual_lows).item()
+        highest = np.max(annual_highs).item()
+
+        price_dict['52weeks_range'] = f"{lowest}-{highest}"
+        table_dict['price'] = price_dict
+
+        # 發行股數 & 市值
+
+        # 今日法人買賣
+        table_dict['latest_trading'] = {
+            "date":
+            daily_data[0]['date'],
+            "table":
+            self.process_latest_trading(daily_data[0]['institution_trading'], daily_data[0]['volume'])
+        }
+        # 一年內法人
+        annual_trading = [
+            {
+                **data['institution_trading'],
+                "收盤價": int(data['close'])
+            }
+            for data in daily_data
+        ]  # 將close也併入這個表格
+        annual_dates = [data['date'] for data in daily_data]
+        table_dict['annual_trading'] = self.process_annual_trading(
+            annual_dates, annual_trading)
+        
+        return table_dict
+
+    def process_latest_trading(self, latest_trading, volume):
+        latest_table = {
+            "foreign": self.default_institution_chart(),
+            "mutual": self.default_institution_chart(),
+            "prop": self.default_institution_chart(),
+            "institutional_investor":self.default_institution_chart(),
+        }
+
+        for key in latest_trading.keys():
+            if (key.find("外陸資") >= 0 or key.find("外資") >= 0):
+                self.target_institution(latest_trading, latest_table['foreign'], key, volume)
+            elif (key.find("自營商") >= 0):
+                self.target_institution(latest_trading,latest_table['prop'], key, volume)
+            elif (key.find("投信") >= 0):
+                self.target_institution(latest_trading,latest_table['mutual'], key, volume)
+            elif (key.find("三大法人") >= 0):
+                self.target_institution(latest_trading,latest_table['institutional_investor'], key, volume)
+
+        frames = []
+        for category, trades in latest_table.items():
+            temp_df = pd.DataFrame(trades).T
+            temp_df['category'] = category
+            frames.append(temp_df)
+        
+        latest_df = pd.concat(frames)
+        latest_df = latest_df.reset_index().rename(columns={'index': 'type'})
+        latest_df = latest_df[['type', 'category', 'stock', 'price', 'average_price', 'percentage']]
+
+        return latest_df
+
+    def process_annual_trading(self, dates, annual_tradings):
+        dates = [date.strftime("%m/%d") for date in dates]
+        return pd.DataFrame(annual_tradings, index=dates)
+
+    def target_institution(self, old_table, new_table, key, volume):
+        if (key.find("買進") >= 0):
+            self.cal_institution(old_table, new_table['buy'], key, volume)
+        elif (key.find("賣出") >= 0):
+            self.cal_institution(old_table, new_table['sell'], key, volume)
+        elif (key.find("買賣超") >= 0):
+            self.cal_institution(old_table, new_table['over_buy_sell'], key, volume)
+        
+    def cal_institution(self, old_table, new_table, key, volume):
+        new_table['stock'] = np.round(old_table[key] / 1000, 2).item()
+        new_table['percentage'] = np.round((old_table[key] / volume) * 100, 2).item()
+    
+    def default_institution_chart(self):
+        return {
+            "buy": {
+                "stock": 0,
+                "price": 0,
+                "average_price": 0,
+                "percentage": 0
+            },
+            "sell": {
+                "stock": 0,
+                "price": 0,
+                "average_price": 0,
+                "percentage": 0
+            },
+            "over_buy_sell": {
+                "stock": 0,
+                "price": 0,
+                "average_price": 0,
+                "percentage": 0
+            },
+        }

{neurostats_API-0.0.10 → neurostats_API-0.0.11}/neurostats_API/fetchers/month_revenue.py

@@ -64,6 +64,17 @@ class MonthRevenueFetcher(StatsFetcher):
     def process_data(self, fetched_data):
 
         monthly_data = fetched_data['monthly_data']
+        for data in monthly_data:
+            for key, value in data.items():
+                if ("YoY" in key):
+                    data[key] = StatsProcessor.cal_percentage(value)
+                elif ("ratio" in key or 'percentage' in key):
+                    data[key] = StatsProcessor.cal_non_percentage(value,
+                                                                  to_str=True,
+                                                                  postfix="%")
+                elif (key not in ('year', 'month')):
+                    data[key] = StatsProcessor.cal_non_percentage(value,
+                                                                  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]
@@ -77,21 +88,26 @@ class MonthRevenueFetcher(StatsFetcher):
 
         grand_total_df.rename(index={target_month: f"grand_total"},
                               inplace=True)
-        month_revenue_df = month_revenue_df.sort_index(ascending = False)
+        month_revenue_df = month_revenue_df.sort_index(ascending=False)
         month_revenue_df = pd.concat([grand_total_df, month_revenue_df],
                                      axis=0)
 
-        fetched_data['month_revenue'] = month_revenue_df[sorted(month_revenue_df.columns, reverse = True)]
+        fetched_data['month_revenue'] = month_revenue_df[sorted(
+            month_revenue_df.columns, reverse=True)]
         # 歷年月營收
         fetched_data[
             'this_month_revenue_over_years'] = target_month_df.set_index(
-                "year")[["revenue", "revenue_increment_ratio", "YoY_1",
-                        "YoY_3", "YoY_5", "YoY_10"]].T
+                "year")[[
+                    "revenue", "revenue_increment_ratio", "YoY_1", "YoY_3",
+                    "YoY_5", "YoY_10"
+                ]].T
         # 歷年營收成長量
         fetched_data['grand_total_over_years'] = target_month_df.set_index(
-            "year")[["grand_total", "grand_total_increment_ratio",
-                    "grand_total_YoY_1", "grand_total_YoY_3",
-                    "grand_total_YoY_5", "grand_total_YoY_10"]].T
+            "year")[[
+                "grand_total", "grand_total_increment_ratio",
+                "grand_total_YoY_1", "grand_total_YoY_3", "grand_total_YoY_5",
+                "grand_total_YoY_10"
+            ]].T
 
         fetched_data.pop("monthly_data")
 

{neurostats_API-0.0.10 → neurostats_API-0.0.11}/neurostats_API/fetchers/profit_lose.py

@@ -115,12 +115,15 @@ class ProfitLoseFetcher(StatsFetcher):
             for index_name, value_dict in profit_lose.items():
                 # (2020Q1, 項目, 金額或%)
                 for item_name, item in value_dict.items():
-                    if (item_name == 'percentage'):
+                    if ('percentage' in item_name):
                         if (isinstance(item, (float, int))):
-                            item = np.round(item, 2)
-                    if ('YoY' in item_name):
+                            item = StatsProcessor.cal_non_percentage(item, to_str=True, postfix="%")
+                    elif ('YoY' in item_name):
                         if (isinstance(item, (float, int))):
-                            item = np.round(item * 100, 2)
+                            item = StatsProcessor.cal_percentage(item)
+                    else:
+                        if (isinstance(item, (float, int))):
+                            item = StatsProcessor.cal_non_percentage(item,  postfix="千元")
                     try:
                         table_dict[index_name][(time_index, item_name)] = item
 

{neurostats_API-0.0.10 → neurostats_API-0.0.11}/neurostats_API.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: neurostats-API
-Version: 0.0.10
+Version: 0.0.11
 Summary: The service of NeuroStats website
 Home-page: https://github.com/NeurowattStats/NeuroStats_API.git
 Author: JasonWang@Neurowatt

{neurostats_API-0.0.10 → neurostats_API-0.0.11}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name='neurostats_API',
-    version='0.0.10',
+    version='0.0.11',
     long_description=open('README.md', 'r', encoding='utf-8').read(),
     long_description_content_type='text/markdown',
     install_requires=[

{neurostats_API-0.0.10 → neurostats_API-0.0.11}/test/test_fetchers.py

@@ -105,6 +105,7 @@ def test_balance_sheet():
 
 def test_finance_overview():
     from neurostats_API.fetchers import FinanceOverviewFetcher
+    company_list = {"2330": "台積電"}
     for ticker in company_list.keys():
         fetcher = FinanceOverviewFetcher(ticker=ticker, db_client=db_client)
         fetched_data = fetcher.query_data()
@@ -183,4 +184,12 @@ def test_finance_overview():
         assert key in fetched_data['seasonal_data'], f"{key} not found in fetched_data"
         # assert fetched_data['seasonal_data'][0][key] is not None, f"{key} is None"
 
+    pp.pprint(fetched_data)
+
+def test_institution_trading():
+    from neurostats_API.fetchers import InstitutionFetcher
+    fetcher = InstitutionFetcher(ticker='2330', db_client = db_client)
+
+    fetched_data = fetcher.query_data()
+
     pp.pprint(fetched_data)

neurostats_API-0.0.10/neurostats_API/__init__.py

@@ -1 +0,0 @@
-__version__='0.0.10'

neurostats_API-0.0.10/neurostats_API/fetchers/institution.py

@@ -1,114 +0,0 @@
-from .base import StatsFetcher
-from datetime import datetime, timedelta
-import json
-import numpy as np
-import pandas as pd
-from ..utils import StatsDateTime, StatsProcessor
-import importlib.resources as pkg_resources
-import yaml
-
-
-class InstitutionFetcher(StatsFetcher):
-    """
-    iFa -> 交易資訊 -> 法人買賣
-
-    包括: 
-    1. 當日交易
-    2. 一年內交易
-    """
-
-    def __init__(self, ticker, db_client):
-        raise(NotImplementedError("InstitutionFetcher : Not done yet"))
-        super().__init__(ticker, db_client)
-
-    def prepare_query(self, start_date, end_date):
-        pipeline = super().prepare_query()
-
-        target_query = {
-            "date": date,
-            "institution_trading": "$$target_season_data.institution_trading"
-        }
-
-
-        pipeline.append({
-            "$project": {
-                "_id": 0,
-                "ticker": 1,
-                "company_name": 1,
-                "profit_loses": {
-                    "$map": {
-                        "input": {
-                            "$filter": {
-                                "input": "$daily_data",
-                                "as": "daily",
-                                "cond": {
-                                        "$and": [
-                                        {"$gte": ["$$daily.date", start_date]},
-                                        {"$lte": ["$$daily.date", end_date]}
-                                    ]
-                                }
-                            }
-                        },
-                        "as": "target_daily_data",
-                        "in": "$$target_daily_data"
-                    }
-                }
-            }
-        })
-
-        return pipeline
-
-    def collect_data(self, date):
-        pipeline = self.prepare_query(date)
-
-        fetched_data = self.collection.aggregate(pipeline).to_list()
-
-        return fetch_data[-1]
-    
-    def query_data(self):
-        try:
-            latest_time = StatsDateTime.get_latest_time(
-                self.ticker, self.collection)['last_update_time']
-            latest_date = latest_time['daily_data']['institution_trading']['last_update']
-            date = latest_date.replace(hour=0, minute=0, second=0, microsecond=0) 
-        except Exception as e:
-            print(f"No updated time for institution_trading in {self.ticker}, use current time instead")
-            date = datetime.now(self.timezone)
-            date = date.replace(hour=0, minute=0, second=0, microsecond=0) 
-
-            if (date.hour < 17):  # 拿不到今天的資料
-                date = date - timedelta(days=1)
-        
-        start_date = start_date - timedelta(days=365)
-
-        daily_data = self.collect_data(date)
-
-        daily_data = sorted(daily_data['daily_data'], key = lambda x : x['date'], reverse = True)
-
-        self.process_data(self.ticker, daily_data)
-    
-    def process_data(self, daily_data):
-        table_dict = dict()
-
-        latest_data = daily_data[0] 
-        yesterday_data = daily_data[1]
-
-        # 交易價格與昨天交易
-        table_dict = {
-            "open": latest_data['open'],
-            'close': latest_data['close'],
-            'range': f"{latest_data['high']}-{latest_data['low']}",
-            'volumn': latest_data['volumn'] / 1000
-
-        }
-
-        # 今日法人買賣
-
-        # 一年內法人
-
-
-
-
-
-
-