neurostats-API 0.0.23b1__py3-none-any.whl → 0.0.24__py3-none-any.whl

neurostats_API/fetchers/profit_lose.py

@@ -22,6 +22,16 @@ class ProfitLoseFetcher(StatsFetcher):
             "us_stats": self.process_data_us
         }
 
+        self.return_keys = [
+            'profit_lose', 'grand_total_profit_lose', 'revenue', 'grand_total_revenue', 
+            'gross_profit', 'grand_total_gross_profit', 'gross_profit_percentage', 
+            'grand_total_gross_profit_percentage', 'operating_income', 'grand_total_operating_income', 'operating_income_percentage', 
+            'grand_total_operating_income_percentage', 'net_income_before_tax', 'grand_total_net_income_before_tax', 'net_income_before_tax_percentage', 
+            'grand_total_net_income_before_tax_percentage', 'net_income', 'grand_total_net_income', 'net_income_percentage', 
+            'grand_total_income_percentage', 'EPS', 'EPS_growth', 'grand_total_EPS', 
+            'grand_total_EPS_growth', 'profit_lose_all', 'profit_lose_YoY'
+        ]
+
     def prepare_query(self):
         pipeline = super().prepare_query()
 
@@ -30,28 +40,25 @@ class ProfitLoseFetcher(StatsFetcher):
         chart_name = name_map.get(self.collection_name, "income_statement")
 
         append_pipeline = [
-            {
-                "$unwind": "$seasonal_data"    # 展開 seasonal_data 陣列
-            },
-            {
-                "$project": {
-                    "_id": 0,
-                    "ticker": 1,
-                    "company_name": 1,
-                    "year": "$seasonal_data.year",
-                    "season": "$seasonal_data.season",
-                    "profit_lose": {
-                        "$ifNull": [f"$seasonal_data.{chart_name}", []]
-                    }    # 避免 null
-                }
-            },
-            {
-                "$sort": {
-                    "year": -1,
-                    "season": -1
+        {
+            "$project": {
+                "_id": 0,
+                "ticker": 1,
+                "company_name": 1,
+                "seasonal_data": {
+                    "$map": {
+                        "input": {"$ifNull": ["$seasonal_data", []]},
+                        "as": "season",
+                        "in": {
+                            "year": "$$season.year",
+                            "season": "$$season.season",
+                            "data": {"$ifNull": [f"$$season.{chart_name}", []]}
+                        }
+                    }
                 }
             }
-        ]
+        }
+    ]
 
         pipeline = pipeline + append_pipeline
 
@@ -63,6 +70,8 @@ class ProfitLoseFetcher(StatsFetcher):
     def query_data(self):
         fetched_data = self.collect_data()
 
+        fetched_data = fetched_data[0]
+
         process_fn = self.process_function_map.get(
             self.collection_name, self.process_data_us
         )
@@ -79,101 +88,108 @@ class ProfitLoseFetcher(StatsFetcher):
             'latest_target_year',
             StatsDateTime.get_today().year - 1
         )
-        target_season = latest_time.get(
-            'seasonal_data',{}
-        ).get('latest_season', 4)
+        target_season = latest_time.get('seasonal_data',
+                                        {}).get('latest_season', 4)
 
         return_dict = {
             "ticker": self.ticker,
-            "company_name": fetched_data[-1]['company_name'],
+            "company_name": fetched_data['company_name'],
         }
 
+        seasonal_data = fetched_data.get('seasonal_data', [])
+
+        if (not seasonal_data):
+            return_dict.update(self._get_empty_structure())
+            return return_dict
+
         profit_lose_dict = {
-            f"{data['year']}Q{data['season']}": data['profit_lose'] 
-            for data in fetched_data
+            f"{data['year']}Q{data['season']}": data['data']
+            for data in seasonal_data
         }
 
+        profit_lose_dict = YoY_Calculator.cal_QoQ(profit_lose_dict)
         profit_lose_df = pd.DataFrame.from_dict(profit_lose_dict)
         target_season_col = profit_lose_df.columns.str.endswith(
             f"Q{target_season}"
         )
         profit_lose_df = profit_lose_df.loc[:, target_season_col]
-        profit_lose_df = StatsProcessor.expand_value_percentage(
+
+        old_profit_lose_df = StatsProcessor.expand_value_percentage(
             profit_lose_df
         )
-
-        value_col = profit_lose_df.columns.str.endswith(f"_value")
-        percentage_col = profit_lose_df.columns.str.endswith(f"_percentage")
-
-        grand_total_value_col = profit_lose_df.columns.str.endswith(
+        # OLD: 回傳包含value & percentage
+        value_col = old_profit_lose_df.columns.str.endswith(f"_value")
+        percentage_col = old_profit_lose_df.columns.str.endswith(f"_percentage")
+        # OLD: 回傳剔除grand_total
+        grand_total_value_col = old_profit_lose_df.columns.str.endswith(
             f"grand_total_value"
         )
-        grand_total_percentage_col = profit_lose_df.columns.str.endswith(
+        grand_total_percentage_col = old_profit_lose_df.columns.str.endswith(
             f"grand_total_percentage"
         )
 
-        profit_lose_stats_df = profit_lose_df.loc[:, (
+        old_profit_lose_df = old_profit_lose_df.loc[:, (
             (value_col & ~grand_total_value_col) |
             (percentage_col & ~grand_total_percentage_col)
         )]
 
-        for time_index, profit_lose in profit_lose_dict.items():
-            # 蒐集整體的keys
-            index_names = list(profit_lose.keys())
-            target_keys = [
-                "value",
-                "percentage",
-                "grand_total",
-                "grand_total_percentage",
-                "YoY_1",
-                "YoY_3",
-                "YoY_5",
-                "YoY_10",
-                "grand_total_YoY_1",
-                "grand_total_YoY_3",
-                "grand_total_YoY_5",
-                "grand_total_YoY_10",
-            ]
-            # flatten dict
-            new_profit_lose = self.flatten_dict(
-                profit_lose, index_names, target_keys
+        for time_index, data_dict in profit_lose_dict.items():
+            profit_lose_dict[time_index] = self.flatten_dict(
+                value_dict=data_dict,
+                indexes=list(data_dict.keys()),
+                target_keys=[
+                    "value", "growth", "percentage", "grand_total",
+                    "grand_total_percentage"
+                ] + [f"YoY_{i}" for i in [1, 3, 5, 10]] +
+                [f"grand_total_YoY_{i}" for i in [1, 3, 5, 10]]
             )
-            profit_lose_dict[time_index] = new_profit_lose
-
-        profit_lose_df = pd.DataFrame.from_dict(profit_lose_dict)
 
+        profit_lose_df = pd.DataFrame.from_dict(profit_lose_dict).T
         # EPS的value用元計算
-        eps_index = profit_lose_df.index.str.endswith(
-            "_value"
-        ) & profit_lose_df.index.str.contains("每股盈餘")
-        profit_lose_df.loc[eps_index] = profit_lose_df.loc[
-            eps_index].apply(
-                lambda x: StatsProcessor.cal_non_percentage(x, postfix="元")
-            )
+        eps_index = (
+            profit_lose_df.columns.str.endswith("_value")
+            & profit_lose_df.columns.str.contains("每股盈餘")
+        )
+        eps_copy = profit_lose_df.loc[:, eps_index].copy()
+        eps_mask_index = eps_copy.columns
+        profit_lose_df[eps_mask_index] = profit_lose_df[eps_mask_index].map(
+            lambda x: StatsProcessor.cal_non_percentage(x, postfix="元")
+        )
 
         # percentage處理
-        percentage_index = profit_lose_df.index.str.endswith("percentage")
-        profit_lose_df.loc[percentage_index] = profit_lose_df.loc[
-            percentage_index].apply(
+        percentage_index = profit_lose_df.columns.str.endswith("percentage")
+        growth_index = profit_lose_df.columns.str.endswith("growth")
+        percentage_mask = (percentage_index | growth_index)
+        percentage_copy = profit_lose_df.loc[:, percentage_mask]
+        percentage_mask_index = percentage_copy.columns
+
+        profit_lose_df[percentage_mask_index] = profit_lose_df[
+            percentage_mask_index].map(
                 lambda x: StatsProcessor.
                 cal_non_percentage(x, to_str=True, postfix="%")
             )
 
         # YoY處理: 乘以100
-        YoY_index = profit_lose_df.index.str.contains("YoY")
-        profit_lose_df.loc[YoY_index] = profit_lose_df.loc[
-            YoY_index].apply(lambda x: StatsProcessor.cal_percentage(x))
+        YoY_index = profit_lose_df.columns.str.contains("YoY")
+        YoY_mask = YoY_index
+        YoY_copy = profit_lose_df.loc[:, YoY_mask]
+        YoY_mask_cols = YoY_copy.columns
+
+        profit_lose_df[YoY_mask_cols] = profit_lose_df[YoY_mask_cols].map(
+            lambda x: StatsProcessor.cal_percentage(x)
+        )
 
         # 剩下的處理: 乘以千元
         value_index = ~(
-            percentage_index | YoY_index | profit_lose_df.index.isin(eps_index)
+            percentage_index | growth_index | YoY_index | eps_index
         )    # 除了上述以外的 index
-        profit_lose_df.loc[value_index] = profit_lose_df.loc[
-            value_index].apply(
-                lambda x: StatsProcessor.cal_non_percentage(x, postfix="千元")
-            )
 
-        total_table = profit_lose_df.replace("N/A", None)
+        value_col = profit_lose_df.loc[:, value_index].columns
+        profit_lose_df[value_col] = profit_lose_df[value_col].map(
+            lambda x: StatsProcessor.cal_non_percentage(x, postfix="千元")
+        )
+
+        total_table = profit_lose_df.replace("N/A", None).T
 
         # 取特定季度
         target_season_columns = total_table.columns.str.endswith(
@@ -192,12 +208,11 @@ class ProfitLoseFetcher(StatsFetcher):
                     )
                     break
                 except Exception as e:
-                    print(str(e))
                     continue
 
         return_dict.update(
             {
-                "profit_lose": profit_lose_stats_df,
+                "profit_lose": old_profit_lose_df,
                 "profit_lose_all": total_table.copy(),
                 "profit_lose_YoY": total_table_YoY
             }
@@ -207,8 +222,8 @@ class ProfitLoseFetcher(StatsFetcher):
     def process_data_us(self, fetched_data):
 
         table_dict = {
-            f"{data['year']}Q{data['season']}": data['profit_lose']
-            for data in fetched_data
+            f"{data['year']}Q{data['season']}": data['data']
+            for data in fetched_data['seasonal_data']
         }
 
         table_dict = YoY_Calculator.cal_QoQ(table_dict)
@@ -218,16 +233,21 @@ class ProfitLoseFetcher(StatsFetcher):
             table_dict[time_index] = self.flatten_dict(
                 value_dict=data_dict,
                 indexes=list(data_dict.keys()),
-                target_keys=["value", "growth"] + 
-                            [f"YoY_{i}" for i in [1, 3, 5, 10]]
+                target_keys=["value", "growth"] +
+                [f"YoY_{i}" for i in [1, 3, 5, 10]]
             )
 
         # 計算QoQ
 
         return_dict = {
             "ticker": self.ticker,
-            "company_name": fetched_data[-1]['company_name'],
+            "company_name": fetched_data['company_name'],
             "profit_lose": pd.DataFrame.from_dict(table_dict)
         }
 
         return return_dict
+
+    def _get_empty_structure(self):
+        return {
+            key: pd.DataFrame(columns= pd.Index([], name = 'date')) for key in self.return_keys
+        }

neurostats_API/fetchers/tech.py

@@ -138,31 +138,6 @@ class TechFetcher(StatsFetcher):
         )
 
         return df
-
-    
-    def conduct_db_search_twse(self):
-        required_cols = ['date', 'open', 'high', 'low', 'close', 'volume']
-        match_query = {"ticker" : self.ticker}
-        proj_query = {"_id": 0, "daily_data": 1}
-
-        full_data = self.twse_collection.find_one(match_query, proj_query)
-
-        if (not full_data):
-            raise ValueError("No ticker found in database twse_stats")
-
-        daily_data = full_data.get("daily_data", [])
-
-        if (not isinstance(daily_data, list)):
-            raise ValueError("No ticker found in database twse_stats")
-
-        df = pd.DataFrame(daily_data)
-        if not self.has_required_columns(df, required_cols):
-            raise KeyError(f"Missing required columns")
-        
-        df = df[required_cols]
-        df = df.sort_values(by = 'date').drop_duplicates(subset=['date'])
-
-        return df
     
     def conduct_db_search_tej(self):
         # 再對TEJ search
@@ -177,7 +152,7 @@ class TechFetcher(StatsFetcher):
         }
 
         query = {'ticker': self.ticker}
-        ticker_full = self.tej_collection.find_one(query)
+        ticker_full = self.collection.find_one(query)
 
         if not ticker_full:
             raise ValueError("No ticker found in database")
@@ -215,10 +190,33 @@ class TechFetcher(StatsFetcher):
             missing_cols = ",".join(missing_cols)
             for col in missing_cols:
                 df[col] = pd.NA
-            # raise KeyError(f"Missing required columns")
 
         return df[required_cols]
 
+    
+    def conduct_db_search_twse(self):
+        required_cols = ['date', 'open', 'high', 'low', 'close', 'volume']
+        match_query = {"ticker" : self.ticker}
+        proj_query = {"_id": 0, "daily_data": 1}
+
+        full_data = self.twse_collection.find_one(match_query, proj_query)
+
+        if (not full_data):
+            raise ValueError("No ticker found in database twse_stats")
+
+        daily_data = full_data.get("daily_data", [])
+
+        if (not isinstance(daily_data, list)):
+            raise ValueError("No ticker found in database twse_stats")
+
+        df = pd.DataFrame(daily_data)
+        if not self.has_required_columns(df, required_cols):
+            raise KeyError(f"Missing required columns")
+        
+        df = df[required_cols]
+        df = df.sort_values(by = 'date').drop_duplicates(subset=['date'])
+
+        return df
 
 class TechProcessor:
 

neurostats_API/fetchers/tej_finance_report.py

@@ -1,6 +1,7 @@
 from .base import BaseTEJFetcher
 from datetime import datetime
 from enum import Enum
+import numpy as np
 import pandas as pd
 from pymongo import MongoClient
 from .tech import TechProcessor
@@ -127,6 +128,8 @@ class FinanceReportFetcher(BaseTEJFetcher):
             lower_bound_year, lower_bound_season, report_type, indexes
         )
         fetched_data = self.collection.aggregate(pipeline).to_list()
+        fetched_data = fetched_data[0]
+        fetched_data = fetched_data.get('data', []) if isinstance(fetched_data, dict) else []
 
         data_dict = self.transform_value(
             StatsProcessor.list_of_dict_to_dict(
@@ -174,11 +177,14 @@ class FinanceReportFetcher(BaseTEJFetcher):
             year_based=True
         )
         fetched_data = self.collection.aggregate(pipeline).to_list()
+        fetched_data = fetched_data[0]
+        fetched_data = fetched_data.get('data', []) if isinstance(fetched_data, dict) else []
+
         data_dict = self.transform_value(
             StatsProcessor.list_of_dict_to_dict(
-                data_list=fetched_data, 
-                keys=["year", "season"], 
-                delimeter="Q", 
+                data_list=fetched_data,
+                keys=["year", "season"],
+                delimeter="Q",
                 data_key=report_type
             )
         )
@@ -198,9 +204,9 @@ class FinanceReportFetcher(BaseTEJFetcher):
                                   (self.percent_index_list, "%")]:
             process_list = list(set(data_df.index) & set(category))
             if postfix == "%":
-                data_df.loc[process_list] = data_df.loc[process_list].astype(
-                    str
-                ).map(lambda x: f"{x}%")
+                data_df = data_df.T
+                data_df[process_list] = data_df[process_list].map(lambda x: f"{x}%") # if (not np.isnan(x)) else None)
+                data_df = data_df.T
             else:
                 data_df.loc[process_list] = data_df.loc[process_list].map(
                     lambda x: StatsProcessor.
@@ -221,67 +227,80 @@ class FinanceReportFetcher(BaseTEJFetcher):
         indexes,
         year_based=False
     ):
-        project_stage = {
-            "_id": 0,
-            "data.year": 1,
-            "data.season": 1,
-            **{
-                f"data.{report_type}.{idx}": 1
-                for idx in indexes
-            }
-        } if indexes else {
-            "_id": 0,
-            "data.year": 1,
-            "data.season": 1,
-            f"data.{report_type}": 1
-        }
 
-        if (year_based):
-            match_stage = {
-                "data.year": {
-                    "$in": start_year
-                } if year_based else {
-                    "$gt": start_year,
-                    "$lt": end_year
-                },
-                "data.season": start_season
+        if year_based:
+            filter_cond = {
+                "$and": [
+                    { "$in": ["$$item.year", start_year] },
+                    { "$eq": ["$$item.season", start_season] }
+                ]
             }
         else:
-            match_stage = {
+            filter_cond = {
                 "$or": [
                     {
-                        "data.year": {
-                            "$gt": start_year,
-                            "$lt": end_year
-                        }
-                    }, {
-                        "data.year": start_year,
-                        "data.season": {
-                            "$gte": start_season
-                        }
-                    }, {
-                        "data.year": end_year,
-                        "data.season": {
-                            "$lte": end_season
-                        }
-                    }, {
-                        "data.year": lower_bound_year,
-                        "data.season": lower_bound_season
+                        "$and": [
+                            { "$gt": ["$$item.year", start_year] },
+                            { "$lt": ["$$item.year", end_year] }
+                        ]
+                    },
+                    {
+                        "$and": [
+                            { "$eq": ["$$item.year", start_year] },
+                            { "$gte": ["$$item.season", start_season] }
+                        ]
+                    },
+                    {
+                        "$and": [
+                            { "$eq": ["$$item.year", end_year] },
+                            { "$lte": ["$$item.season", end_season] }
+                        ]
+                    },
+                    {
+                        "$and": [
+                            { "$eq": ["$$item.year", lower_bound_year] },
+                            { "$eq": ["$$item.season", lower_bound_season] }
+                        ]
                     }
                 ]
             }
 
+        # 每個 filtered item 要輸出哪些欄位
+        item_fields = {
+            "year": "$$item.year",
+            "season": "$$item.season"
+        }
+
+        if indexes:
+            for idx in indexes:
+                item_fields[idx] = f"$$item.{report_type}.{idx}"
+        else:
+            item_fields[report_type] = f"$$item.{report_type}"
+        
         return [
             {
                 "$match": {
                     "ticker": ticker
                 }
-            }, {
-                "$unwind": "$data"
-            }, {
-                "$match": match_stage
-            }, {
-                "$project": project_stage
+            },
+            {
+                "$project": {
+                    "_id": 0,
+                    "ticker": 1,
+                    "data": {
+                        "$map": {
+                            "input": {
+                                "$filter": {
+                                    "input": "$data",
+                                    "as": "item",
+                                    "cond": filter_cond
+                                }
+                            },
+                            "as": "item",
+                            "in": item_fields
+                        }
+                    }
+                }
             }
         ]
 
@@ -330,7 +349,10 @@ class TEJStockPriceFetcher(BaseTEJFetcher):
 
         if (period is not None):
             latest_date = self.get_latest_data_time(ticker)
-            start_date = self.set_time_shift(date=latest_date, period=period)
+            if (latest_date):
+                start_date = self.set_time_shift(date=latest_date, period=period)
+            else:
+                start_date = datetime.strptime(start_date, "%Y-%m-%d")
         else:
             start_date = datetime.strptime(start_date, "%Y-%m-%d")
 
@@ -339,26 +361,36 @@ class TEJStockPriceFetcher(BaseTEJFetcher):
                 "$match": {
                     "ticker": ticker
                 }
-            }, {
-                "$unwind": "$data"
-            }, {
-                "$match": {
-                    "data.mdate": {
-                        "$gt": start_date
-                    }
-                }
-            }, {
+            },
+            {
                 "$project": {
+                    "_id": 0,
                     "ticker": 1,
-                    "data": 1,
-                    "_id": 0
+                    "data": {
+                        "$filter": {
+                            "input": "$data",
+                            "as": "item",
+                            "cond": {
+                                "$gte": ["$$item.mdate", start_date]
+                            }
+                        }
+                    }
                 }
             }
         ]
         datas = self.collection.aggregate(pipeline).to_list()
-
-        elements = [element['data'] for element in datas]
-
-        data_df = pd.DataFrame(elements).set_index('mdate')
+        datas = datas[0]
+        datas = datas.get('data', [])
+        elements = [element for element in datas]
+        try:
+            data_df = pd.DataFrame(elements).set_index('mdate')
+        except:
+            column_names = [
+                "coid", "mdate", "mkt", "open_d", "high_d", "low_d", "close_d",
+                "adjfac", "vol", "amt", "trn", "bid", "offer", "avgprc", "roi",
+                "hmlpct", "turnover", "shares", "mktcap", "mktcap_pct",
+                "amt_pct", "per", "pbr", "div_yid", "cdiv_yid"
+            ]
+            data_df = pd.DataFrame(columns = column_names)
 
         return data_df