From fb6552598189996dd2996dbeb6aa0c1b44e553e9 Mon Sep 17 00:00:00 2001
From: TerenceLau <Terenceliu1012@gmail.com>
Date: Thu, 14 Apr 2022 05:48:32 +0000
Subject: [PATCH] v0.3.6

---
 CEDA/__init__.py      |  2 +-
 CEDA/economic/NBSC.py | 39 +++++++++++++++++----------------------
 example/economic.md   |  5 ++---
 setup.py              |  4 ++--
 4 files changed, 22 insertions(+), 28 deletions(-)

diff --git a/CEDA/__init__.py b/CEDA/__init__.py
index ceb8158..b9d6132 100644
--- a/CEDA/__init__.py
+++ b/CEDA/__init__.py
@@ -1,7 +1,7 @@
 import sys
 import os
 
-__version__ = "0.3.5"
+__version__ = "0.3.6"
 __author__ = "Terence Lau"
 
 
diff --git a/CEDA/economic/NBSC.py b/CEDA/economic/NBSC.py
index 822aca3..65dc8bc 100644
--- a/CEDA/economic/NBSC.py
+++ b/CEDA/economic/NBSC.py
@@ -18,7 +18,7 @@ requests.packages.urllib3.disable_warnings(InsecureRequestWarning)
 
 
 class NBSCData(object):
-    def __init__(self, language:str="en"):
+    def __init__(self, language:str="en", period:str="monthly"):
 
         self.dbcode = []
         self.nid = []
@@ -26,6 +26,7 @@ class NBSCData(object):
         self.name = []
         self.wdcode= []
 
+
         if language == "cn":
             self.url = "https://data.stats.gov.cn/easyquery.htm"
             self.BASE_DIR = os.path.dirname(__file__)
@@ -34,6 +35,13 @@ class NBSCData(object):
             self.url = "https://data.stats.gov.cn/english/easyquery.htm"
             self.BASE_DIR = os.path.dirname(__file__)
             self.__TREE_PATH__ = os.path.join(self.BASE_DIR, "NBSCTree", "data_en.pkl")
+        
+        if period == "monthly":
+            self.dbcode_query = "hgyd"
+        elif period == "quarterly":
+            self.dbcode = "hgjd"
+        elif period == "annual":
+            self.dbcode = "hgnd"
 
     def generate_header(self):
         ua = UserAgent()
@@ -46,7 +54,7 @@ class NBSCData(object):
         inspired by a blog: https://www.cnblogs.com/wang_yb/p/14636575.html
         """
         parent = []
-        r = requests.post("{}?id={}&dbcode=hgnd&wdcode=zb&m=getTree".format(self.url, rid), headers=self.generate_header(), verify=False)
+        r = requests.post("{}?id={}&dbcode={}&wdcode=zb&m=getTree".format(self.url, rid, self.dbcode_query), headers=self.generate_header(), verify=False)
         data = r.json()
 
         for i in range(0, len(data)):
@@ -70,7 +78,7 @@ class NBSCData(object):
         """
         inspired by a blog: https://www.cnblogs.com/wang_yb/p/14636575.html
         """
-        for i in range(0, len(nodes)):
+        for i in tqdm(range(0, len(nodes))):
             node = nodes[i]
             if node["isParent"]:
                 self.toc(node["children"])
@@ -87,24 +95,18 @@ class NBSCData(object):
     
 
     
-    def download_data(self, nid:str=None, sj="1978-", period:str="monthly"):
-
-        if period == "monthly":
-            dbcode="hgyd"
-        elif period == "quarterly":
-            dbcode="hgjd"
-        elif period == "annual":
-            dbcode="hgnd"
+    def download_data(self, nid:str=None, sj="1978-"):
 
         params = {
         "m": "QueryData",
-        "dbcode": dbcode,
+        "dbcode": self.dbcode_query,
         "rowcode": "zb",
         "colcode": "sj",
         "wds": "[]",
         "dfwds": '[{"wdcode":"zb","valuecode":"'
         + nid
         + '"},{"wdcode":"sj","valuecode":"'
+        + sj
         + '"}]',
         "sj": sj
         }
@@ -117,19 +119,12 @@ class NBSCData(object):
                 value.append(data[i]["data"]["data"])
             
             output = pd.DataFrame({"date":date, "value":value})
+            output = output.drop_duplicates("date", keep="first")
             return output
 
 if __name__ == "__main__":
-    nbsc = NBSCData(language="en")
+    nbsc = NBSCData(language="en", period="annual")
     nodes = nbsc.tree_generation()
     toc = nbsc.toc(nodes=nodes)
     toc[toc["name"].str.contains("GDP")]
-    data = nbsc.download_data(nid="A0203")
-
-            
-            
-            
-
-
-
-                
\ No newline at end of file
+    data = nbsc.download_data(nid="A0203")
\ No newline at end of file
diff --git a/example/economic.md b/example/economic.md
index 1317db7..d4eb267 100644
--- a/example/economic.md
+++ b/example/economic.md
@@ -43,11 +43,10 @@ data = oecd.download_data(dataset="QNA", query="QNA/CAN.B1_GE.CQRSA.Q")
 
 ```python
 from CEDA.economic.NBSC import *
-nbsc = NBSCData(language="en")
+nbsc = NBSCData(language="en", period="monthly")
 nbsc_nodes = nbsc.tree_generation()
 nbsc_toc = nbsc.toc(nodes=nbsc_nodes)
-nbsc_toc[nbsc_toc["name"].str.contains("GDP")]
-A0203 = nbsc.download_data(nid="A0203")
+A010301 = nbsc.download_data(nid="A010301")
 ```
 
 ## Xinhua
diff --git a/setup.py b/setup.py
index a65445b..44a1da5 100644
--- a/setup.py
+++ b/setup.py
@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 import os
 setup(
     name = "CEDApy",
-    version = "0.3.5",
+    version = "0.3.6",
     keywords = "quantitative economic data",
     long_description = open(
     os.path.join(
@@ -13,7 +13,7 @@ setup(
     author = "TerenceCKLau",
     author_email = "terenceliu1012@outlook.com",
     url = "https://github.com/TerenceLiu98/CEDApy",
-    packages = (exclude=["test", "example"]),
+    packages = find_packages(exclude=["test", "example"]),
     install_requires=[
         "matplotlib>=3.1.1",
         "numpy>=1.15.4",