githubdata - pypi Package Compare versions

Comparing version 11.1.0 to 12.0.0

src/githubdata/github_data_repo.py

+"""
+
+    """
+
+from pathlib import Path
+
+from giteasy import GitHubRepo
+from mirutil.df import read_data_according_to_type as rdatt
+from mirutil.files import read_json_file as rjf
+
+
+data_file_suffixes = {
+        '.xlsx' : None ,
+        '.prq'  : None ,
+        '.csv'  : None ,
+        }
+
+class GithubDataRepo(GitHubRepo) :
+
+    def __init__(self , repo_url , committing_usr = None , token = None) :
+        super().__init__(repo_url = repo_url ,
+                         committing_usr = committing_usr ,
+                         token = token)
+
+        self.set_data_fps()
+
+        self.data_suf = None
+        self.data_fp: (Path , list)
+        self.meta_fp: Path
+        self.meta: dict
+
+    def clone_overwrite(self , depth = 1) :
+        super().clone_overwrite(depth = depth)
+        self.set_data_fps()
+
+    def _set_defualt_data_suffix(self) :
+        for ky in data_file_suffixes.keys() :
+            fps = self.ret_sorted_fpns_by_suf(ky)
+            if len(fps) >= 1 :
+                self.data_suf = ky
+                return
+
+    def set_data_fps(self) :
+        self._set_defualt_data_suffix()
+
+        if self.data_suf is None :
+            return
+
+        fps = self.ret_sorted_fpns_by_suf(self.data_suf)
+
+        if len(fps) == 1 :
+            self.data_fp = fps[0]
+        else :
+            self.data_fp = fps
+
+    def ret_sorted_fpns_by_suf(self , suffix) :
+        ls = list(self.local_path.glob(f'*{suffix}'))
+        return sorted(ls)
+
+    def read_metadata(self) :
+        fps = self.ret_sorted_fpns_by_suf('.json')
+        if len(fps) == 0 :
+            return
+        fp = fps[0]
+        self.meta_fp = fp
+        self.meta = rjf(fp)
+        return self.meta
+
+    def read_data(self) :
+        if not self.local_path.exists() :
+            self.clone_overwrite()
+        if isinstance(self.data_fp , Path) :
+            return rdatt(self.data_fp)
+
+def get_data_from_github(github_url) :
+    """
+    :param: github_url
+    :return: pandas.DataFrame
+    """
+    gd = GithubDataRepo(github_url)
+    df = gd.read_data()
+    gd.rmdir()
+    return df

PKG-INFO

 Metadata-Version: 2.1
 Name: githubdata
-Version: 11.1.0
+Version: 12.0.0
 Summary: A simple tool to get the lastest version of a dataset in a Github repository
@@ -50,2 +50,3 @@ Project-URL: Homepage, https://github.com/imahdimir/githubdata
 Requires-Dist: giteasy
+Requires-Dist: mirutil
 Requires-Dist: openpyxl
@@ -52,0 +53,0 @@ Requires-Dist: pandas

pyproject.toml

@@ -7,3 +7,3 @@ [build-system]
 name = "githubdata"
-version = "11.1.0"
+version = "12.0.0"
 authors = [{ name = "Mahdi Mir", email = "[e-mail]" }]
@@ -19,2 +19,3 @@ description = "A simple tool to get the lastest version of a dataset in a Github repository"
     "openpyxl",
+    "mirutil"
 ]
@@ -21,0 +22,0 @@ classifiers = [

src/githubdata/__init__.py

@@ -1,2 +0,2 @@
-from .githubdata import get_data_from_github
-from .githubdata import GithubData
+from .github_data_repo import get_data_from_github
+from .github_data_repo import GithubDataRepo

tests/test.py

@@ -7,8 +7,6 @@ """
 
-from src.githubdata import githubdata
 
-
 importlib.reload(githubdata)
 
-from src.githubdata.githubdata import *
+from src.githubdata.github_data_repo import *
 
@@ -22,4 +20,4 @@
 u = 'https://github.com/imahdimir/d-TSETMC_ID-2-FirmTicker'
-repo = GithubData(u)
-repo.overwriting_clone()
+repo = GithubDataRepo(u)
+repo.clone_overwrite()
 
@@ -31,4 +29,4 @@ ##
 u = 'https://github.com/imahdimir/test-public'
-repo = GithubData(u)
-repo.overwriting_clone()
+repo = GithubDataRepo(u)
+repo.clone_overwrite()
 
@@ -44,4 +42,4 @@ ##
 ur = 'https://github.com/imahdimir/test-private'
-rp = GithubData(ur)
-rp.overwriting_clone()
+rp = GithubDataRepo(ur)
+rp.clone_overwrite()
 
@@ -48,0 +46,0 @@ ##

requirements.txt

-pandas
-giteasy
-IPython
-pyarrow
-fastparquet
-openpyxl
-build
-twine

src/githubdata/githubdata.py

-"""
-
-    """
-
-import json
-from pathlib import Path
-
-import pandas as pd
-from giteasy.repo import Repo
-
-
-data_file_suffixes = {
-        '.xlsx' : None ,
-        '.prq'  : None ,
-        '.csv'  : None ,
-        }
-
-class GithubData(Repo) :
-
-    def __init__(self , src_url , github_usr = None , usr_tok_json_fp = None) :
-        super().__init__(src_url = src_url ,
-                         github_usr = github_usr ,
-                         usr_tok_json_fp = usr_tok_json_fp)
-        self.set_data_fps()
-        self.read_metadata()
-
-    def overwriting_clone(self , overwrite = True , depth = 1) :
-        super().overwriting_clone(overwrite = overwrite , depth = depth)
-        self.set_data_fps()
-
-    def _set_defualt_data_suffix(self) :
-        for ky in data_file_suffixes.keys() :
-            fps = self.ret_sorted_fpns_by_suf(ky)
-            if len(fps) >= 1 :
-                self.data_suf = ky
-                return
-
-        self.data_suf = None
-
-    def set_data_fps(self) :
-        self._set_defualt_data_suffix()
-
-        if not self.data_suf :
-            return
-
-        fps = self.ret_sorted_fpns_by_suf(self.data_suf)
-
-        if len(fps) == 1 :
-            self.data_fp = fps[0]
-        else :
-            self.data_fp = fps
-
-    def ret_sorted_fpns_by_suf(self , suffix) :
-        ls = list(self.local_path.glob(f'*{suffix}'))
-        return sorted(ls)
-
-    def read_metadata(self) :
-        fps = self.ret_sorted_fpns_by_suf('.json')
-
-        if len(fps) == 0 :
-            return
-
-        fp = fps[0]
-        self.meta_fp = fp
-
-        with open(fp , 'r') as fi :
-            js = json.load(fi)
-        self.meta = js
-
-        return js
-
-    def read_data(self) :
-        if not self.local_path.exists() :
-            self.overwriting_clone()
-
-        if isinstance(self.data_fp , Path) :
-            if self.data_suf == '.xlsx' :
-                return pd.read_excel(self.data_fp , engine = 'openpyxl')
-            elif self.data_suf == '.prq' :
-                return pd.read_parquet(self.data_fp)
-            elif self.data_suf == '.csv' :
-                return pd.read_csv(self.data_fp)
-
-def get_data_from_github(github_url) :
-    """
-    :param: github_url
-    :return: pandas.DataFrame
-    """
-    gd = GithubData(github_url)
-    df = gd.read_data()
-    gd.rmdir()
-    return df

Alert delta unavailable

Currently unable to show alert delta for PyPI packages.

Worsened metrics

Total package byte prevSize

12357

-2.15%

Number of package files

9

-10%

Lines of code

96

-5.88%